Hugging Face's logo

scrapie
/
dolphin-2.9-llama3-8b-GER-4bit

PEFT
Safetensors
llama-factory
lora
unsloth
Generated from Trainer
Model card Files Community
scrapie commited on
Commit
9283cf9
•
1 Parent(s): efbe348

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +77 -0
  2. adapter_config.json +34 -0
  3. adapter_model.safetensors +3 -0
  4. all_results.json +11 -0
  5. checkpoint-100/README.md +202 -0
  6. checkpoint-100/adapter_config.json +34 -0
  7. checkpoint-100/adapter_model.safetensors +3 -0
  8. checkpoint-100/optimizer.pt +3 -0
  9. checkpoint-100/rng_state_0.pth +3 -0
  10. checkpoint-100/rng_state_1.pth +3 -0
  11. checkpoint-100/scheduler.pt +3 -0
  12. checkpoint-100/special_tokens_map.json +32 -0
  13. checkpoint-100/tokenizer.json +0 -0
  14. checkpoint-100/tokenizer_config.json +2084 -0
  15. checkpoint-100/trainer_state.json +729 -0
  16. checkpoint-100/training_args.bin +3 -0
  17. checkpoint-200/README.md +202 -0
  18. checkpoint-200/adapter_config.json +34 -0
  19. checkpoint-200/adapter_model.safetensors +3 -0
  20. checkpoint-200/optimizer.pt +3 -0
  21. checkpoint-200/rng_state_0.pth +3 -0
  22. checkpoint-200/rng_state_1.pth +3 -0
  23. checkpoint-200/scheduler.pt +3 -0
  24. checkpoint-200/special_tokens_map.json +32 -0
  25. checkpoint-200/tokenizer.json +0 -0
  26. checkpoint-200/tokenizer_config.json +2084 -0
  27. checkpoint-200/trainer_state.json +1437 -0
  28. checkpoint-200/training_args.bin +3 -0
  29. checkpoint-300/README.md +202 -0
  30. checkpoint-300/adapter_config.json +34 -0
  31. checkpoint-300/adapter_model.safetensors +3 -0
  32. checkpoint-300/optimizer.pt +3 -0
  33. checkpoint-300/rng_state_0.pth +3 -0
  34. checkpoint-300/rng_state_1.pth +3 -0
  35. checkpoint-300/scheduler.pt +3 -0
  36. checkpoint-300/special_tokens_map.json +32 -0
  37. checkpoint-300/tokenizer.json +0 -0
  38. checkpoint-300/tokenizer_config.json +2084 -0
  39. checkpoint-300/trainer_state.json +2145 -0
  40. checkpoint-300/training_args.bin +3 -0
  41. checkpoint-400/README.md +202 -0
  42. checkpoint-400/adapter_config.json +34 -0
  43. checkpoint-400/adapter_model.safetensors +3 -0
  44. checkpoint-400/optimizer.pt +3 -0
  45. checkpoint-400/rng_state_0.pth +3 -0
  46. checkpoint-400/rng_state_1.pth +3 -0
  47. checkpoint-400/scheduler.pt +3 -0
  48. checkpoint-400/special_tokens_map.json +32 -0
  49. checkpoint-400/tokenizer.json +0 -0
  50. checkpoint-400/tokenizer_config.json +2084 -0
README.md ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ library_name: peft
4
+ tags:
5
+ - llama-factory
6
+ - lora
7
+ - unsloth
8
+ - generated_from_trainer
9
+ base_model: cognitivecomputations/dolphin-2.9-llama3-8b
10
+ model-index:
11
+ - name: dolphin-2.9-llama3-8b-GER
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # dolphin-2.9-llama3-8b-GER
19
+
20
+ This model is a fine-tuned version of [cognitivecomputations/dolphin-2.9-llama3-8b](https://huggingface.co/cognitivecomputations/dolphin-2.9-llama3-8b) on the identity, the alpaca-gpt4_de, the dolphin_de and the airoboros_de datasets.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.9384
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 0.0002
42
+ - train_batch_size: 2
43
+ - eval_batch_size: 1
44
+ - seed: 42
45
+ - distributed_type: multi-GPU
46
+ - num_devices: 2
47
+ - gradient_accumulation_steps: 4
48
+ - total_train_batch_size: 16
49
+ - total_eval_batch_size: 2
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - lr_scheduler_warmup_ratio: 0.1
53
+ - lr_scheduler_warmup_steps: 80
54
+ - num_epochs: 1.0
55
+ - mixed_precision_training: Native AMP
56
+
57
+ ### Training results
58
+
59
+ | Training Loss | Epoch | Step | Validation Loss |
60
+ |:-------------:|:-----:|:----:|:---------------:|
61
+ | 1.2054 | 0.12 | 100 | 1.0369 |
62
+ | 1.0667 | 0.24 | 200 | 1.0012 |
63
+ | 1.0751 | 0.35 | 300 | 0.9849 |
64
+ | 0.8838 | 0.47 | 400 | 0.9696 |
65
+ | 0.9846 | 0.59 | 500 | 0.9565 |
66
+ | 0.9523 | 0.71 | 600 | 0.9486 |
67
+ | 0.8567 | 0.82 | 700 | 0.9430 |
68
+ | 0.8284 | 0.94 | 800 | 0.9384 |
69
+
70
+
71
+ ### Framework versions
72
+
73
+ - PEFT 0.10.0
74
+ - Transformers 4.39.3
75
+ - Pytorch 2.2.2+cu121
76
+ - Datasets 2.16.0
77
+ - Tokenizers 0.15.2
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "cognitivecomputations/dolphin-2.9-llama3-8b",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": "unsloth",
22
+ "target_modules": [
23
+ "v_proj",
24
+ "k_proj",
25
+ "down_proj",
26
+ "gate_proj",
27
+ "q_proj",
28
+ "up_proj",
29
+ "o_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90800320179ceed9d161db4a4cfb9dd3df8307c72d8217a381bddb71dcecca24
3
+ size 167832240
all_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_loss": 0.9384466409683228,
4
+ "eval_runtime": 547.0457,
5
+ "eval_samples_per_second": 2.76,
6
+ "eval_steps_per_second": 1.38,
7
+ "train_loss": 0.9633775743775429,
8
+ "train_runtime": 18851.463,
9
+ "train_samples_per_second": 0.72,
10
+ "train_steps_per_second": 0.045
11
+ }
checkpoint-100/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: cognitivecomputations/dolphin-2.9-llama3-8b
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.10.0
checkpoint-100/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "cognitivecomputations/dolphin-2.9-llama3-8b",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": "unsloth",
22
+ "target_modules": [
23
+ "v_proj",
24
+ "k_proj",
25
+ "down_proj",
26
+ "gate_proj",
27
+ "q_proj",
28
+ "up_proj",
29
+ "o_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-100/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3405e0fa0866526da58bf13c88078088ef48059e3f6622d6b5a0b7e34e4d2fe5
3
+ size 167832240
checkpoint-100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c24f42f7b92a81ec41b9b3e7dbab6ec43c6c91af86369453e4e16b7a75359fb2
3
+ size 84570708
checkpoint-100/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:382474f6e31a1bad035d5f8c55403be606828290078e27d1aca7753a771d0c35
3
+ size 14512
checkpoint-100/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:088d3d36fa769290aedb14301d626334853d0a53aeb9cd5011e4f4faf54e918c
3
+ size 14512
checkpoint-100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8c0f9ade829fe55ad1631bee6bd666dcbfb03c752a183ada63b138e3b1e3205
3
+ size 1064
checkpoint-100/special_tokens_map.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|im_start|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ }
10
+ ],
11
+ "bos_token": {
12
+ "content": "<|begin_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "eos_token": {
19
+ "content": "<|im_end|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "pad_token": {
26
+ "content": "<|end_of_text|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ }
32
+ }
checkpoint-100/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-100/tokenizer_config.json ADDED
@@ -0,0 +1,2084 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ },
2051
+ "128256": {
2052
+ "content": "<|im_end|>",
2053
+ "lstrip": false,
2054
+ "normalized": false,
2055
+ "rstrip": false,
2056
+ "single_word": false,
2057
+ "special": true
2058
+ },
2059
+ "128257": {
2060
+ "content": "<|im_start|>",
2061
+ "lstrip": false,
2062
+ "normalized": false,
2063
+ "rstrip": false,
2064
+ "single_word": false,
2065
+ "special": true
2066
+ }
2067
+ },
2068
+ "additional_special_tokens": [
2069
+ "<|im_start|>"
2070
+ ],
2071
+ "bos_token": "<|begin_of_text|>",
2072
+ "chat_template": "{% set system_message = 'Du bist ein freundlicher und hilfsbereiter KI-Assistent.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\\n' + system_message + '<|im_end|>\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\\n' + content + '<|im_end|>\\n<|im_start|>assistant\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\\n' }}{% endif %}{% endfor %}",
2073
+ "clean_up_tokenization_spaces": true,
2074
+ "eos_token": "<|im_end|>",
2075
+ "model_input_names": [
2076
+ "input_ids",
2077
+ "attention_mask"
2078
+ ],
2079
+ "model_max_length": 1000000000000000019884624838656,
2080
+ "pad_token": "<|end_of_text|>",
2081
+ "padding_side": "right",
2082
+ "split_special_tokens": false,
2083
+ "tokenizer_class": "PreTrainedTokenizerFast"
2084
+ }
checkpoint-100/trainer_state.json ADDED
@@ -0,0 +1,729 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.0368528366088867,
3
+ "best_model_checkpoint": "/kaggle/working/LLaMA-Factory/output/dolphin-2.9-llama3-8b-GER/checkpoint-100",
4
+ "epoch": 0.11778563015312132,
5
+ "eval_steps": 100,
6
+ "global_step": 100,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "grad_norm": 0.5445218086242676,
14
+ "learning_rate": 2.5e-06,
15
+ "loss": 1.2105,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0,
20
+ "grad_norm": 0.4362960457801819,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.9311,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.0,
27
+ "grad_norm": 0.5098525881767273,
28
+ "learning_rate": 7.5e-06,
29
+ "loss": 1.3604,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.0,
34
+ "grad_norm": 1.0830402374267578,
35
+ "learning_rate": 1e-05,
36
+ "loss": 1.5808,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.01,
41
+ "grad_norm": 0.5936903953552246,
42
+ "learning_rate": 1.25e-05,
43
+ "loss": 1.248,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.01,
48
+ "grad_norm": 0.7212775945663452,
49
+ "learning_rate": 1.5e-05,
50
+ "loss": 1.2712,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.01,
55
+ "grad_norm": 0.4733128845691681,
56
+ "learning_rate": 1.75e-05,
57
+ "loss": 1.3005,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.01,
62
+ "grad_norm": 0.6236618757247925,
63
+ "learning_rate": 2e-05,
64
+ "loss": 1.3398,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.01,
69
+ "grad_norm": 0.5326029658317566,
70
+ "learning_rate": 2.25e-05,
71
+ "loss": 1.0476,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.01,
76
+ "grad_norm": 0.5021428465843201,
77
+ "learning_rate": 2.5e-05,
78
+ "loss": 1.1245,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.01,
83
+ "grad_norm": 0.46588796377182007,
84
+ "learning_rate": 2.7500000000000004e-05,
85
+ "loss": 1.1041,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.01,
90
+ "grad_norm": 0.936045229434967,
91
+ "learning_rate": 3e-05,
92
+ "loss": 1.3201,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.02,
97
+ "grad_norm": 0.5649005770683289,
98
+ "learning_rate": 3.2500000000000004e-05,
99
+ "loss": 1.1596,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.02,
104
+ "grad_norm": 0.5679148435592651,
105
+ "learning_rate": 3.5e-05,
106
+ "loss": 1.2501,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.02,
111
+ "grad_norm": 0.8638319373130798,
112
+ "learning_rate": 3.7500000000000003e-05,
113
+ "loss": 1.237,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.02,
118
+ "grad_norm": 0.5722486972808838,
119
+ "learning_rate": 4e-05,
120
+ "loss": 1.2616,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.02,
125
+ "grad_norm": 0.5802999138832092,
126
+ "learning_rate": 4.25e-05,
127
+ "loss": 0.9578,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.02,
132
+ "grad_norm": 1.2806150913238525,
133
+ "learning_rate": 4.5e-05,
134
+ "loss": 1.3815,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.02,
139
+ "grad_norm": 0.5839210748672485,
140
+ "learning_rate": 4.75e-05,
141
+ "loss": 1.2619,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.02,
146
+ "grad_norm": 0.7132797837257385,
147
+ "learning_rate": 5e-05,
148
+ "loss": 1.2842,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.02,
153
+ "grad_norm": 0.7936571836471558,
154
+ "learning_rate": 5.25e-05,
155
+ "loss": 1.3991,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.03,
160
+ "grad_norm": 0.7268731594085693,
161
+ "learning_rate": 5.500000000000001e-05,
162
+ "loss": 1.2217,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.03,
167
+ "grad_norm": 0.6649657487869263,
168
+ "learning_rate": 5.7499999999999995e-05,
169
+ "loss": 1.2485,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.03,
174
+ "grad_norm": 0.45912331342697144,
175
+ "learning_rate": 6e-05,
176
+ "loss": 1.1452,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.03,
181
+ "grad_norm": 0.49475613236427307,
182
+ "learning_rate": 6.25e-05,
183
+ "loss": 1.256,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.03,
188
+ "grad_norm": 0.6027999520301819,
189
+ "learning_rate": 6.500000000000001e-05,
190
+ "loss": 1.2267,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.03,
195
+ "grad_norm": 0.48380520939826965,
196
+ "learning_rate": 6.750000000000001e-05,
197
+ "loss": 1.202,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.03,
202
+ "grad_norm": 0.6623361706733704,
203
+ "learning_rate": 7e-05,
204
+ "loss": 1.3924,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.03,
209
+ "grad_norm": 0.6632773280143738,
210
+ "learning_rate": 7.25e-05,
211
+ "loss": 1.2443,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.04,
216
+ "grad_norm": 0.5974243879318237,
217
+ "learning_rate": 7.500000000000001e-05,
218
+ "loss": 1.0591,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.04,
223
+ "grad_norm": 0.7902927398681641,
224
+ "learning_rate": 7.75e-05,
225
+ "loss": 1.0192,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.04,
230
+ "grad_norm": 0.7081462144851685,
231
+ "learning_rate": 8e-05,
232
+ "loss": 1.0955,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.04,
237
+ "grad_norm": 0.4744333326816559,
238
+ "learning_rate": 8.25e-05,
239
+ "loss": 1.0564,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.04,
244
+ "grad_norm": 0.703999400138855,
245
+ "learning_rate": 8.5e-05,
246
+ "loss": 1.1022,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.04,
251
+ "grad_norm": 0.5378603339195251,
252
+ "learning_rate": 8.75e-05,
253
+ "loss": 1.063,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.04,
258
+ "grad_norm": 0.6105419397354126,
259
+ "learning_rate": 9e-05,
260
+ "loss": 0.9748,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.04,
265
+ "grad_norm": 0.6250177025794983,
266
+ "learning_rate": 9.250000000000001e-05,
267
+ "loss": 0.9951,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.04,
272
+ "grad_norm": 0.6306005716323853,
273
+ "learning_rate": 9.5e-05,
274
+ "loss": 0.9875,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.05,
279
+ "grad_norm": 0.8635210990905762,
280
+ "learning_rate": 9.75e-05,
281
+ "loss": 1.1825,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.05,
286
+ "grad_norm": 0.5938963890075684,
287
+ "learning_rate": 0.0001,
288
+ "loss": 0.9678,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.05,
293
+ "grad_norm": 0.5765062570571899,
294
+ "learning_rate": 0.0001025,
295
+ "loss": 1.1031,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.05,
300
+ "grad_norm": 0.5162666440010071,
301
+ "learning_rate": 0.000105,
