gabrielmbmb HF staff commited on
Commit
aa3d567
1 Parent(s): 0006e53

Model save

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: llama3.1
4
+ base_model: meta-llama/Llama-3.1-8B
5
+ tags:
6
+ - trl
7
+ - sft
8
+ - generated_from_trainer
9
+ datasets:
10
+ - generator
11
+ model-index:
12
+ - name: Llama-3.1-8B-MagPie-Ultra
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # Llama-3.1-8B-MagPie-Ultra
20
+
21
+ This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on the generator dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.5915
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 2e-05
43
+ - train_batch_size: 4
44
+ - eval_batch_size: 4
45
+ - seed: 42
46
+ - distributed_type: multi-GPU
47
+ - num_devices: 8
48
+ - gradient_accumulation_steps: 4
49
+ - total_train_batch_size: 128
50
+ - total_eval_batch_size: 32
51
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
+ - lr_scheduler_type: cosine
53
+ - lr_scheduler_warmup_ratio: 0.1
54
+ - num_epochs: 1
55
+
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Validation Loss |
59
+ |:-------------:|:------:|:----:|:---------------:|
60
+ | 0.5939 | 0.9998 | 1002 | 0.5915 |
61
+
62
+
63
+ ### Framework versions
64
+
65
+ - Transformers 4.45.0
66
+ - Pytorch 2.4.1+cu121
67
+ - Datasets 3.0.1
68
+ - Tokenizers 0.20.0
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9997505612372163,
3
+ "total_flos": 838984280309760.0,
4
+ "train_loss": 0.6422406448099666,
5
+ "train_runtime": 10627.6191,
6
+ "train_samples": 284873,
7
+ "train_samples_per_second": 12.071,
8
+ "train_steps_per_second": 0.094
9
+ }
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-3.1-8B",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 14336,
15
+ "max_position_embeddings": 131072,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 32,
20
+ "num_key_value_heads": 8,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": {
24
+ "factor": 8.0,
25
+ "high_freq_factor": 4.0,
26
+ "low_freq_factor": 1.0,
27
+ "original_max_position_embeddings": 8192,
28
+ "rope_type": "llama3"
29
+ },
30
+ "rope_theta": 500000.0,
31
+ "tie_word_embeddings": false,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.45.0",
34
+ "use_cache": false,
35
+ "vocab_size": 128256
36
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "do_sample": true,
5
+ "eos_token_id": 128001,
6
+ "temperature": 0.6,
7
+ "top_p": 0.9,
8
+ "transformers_version": "4.45.0"
9
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7d60bf761573ed803edc33d5afee39e7b4ce06a9f9f4310c47968825372478d
3
+ size 4976698672
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b41e0ac636334e47e6dd652bec78802144a78172bf09da0480d15639e5d36fb6
3
+ size 4999802720
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf928589f4aceb7b0be359557994b5af464926e27c7073d54b50304c54d95015
3
+ size 4915916176
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a382fad5c1f030dbc593fbd3c8aa961da5dfe7361eb7c1b0eb5bab5317043823
3
+ size 1168138808
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16060522496
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
296
+ "model.norm.weight": "model-00004-of-00004.safetensors"
297
+ }
298
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
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": "<|eom_id|>",
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": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 2048,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9997505612372163,
3
+ "total_flos": 838984280309760.0,
4
+ "train_loss": 0.6422406448099666,
5
+ "train_runtime": 10627.6191,
6
+ "train_samples": 284873,
7
+ "train_samples_per_second": 12.071,
8
+ "train_steps_per_second": 0.094
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,1457 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9997505612372163,
5
+ "eval_steps": 500,
6
+ "global_step": 1002,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0009977550511349464,
13
+ "grad_norm": 3.95422100343339e+17,
14
+ "learning_rate": 1.9801980198019803e-07,
15
+ "loss": 1.1312,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.004988775255674732,
20
+ "grad_norm": 2182.5525466022195,
21
+ "learning_rate": 9.900990099009902e-07,
22
+ "loss": 1.1202,
23
+ "step": 5
24
+ },
25
+ {
26
+ "epoch": 0.009977550511349464,
27
+ "grad_norm": 10.696306402986602,
28
+ "learning_rate": 1.9801980198019803e-06,
29
+ "loss": 1.0843,
30
+ "step": 10
31
+ },
32
+ {
33
+ "epoch": 0.014966325767024195,
34
+ "grad_norm": 4.8421359026925295,
35
+ "learning_rate": 2.9702970297029703e-06,
36
+ "loss": 1.024,
37
+ "step": 15
38
+ },
39
+ {
40
+ "epoch": 0.01995510102269893,
41
+ "grad_norm": 1.4664994361442427,
42
+ "learning_rate": 3.960396039603961e-06,
43
+ "loss": 0.9479,
44
+ "step": 20
45
+ },
46
+ {
47
+ "epoch": 0.024943876278373658,
48
+ "grad_norm": 1.1625196109582225,
49
+ "learning_rate": 4.950495049504951e-06,
50
+ "loss": 0.8935,
51
+ "step": 25
52
+ },
53
+ {
54
+ "epoch": 0.02993265153404839,
55
+ "grad_norm": 1.2801604519342376,
56
+ "learning_rate": 5.940594059405941e-06,
57
+ "loss": 0.871,
58
+ "step": 30
59
+ },
60
+ {
61
+ "epoch": 0.034921426789723126,
