BoburAmirov
commited on
Commit
•
9f0f12c
1
Parent(s):
507f66d
upload model
Browse files- README.md +202 -0
- adapter_config.json +29 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +48 -0
- trainer_state.json +2343 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: NousResearch/Llama-2-7b-chat-hf
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.11.1
|
adapter_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "NousResearch/Llama-2-7b-chat-hf",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 16,
|
14 |
+
"lora_dropout": 0.1,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 64,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"v_proj"
|
25 |
+
],
|
26 |
+
"task_type": "CAUSAL_LM",
|
27 |
+
"use_dora": false,
|
28 |
+
"use_rslora": false
|
29 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9edabf78265a73047112e538330e8aed34efc6dfbccc79cbae028a3e4d810633
|
3 |
+
size 134235048
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<pad>": 32000
|
3 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cbfcfd1dc6ea07b5fc22accb2456b490bb4a922d89a6214fbbfc09ed614688b4
|
3 |
+
size 268515002
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e29ccbc9c8625a33220ed543bb5e48fe335096cfdec234f7ceccc2c1a452da0
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2ef9b5765263cd51042a755ae529d23e5d6fd529baa4b159cb9626532b6340d
|
3 |
+
size 1064
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": true,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"32000": {
|
30 |
+
"content": "<pad>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": true,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": false
|
36 |
+
}
|
37 |
+
},
|
38 |
+
"bos_token": "<s>",
|
39 |
+
"clean_up_tokenization_spaces": false,
|
40 |
+
"eos_token": "</s>",
|
41 |
+
"legacy": false,
|
42 |
+
"model_max_length": 1000000000000000019884624838656,
|
43 |
+
"pad_token": "</s>",
|
44 |
+
"sp_model_kwargs": {},
|
45 |
+
"tokenizer_class": "LlamaTokenizer",
|
46 |
+
"unk_token": "<unk>",
|
47 |
+
"use_default_system_prompt": false
|
48 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,2343 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 13.2,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 33000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.04,
|
13 |
+
"grad_norm": 1.1794846057891846,
|
14 |
+
"learning_rate": 0.0002,
|
15 |
+
"loss": 2.9634,
|
16 |
+
"step": 100
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.08,
|
20 |
+
"grad_norm": 0.9956796169281006,
|
21 |
+
"learning_rate": 0.0002,
|
22 |
+
"loss": 2.5897,
|
23 |
+
"step": 200
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.12,
|
27 |
+
"grad_norm": 0.7088788747787476,
|
28 |
+
"learning_rate": 0.0002,
|
29 |
+
"loss": 2.3967,
|
30 |
+
"step": 300
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.16,
|
34 |
+
"grad_norm": 0.8429712057113647,
|
35 |
+
"learning_rate": 0.0002,
|
36 |
+
"loss": 2.403,
|
37 |
+
"step": 400
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.2,
|
41 |
+
"grad_norm": 0.7503288388252258,
|
42 |
+
"learning_rate": 0.0002,
|
43 |
+
"loss": 2.3169,
|
44 |
+
"step": 500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.24,
|
48 |
+
"grad_norm": 0.6073698401451111,
|
49 |
+
"learning_rate": 0.0002,
|
50 |
+
"loss": 2.2718,
|
51 |
+
"step": 600
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.28,
|
55 |
+
"grad_norm": 0.6131550073623657,
|
56 |
+
"learning_rate": 0.0002,
|
57 |
+
"loss": 2.1968,
|
58 |
+
"step": 700
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.32,
|
62 |
+
"grad_norm": 1.0864523649215698,
|
63 |
+
"learning_rate": 0.0002,
|
64 |
+
"loss": 2.2322,
|
65 |
+
"step": 800
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.36,