302
+ "loss": 1.0831,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.05,
307
+ "grad_norm": 0.8675170540809631,
308
+ "learning_rate": 0.0001075,
309
+ "loss": 1.0034,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.05,
314
+ "grad_norm": 0.44026264548301697,
315
+ "learning_rate": 0.00011000000000000002,
316
+ "loss": 0.9607,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.05,
321
+ "grad_norm": 0.4922897219657898,
322
+ "learning_rate": 0.00011250000000000001,
323
+ "loss": 1.0251,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.05,
328
+ "grad_norm": 0.5505048632621765,
329
+ "learning_rate": 0.00011499999999999999,
330
+ "loss": 0.6948,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.06,
335
+ "grad_norm": 0.5226988792419434,
336
+ "learning_rate": 0.00011750000000000001,
337
+ "loss": 1.2259,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.06,
342
+ "grad_norm": 0.5105571150779724,
343
+ "learning_rate": 0.00012,
344
+ "loss": 1.1239,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.06,
349
+ "grad_norm": 2.0914857387542725,
350
+ "learning_rate": 0.00012250000000000002,
351
+ "loss": 1.4032,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.06,
356
+ "grad_norm": 0.4611998498439789,
357
+ "learning_rate": 0.000125,
358
+ "loss": 1.1481,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.06,
363
+ "grad_norm": 0.5243968367576599,
364
+ "learning_rate": 0.0001275,
365
+ "loss": 1.0514,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.06,
370
+ "grad_norm": 0.48045778274536133,
371
+ "learning_rate": 0.00013000000000000002,
372
+ "loss": 1.1552,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.06,
377
+ "grad_norm": 0.5543797612190247,
378
+ "learning_rate": 0.0001325,
379
+ "loss": 1.035,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.06,
384
+ "grad_norm": 0.5148913264274597,
385
+ "learning_rate": 0.00013500000000000003,
386
+ "loss": 0.9244,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.06,
391
+ "grad_norm": 0.5708130598068237,
392
+ "learning_rate": 0.0001375,
393
+ "loss": 1.2272,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.07,
398
+ "grad_norm": 0.7507888078689575,
399
+ "learning_rate": 0.00014,
400
+ "loss": 1.1196,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.07,
405
+ "grad_norm": 0.5411068201065063,
406
+ "learning_rate": 0.00014250000000000002,
407
+ "loss": 1.1444,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.07,
412
+ "grad_norm": 0.7314138412475586,
413
+ "learning_rate": 0.000145,
414
+ "loss": 1.3451,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.07,
419
+ "grad_norm": 0.5134022831916809,
420
+ "learning_rate": 0.0001475,
421
+ "loss": 0.8021,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.07,
426
+ "grad_norm": 0.7859703302383423,
427
+ "learning_rate": 0.00015000000000000001,
428
+ "loss": 0.952,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.07,
433
+ "grad_norm": 0.4740566611289978,
434
+ "learning_rate": 0.0001525,
435
+ "loss": 0.8878,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.07,
440
+ "grad_norm": 0.8245677947998047,
441
+ "learning_rate": 0.000155,
442
+ "loss": 1.4341,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.07,
447
+ "grad_norm": 0.5067218542098999,
448
+ "learning_rate": 0.0001575,
449
+ "loss": 0.8404,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.08,
454
+ "grad_norm": 0.40824806690216064,
455
+ "learning_rate": 0.00016,
456
+ "loss": 1.0943,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.08,
461
+ "grad_norm": 0.428151935338974,
462
+ "learning_rate": 0.00016250000000000002,
463
+ "loss": 1.0819,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.08,
468
+ "grad_norm": 0.437532901763916,
469
+ "learning_rate": 0.000165,
470
+ "loss": 1.0461,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.08,
475
+ "grad_norm": 0.4619809091091156,
476
+ "learning_rate": 0.0001675,
477
+ "loss": 1.0232,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.08,
482
+ "grad_norm": 1.3247042894363403,
483
+ "learning_rate": 0.00017,
484
+ "loss": 1.218,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.08,
489
+ "grad_norm": 0.5896454453468323,
490
+ "learning_rate": 0.00017250000000000002,
491
+ "loss": 1.1953,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.08,
496
+ "grad_norm": 0.5605736970901489,
497
+ "learning_rate": 0.000175,
498
+ "loss": 1.2542,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.08,
503
+ "grad_norm": 0.36923155188560486,
504
+ "learning_rate": 0.0001775,
505
+ "loss": 0.7096,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.08,
510
+ "grad_norm": 0.6809273362159729,
511
+ "learning_rate": 0.00018,
512
+ "loss": 1.1959,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.09,
517
+ "grad_norm": 0.42645493149757385,
518
+ "learning_rate": 0.0001825,
519
+ "loss": 1.1829,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.09,
524
+ "grad_norm": 0.7621450424194336,
525
+ "learning_rate": 0.00018500000000000002,
526
+ "loss": 1.1599,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.09,
531
+ "grad_norm": 0.5299301743507385,
532
+ "learning_rate": 0.0001875,
533
+ "loss": 1.0546,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.09,
538
+ "grad_norm": 0.484611451625824,
539
+ "learning_rate": 0.00019,
540
+ "loss": 1.0854,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.09,
545
+ "grad_norm": 0.4027417004108429,
546
+ "learning_rate": 0.00019250000000000002,
547
+ "loss": 0.7812,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.09,
552
+ "grad_norm": 0.7537221908569336,
553
+ "learning_rate": 0.000195,
554
+ "loss": 0.9719,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.09,
559
+ "grad_norm": 0.45811474323272705,
560
+ "learning_rate": 0.00019750000000000003,
561
+ "loss": 0.9684,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.09,
566
+ "grad_norm": 0.5426852107048035,
567
+ "learning_rate": 0.0002,
568
+ "loss": 0.9451,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.1,
573
+ "grad_norm": 0.48964977264404297,
574
+ "learning_rate": 0.000199739921976593,
575
+ "loss": 1.0807,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.1,
580
+ "grad_norm": 0.6225113272666931,
581
+ "learning_rate": 0.00019947984395318597,
582
+ "loss": 1.1913,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.1,
587
+ "grad_norm": 0.47157713770866394,
588
+ "learning_rate": 0.00019921976592977893,
589
+ "loss": 1.0392,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.1,
594
+ "grad_norm": 0.42048129439353943,
595
+ "learning_rate": 0.0001989596879063719,
596
+ "loss": 0.8439,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.1,
601
+ "grad_norm": 0.4129664897918701,
602
+ "learning_rate": 0.0001986996098829649,
603
+ "loss": 1.1025,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.1,
608
+ "grad_norm": 0.5610629320144653,
609
+ "learning_rate": 0.00019843953185955788,
610
+ "loss": 0.9368,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.1,
615
+ "grad_norm": 0.4288642406463623,
616
+ "learning_rate": 0.00019817945383615086,
617
+ "loss": 0.9711,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.1,
622
+ "grad_norm": 0.572507917881012,
623
+ "learning_rate": 0.0001979193758127438,
624
+ "loss": 0.9739,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.1,
629
+ "grad_norm": 0.5115912556648254,
630
+ "learning_rate": 0.0001976592977893368,
631
+ "loss": 0.9356,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.11,
636
+ "grad_norm": 0.608063280582428,
637
+ "learning_rate": 0.00019739921976592978,
638
+ "loss": 1.2459,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.11,
643
+ "grad_norm": 1.0171502828598022,
644
+ "learning_rate": 0.00019713914174252276,
645
+ "loss": 1.0629,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.11,
650
+ "grad_norm": 0.514552116394043,
651
+ "learning_rate": 0.00019687906371911574,
652
+ "loss": 0.9646,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.11,
657
+ "grad_norm": 0.4363428056240082,
658
+ "learning_rate": 0.00019661898569570872,
659
+ "loss": 0.8659,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.11,
664
+ "grad_norm": 0.4470008611679077,
665
+ "learning_rate": 0.0001963589076723017,
666
+ "loss": 1.0338,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.11,
671
+ "grad_norm": 0.5710871815681458,
672
+ "learning_rate": 0.0001960988296488947,
673
+ "loss": 0.946,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.11,
678
+ "grad_norm": 0.6456964612007141,
679
+ "learning_rate": 0.00019583875162548767,
680
+ "loss": 1.0956,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.11,
685
+ "grad_norm": 0.45742425322532654,
686
+ "learning_rate": 0.00019557867360208065,
687
+ "loss": 0.7985,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.12,
692
+ "grad_norm": 0.9953218698501587,
693
+ "learning_rate": 0.0001953185955786736,
694
+ "loss": 0.9476,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.12,
699
+ "grad_norm": 0.5075244307518005,
700
+ "learning_rate": 0.0001950585175552666,
701
+ "loss": 1.1704,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.12,
706
+ "grad_norm": 0.7076822519302368,
707
+ "learning_rate": 0.00019479843953185957,
708
+ "loss": 1.2054,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.12,
713
+ "eval_loss": 1.0368528366088867,
714
+ "eval_runtime": 547.1826,
715
+ "eval_samples_per_second": 2.76,
716
+ "eval_steps_per_second": 1.38,
717
+ "step": 100
718
+ }
719
+ ],
720
+ "logging_steps": 1.0,
721
+ "max_steps": 849,
722
+ "num_input_tokens_seen": 0,
723
+ "num_train_epochs": 1,
724
+ "save_steps": 100,
725
+ "total_flos": 4.587027390739251e+16,
726
+ "train_batch_size": 2,
727
+ "trial_name": null,
728
+ "trial_params": null
729
+ }
checkpoint-100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc06bccd88c12bdcde2e7c89042c088b7ef7838c421f9aaa174c41cce84686e1
3
+ size 5176
checkpoint-200/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: cognitivecomputations/dolphin-2.9-llama3-8b
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.10.0
checkpoint-200/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "cognitivecomputations/dolphin-2.9-llama3-8b",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": "unsloth",
22
+ "target_modules": [
23
+ "v_proj",
24
+ "k_proj",
25
+ "down_proj",
26
+ "gate_proj",
27
+ "q_proj",
28
+ "up_proj",
29
+ "o_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-200/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fd8aeb39f9327d523f26cf3b86b07bb918f03714153f53c779c99f3f5764617
3
+ size 167832240
checkpoint-200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a58970dab5c1b0959a2090572bf2b13e852d813a2cc8a85e9fe1a1a82f3dd22
3
+ size 84570708
checkpoint-200/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c15e4ea835902fd054a1cd08e0c621566e05782e6ccb067c37251b8ecd70033
3
+ size 14512
checkpoint-200/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a63778c7d87efb91f6879293f241b37481726c45540b7d3bb6dabb8836a0b28
3
+ size 14512
checkpoint-200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b838a360320fce46e3655ebb3c6c47fcbd6396c681b491d60cf04e50a31fe717
3
+ size 1064
checkpoint-200/special_tokens_map.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|im_start|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ }
10
+ ],
11
+ "bos_token": {
12
+ "content": "<|begin_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "eos_token": {
19
+ "content": "<|im_end|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "pad_token": {
26
+ "content": "<|end_of_text|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ }
32
+ }
checkpoint-200/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-200/tokenizer_config.json ADDED
@@ -0,0 +1,2084 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ },
2051
+ "128256": {
2052
+ "content": "<|im_end|>",
2053
+ "lstrip": false,
2054
+ "normalized": false,
2055
+ "rstrip": false,
2056
+ "single_word": false,
2057
+ "special": true
2058
+ },
2059
+ "128257": {
2060
+ "content": "<|im_start|>",
2061
+ "lstrip": false,
2062
+ "normalized": false,
2063
+ "rstrip": false,
2064
+ "single_word": false,
2065
+ "special": true
2066
+ }
2067
+ },
2068
+ "additional_special_tokens": [
2069
+ "<|im_start|>"
2070
+ ],
2071
+ "bos_token": "<|begin_of_text|>",
2072
+ "chat_template": "{% set system_message = 'Du bist ein freundlicher und hilfsbereiter KI-Assistent.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\\n' + system_message + '<|im_end|>\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\\n' + content + '<|im_end|>\\n<|im_start|>assistant\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\\n' }}{% endif %}{% endfor %}",
2073
+ "clean_up_tokenization_spaces": true,
2074
+ "eos_token": "<|im_end|>",
2075
+ "model_input_names": [
2076
+ "input_ids",
2077
+ "attention_mask"
2078
+ ],
2079
+ "model_max_length": 1000000000000000019884624838656,
2080
+ "pad_token": "<|end_of_text|>",
2081
+ "padding_side": "right",
2082
+ "split_special_tokens": false,
2083
+ "tokenizer_class": "PreTrainedTokenizerFast"
2084
+ }
checkpoint-200/trainer_state.json ADDED
@@ -0,0 +1,1437 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.0012115240097046,
3
+ "best_model_checkpoint": "/kaggle/working/LLaMA-Factory/output/dolphin-2.9-llama3-8b-GER/checkpoint-200",
4
+ "epoch": 0.23557126030624265,
5
+ "eval_steps": 100,
6
+ "global_step": 200,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "grad_norm": 0.5445218086242676,
14
+ "learning_rate": 2.5e-06,
15
+ "loss": 1.2105,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0,
20
+ "grad_norm": 0.4362960457801819,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.9311,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.0,
27
+ "grad_norm": 0.5098525881767273,
28
+ "learning_rate": 7.5e-06,
29
+ "loss": 1.3604,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.0,
34
+ "grad_norm": 1.0830402374267578,
35
+ "learning_rate": 1e-05,
36
+ "loss": 1.5808,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.01,
41
+ "grad_norm": 0.5936903953552246,
42
+ "learning_rate": 1.25e-05,
43
+ "loss": 1.248,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.01,
48
+ "grad_norm": 0.7212775945663452,
49
+ "learning_rate": 1.5e-05,
50
+ "loss": 1.2712,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.01,
55
+ "grad_norm": 0.4733128845691681,
56
+ "learning_rate": 1.75e-05,
57
+ "loss": 1.3005,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.01,
62
+ "grad_norm": 0.6236618757247925,
63
+ "learning_rate": 2e-05,
64
+ "loss": 1.3398,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.01,
69
+ "grad_norm": 0.5326029658317566,
70
+ "learning_rate": 2.25e-05,
71
+ "loss": 1.0476,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.01,
76
+ "grad_norm": 0.5021428465843201,
77
+ "learning_rate": 2.5e-05,