62
+ "grad_norm": 2.033559906503939,
63
+ "learning_rate": 6.930693069306931e-06,
64
+ "loss": 0.8425,
65
+ "step": 35
66
+ },
67
+ {
68
+ "epoch": 0.03991020204539786,
69
+ "grad_norm": 1.2072354289878107,
70
+ "learning_rate": 7.920792079207921e-06,
71
+ "loss": 0.8193,
72
+ "step": 40
73
+ },
74
+ {
75
+ "epoch": 0.04489897730107259,
76
+ "grad_norm": 1.3137258088382902,
77
+ "learning_rate": 8.910891089108911e-06,
78
+ "loss": 0.8013,
79
+ "step": 45
80
+ },
81
+ {
82
+ "epoch": 0.049887752556747315,
83
+ "grad_norm": 1.1213863664000594,
84
+ "learning_rate": 9.900990099009901e-06,
85
+ "loss": 0.7906,
86
+ "step": 50
87
+ },
88
+ {
89
+ "epoch": 0.05487652781242205,
90
+ "grad_norm": 0.9999895583902438,
91
+ "learning_rate": 1.0891089108910893e-05,
92
+ "loss": 0.7642,
93
+ "step": 55
94
+ },
95
+ {
96
+ "epoch": 0.05986530306809678,
97
+ "grad_norm": 1.3377086334649673,
98
+ "learning_rate": 1.1881188118811881e-05,
99
+ "loss": 0.7495,
100
+ "step": 60
101
+ },
102
+ {
103
+ "epoch": 0.06485407832377152,
104
+ "grad_norm": 1.0583607289478394,
105
+ "learning_rate": 1.2871287128712873e-05,
106
+ "loss": 0.7328,
107
+ "step": 65
108
+ },
109
+ {
110
+ "epoch": 0.06984285357944625,
111
+ "grad_norm": 1.3493827534349543,
112
+ "learning_rate": 1.3861386138613861e-05,
113
+ "loss": 0.7383,
114
+ "step": 70
115
+ },
116
+ {
117
+ "epoch": 0.07483162883512098,
118
+ "grad_norm": 1.2261995345556986,
119
+ "learning_rate": 1.4851485148514853e-05,
120
+ "loss": 0.7281,
121
+ "step": 75
122
+ },
123
+ {
124
+ "epoch": 0.07982040409079572,
125
+ "grad_norm": 1.3328058553211537,
126
+ "learning_rate": 1.5841584158415843e-05,
127
+ "loss": 0.7236,
128
+ "step": 80
129
+ },
130
+ {
131
+ "epoch": 0.08480917934647045,
132
+ "grad_norm": 1.1145579124084846,
133
+ "learning_rate": 1.683168316831683e-05,
134
+ "loss": 0.7255,
135
+ "step": 85
136
+ },
137
+ {
138
+ "epoch": 0.08979795460214518,
139
+ "grad_norm": 0.9193198348331784,
140
+ "learning_rate": 1.7821782178217823e-05,
141
+ "loss": 0.7181,
142
+ "step": 90
143
+ },
144
+ {
145
+ "epoch": 0.0947867298578199,
146
+ "grad_norm": 0.9946484577080871,
147
+ "learning_rate": 1.881188118811881e-05,
148
+ "loss": 0.7103,
149
+ "step": 95
150
+ },
151
+ {
152
+ "epoch": 0.09977550511349463,
153
+ "grad_norm": 1.041681712316516,
154
+ "learning_rate": 1.9801980198019803e-05,
155
+ "loss": 0.7007,
156
+ "step": 100
157
+ },
158
+ {
159
+ "epoch": 0.10476428036916936,
160
+ "grad_norm": 2.164939078852322,
161
+ "learning_rate": 1.9999027402586235e-05,
162
+ "loss": 0.7064,
163
+ "step": 105
164
+ },
165
+ {
166
+ "epoch": 0.1097530556248441,
167
+ "grad_norm": 2.7326170629817335,
168
+ "learning_rate": 1.9995076549835638e-05,
169
+ "loss": 0.7129,
170
+ "step": 110
171
+ },
172
+ {
173
+ "epoch": 0.11474183088051883,
174
+ "grad_norm": 0.958937879949106,
175
+ "learning_rate": 1.9988087854284224e-05,
176
+ "loss": 0.6984,
177
+ "step": 115
178
+ },
179
+ {
180
+ "epoch": 0.11973060613619356,
181
+ "grad_norm": 1.1161507946755316,
182
+ "learning_rate": 1.997806344003363e-05,
183
+ "loss": 0.7025,
184
+ "step": 120
185
+ },
186
+ {
187
+ "epoch": 0.12471938139186829,
188
+ "grad_norm": 0.9783646600814512,
189
+ "learning_rate": 1.996500635384337e-05,
190
+ "loss": 0.6918,
191
+ "step": 125
192
+ },
193
+ {
194
+ "epoch": 0.12970815664754304,
195
+ "grad_norm": 0.8060832238745128,
196
+ "learning_rate": 1.994892056420485e-05,
197
+ "loss": 0.6842,
198
+ "step": 130
199
+ },
200
+ {
201
+ "epoch": 0.13469693190321777,
202
+ "grad_norm": 0.8669120420326126,
203
+ "learning_rate": 1.992981096013517e-05,
204
+ "loss": 0.6806,
205
+ "step": 135
206
+ },
207
+ {
208
+ "epoch": 0.1396857071588925,
209
+ "grad_norm": 0.8551160872182698,
210
+ "learning_rate": 1.990768334969122e-05,
211
+ "loss": 0.6908,
212
+ "step": 140
213
+ },
214
+ {
215
+ "epoch": 0.14467448241456723,
216
+ "grad_norm": 0.6818189908779505,
217
+ "learning_rate": 1.9882544458204386e-05,
218
+ "loss": 0.6888,
219
+ "step": 145
220
+ },
221
+ {
222
+ "epoch": 0.14966325767024197,
223
+ "grad_norm": 0.7649549705168317,
224
+ "learning_rate": 1.9854401926236518e-05,
225
+ "loss": 0.6867,
226
+ "step": 150
227
+ },
228
+ {
229
+ "epoch": 0.1546520329259167,
230
+ "grad_norm": 0.8499401555713652,
231
+ "learning_rate": 1.9823264307257683e-05,
232
+ "loss": 0.6707,
233
+ "step": 155
234
+ },
235
+ {
236
+ "epoch": 0.15964080818159143,
237
+ "grad_norm": 0.7166408203324516,
238
+ "learning_rate": 1.9789141065046495e-05,
239
+ "loss": 0.676,
240
+ "step": 160
241
+ },
242
+ {
243
+ "epoch": 0.16462958343726616,
244
+ "grad_norm": 0.6182479498389858,
245
+ "learning_rate": 1.9752042570813733e-05,
246
+ "loss": 0.6738,
247
+ "step": 165
248
+ },
249
+ {
250
+ "epoch": 0.1696183586929409,
251
+ "grad_norm": 0.6690357471493384,
252
+ "learning_rate": 1.9711980100050196e-05,
253
+ "loss": 0.6672,
254
+ "step": 170
255
+ },
256
+ {
257
+ "epoch": 0.17460713394861563,
258
+ "grad_norm": 0.5822226665191199,
259
+ "learning_rate": 1.966896582909968e-05,
260
+ "loss": 0.6736,
261
+ "step": 175
262
+ },
263
+ {
264
+ "epoch": 0.17959590920429036,
265