|
69 |
+
"grad_norm": 0.7630054950714111,
|
70 |
+
"learning_rate": 0.0002,
|
71 |
+
"loss": 2.2196,
|
72 |
+
"step": 900
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.4,
|
76 |
+
"grad_norm": 0.8388053178787231,
|
77 |
+
"learning_rate": 0.0002,
|
78 |
+
"loss": 2.2967,
|
79 |
+
"step": 1000
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.44,
|
83 |
+
"grad_norm": 0.7474327087402344,
|
84 |
+
"learning_rate": 0.0002,
|
85 |
+
"loss": 2.222,
|
86 |
+
"step": 1100
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.48,
|
90 |
+
"grad_norm": 0.7345255613327026,
|
91 |
+
"learning_rate": 0.0002,
|
92 |
+
"loss": 2.0606,
|
93 |
+
"step": 1200
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.52,
|
97 |
+
"grad_norm": 0.5666030049324036,
|
98 |
+
"learning_rate": 0.0002,
|
99 |
+
"loss": 2.1423,
|
100 |
+
"step": 1300
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.56,
|
104 |
+
"grad_norm": 0.7595005631446838,
|
105 |
+
"learning_rate": 0.0002,
|
106 |
+
"loss": 2.1629,
|
107 |
+
"step": 1400
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.6,
|
111 |
+
"grad_norm": 0.5787087678909302,
|
112 |
+
"learning_rate": 0.0002,
|
113 |
+
"loss": 2.1169,
|
114 |
+
"step": 1500
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.64,
|
118 |
+
"grad_norm": 0.9300134778022766,
|
119 |
+
"learning_rate": 0.0002,
|
120 |
+
"loss": 2.0647,
|
121 |
+
"step": 1600
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.68,
|
125 |
+
"grad_norm": 0.6892948746681213,
|
126 |
+
"learning_rate": 0.0002,
|
127 |
+
"loss": 2.0773,
|
128 |
+
"step": 1700
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.72,
|
132 |
+
"grad_norm": 0.5084001421928406,
|
133 |
+
"learning_rate": 0.0002,
|
134 |
+
"loss": 2.1002,
|
135 |
+
"step": 1800
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.76,
|
139 |
+
"grad_norm": 0.470070481300354,
|
140 |
+
"learning_rate": 0.0002,
|
141 |
+
"loss": 2.0381,
|
142 |
+
"step": 1900
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.8,
|
146 |
+
"grad_norm": 0.6220455169677734,
|
147 |
+
"learning_rate": 0.0002,
|
148 |
+
"loss": 2.0517,
|
149 |
+
"step": 2000
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.84,
|
153 |
+
"grad_norm": 0.8656258583068848,
|
154 |
+
"learning_rate": 0.0002,
|
155 |
+
"loss": 1.9672,
|
156 |
+
"step": 2100
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.88,
|
160 |
+
"grad_norm": 0.7517567873001099,
|
161 |
+
"learning_rate": 0.0002,
|
162 |
+
"loss": 2.0848,
|
163 |
+
"step": 2200
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.92,
|
167 |
+
"grad_norm": 0.7987684011459351,
|
168 |
+
"learning_rate": 0.0002,
|
169 |
+
"loss": 2.0362,
|
170 |
+
"step": 2300
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.96,
|
174 |
+
"grad_norm": 0.6208759546279907,
|
175 |
+
"learning_rate": 0.0002,
|
176 |
+
"loss": 2.0221,
|
177 |
+
"step": 2400
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 1.0,
|
181 |
+
"grad_norm": 0.5592771768569946,
|
182 |
+
"learning_rate": 0.0002,
|
183 |
+
"loss": 1.9436,
|
184 |
+
"step": 2500
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 1.04,
|
188 |
+
"grad_norm": 0.8733409643173218,
|
189 |
+
"learning_rate": 0.0002,
|
190 |
+
"loss": 1.9028,
|
191 |
+
"step": 2600
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 1.08,
|
195 |
+
"grad_norm": 0.6601306200027466,
|
196 |
+
"learning_rate": 0.0002,
|
197 |
+
"loss": 1.9403,
|
198 |
+
"step": 2700
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 1.12,
|
202 |
+
"grad_norm": 0.7789013385772705,
|
203 |
+
"learning_rate": 0.0002,
|
204 |
+
"loss": 1.8257,
|
205 |
+
"step": 2800
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 1.16,
|
209 |
+
"grad_norm": 0.5855867862701416,
|