78
+ "loss": 1.1245,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.01,
83
+ "grad_norm": 0.46588796377182007,
84
+ "learning_rate": 2.7500000000000004e-05,
85
+ "loss": 1.1041,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.01,
90
+ "grad_norm": 0.936045229434967,
91
+ "learning_rate": 3e-05,
92
+ "loss": 1.3201,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.02,
97
+ "grad_norm": 0.5649005770683289,
98
+ "learning_rate": 3.2500000000000004e-05,
99
+ "loss": 1.1596,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.02,
104
+ "grad_norm": 0.5679148435592651,
105
+ "learning_rate": 3.5e-05,
106
+ "loss": 1.2501,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.02,
111
+ "grad_norm": 0.8638319373130798,
112
+ "learning_rate": 3.7500000000000003e-05,
113
+ "loss": 1.237,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.02,
118
+ "grad_norm": 0.5722486972808838,
119
+ "learning_rate": 4e-05,
120
+ "loss": 1.2616,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.02,
125
+ "grad_norm": 0.5802999138832092,
126
+ "learning_rate": 4.25e-05,
127
+ "loss": 0.9578,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.02,
132
+ "grad_norm": 1.2806150913238525,
133
+ "learning_rate": 4.5e-05,
134
+ "loss": 1.3815,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.02,
139
+ "grad_norm": 0.5839210748672485,
140
+ "learning_rate": 4.75e-05,
141
+ "loss": 1.2619,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.02,
146
+ "grad_norm": 0.7132797837257385,
147
+ "learning_rate": 5e-05,
148
+ "loss": 1.2842,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.02,
153
+ "grad_norm": 0.7936571836471558,
154
+ "learning_rate": 5.25e-05,
155
+ "loss": 1.3991,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.03,
160
+ "grad_norm": 0.7268731594085693,
161
+ "learning_rate": 5.500000000000001e-05,
162
+ "loss": 1.2217,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.03,
167
+ "grad_norm": 0.6649657487869263,
168
+ "learning_rate": 5.7499999999999995e-05,
169
+ "loss": 1.2485,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.03,
174
+ "grad_norm": 0.45912331342697144,
175
+ "learning_rate": 6e-05,
176
+ "loss": 1.1452,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.03,
181
+ "grad_norm": 0.49475613236427307,
182
+ "learning_rate": 6.25e-05,
183
+ "loss": 1.256,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.03,
188
+ "grad_norm": 0.6027999520301819,
189
+ "learning_rate": 6.500000000000001e-05,
190
+ "loss": 1.2267,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.03,
195
+ "grad_norm": 0.48380520939826965,
196
+ "learning_rate": 6.750000000000001e-05,
197
+ "loss": 1.202,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.03,
202
+ "grad_norm": 0.6623361706733704,
203
+ "learning_rate": 7e-05,
204
+ "loss": 1.3924,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.03,
209
+ "grad_norm": 0.6632773280143738,
210
+ "learning_rate": 7.25e-05,
211
+ "loss": 1.2443,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.04,
216
+ "grad_norm": 0.5974243879318237,
217
+ "learning_rate": 7.500000000000001e-05,
218
+ "loss": 1.0591,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.04,
223
+ "grad_norm": 0.7902927398681641,
224
+ "learning_rate": 7.75e-05,
225
+ "loss": 1.0192,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.04,
230
+ "grad_norm": 0.7081462144851685,
231
+ "learning_rate": 8e-05,
232
+ "loss": 1.0955,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.04,
237
+ "grad_norm": 0.4744333326816559,
238
+ "learning_rate": 8.25e-05,
239
+ "loss": 1.0564,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.04,
244
+ "grad_norm": 0.703999400138855,
245
+ "learning_rate": 8.5e-05,
246
+ "loss": 1.1022,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.04,
251
+ "grad_norm": 0.5378603339195251,
252
+ "learning_rate": 8.75e-05,
253
+ "loss": 1.063,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.04,
258
+ "grad_norm": 0.6105419397354126,
259
+ "learning_rate": 9e-05,
260
+ "loss": 0.9748,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.04,
265
+ "grad_norm": 0.6250177025794983,
266
+ "learning_rate": 9.250000000000001e-05,
267
+ "loss": 0.9951,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.04,
272
+ "grad_norm": 0.6306005716323853,
273
+ "learning_rate": 9.5e-05,
274
+ "loss": 0.9875,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.05,
279
+ "grad_norm": 0.8635210990905762,
280
+ "learning_rate": 9.75e-05,
281
+ "loss": 1.1825,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.05,
286
+ "grad_norm": 0.5938963890075684,
287
+ "learning_rate": 0.0001,
288
+ "loss": 0.9678,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.05,
293
+ "grad_norm": 0.5765062570571899,
294
+ "learning_rate": 0.0001025,
295
+ "loss": 1.1031,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.05,
300
+ "grad_norm": 0.5162666440010071,
301
+ "learning_rate": 0.000105,
302
+ "loss": 1.0831,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.05,
307
+ "grad_norm": 0.8675170540809631,
308
+ "learning_rate": 0.0001075,
309
+ "loss": 1.0034,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.05,
314
+ "grad_norm": 0.44026264548301697,
315
+ "learning_rate": 0.00011000000000000002,
316
+ "loss": 0.9607,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.05,
321
+ "grad_norm": 0.4922897219657898,
322
+ "learning_rate": 0.00011250000000000001,
323
+ "loss": 1.0251,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.05,
328
+ "grad_norm": 0.5505048632621765,
329
+ "learning_rate": 0.00011499999999999999,
330
+ "loss": 0.6948,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.06,
335
+ "grad_norm": 0.5226988792419434,
336
+ "learning_rate": 0.00011750000000000001,
337
+ "loss": 1.2259,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.06,
342
+ "grad_norm": 0.5105571150779724,
343
+ "learning_rate": 0.00012,
344
+ "loss": 1.1239,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.06,
349
+ "grad_norm": 2.0914857387542725,
350
+ "learning_rate": 0.00012250000000000002,
351
+ "loss": 1.4032,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.06,
356
+ "grad_norm": 0.4611998498439789,
357
+ "learning_rate": 0.000125,
358
+ "loss": 1.1481,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.06,
363
+ "grad_norm": 0.5243968367576599,
364
+ "learning_rate": 0.0001275,
365
+ "loss": 1.0514,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.06,
370
+ "grad_norm": 0.48045778274536133,
371
+ "learning_rate": 0.00013000000000000002,
372
+ "loss": 1.1552,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.06,
377
+ "grad_norm": 0.5543797612190247,
378
+ "learning_rate": 0.0001325,
379
+ "loss": 1.035,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.06,
384
+ "grad_norm": 0.5148913264274597,
385
+ "learning_rate": 0.00013500000000000003,
386
+ "loss": 0.9244,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.06,
391
+ "grad_norm": 0.5708130598068237,
392
+ "learning_rate": 0.0001375,
393
+ "loss": 1.2272,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.07,
398
+ "grad_norm": 0.7507888078689575,
399
+ "learning_rate": 0.00014,
400
+ "loss": 1.1196,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.07,
405
+ "grad_norm": 0.5411068201065063,
406
+ "learning_rate": 0.00014250000000000002,
407
+ "loss": 1.1444,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.07,
412
+ "grad_norm": 0.7314138412475586,
413
+ "learning_rate": 0.000145,
414
+ "loss": 1.3451,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.07,
419
+ "grad_norm": 0.5134022831916809,
420
+ "learning_rate": 0.0001475,
421
+ "loss": 0.8021,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.07,
426
+ "grad_norm": 0.7859703302383423,
427
+ "learning_rate": 0.00015000000000000001,
428
+ "loss": 0.952,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.07,
433
+ "grad_norm": 0.4740566611289978,
434
+ "learning_rate": 0.0001525,
435
+ "loss": 0.8878,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.07,
440
+ "grad_norm": 0.8245677947998047,
441
+ "learning_rate": 0.000155,
442
+ "loss": 1.4341,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.07,
447
+ "grad_norm": 0.5067218542098999,
448
+ "learning_rate": 0.0001575,
449
+ "loss": 0.8404,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.08,
454
+ "grad_norm": 0.40824806690216064,
455
+ "learning_rate": 0.00016,
456
+ "loss": 1.0943,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.08,
461
+ "grad_norm": 0.428151935338974,
462
+ "learning_rate": 0.00016250000000000002,
463
+ "loss": 1.0819,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.08,
468
+ "grad_norm": 0.437532901763916,
469
+ "learning_rate": 0.000165,
470
+ "loss": 1.0461,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.08,
475
+ "grad_norm": 0.4619809091091156,
476
+ "learning_rate": 0.0001675,
477
+ "loss": 1.0232,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.08,
482
+ "grad_norm": 1.3247042894363403,
483
+ "learning_rate": 0.00017,
484
+ "loss": 1.218,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.08,
489
+ "grad_norm": 0.5896454453468323,
490
+ "learning_rate": 0.00017250000000000002,
491
+ "loss": 1.1953,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.08,
496
+ "grad_norm": 0.5605736970901489,
497
+ "learning_rate": 0.000175,
498
+ "loss": 1.2542,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.08,
503
+ "grad_norm": 0.36923155188560486,
504
+ "learning_rate": 0.0001775,
505
+ "loss": 0.7096,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.08,
510
+ "grad_norm": 0.6809273362159729,
511
+ "learning_rate": 0.00018,
512
+ "loss": 1.1959,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.09,
517
+ "grad_norm": 0.42645493149757385,
518
+ "learning_rate": 0.0001825,
519
+ "loss": 1.1829,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.09,
524
+ "grad_norm": 0.7621450424194336,
525
+ "learning_rate": 0.00018500000000000002,
526
+ "loss": 1.1599,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.09,
531
+ "grad_norm": 0.5299301743507385,
532
+ "learning_rate": 0.0001875,
533
+ "loss": 1.0546,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.09,
538
+ "grad_norm": 0.484611451625824,
539
+ "learning_rate": 0.00019,
540
+ "loss": 1.0854,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.09,
545
+ "grad_norm": 0.4027417004108429,
546
+ "learning_rate": 0.00019250000000000002,
547
+ "loss": 0.7812,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.09,
552
+ "grad_norm": 0.7537221908569336,
553
+ "learning_rate": 0.000195,
554
+ "loss": 0.9719,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.09,
559
+ "grad_norm": 0.45811474323272705,
560
+ "learning_rate": 0.00019750000000000003,
561
+ "loss": 0.9684,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.09,
566
+ "grad_norm": 0.5426852107048035,
567
+ "learning_rate": 0.0002,
568
+ "loss": 0.9451,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.1,
573
+ "grad_norm": 0.48964977264404297,
574
+ "learning_rate": 0.000199739921976593,
575
+ "loss": 1.0807,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.1,
580
+ "grad_norm": 0.6225113272666931,
581
+ "learning_rate": 0.00019947984395318597,
582
+ "loss": 1.1913,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.1,
587
+ "grad_norm": 0.47157713770866394,
588
+ "learning_rate": 0.00019921976592977893,
589
+ "loss": 1.0392,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.1,
594
+ "grad_norm": 0.42048129439353943,
595
+ "learning_rate": 0.0001989596879063719,
596
+ "loss": 0.8439,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.1,
601
+ "grad_norm": 0.4129664897918701,
602
+ "learning_rate": 0.0001986996098829649,
603
+ "loss": 1.1025,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.1,
608
+ "grad_norm": 0.5610629320144653,
609
+ "learning_rate": 0.00019843953185955788,
610
+ "loss": 0.9368,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.1,
615
+ "grad_norm": 0.4288642406463623,
616
+ "learning_rate": 0.00019817945383615086,
617
+ "loss": 0.9711,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.1,
622
+ "grad_norm": 0.572507917881012,
623
+ "learning_rate": 0.0001979193758127438,
624
+ "loss": 0.9739,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.1,
629
+ "grad_norm": 0.5115912556648254,
630
+ "learning_rate": 0.0001976592977893368,
631
+ "loss": 0.9356,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.11,
636
+ "grad_norm": 0.608063280582428,
637
+ "learning_rate": 0.00019739921976592978,
638
+ "loss": 1.2459,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.11,
643
+ "grad_norm": 1.0171502828598022,
644
+ "learning_rate": 0.00019713914174252276,
645
+ "loss": 1.0629,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.11,
650
+ "grad_norm": 0.514552116394043,
651
+ "learning_rate": 0.00019687906371911574,
652
+ "loss": 0.9646,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.11,
657
+ "grad_norm": 0.4363428056240082,
658
+ "learning_rate": 0.00019661898569570872,
659
+ "loss": 0.8659,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.11,
664
+ "grad_norm": 0.4470008611679077,
665
+ "learning_rate": 0.0001963589076723017,
666
+ "loss": 1.0338,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.11,
671
+ "grad_norm": 0.5710871815681458,
672
+ "learning_rate": 0.0001960988296488947,
673
+ "loss": 0.946,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.11,
678
+ "grad_norm": 0.6456964612007141,
679
+ "learning_rate": 0.00019583875162548767,
680
+ "loss": 1.0956,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.11,
685
+ "grad_norm": 0.45742425322532654,
686
+ "learning_rate": 0.00019557867360208065,
687
+ "loss": 0.7985,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.12,
692
+ "grad_norm": 0.9953218698501587,
693
+ "learning_rate": 0.0001953185955786736,
694
+ "loss": 0.9476,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.12,
699
+ "grad_norm": 0.5075244307518005,
700
+ "learning_rate": 0.0001950585175552666,
701
+ "loss": 1.1704,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.12,
706
+ "grad_norm": 0.7076822519302368,
707
+ "learning_rate": 0.00019479843953185957,
708
+ "loss": 1.2054,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.12,
713
+ "eval_loss": 1.0368528366088867,
714
+ "eval_runtime": 547.1826,
715
+ "eval_samples_per_second": 2.76,
716
+ "eval_steps_per_second": 1.38,
717
+ "step": 100
718
+ },
719
+ {
720
+ "epoch": 0.12,
721
+ "grad_norm": 0.7408495545387268,
722
+ "learning_rate": 0.00019453836150845255,
723
+ "loss": 1.3149,
724
+ "step": 101
725
+ },
726
+ {
727
+ "epoch": 0.12,
728
+ "grad_norm": 0.5010321736335754,
729
+ "learning_rate": 0.00019427828348504554,
730
+ "loss": 0.8483,
731
+ "step": 102
732
+ },
733
+ {
734
+ "epoch": 0.12,
735
+ "grad_norm": 0.5388755798339844,
736
+ "learning_rate": 0.0001940182054616385,
737
+ "loss": 1.034,