+ "grad_norm": 0.7406095161368872,
266
+ "learning_rate": 1.962301283145819e-05,
267
+ "loss": 0.6761,
268
+ "step": 180
269
+ },
270
+ {
271
+ "epoch": 0.18458468445996506,
272
+ "grad_norm": 0.7296907738291923,
273
+ "learning_rate": 1.957413507380046e-05,
274
+ "loss": 0.6678,
275
+ "step": 185
276
+ },
277
+ {
278
+ "epoch": 0.1895734597156398,
279
+ "grad_norm": 0.8518753276369776,
280
+ "learning_rate": 1.952234741173499e-05,
281
+ "loss": 0.6733,
282
+ "step": 190
283
+ },
284
+ {
285
+ "epoch": 0.19456223497131453,
286
+ "grad_norm": 0.5554147873181055,
287
+ "learning_rate": 1.946766558528895e-05,
288
+ "loss": 0.6621,
289
+ "step": 195
290
+ },
291
+ {
292
+ "epoch": 0.19955101022698926,
293
+ "grad_norm": 0.6525658967181038,
294
+ "learning_rate": 1.941010621412422e-05,
295
+ "loss": 0.6649,
296
+ "step": 200
297
+ },
298
+ {
299
+ "epoch": 0.204539785482664,
300
+ "grad_norm": 0.5780920597815026,
301
+ "learning_rate": 1.9349686792486143e-05,
302
+ "loss": 0.657,
303
+ "step": 205
304
+ },
305
+ {
306
+ "epoch": 0.20952856073833873,
307
+ "grad_norm": 0.5578703671497164,
308
+ "learning_rate": 1.9286425683886403e-05,
309
+ "loss": 0.6687,
310
+ "step": 210
311
+ },
312
+ {
313
+ "epoch": 0.21451733599401346,
314
+ "grad_norm": 0.72305301104437,
315
+ "learning_rate": 1.9220342115521746e-05,
316
+ "loss": 0.6624,
317
+ "step": 215
318
+ },
319
+ {
320
+ "epoch": 0.2195061112496882,
321
+ "grad_norm": 0.6165020865206677,
322
+ "learning_rate": 1.9151456172430186e-05,
323
+ "loss": 0.6532,
324
+ "step": 220
325
+ },
326
+ {
327
+ "epoch": 0.22449488650536292,
328
+ "grad_norm": 0.5606109731701377,
329
+ "learning_rate": 1.9079788791386468e-05,
330
+ "loss": 0.6562,
331
+ "step": 225
332
+ },
333
+ {
334
+ "epoch": 0.22948366176103766,
335
+ "grad_norm": 0.6353820290325317,
336
+ "learning_rate": 1.9005361754538677e-05,
337
+ "loss": 0.6671,
338
+ "step": 230
339
+ },
340
+ {
341
+ "epoch": 0.2344724370167124,
342
+ "grad_norm": 0.5815877946035953,
343
+ "learning_rate": 1.8928197682787914e-05,
344
+ "loss": 0.6593,
345
+ "step": 235
346
+ },
347
+ {
348
+ "epoch": 0.23946121227238712,
349
+ "grad_norm": 0.6348680697801418,
350
+ "learning_rate": 1.8848320028913017e-05,
351
+ "loss": 0.6507,
352
+ "step": 240
353
+ },
354
+ {
355
+ "epoch": 0.24444998752806185,
356
+ "grad_norm": 0.5695451117286802,
357
+ "learning_rate": 1.8765753070442486e-05,
358
+ "loss": 0.6523,
359
+ "step": 245
360
+ },
361
+ {
362
+ "epoch": 0.24943876278373658,
363
+ "grad_norm": 0.5168318177147343,
364
+ "learning_rate": 1.868052190227571e-05,
365
+ "loss": 0.6591,
366
+ "step": 250
367
+ },
368
+ {
369
+ "epoch": 0.2544275380394113,
370
+ "grad_norm": 0.7348069026040828,
371
+ "learning_rate": 1.859265242905577e-05,
372
+ "loss": 0.6541,
373
+ "step": 255
374
+ },
375
+ {
376
+ "epoch": 0.2594163132950861,
377
+ "grad_norm": 0.5329392930102724,
378
+ "learning_rate": 1.8502171357296144e-05,
379
+ "loss": 0.6589,
380
+ "step": 260
381
+ },
382
+ {
383
+ "epoch": 0.2644050885507608,
384
+ "grad_norm": 0.6628783134030882,
385
+ "learning_rate": 1.84091061872637e-05,
386
+ "loss": 0.6443,
387
+ "step": 265
388
+ },
389
+ {
390
+ "epoch": 0.26939386380643554,
391
+ "grad_norm": 0.6959729166297904,
392
+ "learning_rate": 1.8313485204620428e-05,
393
+ "loss": 0.6459,
394
+ "step": 270
395
+ },
396
+ {
397
+ "epoch": 0.27438263906211025,
398
+ "grad_norm": 0.5848246972834032,
399
+ "learning_rate": 1.821533747182645e-05,
400
+ "loss": 0.6606,
401
+ "step": 275
402
+ },
403
+ {
404
+ "epoch": 0.279371414317785,
405
+ "grad_norm": 0.6475331258568309,
406
+ "learning_rate": 1.811469281930698e-05,
407
+ "loss": 0.656,
408
+ "step": 280
409
+ },
410
+ {
411
+ "epoch": 0.2843601895734597,
412
+ "grad_norm": 0.5357406950163816,
413
+ "learning_rate": 1.8011581836385828e-05,
414
+ "loss": 0.6474,
415
+ "step": 285
416
+ },
417
+ {
418
+ "epoch": 0.28934896482913447,
419
+ "grad_norm": 0.5973939212545811,
420
+ "learning_rate": 1.790603586198827e-05,
421
+ "loss": 0.6376,
422
+ "step": 290
423
+ },
424
+ {
425
+ "epoch": 0.2943377400848092,
426
+ "grad_norm": 0.5096252662581786,
427
+ "learning_rate": 1.7798086975116096e-05,
428
+ "loss": 0.6487,
429
+ "step": 295
430
+ },
431
+ {
432
+ "epoch": 0.29932651534048393,
433
+ "grad_norm": 0.545088543038122,
434
+ "learning_rate": 1.7687767985097695e-05,
435
+ "loss": 0.6526,
436
+ "step": 300
437
+ },
438
+ {
439
+ "epoch": 0.30431529059615864,
440
+ "grad_norm": 0.707465419807657,
441
+ "learning_rate": 1.7575112421616203e-05,
442
+ "loss": 0.6465,
443
+ "step": 305
444
+ },
445
+ {
446
+ "epoch": 0.3093040658518334,
447
+ "grad_norm": 0.520929461518716,
448
+ "learning_rate": 1.7460154524518688e-05,
449
+ "loss": 0.6346,
450
+ "step": 310
451
+ },
452
+ {
453
+ "epoch": 0.3142928411075081,
454
+ "grad_norm": 0.5724374980096262,
455
+ "learning_rate": 1.73429292334095e-05,
456
+ "loss": 0.6533,
457
+ "step": 315
458
+ },
459
+ {
460
+ "epoch": 0.31928161636318286,
461
+ "grad_norm": 0.545092535159253,
462
+ "learning_rate": 1.722347217703094e-05,
463
+ "loss": 0.6437,
464
+ "step": 320
465
+ },
466
+ {
467
+ "epoch": 0.32427039161885757,
468
+ "grad_norm": 0.49712776699676936,
469
+ "learning_rate": 1.710181966243447e-05,
470
+ "loss": 0.6373,
471
+ "step": 325
472
+ },
473
+ {
474
+ "epoch": 0.3292591668745323,
475
+ "grad_norm": 0.5463641929477563,
476
+ "learning_rate": 1.6978008663945794e-05,
477
+ "loss": 0.6496,
478
+ "step": 330
479
+ },
480
+ {
481
+ "epoch": 0.33424794213020703,
482
+ "grad_norm": 0.5263242364290428,
483
+ "learning_rate": 1.6852076811927066e-05,
484
+ "loss": 0.6369,
485
+ "step": 335
486
+ },
487
+ {
488
+ "epoch": 0.3392367173858818,
489
+ "grad_norm": 0.5461638677630304,
490
+ "learning_rate": 1.672406238133978e-05,
491
+ "loss": 0.639,
492
+ "step": 340
493
+ },
494
+ {
495
+ "epoch": 0.3442254926415565,
496
+ "grad_norm": 0.5328798983853884,
497
+ "learning_rate": 1.6594004280111697e-05,
498
+ "loss": 0.6497,
499
+ "step": 345
500
+ },
501
+ {
502
+ "epoch": 0.34921426789723126,
503
+ "grad_norm": 0.5449564175014876,
504
+ "learning_rate": 1.6461942037311406e-05,
505
+ "loss": 0.64,
506
+ "step": 350
507
+ },
508
+ {
509
+ "epoch": 0.35420304315290596,
510
+ "grad_norm": 0.4924182140259062,
511
+ "learning_rate": 1.6327915791134107e-05,
512
+ "loss": 0.6396,
513
+ "step": 355
514
+ },
515
+ {
516
+ "epoch": 0.3591918184085807,
517
+ "grad_norm": 0.6190239635709287,
518
+ "learning_rate": 1.6191966276702235e-05,
519
+ "loss": 0.6377,
520
+ "step": 360
521
+ },
522
+ {
523
+ "epoch": 0.3641805936642554,
524
+ "grad_norm": 0.6147520812137072,
525
+ "learning_rate": 1.6054134813684697e-05,
526
+ "loss": 0.6375,
527
+ "step": 365
528
+ },
529
+ {
530
+ "epoch": 0.36916936891993013,
531
+ "grad_norm": 0.5215763519986214,
532
+ "learning_rate": 1.5914463293738402e-05,
533
+ "loss": 0.6368,
534
+ "step": 370
535
+ },
536
+ {
537
+ "epoch": 0.3741581441756049,
538
+ "grad_norm": 0.6214647949635035,
539
+ "learning_rate": 1.5772994167775986e-05,
540
+ "loss": 0.6303,
541
+ "step": 375
542
+ },
543
+ {
544
+ "epoch": 0.3791469194312796,
545
+ "grad_norm": 0.6365612833821749,
546
+ "learning_rate": 1.5629770433063523e-05,
547
+ "loss": 0.6244,
548
+ "step": 380
549
+ },
550
+ {
551
+ "epoch": 0.38413569468695435,
552
+ "grad_norm": 0.594264835461608,
553
+ "learning_rate": 1.5484835620152198e-05,
554
+ "loss": 0.6323,
555
+ "step": 385
556
+ },
557
+ {
558
+ "epoch": 0.38912446994262906,
559
+ "grad_norm": 0.6107791643380025,
560
+ "learning_rate": 1.533823377964791e-05,
561
+ "loss": 0.6298,
562
+ "step": 390
563
+ },
564
+ {
565
+ "epoch": 0.3941132451983038,
566
+ "grad_norm": 0.6001005800935538,
567
+ "learning_rate": 1.5190009468822782e-05,
568
+ "loss": 0.63,
569
+ "step": 395
570
+ },
571
+ {
572
+ "epoch": 0.3991020204539785,
573
+ "grad_norm": 0.5176320349977592,
574
+ "learning_rate": 1.5040207738072714e-05,
575
+ "loss": 0.6296,
576
+ "step": 400
577
+ },
578
+ {
579
+ "epoch": 0.4040907957096533,
580
+ "grad_norm": 0.5530769815557066,
581
+ "learning_rate": 1.4888874117225013e-05,
582
+ "loss": 0.6202,
583
+ "step": 405
584
+ },
585
+ {
586
+ "epoch": 0.409079570965328,
587
+ "grad_norm": 0.4750983813132654,
588
+ "learning_rate": 1.4736054601700361e-05,
589
+ "loss": 0.6339,
590
+ "step": 410
591
+ },
592
+ {
593
+ "epoch": 0.41406834622100275,
594
+ "grad_norm": 0.5280260411948464,
595
+ "learning_rate": 1.4581795638533227e-05,
596
+ "loss": 0.6244,
597
+ "step": 415
598
+ },
599
+ {
600
+ "epoch": 0.41905712147667745,
601
+ "grad_norm": 0.49444720544930004,
602
+ "learning_rate": 1.4426144112255057e-05,
603
+ "loss": 0.6226,
604
+ "step": 420
605
+ },
606
+ {
607
+ "epoch": 0.4240458967323522,
608
+ "grad_norm": 0.5416758041687645,
609
+ "learning_rate": 1.426914733064444e-05,
610
+ "loss": 0.6281,
611
+ "step": 425
612
+ },
613
+ {
614
+ "epoch": 0.4290346719880269,
615
+ "grad_norm": 0.4913059879733367,
616
+ "learning_rate": 1.4110853010348717e-05,
617
+ "loss": 0.6327,
618
+ "step": 430
619
+ },
620
+ {
621
+ "epoch": 0.4340234472437017,
622
+ "grad_norm": 0.5475336882998988,
623
+ "learning_rate": 1.3951309262381231e-05,
624
+ "loss": 0.6319,
625
+ "step": 435
626
+ },
627
+ {
628
+ "epoch": 0.4390122224993764,
629
+ "grad_norm": 0.5887136176843448,
630
+ "learning_rate": 1.3790564577498791e-05,
631
+ "loss": 0.6323,
632
+ "step": 440
633
+ },
634
+ {
635
+ "epoch": 0.44400099775505114,
636
+ "grad_norm": 0.53325274747872,
637
+ "learning_rate": 1.3628667811463654e-05,
638
+ "loss": 0.6165,
639
+ "step": 445
640
+ },
641
+ {
642
+ "epoch": 0.44898977301072585,
643
+ "grad_norm": 0.5538441977213863,
644
+ "learning_rate": 1.3465668170194633e-05,
645
+ "loss": 0.6259,
646
+ "step": 450
647
+ },
648
+ {
649
+ "epoch": 0.4539785482664006,
650
+ "grad_norm": 0.516406002882252,
651
+ "learning_rate": 1.330161519481172e-05,
652
+ "loss": 0.6251,
653
+ "step": 455
654
+ },
655
+ {
656
+ "epoch": 0.4589673235220753,
657
+ "grad_norm": 0.5294430423934866,
658
+ "learning_rate": 1.3136558746578888e-05,
659
+ "loss": 0.6269,
660
+ "step": 460
661
+ },
662
+ {
663
+ "epoch": 0.46395609877775007,
664
+ "grad_norm": 0.5548195323966518,
665
+ "learning_rate": 1.2970548991749538e-05,
666
+ "loss": 0.6239,
667
+ "step": 465
668
+ },
669
+ {
670
+ "epoch": 0.4689448740334248,