738
+ "step": 103
739
+ },
740
+ {
741
+ "epoch": 0.12,
742
+ "grad_norm": 0.32918357849121094,
743
+ "learning_rate": 0.00019375812743823147,
744
+ "loss": 1.0762,
745
+ "step": 104
746
+ },
747
+ {
748
+ "epoch": 0.12,
749
+ "grad_norm": 0.4812282919883728,
750
+ "learning_rate": 0.00019349804941482446,
751
+ "loss": 1.0797,
752
+ "step": 105
753
+ },
754
+ {
755
+ "epoch": 0.12,
756
+ "grad_norm": 0.6160157918930054,
757
+ "learning_rate": 0.00019323797139141744,
758
+ "loss": 0.9488,
759
+ "step": 106
760
+ },
761
+ {
762
+ "epoch": 0.13,
763
+ "grad_norm": 0.41306182742118835,
764
+ "learning_rate": 0.00019297789336801042,
765
+ "loss": 1.0742,
766
+ "step": 107
767
+ },
768
+ {
769
+ "epoch": 0.13,
770
+ "grad_norm": 0.5411396026611328,
771
+ "learning_rate": 0.00019271781534460338,
772
+ "loss": 1.1162,
773
+ "step": 108
774
+ },
775
+ {
776
+ "epoch": 0.13,
777
+ "grad_norm": 0.45688003301620483,
778
+ "learning_rate": 0.00019245773732119636,
779
+ "loss": 0.8042,
780
+ "step": 109
781
+ },
782
+ {
783
+ "epoch": 0.13,
784
+ "grad_norm": 0.4660446047782898,
785
+ "learning_rate": 0.00019219765929778934,
786
+ "loss": 0.8234,
787
+ "step": 110
788
+ },
789
+ {
790
+ "epoch": 0.13,
791
+ "grad_norm": 0.6277762055397034,
792
+ "learning_rate": 0.00019193758127438232,
793
+ "loss": 1.0324,
794
+ "step": 111
795
+ },
796
+ {
797
+ "epoch": 0.13,
798
+ "grad_norm": 0.6119320392608643,
799
+ "learning_rate": 0.0001916775032509753,
800
+ "loss": 0.6912,
801
+ "step": 112
802
+ },
803
+ {
804
+ "epoch": 0.13,
805
+ "grad_norm": 0.5463618040084839,
806
+ "learning_rate": 0.00019141742522756826,
807
+ "loss": 1.1297,
808
+ "step": 113
809
+ },
810
+ {
811
+ "epoch": 0.13,
812
+ "grad_norm": 0.4918029010295868,
813
+ "learning_rate": 0.00019115734720416124,
814
+ "loss": 1.0857,
815
+ "step": 114
816
+ },
817
+ {
818
+ "epoch": 0.14,
819
+ "grad_norm": 0.4734187424182892,
820
+ "learning_rate": 0.00019089726918075422,
821
+ "loss": 1.0246,
822
+ "step": 115
823
+ },
824
+ {
825
+ "epoch": 0.14,
826
+ "grad_norm": 0.5416173934936523,
827
+ "learning_rate": 0.0001906371911573472,
828
+ "loss": 1.0262,
829
+ "step": 116
830
+ },
831
+ {
832
+ "epoch": 0.14,
833
+ "grad_norm": 0.486284464597702,
834
+ "learning_rate": 0.0001903771131339402,
835
+ "loss": 1.2198,
836
+ "step": 117
837
+ },
838
+ {
839
+ "epoch": 0.14,
840
+ "grad_norm": 0.4003067910671234,
841
+ "learning_rate": 0.00019011703511053317,
842
+ "loss": 0.8525,
843
+ "step": 118
844
+ },
845
+ {
846
+ "epoch": 0.14,
847
+ "grad_norm": 0.38142916560173035,
848
+ "learning_rate": 0.00018985695708712615,
849
+ "loss": 1.1475,
850
+ "step": 119
851
+ },
852
+ {
853
+ "epoch": 0.14,
854
+ "grad_norm": 0.42364147305488586,
855
+ "learning_rate": 0.00018959687906371913,
856
+ "loss": 0.8207,
857
+ "step": 120
858
+ },
859
+ {
860
+ "epoch": 0.14,
861
+ "grad_norm": 0.384432852268219,
862
+ "learning_rate": 0.00018933680104031212,
863
+ "loss": 0.9451,
864
+ "step": 121
865
+ },
866
+ {
867
+ "epoch": 0.14,
868
+ "grad_norm": 0.38188567757606506,
869
+ "learning_rate": 0.0001890767230169051,
870
+ "loss": 0.921,
871
+ "step": 122
872
+ },
873
+ {
874
+ "epoch": 0.14,
875
+ "grad_norm": 0.4212167263031006,
876
+ "learning_rate": 0.00018881664499349805,
877
+ "loss": 0.8532,
878
+ "step": 123
879
+ },
880
+ {
881
+ "epoch": 0.15,
882
+ "grad_norm": 0.7674171924591064,
883
+ "learning_rate": 0.00018855656697009104,
884
+ "loss": 1.1751,
885
+ "step": 124
886
+ },
887
+ {
888
+ "epoch": 0.15,
889
+ "grad_norm": 0.4111984074115753,
890
+ "learning_rate": 0.00018829648894668402,
891
+ "loss": 0.906,
892
+ "step": 125
893
+ },
894
+ {
895
+ "epoch": 0.15,
896
+ "grad_norm": 0.6682639718055725,
897
+ "learning_rate": 0.000188036410923277,
898
+ "loss": 1.1284,
899
+ "step": 126
900
+ },
901
+ {
902
+ "epoch": 0.15,
903
+ "grad_norm": 0.3887438178062439,
904
+ "learning_rate": 0.00018777633289986998,
905
+ "loss": 1.0324,
906
+ "step": 127
907
+ },
908
+ {
909
+ "epoch": 0.15,
910
+ "grad_norm": 0.5829350352287292,
911
+ "learning_rate": 0.00018751625487646294,
912
+ "loss": 1.038,
913
+ "step": 128
914
+ },
915
+ {
916
+ "epoch": 0.15,
917
+ "grad_norm": 0.5861855149269104,
918
+ "learning_rate": 0.00018725617685305592,
919
+ "loss": 0.9453,
920
+ "step": 129
921
+ },
922
+ {
923
+ "epoch": 0.15,
924
+ "grad_norm": 0.40044718980789185,
925
+ "learning_rate": 0.0001869960988296489,
926
+ "loss": 1.1971,
927
+ "step": 130
928
+ },
929
+ {
930
+ "epoch": 0.15,
931
+ "grad_norm": 0.4322098195552826,
932
+ "learning_rate": 0.00018673602080624188,
933
+ "loss": 0.9792,
934
+ "step": 131
935
+ },
936
+ {
937
+ "epoch": 0.16,
938
+ "grad_norm": 0.4132952392101288,
939
+ "learning_rate": 0.00018647594278283487,
940
+ "loss": 0.9597,
941
+ "step": 132
942
+ },
943
+ {
944
+ "epoch": 0.16,
945
+ "grad_norm": 0.4141194224357605,
946
+ "learning_rate": 0.00018621586475942782,
947
+ "loss": 1.0785,
948
+ "step": 133
949
+ },
950
+ {
951
+ "epoch": 0.16,
952
+ "grad_norm": 0.5526332855224609,
953
+ "learning_rate": 0.0001859557867360208,
954
+ "loss": 1.0762,
955
+ "step": 134
956
+ },
957
+ {
958
+ "epoch": 0.16,
959
+ "grad_norm": 0.6953147053718567,
960
+ "learning_rate": 0.00018569570871261379,
961
+ "loss": 1.1048,
962
+ "step": 135
963
+ },
964
+ {
965
+ "epoch": 0.16,
966
+ "grad_norm": 0.4306538701057434,
967
+ "learning_rate": 0.00018543563068920677,
968
+ "loss": 0.9798,
969
+ "step": 136
970
+ },
971
+ {
972
+ "epoch": 0.16,
973
+ "grad_norm": 0.32605746388435364,
974
+ "learning_rate": 0.00018517555266579975,
975
+ "loss": 0.9825,
976
+ "step": 137
977
+ },
978
+ {
979
+ "epoch": 0.16,
980
+ "grad_norm": 0.48711439967155457,
981
+ "learning_rate": 0.0001849154746423927,
982
+ "loss": 0.9685,
983
+ "step": 138
984
+ },
985
+ {
986
+ "epoch": 0.16,
987
+ "grad_norm": 0.7728849649429321,
988
+ "learning_rate": 0.0001846553966189857,
989
+ "loss": 1.2843,
990
+ "step": 139
991
+ },
992
+ {
993
+ "epoch": 0.16,
994
+ "grad_norm": 0.38121744990348816,
995
+ "learning_rate": 0.00018439531859557867,
996
+ "loss": 0.8289,
997
+ "step": 140
998
+ },
999
+ {
1000
+ "epoch": 0.17,
1001
+ "grad_norm": 0.5053502321243286,
1002
+ "learning_rate": 0.00018413524057217165,
1003
+ "loss": 1.0824,
1004
+ "step": 141
1005
+ },
1006
+ {
1007
+ "epoch": 0.17,
1008
+ "grad_norm": 0.44003796577453613,
1009
+ "learning_rate": 0.00018387516254876463,
1010
+ "loss": 1.0957,
1011
+ "step": 142
1012
+ },
1013
+ {
1014
+ "epoch": 0.17,
1015
+ "grad_norm": 0.35713884234428406,
1016
+ "learning_rate": 0.00018361508452535762,
1017
+ "loss": 0.7869,
1018
+ "step": 143
1019
+ },
1020
+ {
1021
+ "epoch": 0.17,
1022
+ "grad_norm": 0.6612699627876282,
1023
+ "learning_rate": 0.0001833550065019506,
1024
+ "loss": 1.1621,
1025
+ "step": 144
1026
+ },
1027
+ {
1028
+ "epoch": 0.17,
1029
+ "grad_norm": 0.4270091950893402,
1030
+ "learning_rate": 0.00018309492847854358,
1031
+ "loss": 0.8964,
1032
+ "step": 145
1033
+ },
1034
+ {
1035
+ "epoch": 0.17,
1036
+ "grad_norm": 0.42207202315330505,
1037
+ "learning_rate": 0.00018283485045513656,
1038
+ "loss": 1.1403,
1039
+ "step": 146
1040
+ },
1041
+ {
1042
+ "epoch": 0.17,
1043
+ "grad_norm": 0.48486125469207764,
1044
+ "learning_rate": 0.00018257477243172954,
1045
+ "loss": 0.9993,
1046
+ "step": 147
1047
+ },
1048
+ {
1049
+ "epoch": 0.17,
1050
+ "grad_norm": 0.4205480217933655,
1051
+ "learning_rate": 0.0001823146944083225,
1052
+ "loss": 1.0404,
1053
+ "step": 148
1054
+ },
1055
+ {
1056
+ "epoch": 0.18,
1057
+ "grad_norm": 0.3420919179916382,
1058
+ "learning_rate": 0.00018205461638491548,
1059
+ "loss": 1.1434,
1060
+ "step": 149
1061
+ },
1062
+ {
1063
+ "epoch": 0.18,
1064
+ "grad_norm": 0.6411290168762207,
1065
+ "learning_rate": 0.00018179453836150846,
1066
+ "loss": 1.2055,
1067
+ "step": 150
1068
+ },
1069
+ {
1070
+ "epoch": 0.18,
1071
+ "grad_norm": 0.7193886637687683,
1072
+ "learning_rate": 0.00018153446033810145,
1073
+ "loss": 0.9436,
1074
+ "step": 151
1075
+ },
1076
+ {
1077
+ "epoch": 0.18,
1078
+ "grad_norm": 0.34661969542503357,
1079
+ "learning_rate": 0.00018127438231469443,
1080
+ "loss": 0.8158,
1081
+ "step": 152
1082
+ },
1083
+ {
1084
+ "epoch": 0.18,
1085
+ "grad_norm": 0.4028843939304352,
1086
+ "learning_rate": 0.00018101430429128738,
1087
+ "loss": 0.9863,
1088
+ "step": 153
1089
+ },
1090
+ {
1091
+ "epoch": 0.18,
1092
+ "grad_norm": 0.3898251950740814,
1093
+ "learning_rate": 0.00018075422626788037,
1094
+ "loss": 0.9215,
1095
+ "step": 154
1096
+ },
1097
+ {
1098
+ "epoch": 0.18,
1099
+ "grad_norm": 0.3827955424785614,
1100
+ "learning_rate": 0.00018049414824447335,
1101
+ "loss": 0.9513,
1102
+ "step": 155
1103
+ },
1104
+ {
1105
+ "epoch": 0.18,
1106
+ "grad_norm": 0.3840239644050598,
1107
+ "learning_rate": 0.00018023407022106633,
1108
+ "loss": 0.8303,
1109
+ "step": 156
1110
+ },
1111
+ {
1112
+ "epoch": 0.18,
1113
+ "grad_norm": 0.42413073778152466,
1114
+ "learning_rate": 0.0001799739921976593,
1115
+ "loss": 0.8909,
1116
+ "step": 157
1117
+ },
1118
+ {
1119
+ "epoch": 0.19,
1120
+ "grad_norm": 0.47216784954071045,
1121
+ "learning_rate": 0.00017971391417425227,
1122
+ "loss": 1.0413,
1123
+ "step": 158
1124
+ },
1125
+ {
1126
+ "epoch": 0.19,
1127
+ "grad_norm": 0.35447853803634644,
1128
+ "learning_rate": 0.00017945383615084525,
1129
+ "loss": 0.9781,
1130
+ "step": 159
1131
+ },
1132
+ {
1133
+ "epoch": 0.19,
1134
+ "grad_norm": 0.46554017066955566,
1135
+ "learning_rate": 0.00017919375812743823,
1136
+ "loss": 0.7186,
1137
+ "step": 160
1138
+ },
1139
+ {
1140
+ "epoch": 0.19,
1141
+ "grad_norm": 0.3696407973766327,
1142
+ "learning_rate": 0.00017893368010403121,
1143
+ "loss": 1.0137,
1144
+ "step": 161
1145
+ },
1146
+ {
1147
+ "epoch": 0.19,
1148
+ "grad_norm": 0.5633952617645264,
1149
+ "learning_rate": 0.0001786736020806242,
1150
+ "loss": 1.0944,
1151
+ "step": 162
1152
+ },
1153
+ {
1154
+ "epoch": 0.19,
1155
+ "grad_norm": 0.3334963917732239,
1156
+ "learning_rate": 0.00017841352405721715,
1157
+ "loss": 1.2606,
1158
+ "step": 163
1159
+ },
1160
+ {
1161
+ "epoch": 0.19,
1162
+ "grad_norm": 0.4501505494117737,
1163
+ "learning_rate": 0.00017815344603381013,
1164
+ "loss": 0.7306,
1165
+ "step": 164
1166
+ },
1167
+ {
1168
+ "epoch": 0.19,
1169
+ "grad_norm": 0.44553884863853455,
1170
+ "learning_rate": 0.00017789336801040312,
1171
+ "loss": 0.871,
1172
+ "step": 165
1173
+ },
1174
+ {
1175
+ "epoch": 0.2,
1176
+ "grad_norm": 0.474342405796051,
1177
+ "learning_rate": 0.0001776332899869961,
1178
+ "loss": 0.7593,
1179
+ "step": 166
1180
+ },
1181
+ {
1182
+ "epoch": 0.2,
1183
+ "grad_norm": 0.7258349061012268,
1184
+ "learning_rate": 0.00017737321196358908,
1185
+ "loss": 1.4035,
1186
+ "step": 167
1187
+ },
1188
+ {
1189
+ "epoch": 0.2,
1190
+ "grad_norm": 0.43586501479148865,
1191
+ "learning_rate": 0.00017711313394018206,
1192
+ "loss": 1.1679,
1193
+ "step": 168
1194
+ },
1195
+ {
1196
+ "epoch": 0.2,
1197
+ "grad_norm": 0.4580634832382202,
1198
+ "learning_rate": 0.00017685305591677504,
1199
+ "loss": 0.9496,
1200
+ "step": 169
1201
+ },
1202
+ {
1203
+ "epoch": 0.2,
1204
+ "grad_norm": 0.40509316325187683,
1205
+ "learning_rate": 0.00017659297789336803,
1206
+ "loss": 0.9515,
1207
+ "step": 170
1208
+ },
1209
+ {
1210
+ "epoch": 0.2,
1211
+ "grad_norm": 0.3496972620487213,
1212
+ "learning_rate": 0.000176332899869961,
1213
+ "loss": 1.1846,
1214
+ "step": 171
1215
+ },
1216
+ {
1217
+ "epoch": 0.2,
1218
+ "grad_norm": 0.6468595862388611,
1219
+ "learning_rate": 0.000176072821846554,
1220
+ "loss": 1.0307,
1221
+ "step": 172
1222
+ },
1223
+ {
1224
+ "epoch": 0.2,
1225
+ "grad_norm": 0.3840126693248749,
1226
+ "learning_rate": 0.00017581274382314695,
1227
+ "loss": 1.0248,
1228
+ "step": 173
1229
+ },
1230
+ {
1231
+ "epoch": 0.2,
1232
+ "grad_norm": 0.4715554118156433,
1233
+ "learning_rate": 0.00017555266579973993,
1234
+ "loss": 1.1017,
1235
+ "step": 174
1236
+ },
1237
+ {
1238
+ "epoch": 0.21,
1239
+ "grad_norm": 0.38534194231033325,
1240
+ "learning_rate": 0.0001752925877763329,
1241
+ "loss": 1.0073,
1242
+ "step": 175
1243
+ },
1244
+ {
1245
+ "epoch": 0.21,
1246
+ "grad_norm": 0.3881916403770447,
1247
+ "learning_rate": 0.0001750325097529259,
1248
+ "loss": 0.8961,
1249
+ "step": 176
1250
+ },
1251
+ {
1252
+ "epoch": 0.21,
1253
+ "grad_norm": 0.49220091104507446,
1254
+ "learning_rate": 0.00017477243172951887,
1255
+ "loss": 1.0184,
1256
+ "step": 177
1257
+ },
1258
+ {
1259
+ "epoch": 0.21,
1260
+ "grad_norm": 0.38170936703681946,
1261
+ "learning_rate": 0.00017451235370611186,
1262
+ "loss": 1.0939,
1263
+ "step": 178
1264
+ },
1265
+ {
1266
+ "epoch": 0.21,
1267
+ "grad_norm": 0.3692156672477722,
1268
+ "learning_rate": 0.0001742522756827048,
1269
+ "loss": 1.085,
1270
+ "step": 179
1271
+ },
1272
+ {
1273
+ "epoch": 0.21,
1274
+ "grad_norm": 0.43161171674728394,
1275
+ "learning_rate": 0.0001739921976592978,
1276
+ "loss": 0.9098,
1277
+ "step": 180
1278
+ },
1279
+ {
1280
+ "epoch": 0.21,
1281
+ "grad_norm": 0.3874380886554718,
1282
+ "learning_rate": 0.00017373211963589078,
1283
+ "loss": 1.0108,
1284
+ "step": 181
1285
+ },
1286
+ {
1287
+ "epoch": 0.21,
1288
+ "grad_norm": 0.37556958198547363,
1289
+ "learning_rate": 0.00017347204161248376,
1290
+ "loss": 1.0344,
1291
+ "step": 182
1292
+ },
1293
+ {
1294
+ "epoch": 0.22,
1295
+ "grad_norm": 0.4288795292377472,
1296
+ "learning_rate": 0.00017321196358907674,
1297
+ "loss": 0.9329,
1298
+ "step": 183
1299
+ },
1300
+ {
1301
+ "epoch": 0.22,
1302
+ "grad_norm": 0.6587222218513489,
1303
+ "learning_rate": 0.0001729518855656697,
1304
+ "loss": 1.0312,
1305
+ "step": 184
1306
+ },
1307
+ {
1308
+ "epoch": 0.22,
1309
+ "grad_norm": 0.6700361371040344,
1310
+ "learning_rate": 0.00017269180754226268,
1311
+ "loss": 1.035,
1312
+ "step": 185
1313
+ },
1314
+ {
1315
+ "epoch": 0.22,
1316
+ "grad_norm": 0.5208828449249268,
1317
+ "learning_rate": 0.00017243172951885566,
1318
+ "loss": 1.0334,
1319
+ "step": 186
1320
+ },
1321
+ {
1322
+ "epoch": 0.22,
1323
+ "grad_norm": 0.5774813294410706,
1324
+ "learning_rate": 0.00017217165149544864,
1325
+ "loss": 1.0366,
1326
+ "step": 187
1327
+ },
1328
+ {
1329
+ "epoch": 0.22,
1330
+ "grad_norm": 0.3492725193500519,
1331
+ "learning_rate": 0.00017191157347204162,
1332
+ "loss": 1.0225,
1333
+ "step": 188
1334
+ },
1335
+ {
1336
+ "epoch": 0.22,
1337
+ "grad_norm": 0.3714265525341034,
1338
+ "learning_rate": 0.00017165149544863458,
1339
+ "loss": 1.0355,
1340
+ "step": 189
1341
+ },
1342
+ {
1343
+ "epoch": 0.22,
1344
+ "grad_norm": 0.4425973892211914,
1345
+ "learning_rate": 0.00017139141742522756,
1346
+ "loss": 0.974,
1347
+ "step": 190
1348
+ },
1349
+ {
1350
+ "epoch": 0.22,
1351
+ "grad_norm": 0.43257299065589905,
1352
+ "learning_rate": 0.00017113133940182054,
1353
+ "loss": 0.8614,
1354
+ "step": 191
1355
+ },
1356
+ {
1357
+ "epoch": 0.23,
1358