671
+ "grad_norm": 0.48735736648704486,
672
+ "learning_rate": 1.2803636386319288e-05,
673
+ "loss": 0.62,
674
+ "step": 470
675
+ },
676
+ {
677
+ "epoch": 0.47393364928909953,
678
+ "grad_norm": 0.5093962136183301,
679
+ "learning_rate": 1.2635871660690677e-05,
680
+ "loss": 0.6259,
681
+ "step": 475
682
+ },
683
+ {
684
+ "epoch": 0.47892242454477424,
685
+ "grad_norm": 0.5220605413877938,
686
+ "learning_rate": 1.2467305804254472e-05,
687
+ "loss": 0.6233,
688
+ "step": 480
689
+ },
690
+ {
691
+ "epoch": 0.483911199800449,
692
+ "grad_norm": 0.46987756163402217,
693
+ "learning_rate": 1.2297990049892274e-05,
694
+ "loss": 0.6224,
695
+ "step": 485
696
+ },
697
+ {
698
+ "epoch": 0.4888999750561237,
699
+ "grad_norm": 0.4851271226507692,
700
+ "learning_rate": 1.2127975858405096e-05,
701
+ "loss": 0.6248,
702
+ "step": 490
703
+ },
704
+ {
705
+ "epoch": 0.49388875031179846,
706
+ "grad_norm": 0.49812035008570954,
707
+ "learning_rate": 1.1957314902872686e-05,
708
+ "loss": 0.6162,
709
+ "step": 495
710
+ },
711
+ {
712
+ "epoch": 0.49887752556747317,
713
+ "grad_norm": 0.4543789239256326,
714
+ "learning_rate": 1.178605905294832e-05,
715
+ "loss": 0.6191,
716
+ "step": 500
717
+ },
718
+ {
719
+ "epoch": 0.5038663008231479,
720
+ "grad_norm": 0.49450863626445246,
721
+ "learning_rate": 1.1614260359093869e-05,
722
+ "loss": 0.6298,
723
+ "step": 505
724
+ },
725
+ {
726
+ "epoch": 0.5088550760788226,
727
+ "grad_norm": 0.46204592956818197,
728
+ "learning_rate": 1.144197103675988e-05,
729
+ "loss": 0.6108,
730
+ "step": 510
731
+ },
732
+ {
733
+ "epoch": 0.5138438513344974,
734
+ "grad_norm": 0.46446807942496315,
735
+ "learning_rate": 1.1269243450515537e-05,
736
+ "loss": 0.6255,
737
+ "step": 515
738
+ },
739
+ {
740
+ "epoch": 0.5188326265901722,
741
+ "grad_norm": 0.4523344385336006,
742
+ "learning_rate": 1.1096130098133296e-05,
743
+ "loss": 0.621,
744
+ "step": 520
745
+ },
746
+ {
747
+ "epoch": 0.5238214018458468,
748
+ "grad_norm": 0.5281185337565003,
749
+ "learning_rate": 1.092268359463302e-05,
750
+ "loss": 0.6181,
751
+ "step": 525
752
+ },
753
+ {
754
+ "epoch": 0.5288101771015216,
755
+ "grad_norm": 0.5592357254092617,
756
+ "learning_rate": 1.0748956656290512e-05,
757
+ "loss": 0.625,
758
+ "step": 530
759
+ },
760
+ {
761
+ "epoch": 0.5337989523571963,
762
+ "grad_norm": 0.49985683194766767,
763
+ "learning_rate": 1.057500208461522e-05,
764
+ "loss": 0.6088,
765
+ "step": 535
766
+ },
767
+ {
768
+ "epoch": 0.5387877276128711,
769
+ "grad_norm": 0.5348402703139689,
770
+ "learning_rate": 1.0400872750302095e-05,
771
+ "loss": 0.6215,
772
+ "step": 540
773
+ },
774
+ {
775
+ "epoch": 0.5437765028685457,
776
+ "grad_norm": 0.5016453093230498,
777
+ "learning_rate": 1.0226621577162377e-05,
778
+ "loss": 0.6067,
779
+ "step": 545
780
+ },
781
+ {
782
+ "epoch": 0.5487652781242205,
783
+ "grad_norm": 0.5033968932851582,
784
+ "learning_rate": 1.005230152603826e-05,
785
+ "loss": 0.6056,
786
+ "step": 550
787
+ },
788
+ {
789
+ "epoch": 0.5537540533798953,
790
+ "grad_norm": 0.4779633495557308,
791
+ "learning_rate": 9.877965578706286e-06,
792
+ "loss": 0.6158,
793
+ "step": 555
794
+ },
795
+ {
796
+ "epoch": 0.55874282863557,
797
+ "grad_norm": 0.507768651916945,
798
+ "learning_rate": 9.703666721774403e-06,
799
+ "loss": 0.6168,
800
+ "step": 560
801
+ },
802
+ {
803
+ "epoch": 0.5637316038912447,
804
+ "grad_norm": 0.4975220405187006,
805
+ "learning_rate": 9.52945793057753e-06,
806
+ "loss": 0.6133,
807
+ "step": 565
808
+ },
809
+ {
810
+ "epoch": 0.5687203791469194,
811
+ "grad_norm": 0.567581970238524,
812
+ "learning_rate": 9.355392153076541e-06,
813
+ "loss": 0.6153,
814
+ "step": 570
815
+ },
816
+ {
817
+ "epoch": 0.5737091544025942,
818
+ "grad_norm": 0.45994820207954157,
819
+ "learning_rate": 9.18152229376561e-06,
820
+ "loss": 0.6075,
821
+ "step": 575
822
+ },
823
+ {
824
+ "epoch": 0.5786979296582689,
825
+ "grad_norm": 0.4776147923803636,
826
+ "learning_rate": 9.007901197592722e-06,
827
+ "loss": 0.6083,
828
+ "step": 580
829
+ },
830
+ {
831
+ "epoch": 0.5836867049139436,
832
+ "grad_norm": 0.4458298111691603,
833
+ "learning_rate": 8.834581633898307e-06,
834
+ "loss": 0.6151,
835
+ "step": 585
836
+ },
837
+ {
838
+ "epoch": 0.5886754801696183,
839
+ "grad_norm": 0.5015975267018272,
840
+ "learning_rate": 8.661616280376846e-06,
841
+ "loss": 0.6083,
842
+ "step": 590
843
+ },
844
+ {
845
+ "epoch": 0.5936642554252931,
846
+ "grad_norm": 0.44736317209890847,
847
+ "learning_rate": 8.489057707066335e-06,
848
+ "loss": 0.6077,
849
+ "step": 595
850
+ },
851
+ {
852
+ "epoch": 0.5986530306809679,
853
+ "grad_norm": 0.4542312795928054,
854
+ "learning_rate": 8.316958360370462e-06,
855
+ "loss": 0.6089,
856
+ "step": 600
857
+ },
858
+ {
859
+ "epoch": 0.6036418059366425,
860
+ "grad_norm": 0.4669024055915673,
861
+ "learning_rate": 8.145370547118374e-06,
862
+ "loss": 0.614,
863
+ "step": 605
864
+ },
865
+ {
866
+ "epoch": 0.6086305811923173,
867
+ "grad_norm": 0.460625150490194,
868
+ "learning_rate": 7.974346418666854e-06,
869
+ "loss": 0.6097,
870
+ "step": 610
871
+ },
872
+ {
873
+ "epoch": 0.613619356447992,
874
+ "grad_norm": 0.45169077334743357,
875
+ "learning_rate": 7.803937955049743e-06,
876
+ "loss": 0.6134,
877
+ "step": 615
878
+ },
879
+ {
880
+ "epoch": 0.6186081317036668,
881
+ "grad_norm": 0.5045442729073779,
882
+ "learning_rate": 7.634196949179472e-06,
883
+ "loss": 0.6056,
884
+ "step": 620
885
+ },
886
+ {
887
+ "epoch": 0.6235969069593414,
888
+ "grad_norm": 0.4976507270581154,
889
+ "learning_rate": 7.465174991105405e-06,
890
+ "loss": 0.6087,
891
+ "step": 625
892
+ },
893
+ {
894
+ "epoch": 0.6285856822150162,
895
+ "grad_norm": 0.47413589578954074,
896
+ "learning_rate": 7.296923452333908e-06,
897
+ "loss": 0.6073,
898
+ "step": 630
899
+ },
900
+ {
901
+ "epoch": 0.633574457470691,
902
+ "grad_norm": 0.4468358705510705,
903
+ "learning_rate": 7.129493470214775e-06,
904
+ "loss": 0.6065,
905
+ "step": 635
906
+ },
907
+ {
908
+ "epoch": 0.6385632327263657,
909
+ "grad_norm": 0.44813379558060285,
910
+ "learning_rate": 6.962935932398862e-06,
911
+ "loss": 0.5989,
912
+ "step": 640
913
+ },
914
+ {
915
+ "epoch": 0.6435520079820404,
916
+ "grad_norm": 0.4267618712107622,
917
+ "learning_rate": 6.797301461371626e-06,
918
+ "loss": 0.5981,
919
+ "step": 645
920
+ },
921
+ {
922
+ "epoch": 0.6485407832377151,
923
+ "grad_norm": 0.44491038507852154,
924
+ "learning_rate": 6.632640399067197e-06,
925
+ "loss": 0.602,
926
+ "step": 650
927
+ },
928
+ {
929
+ "epoch": 0.6535295584933899,
930
+ "grad_norm": 0.455548462410925,
931
+ "learning_rate": 6.469002791567792e-06,
932
+ "loss": 0.6077,
933
+ "step": 655
934
+ },
935
+ {
936
+ "epoch": 0.6585183337490647,
937
+ "grad_norm": 0.4655649758885719,
938
+ "learning_rate": 6.306438373892985e-06,
939
+ "loss": 0.6027,
940
+ "step": 660
941
+ },
942
+ {
943
+ "epoch": 0.6635071090047393,
944
+ "grad_norm": 0.4603705069002276,
945
+ "learning_rate": 6.144996554883556e-06,
946
+ "loss": 0.6072,
947
+ "step": 665
948
+ },
949
+ {
950
+ "epoch": 0.6684958842604141,
951
+ "grad_norm": 0.42809636369496656,
952
+ "learning_rate": 5.98472640218449e-06,
953
+ "loss": 0.5984,
954
+ "step": 670
955
+ },
956
+ {
957
+ "epoch": 0.6734846595160888,
958
+ "grad_norm": 0.4311787554066561,
959
+ "learning_rate": 5.825676627331614e-06,
960
+ "loss": 0.5997,
961
+ "step": 675
962
+ },
963
+ {
964
+ "epoch": 0.6784734347717636,
965
+ "grad_norm": 0.45825795981326356,
966
+ "learning_rate": 5.667895570946554e-06,
967
+ "loss": 0.6034,
968
+ "step": 680
969
+ },
970
+ {
971
+ "epoch": 0.6834622100274382,
972
+ "grad_norm": 0.4167893564717864,
973
+ "learning_rate": 5.5114311880443374e-06,
974
+ "loss": 0.5975,
975
+ "step": 685
976
+ },
977
+ {
978
+ "epoch": 0.688450985283113,
979
+ "grad_norm": 0.46394354368013807,
980
+ "learning_rate": 5.356331033458276e-06,
981
+ "loss": 0.6065,
982
+ "step": 690
983
+ },
984
+ {
985
+ "epoch": 0.6934397605387878,
986
+ "grad_norm": 0.45003494825662715,
987
+ "learning_rate": 5.202642247386409e-06,
988
+ "loss": 0.6052,
989
+ "step": 695
990
+ },
991
+ {
992
+ "epoch": 0.6984285357944625,
993
+ "grad_norm": 0.40702863232292363,
994
+ "learning_rate": 5.0504115410640105e-06,
995
+ "loss": 0.5985,
996
+ "step": 700
997
+ },
998
+ {
999
+ "epoch": 0.7034173110501372,
1000
+ "grad_norm": 0.42165174105900677,
1001
+ "learning_rate": 4.899685182566472e-06,
1002
+ "loss": 0.5917,
1003
+ "step": 705
1004
+ },
1005
+ {
1006
+ "epoch": 0.7084060863058119,
1007
+ "grad_norm": 0.5050037064515478,
1008
+ "learning_rate": 4.7505089827468335e-06,
1009
+ "loss": 0.5959,
1010
+ "step": 710
1011
+ },
1012
+ {
1013
+ "epoch": 0.7133948615614867,
1014
+ "grad_norm": 0.4558754163109762,
1015
+ "learning_rate": 4.602928281312351e-06,
1016
+ "loss": 0.5933,
1017
+ "step": 715
1018
+ },
1019
+ {
1020
+ "epoch": 0.7183836368171614,
1021
+ "grad_norm": 0.4071864016802162,
1022
+ "learning_rate": 4.456987933044185e-06,
1023
+ "loss": 0.5992,
1024
+ "step": 720
1025
+ },
1026
+ {
1027
+ "epoch": 0.7233724120728361,
1028
+ "grad_norm": 0.4248472014437075,
1029
+ "learning_rate": 4.3127322941645385e-06,
1030
+ "loss": 0.5937,
1031
+ "step": 725
1032
+ },
1033
+ {
1034
+ "epoch": 0.7283611873285109,
1035
+ "grad_norm": 0.40980252115955373,
1036
+ "learning_rate": 4.170205208855281e-06,
1037
+ "loss": 0.5968,
1038
+ "step": 730
1039
+ },
1040
+ {
1041
+ "epoch": 0.7333499625841856,
1042
+ "grad_norm": 0.4052569143394039,
1043
+ "learning_rate": 4.029449995932213e-06,
1044
+ "loss": 0.5926,
1045
+ "step": 735
1046
+ },
1047
+ {
1048
+ "epoch": 0.7383387378398603,
1049
+ "grad_norm": 0.41360853365570666,
1050
+ "learning_rate": 3.890509435679026e-06,
1051
+ "loss": 0.6021,
1052
+ "step": 740
1053
+ },
1054
+ {
1055
+ "epoch": 0.743327513095535,
1056
+ "grad_norm": 0.41835345554744635,
1057
+ "learning_rate": 3.7534257568448995e-06,
1058
+ "loss": 0.5952,
1059
+ "step": 745
1060
+ },
1061
+ {
1062
+ "epoch": 0.7483162883512098,
1063
+ "grad_norm": 0.401256370852048,
1064
+ "learning_rate": 3.6182406238097745e-06,
1065
+ "loss": 0.5972,
1066
+ "step": 750
1067
+ },
1068
+ {
1069
+ "epoch": 0.7533050636068845,
1070
+ "grad_norm": 0.4174244244132666,
1071
+ "learning_rate": 3.484995123921112e-06,
1072
+ "loss": 0.5945,