+ "grad_norm": 0.37084296345710754,
1359
+ "learning_rate": 0.00017087126137841353,
1360
+ "loss": 0.7135,
1361
+ "step": 192
1362
+ },
1363
+ {
1364
+ "epoch": 0.23,
1365
+ "grad_norm": 0.6695109009742737,
1366
+ "learning_rate": 0.0001706111833550065,
1367
+ "loss": 0.7722,
1368
+ "step": 193
1369
+ },
1370
+ {
1371
+ "epoch": 0.23,
1372
+ "grad_norm": 0.5144183039665222,
1373
+ "learning_rate": 0.0001703511053315995,
1374
+ "loss": 0.9364,
1375
+ "step": 194
1376
+ },
1377
+ {
1378
+ "epoch": 0.23,
1379
+ "grad_norm": 0.58673095703125,
1380
+ "learning_rate": 0.00017009102730819247,
1381
+ "loss": 1.1141,
1382
+ "step": 195
1383
+ },
1384
+ {
1385
+ "epoch": 0.23,
1386
+ "grad_norm": 0.4033479392528534,
1387
+ "learning_rate": 0.00016983094928478545,
1388
+ "loss": 1.0002,
1389
+ "step": 196
1390
+ },
1391
+ {
1392
+ "epoch": 0.23,
1393
+ "grad_norm": 0.38111910223960876,
1394
+ "learning_rate": 0.00016957087126137844,
1395
+ "loss": 0.9318,
1396
+ "step": 197
1397
+ },
1398
+ {
1399
+ "epoch": 0.23,
1400
+ "grad_norm": 0.4174363613128662,
1401
+ "learning_rate": 0.00016931079323797142,
1402
+ "loss": 0.9381,
1403
+ "step": 198
1404
+ },
1405
+ {
1406
+ "epoch": 0.23,
1407
+ "grad_norm": 0.3726828098297119,
1408
+ "learning_rate": 0.00016905071521456437,
1409
+ "loss": 1.0405,
1410
+ "step": 199
1411
+ },
1412
+ {
1413
+ "epoch": 0.24,
1414
+ "grad_norm": 0.5414443612098694,
1415
+ "learning_rate": 0.00016879063719115736,
1416
+ "loss": 1.0667,
1417
+ "step": 200
1418
+ },
1419
+ {
1420
+ "epoch": 0.24,
1421
+ "eval_loss": 1.0012115240097046,
1422
+ "eval_runtime": 546.9226,
1423
+ "eval_samples_per_second": 2.761,
1424
+ "eval_steps_per_second": 1.38,
1425
+ "step": 200
1426
+ }
1427
+ ],
1428
+ "logging_steps": 1.0,
1429
+ "max_steps": 849,
1430
+ "num_input_tokens_seen": 0,
1431
+ "num_train_epochs": 1,
1432
+ "save_steps": 100,
1433
+ "total_flos": 9.369017756994765e+16,
1434
+ "train_batch_size": 2,
1435
+ "trial_name": null,
1436
+ "trial_params": null
1437
+ }
checkpoint-200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc06bccd88c12bdcde2e7c89042c088b7ef7838c421f9aaa174c41cce84686e1
3
+ size 5176
checkpoint-300/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: cognitivecomputations/dolphin-2.9-llama3-8b
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.10.0
checkpoint-300/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "cognitivecomputations/dolphin-2.9-llama3-8b",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": "unsloth",
22
+ "target_modules": [
23
+ "v_proj",
24
+ "k_proj",
25
+ "down_proj",
26
+ "gate_proj",
27
+ "q_proj",
28
+ "up_proj",
29
+ "o_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-300/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fcf8e24870c822336241cf251bc598cb9f5e96447732ddd709137ff74ea2a81
3
+ size 167832240
checkpoint-300/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:866301fa622a0467f8be7bbe13e098fd431ac7ab4f2dc1aa0565fbbdb41f7114
3
+ size 84571156
checkpoint-300/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e2179a9443411fe03fd0a870610f99f73cd94d0de1b5e8c382bd313cdd74f
3
+ size 14512
checkpoint-300/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce931da9682a851064f9e731d3f6cc76a7ef9a7498bcb0d380a3960b8e1e36b6
3
+ size 14512
checkpoint-300/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d33b04b90750ccdd1239c32bd437f39a8ff32167070ddc987aa20bb87100b3d3
3
+ size 1064
checkpoint-300/special_tokens_map.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|im_start|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ }
10
+ ],
11
+ "bos_token": {
12
+ "content": "<|begin_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "eos_token": {
19
+ "content": "<|im_end|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "pad_token": {
26
+ "content": "<|end_of_text|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ }
32
+ }
checkpoint-300/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-300/tokenizer_config.json ADDED
@@ -0,0 +1,2084 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ },
2051
+ "128256": {
2052
+ "content": "<|im_end|>",
2053
+ "lstrip": false,
2054
+ "normalized": false,
2055
+ "rstrip": false,
2056
+ "single_word": false,
2057
+ "special": true
2058
+ },
2059
+ "128257": {
2060
+ "content": "<|im_start|>",
2061
+ "lstrip": false,
2062
+ "normalized": false,
2063
+ "rstrip": false,
2064
+ "single_word": false,
2065
+ "special": true
2066
+ }
2067
+ },
2068
+ "additional_special_tokens": [
2069
+ "<|im_start|>"
2070
+ ],
2071
+ "bos_token": "<|begin_of_text|>",
2072
+ "chat_template": "{% set system_message = 'Du bist ein freundlicher und hilfsbereiter KI-Assistent.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\\n' + system_message + '<|im_end|>\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\\n' + content + '<|im_end|>\\n<|im_start|>assistant\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\\n' }}{% endif %}{% endfor %}",
2073
+ "clean_up_tokenization_spaces": true,
2074
+ "eos_token": "<|im_end|>",
2075
+ "model_input_names": [
2076
+ "input_ids",
2077
+ "attention_mask"
2078
+ ],
2079
+ "model_max_length": 1000000000000000019884624838656,
2080
+ "pad_token": "<|end_of_text|>",
2081
+ "padding_side": "right",
2082
+ "split_special_tokens": false,
2083
+ "tokenizer_class": "PreTrainedTokenizerFast"
2084
+ }
checkpoint-300/trainer_state.json ADDED
@@ -0,0 +1,2145 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9849200248718262,
3
+ "best_model_checkpoint": "/kaggle/working/LLaMA-Factory/output/dolphin-2.9-llama3-8b-GER/checkpoint-300",
4
+ "epoch": 0.35335689045936397,
5
+ "eval_steps": 100,
6
+ "global_step": 300,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "grad_norm": 0.5445218086242676,
14
+ "learning_rate": 2.5e-06,
15
+ "loss": 1.2105,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0,
20
+ "grad_norm": 0.4362960457801819,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.9311,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.0,
27
+ "grad_norm": 0.5098525881767273,
28
+ "learning_rate": 7.5e-06,
29
+ "loss": 1.3604,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.0,
34
+ "grad_norm": 1.0830402374267578,
35
+ "learning_rate": 1e-05,
36
+ "loss": 1.5808,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.01,
41
+ "grad_norm": 0.5936903953552246,
42
+ "learning_rate": 1.25e-05,
43
+ "loss": 1.248,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.01,
48
+ "grad_norm": 0.7212775945663452,
49
+ "learning_rate": 1.5e-05,
50
+ "loss": 1.2712,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.01,
55
+ "grad_norm": 0.4733128845691681,
56
+ "learning_rate": 1.75e-05,
57
+ "loss": 1.3005,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.01,
62
+ "grad_norm": 0.6236618757247925,
63
+ "learning_rate": 2e-05,
64
+ "loss": 1.3398,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.01,
69
+ "grad_norm": 0.5326029658317566,
70
+ "learning_rate": 2.25e-05,
71
+ "loss": 1.0476,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.01,
76
+ "grad_norm": 0.5021428465843201,
77
+ "learning_rate": 2.5e-05,
78
+ "loss": 1.1245,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.01,
83
+ "grad_norm": 0.46588796377182007,
84
+ "learning_rate": 2.7500000000000004e-05,
85
+ "loss": 1.1041,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.01,
90
+ "grad_norm": 0.936045229434967,
91
+ "learning_rate": 3e-05,
92
+ "loss": 1.3201,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.02,
97
+ "grad_norm": 0.5649005770683289,
98
+ "learning_rate": 3.2500000000000004e-05,
99
+ "loss": 1.1596,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.02,
104
+ "grad_norm": 0.5679148435592651,
105
+ "learning_rate": 3.5e-05,
106
+ "loss": 1.2501,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.02,
111
+ "grad_norm": 0.8638319373130798,
112
+ "learning_rate": 3.7500000000000003e-05,
113
+ "loss": 1.237,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.02,
118
+ "grad_norm": 0.5722486972808838,
119
+ "learning_rate": 4e-05,
120
+ "loss": 1.2616,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.02,
125
+ "grad_norm": 0.5802999138832092,
126
+ "learning_rate": 4.25e-05,
127
+ "loss": 0.9578,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.02,
132
+ "grad_norm": 1.2806150913238525,
133
+ "learning_rate": 4.5e-05,
134
+ "loss": 1.3815,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.02,
139
+ "grad_norm": 0.5839210748672485,
140
+ "learning_rate": 4.75e-05,
141
+ "loss": 1.2619,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.02,
146
+ "grad_norm": 0.7132797837257385,
147
+ "learning_rate": 5e-05,
148
+ "loss": 1.2842,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.02,
153
+ "grad_norm": 0.7936571836471558,
154
+ "learning_rate": 5.25e-05,
155
+ "loss": 1.3991,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.03,
160
+ "grad_norm": 0.7268731594085693,
161
+ "learning_rate": 5.500000000000001e-05,
162
+ "loss": 1.2217,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.03,
167
+ "grad_norm": 0.6649657487869263,
168
+ "learning_rate": 5.7499999999999995e-05,
169
+ "loss": 1.2485,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.03,
174
+ "grad_norm": 0.45912331342697144,
175
+ "learning_rate": 6e-05,
176
+ "loss": 1.1452,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.03,
181
+ "grad_norm": 0.49475613236427307,
182
+ "learning_rate": 6.25e-05,
183
+ "loss": 1.256,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.03,
188
+ "grad_norm": 0.6027999520301819,
189
+ "learning_rate": 6.500000000000001e-05,
190
+ "loss": 1.2267,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.03,
195
+ "grad_norm": 0.48380520939826965,
196
+ "learning_rate": 6.750000000000001e-05,
197
+ "loss": 1.202,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.03,
202
+ "grad_norm": 0.6623361706733704,
203
+ "learning_rate": 7e-05,
204
+ "loss": 1.3924,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.03,
209
+ "grad_norm": 0.6632773280143738,
210
+ "learning_rate": 7.25e-05,
211
+ "loss": 1.2443,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.04,
216
+ "grad_norm": 0.5974243879318237,
217
+ "learning_rate": 7.500000000000001e-05,
218
+ "loss": 1.0591,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.04,
223
+ "grad_norm": 0.7902927398681641,
224
+ "learning_rate": 7.75e-05,
225
+ "loss": 1.0192,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.04,
230
+ "grad_norm": 0.7081462144851685,
231
+ "learning_rate": 8e-05,
232
+ "loss": 1.0955,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.04,
237
+ "grad_norm": 0.4744333326816559,
238
+ "learning_rate": 8.25e-05,
239
+ "loss": 1.0564,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.04,
244
+ "grad_norm": 0.703999400138855,
245
+ "learning_rate": 8.5e-05,
246
+ "loss": 1.1022,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.04,
251
+ "grad_norm": 0.5378603339195251,
252
+ "learning_rate": 8.75e-05,
253
+ "loss": 1.063,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.04,
258
+ "grad_norm": 0.6105419397354126,
259
+ "learning_rate": 9e-05,
260
+ "loss": 0.9748,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.04,
265
+ "grad_norm": 0.6250177025794983,
266
+ "learning_rate": 9.250000000000001e-05,
267
+ "loss": 0.9951,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.04,
272
+ "grad_norm": 0.6306005716323853,
273
+ "learning_rate": 9.5e-05,
274
+ "loss": 0.9875,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.05,
279
+ "grad_norm": 0.8635210990905762,
280
+ "learning_rate": 9.75e-05,
281
+ "loss": 1.1825,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.05,
286
+ "grad_norm": 0.5938963890075684,
287
+ "learning_rate": 0.0001,
288
+ "loss": 0.9678,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.05,
293
+ "grad_norm": 0.5765062570571899,
294
+ "learning_rate": 0.0001025,
295
+ "loss": 1.1031,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.05,
300
+ "grad_norm": 0.5162666440010071,
301
+ "learning_rate": 0.000105,
302
+ "loss": 1.0831,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.05,
307
+ "grad_norm": 0.8675170540809631,
308
+ "learning_rate": 0.0001075,
309
+ "loss": 1.0034,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.05,
314
+ "grad_norm": 0.44026264548301697,
315
+ "learning_rate": 0.00011000000000000002,
316
+ "loss": 0.9607,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.05,
321
+ "grad_norm": 0.4922897219657898,
322
+ "learning_rate": 0.00011250000000000001,
323
+ "loss": 1.0251,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.05,
328
+ "grad_norm": 0.5505048632621765,
329
+ "learning_rate": 0.00011499999999999999,
330
+ "loss": 0.6948,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.06,
335
+ "grad_norm": 0.5226988792419434,
336
+ "learning_rate": 0.00011750000000000001,
337
+ "loss": 1.2259,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.06,
342
+ "grad_norm": 0.5105571150779724,
343
+ "learning_rate": 0.00012,
344
+ "loss": 1.1239,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.06,
349
+ "grad_norm": 2.0914857387542725,
350
+ "learning_rate": 0.00012250000000000002,
351
+ "loss": 1.4032,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.06,
356
+ "grad_norm": 0.4611998498439789,
357
+ "learning_rate": 0.000125,
358
+ "loss": 1.1481,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.06,
363
+ "grad_norm": 0.5243968367576599,
364
+ "learning_rate": 0.0001275,
365
+ "loss": 1.0514,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.06,
370
+ "grad_norm": 0.48045778274536133,
371
+ "learning_rate": 0.00013000000000000002,
372
+ "loss": 1.1552,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.06,
377
+ "grad_norm": 0.5543797612190247,
378
+ "learning_rate": 0.0001325,
379
+ "loss": 1.035,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.06,
384
+ "grad_norm": 0.5148913264274597,
385
+ "learning_rate": 0.00013500000000000003,
386
+ "loss": 0.9244,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.06,
391
+ "grad_norm": 0.5708130598068237,
392
+ "learning_rate": 0.0001375,
393
+ "loss": 1.2272,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.07,
398
+ "grad_norm": 0.7507888078689575,
399
+ "learning_rate": 0.00014,
400
+ "loss": 1.1196,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.07,
405
+ "grad_norm": 0.5411068201065063,
406
+ "learning_rate": 0.00014250000000000002,
407
+ "loss": 1.1444,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.07,
412
+ "grad_norm": 0.7314138412475586,
413
+ "learning_rate": 0.000145,
414
+ "loss": 1.3451,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.07,
419
+ "grad_norm": 0.5134022831916809,
420
+ "learning_rate": 0.0001475,
421
+ "loss": 0.8021,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.07,
426
+ "grad_norm": 0.7859703302383423,
427
+ "learning_rate": 0.00015000000000000001,