1073
+ "step": 755
1074
+ },
1075
+ {
1076
+ "epoch": 0.7582938388625592,
1077
+ "grad_norm": 0.4081805968439954,
1078
+ "learning_rate": 3.353729755006081e-06,
1079
+ "loss": 0.5952,
1080
+ "step": 760
1081
+ },
1082
+ {
1083
+ "epoch": 0.763282614118234,
1084
+ "grad_norm": 0.40126195224404465,
1085
+ "learning_rate": 3.2244844130628684e-06,
1086
+ "loss": 0.5869,
1087
+ "step": 765
1088
+ },
1089
+ {
1090
+ "epoch": 0.7682713893739087,
1091
+ "grad_norm": 0.4252743360297237,
1092
+ "learning_rate": 3.0972983801349464e-06,
1093
+ "loss": 0.6057,
1094
+ "step": 770
1095
+ },
1096
+ {
1097
+ "epoch": 0.7732601646295835,
1098
+ "grad_norm": 0.40849879013758245,
1099
+ "learning_rate": 2.9722103123719324e-06,
1100
+ "loss": 0.5987,
1101
+ "step": 775
1102
+ },
1103
+ {
1104
+ "epoch": 0.7782489398852581,
1105
+ "grad_norm": 0.4124888296503082,
1106
+ "learning_rate": 2.849258228280656e-06,
1107
+ "loss": 0.6048,
1108
+ "step": 780
1109
+ },
1110
+ {
1111
+ "epoch": 0.7832377151409329,
1112
+ "grad_norm": 0.408929858016356,
1113
+ "learning_rate": 2.728479497170066e-06,
1114
+ "loss": 0.591,
1115
+ "step": 785
1116
+ },
1117
+ {
1118
+ "epoch": 0.7882264903966076,
1119
+ "grad_norm": 0.40717905524554926,
1120
+ "learning_rate": 2.6099108277934105e-06,
1121
+ "loss": 0.5957,
1122
+ "step": 790
1123
+ },
1124
+ {
1125
+ "epoch": 0.7932152656522824,
1126
+ "grad_norm": 0.40906715914325326,
1127
+ "learning_rate": 2.4935882571912107e-06,
1128
+ "loss": 0.585,
1129
+ "step": 795
1130
+ },
1131
+ {
1132
+ "epoch": 0.798204040907957,
1133
+ "grad_norm": 0.39973439105002123,
1134
+ "learning_rate": 2.379547139738392e-06,
1135
+ "loss": 0.5881,
1136
+ "step": 800
1137
+ },
1138
+ {
1139
+ "epoch": 0.8031928161636318,
1140
+ "grad_norm": 0.39566194107090014,
1141
+ "learning_rate": 2.267822136398864e-06,
1142
+ "loss": 0.5948,
1143
+ "step": 805
1144
+ },
1145
+ {
1146
+ "epoch": 0.8081815914193066,
1147
+ "grad_norm": 0.3943529028329431,
1148
+ "learning_rate": 2.15844720419091e-06,
1149
+ "loss": 0.5928,
1150
+ "step": 810
1151
+ },
1152
+ {
1153
+ "epoch": 0.8131703666749813,
1154
+ "grad_norm": 0.396743086451483,
1155
+ "learning_rate": 2.0514555858664663e-06,
1156
+ "loss": 0.5955,
1157
+ "step": 815
1158
+ },
1159
+ {
1160
+ "epoch": 0.818159141930656,
1161
+ "grad_norm": 0.4158031464312053,
1162
+ "learning_rate": 1.9468797998075494e-06,
1163
+ "loss": 0.5938,
1164
+ "step": 820
1165
+ },
1166
+ {
1167
+ "epoch": 0.8231479171863307,
1168
+ "grad_norm": 0.4159354667890639,
1169
+ "learning_rate": 1.844751630142797e-06,
1170
+ "loss": 0.5811,
1171
+ "step": 825
1172
+ },
1173
+ {
1174
+ "epoch": 0.8281366924420055,
1175
+ "grad_norm": 0.38601272105412726,
1176
+ "learning_rate": 1.7451021170871974e-06,
1177
+ "loss": 0.5933,
1178
+ "step": 830
1179
+ },
1180
+ {
1181
+ "epoch": 0.8331254676976803,
1182
+ "grad_norm": 0.3986644463931031,
1183
+ "learning_rate": 1.6479615475079291e-06,
1184
+ "loss": 0.5892,
1185
+ "step": 835
1186
+ },
1187
+ {
1188
+ "epoch": 0.8381142429533549,
1189
+ "grad_norm": 0.40080909281458676,
1190
+ "learning_rate": 1.5533594457191326e-06,
1191
+ "loss": 0.5898,
1192
+ "step": 840
1193
+ },
1194
+ {
1195
+ "epoch": 0.8431030182090297,
1196
+ "grad_norm": 0.3942697489480343,
1197
+ "learning_rate": 1.4613245645084894e-06,
1198
+ "loss": 0.5863,
1199
+ "step": 845
1200
+ },
1201
+ {
1202
+ "epoch": 0.8480917934647044,
1203
+ "grad_norm": 0.39162896724772583,
1204
+ "learning_rate": 1.3718848763982596e-06,
1205
+ "loss": 0.5963,
1206
+ "step": 850
1207
+ },
1208
+ {
1209
+ "epoch": 0.8530805687203792,
1210
+ "grad_norm": 0.38744891578031804,
1211
+ "learning_rate": 1.2850675651434962e-06,
1212
+ "loss": 0.5931,
1213
+ "step": 855
1214
+ },
1215
+ {
1216
+ "epoch": 0.8580693439760538,
1217
+ "grad_norm": 0.3757895616733075,
1218
+ "learning_rate": 1.2008990174699685e-06,
1219
+ "loss": 0.5958,
1220
+ "step": 860
1221
+ },
1222
+ {
1223
+ "epoch": 0.8630581192317286,
1224
+ "grad_norm": 0.38105622554372953,
1225
+ "learning_rate": 1.1194048150543457e-06,
1226
+ "loss": 0.5928,
1227
+ "step": 865
1228
+ },
1229
+ {
1230
+ "epoch": 0.8680468944874034,
1231
+ "grad_norm": 0.38949843229532266,
1232
+ "learning_rate": 1.0406097267490644e-06,
1233
+ "loss": 0.5894,
1234
+ "step": 870
1235
+ },
1236
+ {
1237
+ "epoch": 0.8730356697430781,
1238
+ "grad_norm": 0.39133896634308507,
1239
+ "learning_rate": 9.645377010542212e-07,
1240
+ "loss": 0.5893,
1241
+ "step": 875
1242
+ },
1243
+ {
1244
+ "epoch": 0.8780244449987528,
1245
+ "grad_norm": 0.4015625907458179,
1246
+ "learning_rate": 8.91211858838823e-07,
1247
+ "loss": 0.5982,
1248
+ "step": 880
1249
+ },
1250
+ {
1251
+ "epoch": 0.8830132202544275,
1252
+ "grad_norm": 0.4047912248494648,
1253
+ "learning_rate": 8.206544863135612e-07,
1254
+ "loss": 0.5865,
1255
+ "step": 885
1256
+ },
1257
+ {
1258
+ "epoch": 0.8880019955101023,
1259
+ "grad_norm": 0.38503511137561774,
1260
+ "learning_rate": 7.528870282572864e-07,
1261
+ "loss": 0.5831,
1262
+ "step": 890
1263
+ },
1264
+ {
1265
+ "epoch": 0.892990770765777,
1266
+ "grad_norm": 0.387759644652555,
1267
+ "learning_rate": 6.879300814992007e-07,