428
+ "loss": 0.952,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.07,
433
+ "grad_norm": 0.4740566611289978,
434
+ "learning_rate": 0.0001525,
435
+ "loss": 0.8878,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.07,
440
+ "grad_norm": 0.8245677947998047,
441
+ "learning_rate": 0.000155,
442
+ "loss": 1.4341,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.07,
447
+ "grad_norm": 0.5067218542098999,
448
+ "learning_rate": 0.0001575,
449
+ "loss": 0.8404,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.08,
454
+ "grad_norm": 0.40824806690216064,
455
+ "learning_rate": 0.00016,
456
+ "loss": 1.0943,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.08,
461
+ "grad_norm": 0.428151935338974,
462
+ "learning_rate": 0.00016250000000000002,
463
+ "loss": 1.0819,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.08,
468
+ "grad_norm": 0.437532901763916,
469
+ "learning_rate": 0.000165,
470
+ "loss": 1.0461,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.08,
475
+ "grad_norm": 0.4619809091091156,
476
+ "learning_rate": 0.0001675,
477
+ "loss": 1.0232,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.08,
482
+ "grad_norm": 1.3247042894363403,
483
+ "learning_rate": 0.00017,
484
+ "loss": 1.218,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.08,
489
+ "grad_norm": 0.5896454453468323,
490
+ "learning_rate": 0.00017250000000000002,
491
+ "loss": 1.1953,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.08,
496
+ "grad_norm": 0.5605736970901489,
497
+ "learning_rate": 0.000175,
498
+ "loss": 1.2542,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.08,
503
+ "grad_norm": 0.36923155188560486,
504
+ "learning_rate": 0.0001775,
505
+ "loss": 0.7096,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.08,
510
+ "grad_norm": 0.6809273362159729,
511
+ "learning_rate": 0.00018,
512
+ "loss": 1.1959,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.09,
517
+ "grad_norm": 0.42645493149757385,
518
+ "learning_rate": 0.0001825,
519
+ "loss": 1.1829,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.09,
524
+ "grad_norm": 0.7621450424194336,
525
+ "learning_rate": 0.00018500000000000002,
526
+ "loss": 1.1599,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.09,
531
+ "grad_norm": 0.5299301743507385,
532
+ "learning_rate": 0.0001875,
533
+ "loss": 1.0546,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.09,
538
+ "grad_norm": 0.484611451625824,
539
+ "learning_rate": 0.00019,
540
+ "loss": 1.0854,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.09,
545
+ "grad_norm": 0.4027417004108429,
546
+ "learning_rate": 0.00019250000000000002,
547
+ "loss": 0.7812,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.09,
552
+ "grad_norm": 0.7537221908569336,
553
+ "learning_rate": 0.000195,
554
+ "loss": 0.9719,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.09,
559
+ "grad_norm": 0.45811474323272705,
560
+ "learning_rate": 0.00019750000000000003,
561
+ "loss": 0.9684,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.09,
566
+ "grad_norm": 0.5426852107048035,
567
+ "learning_rate": 0.0002,
568
+ "loss": 0.9451,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.1,
573
+ "grad_norm": 0.48964977264404297,
574
+ "learning_rate": 0.000199739921976593,
575
+ "loss": 1.0807,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.1,
580
+ "grad_norm": 0.6225113272666931,
581
+ "learning_rate": 0.00019947984395318597,
582
+ "loss": 1.1913,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.1,
587
+ "grad_norm": 0.47157713770866394,
588
+ "learning_rate": 0.00019921976592977893,
589
+ "loss": 1.0392,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.1,
594
+ "grad_norm": 0.42048129439353943,
595
+ "learning_rate": 0.0001989596879063719,
596
+ "loss": 0.8439,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.1,
601
+ "grad_norm": 0.4129664897918701,
602
+ "learning_rate": 0.0001986996098829649,
603
+ "loss": 1.1025,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.1,
608
+ "grad_norm": 0.5610629320144653,
609
+ "learning_rate": 0.00019843953185955788,
610
+ "loss": 0.9368,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.1,
615
+ "grad_norm": 0.4288642406463623,
616
+ "learning_rate": 0.00019817945383615086,
617
+ "loss": 0.9711,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.1,
622
+ "grad_norm": 0.572507917881012,
623
+ "learning_rate": 0.0001979193758127438,
624
+ "loss": 0.9739,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.1,
629
+ "grad_norm": 0.5115912556648254,
630
+ "learning_rate": 0.0001976592977893368,
631
+ "loss": 0.9356,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.11,
636
+ "grad_norm": 0.608063280582428,
637
+ "learning_rate": 0.00019739921976592978,
638
+ "loss": 1.2459,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.11,
643
+ "grad_norm": 1.0171502828598022,
644
+ "learning_rate": 0.00019713914174252276,
645
+ "loss": 1.0629,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.11,
650
+ "grad_norm": 0.514552116394043,
651
+ "learning_rate": 0.00019687906371911574,
652
+ "loss": 0.9646,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.11,
657
+ "grad_norm": 0.4363428056240082,
658
+ "learning_rate": 0.00019661898569570872,
659
+ "loss": 0.8659,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.11,
664
+ "grad_norm": 0.4470008611679077,
665
+ "learning_rate": 0.0001963589076723017,
666
+ "loss": 1.0338,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.11,
671
+ "grad_norm": 0.5710871815681458,
672
+ "learning_rate": 0.0001960988296488947,
673
+ "loss": 0.946,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.11,
678
+ "grad_norm": 0.6456964612007141,
679
+ "learning_rate": 0.00019583875162548767,
680
+ "loss": 1.0956,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.11,
685
+ "grad_norm": 0.45742425322532654,
686
+ "learning_rate": 0.00019557867360208065,
687
+ "loss": 0.7985,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.12,
692
+ "grad_norm": 0.9953218698501587,
693
+ "learning_rate": 0.0001953185955786736,
694
+ "loss": 0.9476,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.12,
699
+ "grad_norm": 0.5075244307518005,
700
+ "learning_rate": 0.0001950585175552666,
701
+ "loss": 1.1704,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.12,
706
+ "grad_norm": 0.7076822519302368,
707
+ "learning_rate": 0.00019479843953185957,
708
+ "loss": 1.2054,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.12,
713
+ "eval_loss": 1.0368528366088867,
714
+ "eval_runtime": 547.1826,
715
+ "eval_samples_per_second": 2.76,
716
+ "eval_steps_per_second": 1.38,
717
+ "step": 100
718
+ },
719
+ {
720
+ "epoch": 0.12,
721
+ "grad_norm": 0.7408495545387268,
722
+ "learning_rate": 0.00019453836150845255,
723
+ "loss": 1.3149,
724
+ "step": 101
725
+ },
726
+ {
727
+ "epoch": 0.12,
728
+ "grad_norm": 0.5010321736335754,
729
+ "learning_rate": 0.00019427828348504554,
730
+ "loss": 0.8483,
731
+ "step": 102
732
+ },
733
+ {
734
+ "epoch": 0.12,
735
+ "grad_norm": 0.5388755798339844,
736
+ "learning_rate": 0.0001940182054616385,
737
+ "loss": 1.034,
738
+ "step": 103
739
+ },
740
+ {
741
+ "epoch": 0.12,
742
+ "grad_norm": 0.32918357849121094,
743
+ "learning_rate": 0.00019375812743823147,
744
+ "loss": 1.0762,
745
+ "step": 104
746
+ },
747
+ {
748
+ "epoch": 0.12,
749
+ "grad_norm": 0.4812282919883728,
750
+ "learning_rate": 0.00019349804941482446,
751
+ "loss": 1.0797,
752
+ "step": 105
753
+ },
754
+ {
755
+ "epoch": 0.12,
756
+ "grad_norm": 0.6160157918930054,
757
+ "learning_rate": 0.00019323797139141744,
758
+ "loss": 0.9488,
759
+ "step": 106
760
+ },
761
+ {
762
+ "epoch": 0.13,
763
+ "grad_norm": 0.41306182742118835,
764
+ "learning_rate": 0.00019297789336801042,
765
+ "loss": 1.0742,
766
+ "step": 107
767
+ },
768
+ {
769
+ "epoch": 0.13,
770
+ "grad_norm": 0.5411396026611328,
771
+ "learning_rate": 0.00019271781534460338,
772
+ "loss": 1.1162,
773
+ "step": 108
774
+ },
775
+ {
776
+ "epoch": 0.13,
777
+ "grad_norm": 0.45688003301620483,
778
+ "learning_rate": 0.00019245773732119636,
779
+ "loss": 0.8042,
780
+ "step": 109
781
+ },
782
+ {
783
+ "epoch": 0.13,
784
+ "grad_norm": 0.4660446047782898,
785
+ "learning_rate": 0.00019219765929778934,
786
+ "loss": 0.8234,
787
+ "step": 110
788
+ },
789
+ {
790
+ "epoch": 0.13,
791
+ "grad_norm": 0.6277762055397034,
792
+ "learning_rate": 0.00019193758127438232,
793
+ "loss": 1.0324,
794
+ "step": 111
795
+ },
796
+ {
797
+ "epoch": 0.13,
798
+ "grad_norm": 0.6119320392608643,
799
+ "learning_rate": 0.0001916775032509753,
800
+ "loss": 0.6912,
801
+ "step": 112
802
+ },
803
+ {
804
+ "epoch": 0.13,
805
+ "grad_norm": 0.5463618040084839,
806
+ "learning_rate": 0.00019141742522756826,
807
+ "loss": 1.1297,
808
+ "step": 113
809
+ },
810
+ {
811
+ "epoch": 0.13,
812
+ "grad_norm": 0.4918029010295868,
813
+ "learning_rate": 0.00019115734720416124,
814
+ "loss": 1.0857,
815
+ "step": 114
816
+ },
817
+ {
818
+ "epoch": 0.14,
819
+ "grad_norm": 0.4734187424182892,
820
+ "learning_rate": 0.00019089726918075422,
821
+ "loss": 1.0246,
822
+ "step": 115
823
+ },
824
+ {
825
+ "epoch": 0.14,
826
+ "grad_norm": 0.5416173934936523,
827
+ "learning_rate": 0.0001906371911573472,
828
+ "loss": 1.0262,
829
+ "step": 116
830
+ },
831
+ {
832
+ "epoch": 0.14,
833
+ "grad_norm": 0.486284464597702,
834
+ "learning_rate": 0.0001903771131339402,
835
+ "loss": 1.2198,
836
+ "step": 117
837
+ },
838
+ {
839
+ "epoch": 0.14,
840
+ "grad_norm": 0.4003067910671234,
841
+ "learning_rate": 0.00019011703511053317,
842
+ "loss": 0.8525,
843
+ "step": 118
844
+ },
845
+ {
846
+ "epoch": 0.14,
847
+ "grad_norm": 0.38142916560173035,
848
+ "learning_rate": 0.00018985695708712615,
849
+ "loss": 1.1475,
850
+ "step": 119
851
+ },
852
+ {
853
+ "epoch": 0.14,
854
+ "grad_norm": 0.42364147305488586,
855
+ "learning_rate": 0.00018959687906371913,
856
+ "loss": 0.8207,
857
+ "step": 120
858
+ },
859
+ {
860
+ "epoch": 0.14,
861
+ "grad_norm": 0.384432852268219,
862
+ "learning_rate": 0.00018933680104031212,
863
+ "loss": 0.9451,
864
+ "step": 121
865
+ },
866
+ {
867
+ "epoch": 0.14,
868
+ "grad_norm": 0.38188567757606506,
869
+ "learning_rate": 0.0001890767230169051,
870
+ "loss": 0.921,
871
+ "step": 122
872
+ },
873
+ {
874
+ "epoch": 0.14,
875
+ "grad_norm": 0.4212167263031006,
876
+ "learning_rate": 0.00018881664499349805,
877
+ "loss": 0.8532,
878
+ "step": 123
879
+ },
880
+ {
881
+ "epoch": 0.15,
882
+ "grad_norm": 0.7674171924591064,
883
+ "learning_rate": 0.00018855656697009104,
884
+ "loss": 1.1751,
885
+ "step": 124
886
+ },
887
+ {
888
+ "epoch": 0.15,
889
+ "grad_norm": 0.4111984074115753,
890
+ "learning_rate": 0.00018829648894668402,
891
+ "loss": 0.906,
892
+ "step": 125
893
+ },
894
+ {
895
+ "epoch": 0.15,
896
+ "grad_norm": 0.6682639718055725,
897
+ "learning_rate": 0.000188036410923277,
898
+ "loss": 1.1284,
899
+ "step": 126
900
+ },
901
+ {
902
+ "epoch": 0.15,
903
+ "grad_norm": 0.3887438178062439,
904
+ "learning_rate": 0.00018777633289986998,
905
+ "loss": 1.0324,
906
+ "step": 127
907
+ },
908
+ {
909
+ "epoch": 0.15,
910
+ "grad_norm": 0.5829350352287292,
911
+ "learning_rate": 0.00018751625487646294,
912
+ "loss": 1.038,
913
+ "step": 128
914
+ },
915
+ {
916
+ "epoch": 0.15,
917
+ "grad_norm": 0.5861855149269104,
918
+ "learning_rate": 0.00018725617685305592,
919
+ "loss": 0.9453,
920
+ "step": 129
921
+ },
922
+ {
923
+ "epoch": 0.15,
924
+ "grad_norm": 0.40044718980789185,
925
+ "learning_rate": 0.0001869960988296489,
926
+ "loss": 1.1971,
927
+ "step": 130
928
+ },
929
+ {
930
+ "epoch": 0.15,
931
+ "grad_norm": 0.4322098195552826,
932
+ "learning_rate": 0.00018673602080624188,
933
+ "loss": 0.9792,
934
+ "step": 131
935
+ },
936
+ {
937
+ "epoch": 0.16,
938
+ "grad_norm": 0.4132952392101288,
939
+ "learning_rate": 0.00018647594278283487,
940
+ "loss": 0.9597,
941
+ "step": 132
942
+ },
943
+ {
944
+ "epoch": 0.16,
945
+ "grad_norm": 0.4141194224357605,
946
+ "learning_rate": 0.00018621586475942782,
947
+ "loss": 1.0785,
948
+ "step": 133
949
+ },
950
+ {
951
+ "epoch": 0.16,
952
+ "grad_norm": 0.5526332855224609,
953
+ "learning_rate": 0.0001859557867360208,
954
+ "loss": 1.0762,
955
+ "step": 134
956
+ },
957
+ {
958
+ "epoch": 0.16,
959
+ "grad_norm": 0.6953147053718567,
960
+ "learning_rate": 0.00018569570871261379,
961
+ "loss": 1.1048,
962
+ "step": 135
963
+ },
964
+ {
965
+ "epoch": 0.16,
966
+ "grad_norm": 0.4306538701057434,
967
+ "learning_rate": 0.00018543563068920677,
968
+ "loss": 0.9798,
969
+ "step": 136
970
+ },
971
+ {
972
+ "epoch": 0.16,
973
+ "grad_norm": 0.32605746388435364,
974
+ "learning_rate": 0.00018517555266579975,
975
+ "loss": 0.9825,
976
+ "step": 137
977
+ },
978
+ {
979
+ "epoch": 0.16,
980
+ "grad_norm": 0.48711439967155457,
981
+ "learning_rate": 0.0001849154746423927,
982
+ "loss": 0.9685,
983
+ "step": 138
984
+ },
985
+ {
986
+ "epoch": 0.16,
987
+ "grad_norm": 0.7728849649429321,
988
+ "learning_rate": 0.0001846553966189857,
989
+ "loss": 1.2843,
990
+ "step": 139
991
+ },
992
+ {
993
+ "epoch": 0.16,
994
+ "grad_norm": 0.38121744990348816,
995
+ "learning_rate": 0.00018439531859557867,
996
+ "loss": 0.8289,
997
+ "step": 140
998
+ },
999
+ {
1000
+ "epoch": 0.17,
1001
+ "grad_norm": 0.5053502321243286,
1002
+ "learning_rate": 0.00018413524057217165,
1003
+ "loss": 1.0824,
1004
+ "step": 141
1005
+ },
1006
+ {
1007
+ "epoch": 0.17,
1008
+ "grad_norm": 0.44003796577453613,
1009
+ "learning_rate": 0.00018387516254876463,
1010
+ "loss": 1.0957,
1011
+ "step": 142
1012
+ },
1013
+ {
1014
+ "epoch": 0.17,
1015
+ "grad_norm": 0.35713884234428406,
1016
+ "learning_rate": 0.00018361508452535762,
1017
+ "loss": 0.7869,
1018
+ "step": 143
1019
+ },
1020
+ {
1021
+ "epoch": 0.17,
1022
+ "grad_norm": 0.6612699627876282,
1023
+ "learning_rate": 0.0001833550065019506,
1024
+ "loss": 1.1621,
1025
+ "step": 144
1026
+ },
1027
+ {
1028
+ "epoch": 0.17,
1029
+ "grad_norm": 0.4270091950893402,
1030
+ "learning_rate": 0.00018309492847854358,
1031
+ "loss": 0.8964,
1032
+ "step": 145
1033
+ },
1034
+ {
1035
+ "epoch": 0.17,
1036
+ "grad_norm": 0.42207202315330505,
1037
+ "learning_rate": 0.00018283485045513656,
1038
+ "loss": 1.1403,
1039
+ "step": 146
1040
+ },
1041
+ {
1042
+ "epoch": 0.17,
1043
+ "grad_norm": 0.48486125469207764,
1044
+ "learning_rate": 0.00018257477243172954,
1045
+ "loss": 0.9993,
1046
+ "step": 147
1047
+ },
1048
+ {
1049
+ "epoch": 0.17,
1050
+ "grad_norm": 0.4205480217933655,
1051
+ "learning_rate": 0.0001823146944083225,
1052
+ "loss": 1.0404,
1053
+ "step": 148
1054
+ },
1055
+ {
1056
+ "epoch": 0.18,
1057
+ "grad_norm": 0.3420919179916382,
1058
+ "learning_rate": 0.00018205461638491548,
1059
+ "loss": 1.1434,
1060
+ "step": 149
1061
+ },
1062
+ {
1063
+ "epoch": 0.18,
1064
+ "grad_norm": 0.6411290168762207,
1065
+ "learning_rate": 0.00018179453836150846,
1066
+ "loss": 1.2055,
1067
+ "step": 150
1068
+ },
1069
+ {
1070
+ "epoch": 0.18,
1071
+ "grad_norm": 0.7193886637687683,
1072
+ "learning_rate": 0.00018153446033810145,
1073
+ "loss": 0.9436,
1074
+ "step": 151
1075
+ },
1076
+ {
1077
+ "epoch": 0.18,
1078
+ "grad_norm": 0.34661969542503357,
1079
+ "learning_rate": 0.00018127438231469443,
1080
+ "loss": 0.8158,
1081
+ "step": 152
1082
+ },
1083
+ {
1084
+ "epoch": 0.18,
1085
+ "grad_norm": 0.4028843939304352,
1086
+ "learning_rate": 0.00018101430429128738,
1087
+ "loss": 0.9863,
1088
+ "step": 153
1089
+ },
1090
+ {
1091
+ "epoch": 0.18,
1092
+ "grad_norm": 0.3898251950740814,
1093
+ "learning_rate": 0.00018075422626788037,
1094
+ "loss": 0.9215,
1095
+ "step": 154
1096
+ },
1097
+ {
1098
+ "epoch": 0.18,
1099
+ "grad_norm": 0.3827955424785614,
1100
+ "learning_rate": 0.00018049414824447335,
1101
+ "loss": 0.9513,
1102
+ "step": 155
1103
+ },
1104
+ {
1105
+ "epoch": 0.18,
1106
+ "grad_norm": 0.3840239644050598,
1107
+ "learning_rate": 0.00018023407022106633,
1108
+ "loss": 0.8303,
1109
+ "step": 156
1110
+ },
1111
+ {
1112
+ "epoch": 0.18,
1113
+ "grad_norm": 0.42413073778152466,
1114
+ "learning_rate": 0.0001799739921976593,
1115
+ "loss": 0.8909,
1116
+ "step": 157
1117
+ },
1118
+ {
1119
+ "epoch": 0.19,
1120
+ "grad_norm": 0.47216784954071045,
1121
+ "learning_rate": 0.00017971391417425227,
1122
+ "loss": 1.0413,
1123
+ "step": 158
1124
+ },
1125
+ {
1126
+ "epoch": 0.19,
1127
+ "grad_norm": 0.35447853803634644,
1128
+ "learning_rate": 0.00017945383615084525,
1129
+ "loss": 0.9781,
1130
+ "step": 159
1131
+ },
1132
+ {
1133
+ "epoch": 0.19,
1134
+ "grad_norm": 0.46554017066955566,
1135
+ "learning_rate": 0.00017919375812743823,
1136
+ "loss": 0.7186,
1137
+ "step": 160
1138
+ },
1139
+ {
1140
+ "epoch": 0.19,
1141
+ "grad_norm": 0.3696407973766327,
1142
+ "learning_rate": 0.00017893368010403121,
1143
+ "loss": 1.0137,
1144
+ "step": 161
1145
+ },
1146
+ {
1147
+ "epoch": 0.19,
1148
+ "grad_norm": 0.5633952617645264,
1149
+ "learning_rate": 0.0001786736020806242,
1150
+ "loss": 1.0944,
1151
+ "step": 162
1152
+ },
1153
+ {
1154
+ "epoch": 0.19,
1155
+ "grad_norm": 0.3334963917732239,
1156
+ "learning_rate": 0.00017841352405721715,
1157
+ "loss": 1.2606,
1158
+ "step": 163
1159
+ },
1160
+ {
1161
+ "epoch": 0.19,
1162
+ "grad_norm": 0.4501505494117737,
1163
+ "learning_rate": 0.00017815344603381013,
1164
+ "loss": 0.7306,
1165
+ "step": 164
1166
+ },
1167
+ {
1168
+ "epoch": 0.19,
1169
+ "grad_norm": 0.44553884863853455,
1170
+ "learning_rate": 0.00017789336801040312,
1171
+ "loss": 0.871,
1172
+ "step": 165
1173
+ },
1174
+ {
1175
+ "epoch": 0.2,
1176
+ "grad_norm": 0.474342405796051,
1177
+ "learning_rate": 0.0001776332899869961,
1178
+ "loss": 0.7593,
1179
+ "step": 166
1180
+ },
1181
+ {
1182
+ "epoch": 0.2,
1183
+ "grad_norm": 0.7258349061012268,
1184
+ "learning_rate": 0.00017737321196358908,
1185
+ "loss": 1.4035,
1186
+ "step": 167
1187
+ },
1188
+ {
1189
+ "epoch": 0.2,
1190
+ "grad_norm": 0.43586501479148865,
1191
+ "learning_rate": 0.00017711313394018206,
1192
+ "loss": 1.1679,
1193
+ "step": 168
1194
+ },
1195
+ {
1196
+ "epoch": 0.2,
1197
+ "grad_norm": 0.4580634832382202,
1198
+ "learning_rate": 0.00017685305591677504,
1199
+ "loss": 0.9496,
1200
+ "step": 169
1201
+ },
1202
+ {
1203
+ "epoch": 0.2,
1204
+ "grad_norm": 0.40509316325187683,
1205
+ "learning_rate": 0.00017659297789336803,
1206
+ "loss": 0.9515,
1207
+ "step": 170
1208
+ },
1209
+ {
1210
+ "epoch": 0.2,
1211
+ "grad_norm": 0.3496972620487213,
1212
+ "learning_rate": 0.000176332899869961,
1213
+ "loss": 1.1846,
1214
+ "step": 171
1215
+ },
1216
+ {
1217
+ "epoch": 0.2,
1218
+ "grad_norm": 0.6468595862388611,
1219
+ "learning_rate": 0.000176072821846554,
1220
+ "loss": 1.0307,
1221
+ "step": 172
1222
+ },
1223
+ {
1224
+ "epoch": 0.2,
1225
+ "grad_norm": 0.3840126693248749,
1226
+ "learning_rate": 0.00017581274382314695,
1227
+ "loss": 1.0248,
1228
+ "step": 173
1229
+ },
1230
+ {
1231
+ "epoch": 0.2,
1232
+ "grad_norm": 0.4715554118156433,
1233
+ "learning_rate": 0.00017555266579973993,
1234
+ "loss": 1.1017,
1235
+ "step": 174
1236
+ },
1237
+ {
1238
+ "epoch": 0.21,
1239
+ "grad_norm": 0.38534194231033325,
1240
+ "learning_rate": 0.0001752925877763329,
1241
+ "loss": 1.0073,
1242
+ "step": 175
1243
+ },
1244
+ {
1245
+ "epoch": 0.21,
1246
+ "grad_norm": 0.3881916403770447,
1247
+ "learning_rate": 0.0001750325097529259,
1248
+ "loss": 0.8961,
1249
+ "step": 176
1250
+ },
1251
+ {
1252
+ "epoch": 0.21,
1253
+ "grad_norm": 0.49220091104507446,
1254
+ "learning_rate": 0.00017477243172951887,
1255
+ "loss": 1.0184,
1256
+ "step": 177
1257
+ },
1258
+ {
1259
+ "epoch": 0.21,
1260
+ "grad_norm": 0.38170936703681946,
1261
+ "learning_rate": 0.00017451235370611186,
1262
+ "loss": 1.0939,
1263
+ "step": 178
1264
+ },
1265
+ {
1266
+ "epoch": 0.21,
1267
+ "grad_norm": 0.3692156672477722,
1268
+ "learning_rate": 0.0001742522756827048,
1269
+ "loss": 1.085,
1270
+ "step": 179
1271
+ },
1272
+ {
1273
+ "epoch": 0.21,
1274
+ "grad_norm": 0.43161171674728394,
1275
+ "learning_rate": 0.0001739921976592978,
1276
+ "loss": 0.9098,
1277
+ "step": 180
1278
+ },
1279
+ {
1280
+ "epoch": 0.21,
1281
+ "grad_norm": 0.3874380886554718,
1282
+ "learning_rate": 0.00017373211963589078,
1283
+ "loss": 1.0108,
1284
+ "step": 181
1285
+ },
1286
+ {
1287
+ "epoch": 0.21,
1288
+ "grad_norm": 0.37556958198547363,
1289
+ "learning_rate": 0.00017347204161248376,
1290
+ "loss": 1.0344,
1291
+ "step": 182
1292
+ },
1293
+ {
1294
+ "epoch": 0.22,
1295
+ "grad_norm": 0.4288795292377472,
1296
+ "learning_rate": 0.00017321196358907674,
1297
+ "loss": 0.9329,
1298
+ "step": 183
1299
+ },
1300
+ {
1301
+ "epoch": 0.22,
1302
+ "grad_norm": 0.6587222218513489,
1303
+ "learning_rate": 0.0001729518855656697,
1304
+ "loss": 1.0312,
1305
+ "step": 184
1306
+ },
1307
+ {
1308
+ "epoch": 0.22,
1309
+ "grad_norm": 0.6700361371040344,
1310
+ "learning_rate": 0.00017269180754226268,
1311
+ "loss": 1.035,
1312
+ "step": 185
1313
+ },
1314
+ {
1315
+ "epoch": 0.22,
1316
+ "grad_norm": 0.5208828449249268,
1317
+ "learning_rate": 0.00017243172951885566,
1318
+ "loss": 1.0334,
1319
+ "step": 186
1320
+ },
1321
+ {
1322
+ "epoch": 0.22,
1323
+ "grad_norm": 0.5774813294410706,
1324
+ "learning_rate": 0.00017217165149544864,
1325
+ "loss": 1.0366,
1326
+ "step": 187
1327
+ },
1328
+ {
1329
+ "epoch": 0.22,
1330
+ "grad_norm": 0.3492725193500519,
1331
+ "learning_rate": 0.00017191157347204162,
1332
+ "loss": 1.0225,
1333
+ "step": 188
1334
+ },
1335
+ {
1336
+ "epoch": 0.22,
1337
+ "grad_norm": 0.3714265525341034,
1338
+ "learning_rate": 0.00017165149544863458,
1339
+ "loss": 1.0355,
1340
+ "step": 189
1341
+ },
1342
+ {
1343
+ "epoch": 0.22,
1344
+ "grad_norm": 0.4425973892211914,
1345
+ "learning_rate": 0.00017139141742522756,
1346
+ "loss": 0.974,
1347
+ "step": 190
1348
+ },
1349
+ {
1350
+ "epoch": 0.22,
1351
+ "grad_norm": 0.43257299065589905,
1352
+ "learning_rate": 0.00017113133940182054,
1353
+ "loss": 0.8614,
1354
+ "step": 191
1355
+ },
1356
+ {
1357
+ "epoch": 0.23,
1358
+ "grad_norm": 0.37084296345710754,
1359
+ "learning_rate": 0.00017087126137841353,
1360
+ "loss": 0.7135,
1361
+ "step": 192
1362
+ },
1363
+ {
1364
+ "epoch": 0.23,
1365
+ "grad_norm": 0.6695109009742737,
1366
+ "learning_rate": 0.0001706111833550065,
1367
+ "loss": 0.7722,
1368
+ "step": 193
1369
+ },
1370
+ {
1371
+ "epoch": 0.23,
1372
+ "grad_norm": 0.5144183039665222,
1373
+ "learning_rate": 0.0001703511053315995,
1374
+ "loss": 0.9364,
1375
+ "step": 194
1376
+ },
1377
+ {
1378
+ "epoch": 0.23,
1379
+ "grad_norm": 0.58673095703125,
1380
+ "learning_rate": 0.00017009102730819247,
1381
+ "loss": 1.1141,
1382
+ "step": 195
1383
+ },
1384
+ {
1385
+ "epoch": 0.23,
1386
+ "grad_norm": 0.4033479392528534,
1387
+ "learning_rate": 0.00016983094928478545,
1388
+ "loss": 1.0002,
1389
+ "step": 196
1390
+ },
1391
+ {
1392
+ "epoch": 0.23,
1393
+ "grad_norm": 0.38111910223960876,
1394
+ "learning_rate": 0.00016957087126137844,
1395
+ "loss": 0.9318,
1396
+ "step": 197
1397
+ },
1398
+ {
1399
+ "epoch": 0.23,
1400
+ "grad_norm": 0.4174363613128662,
1401
+ "learning_rate": 0.00016931079323797142,
1402
+ "loss": 0.9381,
1403
+ "step": 198
1404
+ },
1405
+ {
1406
+ "epoch": 0.23,
1407
+ "grad_norm": 0.3726828098297119,
1408
+ "learning_rate": 0.00016905071521456437,
1409
+ "loss": 1.0405,
1410
+ "step": 199
1411
+ },
1412
+ {
1413
+ "epoch": 0.24,
1414
+ "grad_norm": 0.5414443612098694,
1415
+ "learning_rate": 0.00016879063719115736,
1416
+ "loss": 1.0667,
1417
+ "step": 200
1418
+ },
1419
+ {
1420
+ "epoch": 0.24,
1421
+ "eval_loss": 1.0012115240097046,
1422
+ "eval_runtime": 546.9226,
1423
+ "eval_samples_per_second": 2.761,
1424
+ "eval_steps_per_second": 1.38,
1425
+ "step": 200
1426
+ },
1427
+ {
1428
+ "epoch": 0.24,
1429
+ "grad_norm": 0.523889422416687,
1430
+ "learning_rate": 0.00016853055916775034,
1431
+ "loss": 1.0408,
1432
+ "step": 201
1433
+ },
1434
+ {
1435
+ "epoch": 0.24,
1436
+ "grad_norm": 0.47460106015205383,
1437
+ "learning_rate": 0.00016827048114434332,
1438
+ "loss": 1.0327,
1439
+ "step": 202
1440
+ },
1441
+ {
1442
+ "epoch": 0.24,
1443
+ "grad_norm": 0.5161871314048767,
1444
+ "learning_rate": 0.0001680104031209363,
1445
+ "loss": 0.9104,
1446
+ "step": 203
1447
+ },
1448
+ {
1449
+ "epoch": 0.24,
1450
+ "grad_norm": 0.3816511631011963,
1451
+ "learning_rate": 0.00016775032509752926,
1452
+ "loss": 0.6875,
1453
+ "step": 204
1454
+ },
1455
+ {
1456
+ "epoch": 0.24,
1457
+ "grad_norm": 0.3574850261211395,
1458
+ "learning_rate": 0.00016749024707412224,
1459
+ "loss": 0.8079,
1460
+ "step": 205
1461
+ },
1462
+ {
1463
+ "epoch": 0.24,
1464
+ "grad_norm": 0.37416210770606995,
1465
+ "learning_rate": 0.00016723016905071522,
1466
+ "loss": 0.7479,
1467
+ "step": 206
1468
+ },
1469
+ {
1470
+ "epoch": 0.24,
1471
+ "grad_norm": 0.648332417011261,
1472
+ "learning_rate": 0.0001669700910273082,
1473
+ "loss": 1.0868,
1474
+ "step": 207
1475
+ },
1476
+ {
1477
+ "epoch": 0.24,
1478
+ "grad_norm": 0.37010350823402405,
1479
+ "learning_rate": 0.0001667100130039012,
1480
+ "loss": 0.8634,
1481
+ "step": 208
1482
+ },
1483
+ {
1484
+ "epoch": 0.25,
1485
+ "grad_norm": 0.5206050872802734,
1486
+ "learning_rate": 0.00016644993498049414,
1487
+ "loss": 0.8827,
1488
+ "step": 209
1489
+ },
1490
+ {
1491
+ "epoch": 0.25,
1492
+ "grad_norm": 0.4001045525074005,
1493
+ "learning_rate": 0.00016618985695708712,
1494
+ "loss": 1.1029,
1495
+ "step": 210
1496
+ },
1497
+ {
1498
+ "epoch": 0.25,
1499
+ "grad_norm": 0.3948250114917755,
1500
+ "learning_rate": 0.0001659297789336801,
1501
+ "loss": 0.7248,
1502
+ "step": 211
1503
+ },
1504
+ {
1505
+ "epoch": 0.25,
1506
+ "grad_norm": 0.4833560287952423,
1507
+ "learning_rate": 0.0001656697009102731,
1508
+ "loss": 0.7379,
1509
+ "step": 212
1510
+ },
1511
+ {
1512
+ "epoch": 0.25,
1513
+ "grad_norm": 0.4951235055923462,
1514
+ "learning_rate": 0.00016540962288686607,
1515
+ "loss": 1.0003,
1516
+ "step": 213
1517
+ },
1518
+ {
1519
+ "epoch": 0.25,
1520
+ "grad_norm": 0.7607774138450623,
1521
+ "learning_rate": 0.00016514954486345903,
1522
+ "loss": 0.8599,
1523
+ "step": 214
1524
+ },
1525
+ {
1526
+ "epoch": 0.25,
1527
+ "grad_norm": 0.3604733347892761,
1528
+ "learning_rate": 0.000164889466840052,
1529
+ "loss": 1.0301,
1530
+ "step": 215
1531
+ },
1532
+ {
1533
+ "epoch": 0.25,
1534
+ "grad_norm": 0.3514990508556366,
1535
+ "learning_rate": 0.000164629388816645,
1536
+ "loss": 1.072,
1537
+ "step": 216
1538
+ },
1539
+ {
1540
+ "epoch": 0.26,
1541
+ "grad_norm": 0.8136312365531921,
1542
+ "learning_rate": 0.00016436931079323797,
1543
+ "loss": 1.0795,
1544
+ "step": 217
1545
+ },
1546
+ {
1547
+ "epoch": 0.26,
1548
+ "grad_norm": 0.4305706024169922,
1549
+ "learning_rate": 0.00016410923276983095,
1550
+ "loss": 0.8288,
1551
+ "step": 218
1552
+ },
1553
+ {
1554
+ "epoch": 0.26,
1555
+ "grad_norm": 0.4228506088256836,
1556
+ "learning_rate": 0.00016384915474642394,
1557
+ "loss": 0.863,
1558
+ "step": 219
1559
+ },
1560
+ {
1561
+ "epoch": 0.26,
1562
+ "grad_norm": 0.3303283751010895,
1563
+ "learning_rate": 0.00016358907672301692,
1564
+ "loss": 0.8992,
1565
+ "step": 220
1566
+ },
1567
+ {
1568
+ "epoch": 0.26,
1569
+ "grad_norm": 0.4840926229953766,
1570
+ "learning_rate": 0.0001633289986996099,
1571
+ "loss": 0.9309,
1572
+ "step": 221
1573
+ },
1574
+ {
1575
+ "epoch": 0.26,
1576
+ "grad_norm": 0.3939206600189209,
1577
+ "learning_rate": 0.00016306892067620288,
1578
+ "loss": 1.0456,
1579
+ "step": 222
1580
+ },
1581
+ {
1582
+ "epoch": 0.26,
1583
+ "grad_norm": 0.4611961245536804,
1584
+ "learning_rate": 0.00016280884265279587,
1585
+ "loss": 1.1839,
1586
+ "step": 223
1587
+ },
1588
+ {
1589
+ "epoch": 0.26,
1590
+ "grad_norm": 0.4443643093109131,
1591
+ "learning_rate": 0.00016254876462938882,
1592
+ "loss": 0.8566,
1593
+ "step": 224
1594
+ },
1595
+ {
1596
+ "epoch": 0.27,
1597
+ "grad_norm": 0.38910534977912903,
1598
+ "learning_rate": 0.0001622886866059818,
1599
+ "loss": 0.9426,
1600
+ "step": 225
1601
+ },
1602
+ {
1603
+ "epoch": 0.27,
1604
+ "grad_norm": 0.6585952043533325,
1605
+ "learning_rate": 0.00016202860858257478,
1606
+ "loss": 1.0632,
1607
+ "step": 226
1608
+ },
1609
+ {
1610
+ "epoch": 0.27,
1611
+ "grad_norm": 0.2883739173412323,
1612
+ "learning_rate": 0.00016176853055916777,
1613
+ "loss": 0.8594,
1614
+ "step": 227
1615
+ },
1616
+ {
1617
+ "epoch": 0.27,
1618
+ "grad_norm": 0.4793940484523773,
1619
+ "learning_rate": 0.00016150845253576075,
1620
+ "loss": 0.9258,
1621
+ "step": 228
1622
+ },
1623
+ {
1624
+ "epoch": 0.27,
1625
+ "grad_norm": 0.45249128341674805,
1626
+ "learning_rate": 0.0001612483745123537,
1627
+ "loss": 0.875,
1628
+ "step": 229
1629
+ },
1630
+ {
1631
+ "epoch": 0.27,
1632
+ "grad_norm": 0.7601549029350281,
1633
+ "learning_rate": 0.00016098829648894669,
1634
+ "loss": 1.0903,
1635
+ "step": 230
1636
+ },
1637
+ {
1638
+ "epoch": 0.27,
1639
+ "grad_norm": 0.4474358856678009,
1640
+ "learning_rate": 0.00016072821846553967,
1641
+ "loss": 0.8636,
1642
+ "step": 231
1643
+ },
1644
+ {
1645
+ "epoch": 0.27,
1646
+ "grad_norm": 0.4709658920764923,
1647
+ "learning_rate": 0.00016046814044213265,
1648
+ "loss": 1.01,
1649
+ "step": 232
1650
+ },
1651
+ {
1652
+ "epoch": 0.27,
1653
+ "grad_norm": 0.49074116349220276,
1654
+ "learning_rate": 0.00016020806241872563,
1655
+ "loss": 1.129,
1656
+ "step": 233
1657
+ },
1658
+ {
1659
+ "epoch": 0.28,
1660
+ "grad_norm": 0.40011027455329895,
1661
+ "learning_rate": 0.0001599479843953186,
1662
+ "loss": 0.9789,
1663
+ "step": 234
1664
+ },
1665
+ {
1666
+ "epoch": 0.28,
1667
+ "grad_norm": 0.36765021085739136,
1668
+ "learning_rate": 0.00015968790637191157,
1669
+ "loss": 0.9647,
1670
+ "step": 235
1671
+ },
1672
+ {
1673
+ "epoch": 0.28,
1674
+ "grad_norm": 0.4226991832256317,