1268
+ "loss": 0.5985,
1269
+ "step": 895
1270
+ },
1271
+ {
1272
+ "epoch": 0.8979795460214517,
1273
+ "grad_norm": 0.39050325202063846,
1274
+ "learning_rate": 6.258033886587911e-07,
1275
+ "loss": 0.5881,
1276
+ "step": 900
1277
+ },
1278
+ {
1279
+ "epoch": 0.9029683212771265,
1280
+ "grad_norm": 0.3870890888051975,
1281
+ "learning_rate": 5.66525832145377e-07,
1282
+ "loss": 0.5945,
1283
+ "step": 905
1284
+ },
1285
+ {
1286
+ "epoch": 0.9079570965328012,
1287
+ "grad_norm": 0.3856245616892951,
1288
+ "learning_rate": 5.101154284191035e-07,
1289
+ "loss": 0.5929,
1290
+ "step": 910
1291
+ },
1292
+ {
1293
+ "epoch": 0.912945871788476,
1294
+ "grad_norm": 0.3910109970295147,
1295
+ "learning_rate": 4.5658932251512856e-07,
1296
+ "loss": 0.6021,
1297
+ "step": 915
1298
+ },
1299
+ {
1300
+ "epoch": 0.9179346470441506,
1301
+ "grad_norm": 0.3676846272782438,
1302
+ "learning_rate": 4.059637828326657e-07,
1303
+ "loss": 0.5878,
1304
+ "step": 920
1305
+ },
1306
+ {
1307
+ "epoch": 0.9229234222998254,
1308
+ "grad_norm": 0.3819934536854667,
1309
+ "learning_rate": 3.5825419619046176e-07,
1310
+ "loss": 0.5936,
1311
+ "step": 925
1312
+ },
1313
+ {
1314
+ "epoch": 0.9279121975555001,
1315
+ "grad_norm": 0.3875995828243716,
1316
+ "learning_rate": 3.1347506315023036e-07,
1317
+ "loss": 0.6038,
1318
+ "step": 930
1319
+ },
1320
+ {
1321
+ "epoch": 0.9329009728111749,
1322
+ "grad_norm": 0.38002441832217876,
1323
+ "learning_rate": 2.716399936094294e-07,
1324
+ "loss": 0.5931,
1325
+ "step": 935
1326
+ },
1327
+ {
1328
+ "epoch": 0.9378897480668495,
1329
+ "grad_norm": 0.3848197669462124,
1330
+ "learning_rate": 2.327617026647533e-07,
1331
+ "loss": 0.595,
1332
+ "step": 940
1333
+ },
1334
+ {
1335
+ "epoch": 0.9428785233225243,
1336
+ "grad_norm": 0.38930339170989675,
1337
+ "learning_rate": 1.968520067475921e-07,
1338
+ "loss": 0.5938,
1339
+ "step": 945
1340
+ },
1341
+ {
1342
+ "epoch": 0.9478672985781991,
1343
+ "grad_norm": 0.3797874082101493,
1344
+ "learning_rate": 1.6392182003260427e-07,
1345
+ "loss": 0.5942,
1346
+ "step": 950
1347
+ },
1348
+ {
1349
+ "epoch": 0.9528560738338738,
1350
+ "grad_norm": 0.3803276424025686,
1351
+ "learning_rate": 1.3398115112054243e-07,
1352
+ "loss": 0.5876,
1353
+ "step": 955
1354
+ },
1355
+ {
1356
+ "epoch": 0.9578448490895485,
1357
+ "grad_norm": 0.3765573493263119,
1358
+ "learning_rate": 1.070390999962867e-07,
1359
+ "loss": 0.5922,
1360
+ "step": 960
1361
+ },
1362
+ {
1363
+ "epoch": 0.9628336243452232,
1364
+ "grad_norm": 0.3849948624629748,
1365
+ "learning_rate": 8.31038552630603e-08,
1366
+ "loss": 0.5945,
1367
+ "step": 965
1368
+ },
1369
+ {
1370
+ "epoch": 0.967822399600898,
1371
+ "grad_norm": 0.38879243314742995,
1372
+ "learning_rate": 6.218269165363166e-08,
1373
+ "loss": 0.5954,
1374
+ "step": 970
1375
+ },
1376
+ {
1377
+ "epoch": 0.9728111748565728,
1378
+ "grad_norm": 0.38003968946404176,
1379
+ "learning_rate": 4.42819678192774e-08,
1380
+ "loss": 0.5913,
1381
+ "step": 975
1382
+ },
1383
+ {
1384
+ "epoch": 0.9777999501122474,
1385
+ "grad_norm": 0.3869545513042188,
1386
+ "learning_rate": 2.9407124397169418e-08,
1387
+ "loss": 0.594,
1388
+ "step": 980
1389
+ },
1390
+ {
1391
+ "epoch": 0.9827887253679222,
1392
+ "grad_norm": 0.3851047915663657,
1393
+ "learning_rate": 1.7562682356786488e-08,
1394
+ "loss": 0.5925,
1395
+ "step": 985
1396
+ },
1397
+ {
1398
+ "epoch": 0.9877775006235969,
1399
+ "grad_norm": 0.38621262692876246,
1400
+ "learning_rate": 8.752241625831215e-09,
1401
+ "loss": 0.6004,
1402
+ "step": 990
1403
+ },
1404
+ {
1405
+ "epoch": 0.9927662758792717,
1406
+ "grad_norm": 0.3798867531020366,
1407
+ "learning_rate": 2.978479996098571e-09,
1408
+ "loss": 0.5909,
1409
+ "step": 995
1410
+ },
1411
+ {
1412
+ "epoch": 0.9977550511349463,
1413
+ "grad_norm": 0.38274768291794226,
1414
+ "learning_rate": 2.4315230959359726e-10,
1415
+ "loss": 0.5939,
1416
+ "step": 1000
1417
+ },
1418
+ {
1419
+ "epoch": 0.9997505612372163,
1420
+ "eval_loss": 0.5914663672447205,
1421
+ "eval_runtime": 139.1149,
1422
+ "eval_samples_per_second": 48.528,
1423
+ "eval_steps_per_second": 1.517,
1424
+ "step": 1002
1425
+ },
1426
+ {
1427
+ "epoch": 0.9997505612372163,
1428
+ "step": 1002,
1429
+ "total_flos": 838984280309760.0,
1430
+ "train_loss": 0.6422406448099666,
1431
+ "train_runtime": 10627.6191,
1432
+ "train_samples_per_second": 12.071,
1433
+ "train_steps_per_second": 0.094
1434
+ }
1435
+ ],
1436
+ "logging_steps": 5,
1437
+ "max_steps": 1002,
1438
+ "num_input_tokens_seen": 0,
1439
+ "num_train_epochs": 1,
1440
+ "save_steps": 500,
1441
+ "stateful_callbacks": {
1442
+ "TrainerControl": {
1443
+ "args": {
1444
+ "should_epoch_stop": false,
1445
+ "should_evaluate": false,
1446
+ "should_log": false,
1447
+ "should_save": false,
1448
+ "should_training_stop": false
1449
+ },
1450
+ "attributes": {}
1451
+ }
1452
+ },
1453
+ "total_flos": 838984280309760.0,
1454
+ "train_batch_size": 4,
1455
+ "trial_name": null,
1456
+ "trial_params": null
1457
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:393dfdf52d36044ffb8135d03929ff5060d24281420df6c028a93b84ddf97039
3
+ size 7096