1675
+ "learning_rate": 0.00015942782834850455,
1676
+ "loss": 1.0593,
1677
+ "step": 236
1678
+ },
1679
+ {
1680
+ "epoch": 0.28,
1681
+ "grad_norm": 0.5633476376533508,
1682
+ "learning_rate": 0.00015916775032509753,
1683
+ "loss": 1.139,
1684
+ "step": 237
1685
+ },
1686
+ {
1687
+ "epoch": 0.28,
1688
+ "grad_norm": 0.4227031171321869,
1689
+ "learning_rate": 0.00015890767230169052,
1690
+ "loss": 0.9766,
1691
+ "step": 238
1692
+ },
1693
+ {
1694
+ "epoch": 0.28,
1695
+ "grad_norm": 0.7903754711151123,
1696
+ "learning_rate": 0.00015864759427828347,
1697
+ "loss": 1.0215,
1698
+ "step": 239
1699
+ },
1700
+ {
1701
+ "epoch": 0.28,
1702
+ "grad_norm": 0.5319734811782837,
1703
+ "learning_rate": 0.00015838751625487645,
1704
+ "loss": 1.0351,
1705
+ "step": 240
1706
+ },
1707
+ {
1708
+ "epoch": 0.28,
1709
+ "grad_norm": 0.38870692253112793,
1710
+ "learning_rate": 0.00015812743823146944,
1711
+ "loss": 1.1089,
1712
+ "step": 241
1713
+ },
1714
+ {
1715
+ "epoch": 0.29,
1716
+ "grad_norm": 0.5061522126197815,
1717
+ "learning_rate": 0.00015786736020806242,
1718
+ "loss": 0.9956,
1719
+ "step": 242
1720
+ },
1721
+ {
1722
+ "epoch": 0.29,
1723
+ "grad_norm": 0.6587597131729126,
1724
+ "learning_rate": 0.0001576072821846554,
1725
+ "loss": 0.9433,
1726
+ "step": 243
1727
+ },
1728
+ {
1729
+ "epoch": 0.29,
1730
+ "grad_norm": 0.500415027141571,
1731
+ "learning_rate": 0.00015734720416124838,
1732
+ "loss": 0.9071,
1733
+ "step": 244
1734
+ },
1735
+ {
1736
+ "epoch": 0.29,
1737
+ "grad_norm": 0.49865788221359253,
1738
+ "learning_rate": 0.00015708712613784136,
1739
+ "loss": 1.013,
1740
+ "step": 245
1741
+ },
1742
+ {
1743
+ "epoch": 0.29,
1744
+ "grad_norm": 0.472517192363739,
1745
+ "learning_rate": 0.00015682704811443435,
1746
+ "loss": 1.0552,
1747
+ "step": 246
1748
+ },
1749
+ {
1750
+ "epoch": 0.29,
1751
+ "grad_norm": 0.5091108083724976,
1752
+ "learning_rate": 0.00015656697009102733,
1753
+ "loss": 0.9919,
1754
+ "step": 247
1755
+ },
1756
+ {
1757
+ "epoch": 0.29,
1758
+ "grad_norm": 0.39484265446662903,
1759
+ "learning_rate": 0.0001563068920676203,
1760
+ "loss": 0.9945,
1761
+ "step": 248
1762
+ },
1763
+ {
1764
+ "epoch": 0.29,
1765
+ "grad_norm": 0.47099944949150085,
1766
+ "learning_rate": 0.00015604681404421327,
1767
+ "loss": 0.847,
1768
+ "step": 249
1769
+ },
1770
+ {
1771
+ "epoch": 0.29,
1772
+ "grad_norm": 0.4681323766708374,
1773
+ "learning_rate": 0.00015578673602080625,
1774
+ "loss": 0.8998,
1775
+ "step": 250
1776
+ },
1777
+ {
1778
+ "epoch": 0.3,
1779
+ "grad_norm": 0.35557135939598083,
1780
+ "learning_rate": 0.00015552665799739923,
1781
+ "loss": 0.7108,
1782
+ "step": 251
1783
+ },
1784
+ {
1785
+ "epoch": 0.3,
1786
+ "grad_norm": 0.7873208522796631,
1787
+ "learning_rate": 0.0001552665799739922,
1788
+ "loss": 1.1322,
1789
+ "step": 252
1790
+ },
1791
+ {
1792
+ "epoch": 0.3,
1793
+ "grad_norm": 0.45806723833084106,
1794
+ "learning_rate": 0.0001550065019505852,
1795
+ "loss": 0.9095,
1796
+ "step": 253
1797
+ },
1798
+ {
1799
+ "epoch": 0.3,
1800
+ "grad_norm": 0.639227032661438,
1801
+ "learning_rate": 0.00015474642392717815,
1802
+ "loss": 1.1761,
1803
+ "step": 254
1804
+ },
1805
+ {
1806
+ "epoch": 0.3,
1807
+ "grad_norm": 0.6849457621574402,
1808
+ "learning_rate": 0.00015448634590377113,
1809
+ "loss": 1.1391,
1810
+ "step": 255
1811
+ },
1812
+ {
1813
+ "epoch": 0.3,
1814
+ "grad_norm": 0.5833932757377625,
1815
+ "learning_rate": 0.00015422626788036411,
1816
+ "loss": 1.0434,
1817
+ "step": 256
1818
+ },
1819
+ {
1820
+ "epoch": 0.3,
1821
+ "grad_norm": 0.684618353843689,
1822
+ "learning_rate": 0.0001539661898569571,
1823
+ "loss": 0.9719,
1824
+ "step": 257
1825
+ },
1826
+ {
1827
+ "epoch": 0.3,
1828
+ "grad_norm": 0.4258657991886139,
1829
+ "learning_rate": 0.00015370611183355008,
1830
+ "loss": 1.1534,
1831
+ "step": 258
1832
+ },
1833
+ {
1834
+ "epoch": 0.31,
1835
+ "grad_norm": 0.5763025879859924,
1836
+ "learning_rate": 0.00015344603381014303,
1837
+ "loss": 0.9974,
1838
+ "step": 259
1839
+ },
1840
+ {
1841
+ "epoch": 0.31,
1842
+ "grad_norm": 0.5415167808532715,
1843
+ "learning_rate": 0.00015318595578673602,
1844
+ "loss": 1.0696,
1845
+ "step": 260
1846
+ },
1847
+ {
1848
+ "epoch": 0.31,
1849
+ "grad_norm": 0.43196481466293335,
1850
+ "learning_rate": 0.000152925877763329,
1851
+ "loss": 0.8191,
1852
+ "step": 261
1853
+ },
1854
+ {
1855
+ "epoch": 0.31,
1856
+ "grad_norm": 0.3914147913455963,
1857
+ "learning_rate": 0.00015266579973992198,
1858
+ "loss": 0.8465,
1859
+ "step": 262
1860
+ },
1861
+ {
1862
+ "epoch": 0.31,
1863
+ "grad_norm": 0.4838383197784424,
1864
+ "learning_rate": 0.00015240572171651496,
1865
+ "loss": 1.0027,
1866
+ "step": 263
1867
+ },
1868
+ {
1869
+ "epoch": 0.31,
1870
+ "grad_norm": 0.3581622540950775,
1871
+ "learning_rate": 0.00015214564369310792,
1872
+ "loss": 1.1247,
1873
+ "step": 264
1874
+ },
1875
+ {
1876
+ "epoch": 0.31,
1877
+ "grad_norm": 0.9383752942085266,
1878
+ "learning_rate": 0.0001518855656697009,
1879
+ "loss": 1.2207,
1880
+ "step": 265
1881
+ },
1882
+ {
1883
+ "epoch": 0.31,
1884
+ "grad_norm": 0.5058914422988892,
1885
+ "learning_rate": 0.00015162548764629388,
1886
+ "loss": 1.0036,
1887
+ "step": 266
1888
+ },
1889
+ {
1890
+ "epoch": 0.31,
1891
+ "grad_norm": 0.4513028860092163,
1892
+ "learning_rate": 0.0001513654096228869,
1893
+ "loss": 1.0949,
1894
+ "step": 267
1895
+ },
1896
+ {
1897
+ "epoch": 0.32,
1898
+ "grad_norm": 0.5779305696487427,
1899
+ "learning_rate": 0.00015110533159947987,
1900
+ "loss": 1.0035,
1901
+ "step": 268
1902
+ },
1903
+ {
1904
+ "epoch": 0.32,
1905
+ "grad_norm": 0.6758905649185181,
1906
+ "learning_rate": 0.00015084525357607283,
1907
+ "loss": 1.0163,
1908
+ "step": 269
1909
+ },
1910
+ {
1911
+ "epoch": 0.32,
1912
+ "grad_norm": 0.5109132528305054,
1913
+ "learning_rate": 0.0001505851755526658,
1914
+ "loss": 0.7357,
1915
+ "step": 270
1916
+ },
1917
+ {
1918
+ "epoch": 0.32,
1919
+ "grad_norm": 0.42248305678367615,
1920
+ "learning_rate": 0.0001503250975292588,
1921
+ "loss": 1.0664,
1922
+ "step": 271
1923
+ },
1924
+ {
1925
+ "epoch": 0.32,
1926
+ "grad_norm": 0.7441749572753906,
1927
+ "learning_rate": 0.00015006501950585178,
1928
+ "loss": 0.9483,
1929
+ "step": 272
1930
+ },
1931
+ {
1932
+ "epoch": 0.32,
1933
+ "grad_norm": 0.5364653468132019,
1934
+ "learning_rate": 0.00014980494148244476,
1935
+ "loss": 1.1671,
1936
+ "step": 273
1937
+ },
1938
+ {
1939
+ "epoch": 0.32,
1940
+ "grad_norm": 0.3390597701072693,
1941
+ "learning_rate": 0.0001495448634590377,
1942
+ "loss": 0.9616,
1943
+ "step": 274
1944
+ },
1945
+ {
1946
+ "epoch": 0.32,
1947
+ "grad_norm": 0.3810036778450012,
1948
+ "learning_rate": 0.0001492847854356307,
1949
+ "loss": 0.9419,
1950
+ "step": 275
1951
+ },
1952
+ {
1953
+ "epoch": 0.33,
1954
+ "grad_norm": 0.39790648221969604,
1955
+ "learning_rate": 0.00014902470741222368,
1956
+ "loss": 0.947,
1957
+ "step": 276
1958
+ },
1959
+ {
1960
+ "epoch": 0.33,
1961
+ "grad_norm": 0.5461649894714355,
1962
+ "learning_rate": 0.00014876462938881666,
1963
+ "loss": 1.0065,
1964
+ "step": 277
1965
+ },
1966
+ {
1967
+ "epoch": 0.33,
1968
+ "grad_norm": 0.376022607088089,
1969
+ "learning_rate": 0.00014850455136540964,
1970
+ "loss": 0.8626,
1971
+ "step": 278
1972
+ },
1973
+ {
1974
+ "epoch": 0.33,
1975
+ "grad_norm": 0.47341254353523254,
1976
+ "learning_rate": 0.0001482444733420026,
1977
+ "loss": 0.9812,
1978
+ "step": 279
1979
+ },
1980
+ {
1981
+ "epoch": 0.33,
1982
+ "grad_norm": 0.5151678323745728,
1983
+ "learning_rate": 0.00014798439531859558,
1984
+ "loss": 0.9688,
1985
+ "step": 280
1986
+ },
1987
+ {
1988
+ "epoch": 0.33,
1989
+ "grad_norm": 0.4801676273345947,
1990
+ "learning_rate": 0.00014772431729518856,
1991
+ "loss": 0.9348,
1992
+ "step": 281
1993
+ },
1994
+ {
1995
+ "epoch": 0.33,
1996
+ "grad_norm": 0.43506500124931335,
1997
+ "learning_rate": 0.00014746423927178154,
1998
+ "loss": 1.0792,
1999
+ "step": 282
2000
+ },
2001
+ {
2002
+ "epoch": 0.33,
2003
+ "grad_norm": 0.5347827076911926,
2004
+ "learning_rate": 0.00014720416124837452,
2005
+ "loss": 1.1285,
2006
+ "step": 283
2007
+ },
2008
+ {
2009
+ "epoch": 0.33,
2010
+ "grad_norm": 0.5323308706283569,
2011
+ "learning_rate": 0.00014694408322496748,
2012
+ "loss": 1.047,
2013
+ "step": 284
2014
+ },
2015
+ {
2016
+ "epoch": 0.34,
2017
+ "grad_norm": 0.364046573638916,
2018
+ "learning_rate": 0.00014668400520156046,
2019
+ "loss": 1.0206,
2020
+ "step": 285
2021
+ },
2022
+ {
2023
+ "epoch": 0.34,
2024
+ "grad_norm": 0.41780295968055725,
2025
+ "learning_rate": 0.00014642392717815344,
2026
+ "loss": 1.011,
2027
+ "step": 286
2028
+ },
2029
+ {
2030
+ "epoch": 0.34,
2031
+ "grad_norm": 0.6010937690734863,
2032
+ "learning_rate": 0.00014616384915474643,
2033
+ "loss": 0.9836,
2034
+ "step": 287
2035
+ },
2036
+ {
2037
+ "epoch": 0.34,
2038
+ "grad_norm": 0.3574303090572357,
2039
+ "learning_rate": 0.0001459037711313394,
2040
+ "loss": 0.9051,
2041
+ "step": 288
2042
+ },
2043
+ {
2044
+ "epoch": 0.34,
2045
+ "grad_norm": 0.3346600830554962,
2046
+ "learning_rate": 0.0001456436931079324,
2047
+ "loss": 1.0333,
2048
+ "step": 289
2049
+ },
2050
+ {
2051
+ "epoch": 0.34,
2052
+ "grad_norm": 0.48559319972991943,
2053
+ "learning_rate": 0.00014538361508452537,
2054
+ "loss": 0.8363,
2055
+ "step": 290
2056
+ },
2057
+ {
2058
+ "epoch": 0.34,
2059
+ "grad_norm": 0.4872112274169922,
2060
+ "learning_rate": 0.00014512353706111836,
2061
+ "loss": 0.9565,
2062
+ "step": 291
2063
+ },
2064
+ {
2065
+ "epoch": 0.34,
2066
+ "grad_norm": 0.37863266468048096,
2067
+ "learning_rate": 0.00014486345903771134,
2068
+ "loss": 0.9869,
2069
+ "step": 292
2070
+ },
2071
+ {
2072
+ "epoch": 0.35,
2073
+ "grad_norm": 0.6248475909233093,
2074
+ "learning_rate": 0.00014460338101430432,
2075
+ "loss": 1.1117,
2076
+ "step": 293
2077
+ },
2078
+ {
2079
+ "epoch": 0.35,
2080
+ "grad_norm": 0.40380629897117615,
2081
+ "learning_rate": 0.00014434330299089727,
2082
+ "loss": 0.895,
2083
+ "step": 294
2084
+ },
2085
+ {
2086
+ "epoch": 0.35,
2087
+ "grad_norm": 0.4236217439174652,
2088
+ "learning_rate": 0.00014408322496749026,
2089
+ "loss": 0.8849,
2090
+ "step": 295
2091
+ },
2092
+ {
2093
+ "epoch": 0.35,
2094
+ "grad_norm": 0.35017380118370056,
2095
+ "learning_rate": 0.00014382314694408324,
2096
+ "loss": 0.8472,
2097
+ "step": 296
2098
+ },
2099
+ {
2100
+ "epoch": 0.35,
2101
+ "grad_norm": 0.5927186608314514,
2102
+ "learning_rate": 0.00014356306892067622,
2103
+ "loss": 1.0073,
2104
+ "step": 297
2105
+ },
2106
+ {
2107
+ "epoch": 0.35,
2108
+ "grad_norm": 0.7567859292030334,
2109
+ "learning_rate": 0.0001433029908972692,
2110
+ "loss": 0.9784,
2111
+ "step": 298
2112
+ },
2113
+ {
2114
+ "epoch": 0.35,
2115
+ "grad_norm": 0.4356285035610199,
2116
+ "learning_rate": 0.00014304291287386216,
2117
+ "loss": 0.8339,
2118
+ "step": 299
2119
+ },
2120
+ {
2121
+ "epoch": 0.35,
2122
+ "grad_norm": 0.3144444525241852,
2123
+ "learning_rate": 0.00014278283485045514,
2124
+ "loss": 1.0751,
2125
+ "step": 300
2126
+ },
2127
+ {
2128
+ "epoch": 0.35,
2129
+ "eval_loss": 0.9849200248718262,
2130
+ "eval_runtime": 546.1357,
2131
+ "eval_samples_per_second": 2.765,
2132
+ "eval_steps_per_second": 1.382,
2133
+ "step": 300
2134
+ }
2135
+ ],
2136
+ "logging_steps": 1.0,
2137
+ "max_steps": 849,
2138
+ "num_input_tokens_seen": 0,
2139
+ "num_train_epochs": 1,
2140
+ "save_steps": 100,
2141
+ "total_flos": 1.4054359796233011e+17,
2142
+ "train_batch_size": 2,
2143
+ "trial_name": null,
2144
+ "trial_params": null
2145
+ }
checkpoint-300/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc06bccd88c12bdcde2e7c89042c088b7ef7838c421f9aaa174c41cce84686e1
3
+ size 5176
checkpoint-400/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: cognitivecomputations/dolphin-2.9-llama3-8b
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.10.0
checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "cognitivecomputations/dolphin-2.9-llama3-8b",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": "unsloth",
22
+ "target_modules": [
23
+ "v_proj",
24
+ "k_proj",
25
+ "down_proj",
26
+ "gate_proj",
27
+ "q_proj",
28
+ "up_proj",
29
+ "o_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-400/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4406a9f37e89864e4b13431dd67a21030ec4c6a820aada50573f43d371bf09d
3
+ size 167832240
checkpoint-400/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eb5f88addd5e5e950f9862264bd88077b7fb8553489a90cb94d8622a644ee82
3
+ size 84571156
checkpoint-400/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ef99d93302b6f6c78b61381a4657e445531e2da311bd3ac25675a844a65c9fb
3
+ size 14512
checkpoint-400/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7331ba620523c7754170a9d62d7ecbcf5b0fcb402fb592a54f4a7f92919fe1fb
3
+ size 14512
checkpoint-400/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb2cec54365f2bdfbfb129baed0112552fde91ac96b86dc7776a5c276122711c
3
+ size 1064
checkpoint-400/special_tokens_map.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|im_start|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ }
10
+ ],
11
+ "bos_token": {
12
+ "content": "<|begin_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "eos_token": {
19
+ "content": "<|im_end|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "pad_token": {
26
+ "content": "<|end_of_text|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ }
32
+ }
checkpoint-400/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-400/tokenizer_config.json ADDED
@@ -0,0 +1,2084 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ },
2051
+ "128256": {
2052
+ "content": "<|im_end|>",
2053
+ "lstrip": false,
2054
+ "normalized": false,
2055
+ "rstrip": false,
2056
+ "single_word": false,
2057
+ "special": true
2058
+ },
2059
+ "128257": {
2060
+ "content": "<|im_start|>",
2061
+ "lstrip": false,
2062
+ "normalized": false,
2063
+ "rstrip": false,
2064
+ "single_word": false,
2065
+ "special": true
2066
+ }
2067
+ },
2068
+ "additional_special_tokens": [
2069
+ "<|im_start|>"
2070
+ ],
2071
+ "bos_token": "<|begin_of_text|>",
2072
+ "chat_template": "{% set system_message = 'Du bist ein freundlicher und hilfsbereiter KI-Assistent.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\\n' + system_message + '<|im_end|>\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\\n' + content + '<|im_end|>\\n<|im_start|>assistant\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\\n' }}{% endif %}{% endfor %}",
2073
+ "clean_up_tokenization_spaces": true,
2074
+ "eos_token": "<|im_end|>",
2075
+ "model_input_names": [
2076
+ "input_ids",
2077
+ "attention_mask"
2078
+ ],
2079
+ "model_max_length": 1000000000000000019884624838656,
2080
+ "pad_token": "<|end_of_text|>",
2081
+ "padding_side": "right",
2082
+ "split_special_tokens": false,
2083
+ "tokenizer_class": "PreTrainedTokenizerFast"
2084
+ }