210 |
+
"learning_rate": 0.0002,
|
211 |
+
"loss": 1.9351,
|
212 |
+
"step": 2900
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 1.2,
|
216 |
+
"grad_norm": 0.5030935406684875,
|
217 |
+
"learning_rate": 0.0002,
|
218 |
+
"loss": 1.9253,
|
219 |
+
"step": 3000
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 1.24,
|
223 |
+
"grad_norm": 0.6684442758560181,
|
224 |
+
"learning_rate": 0.0002,
|
225 |
+
"loss": 1.9153,
|
226 |
+
"step": 3100
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 1.28,
|
230 |
+
"grad_norm": 0.6724442839622498,
|
231 |
+
"learning_rate": 0.0002,
|
232 |
+
"loss": 1.8726,
|
233 |
+
"step": 3200
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 1.32,
|
237 |
+
"grad_norm": 0.48911118507385254,
|
238 |
+
"learning_rate": 0.0002,
|
239 |
+
"loss": 1.9423,
|
240 |
+
"step": 3300
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 1.3599999999999999,
|
244 |
+
"grad_norm": 0.7769139409065247,
|
245 |
+
"learning_rate": 0.0002,
|
246 |
+
"loss": 1.7886,
|
247 |
+
"step": 3400
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 1.4,
|
251 |
+
"grad_norm": 0.639460027217865,
|
252 |
+
"learning_rate": 0.0002,
|
253 |
+
"loss": 1.9118,
|
254 |
+
"step": 3500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 1.44,
|
258 |
+
"grad_norm": 0.5745570659637451,
|
259 |
+
"learning_rate": 0.0002,
|
260 |
+
"loss": 1.8423,
|
261 |
+
"step": 3600
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 1.48,
|
265 |
+
"grad_norm": 0.6319829225540161,
|
266 |
+
"learning_rate": 0.0002,
|
267 |
+
"loss": 1.8893,
|
268 |
+
"step": 3700
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 1.52,
|
272 |
+
"grad_norm": 0.5839726328849792,
|
273 |
+
"learning_rate": 0.0002,
|
274 |
+
"loss": 1.8506,
|
275 |
+
"step": 3800
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 1.56,
|
279 |
+
"grad_norm": 0.7453562617301941,
|
280 |
+
"learning_rate": 0.0002,
|
281 |
+
"loss": 1.8698,
|
282 |
+
"step": 3900
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 1.6,
|
286 |
+
"grad_norm": 0.7091575264930725,
|
287 |
+
"learning_rate": 0.0002,
|
288 |
+
"loss": 1.8367,
|
289 |
+
"step": 4000
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 1.6400000000000001,
|
293 |
+
"grad_norm": 0.722655177116394,
|
294 |
+
"learning_rate": 0.0002,
|
295 |
+
"loss": 1.8939,
|
296 |
+
"step": 4100
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 1.6800000000000002,
|
300 |
+
"grad_norm": 0.566392183303833,
|
301 |
+
"learning_rate": 0.0002,
|
302 |
+
"loss": 1.7557,
|
303 |
+
"step": 4200
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 1.72,
|
307 |
+
"grad_norm": 0.564018189907074,
|
308 |
+
"learning_rate": 0.0002,
|
309 |
+
"loss": 1.72,
|
310 |
+
"step": 4300
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 1.76,
|
314 |
+
"grad_norm": 0.7120116949081421,
|
315 |
+
"learning_rate": 0.0002,
|
316 |
+
"loss": 1.7436,
|
317 |
+
"step": 4400
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 1.8,
|
321 |
+
"grad_norm": 0.7515490651130676,
|
322 |
+
"learning_rate": 0.0002,
|
323 |
+
"loss": 1.83,
|
324 |
+
"step": 4500
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 1.8399999999999999,
|
328 |
+
"grad_norm": 0.6733573079109192,
|
329 |
+
"learning_rate": 0.0002,
|
330 |
+
"loss": 1.8012,
|
331 |
+
"step": 4600
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 1.88,
|
335 |
+
"grad_norm": 1.0119801759719849,
|
336 |
+
"learning_rate": 0.0002,
|
337 |
+
"loss": 1.8833,
|
338 |
+
"step": 4700
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 1.92,
|
342 |
+
"grad_norm": 0.73843914270401,
|
343 |
+
"learning_rate": 0.0002,
|
344 |
+
"loss": 1.8012,
|
345 |
+
"step": 4800
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 1.96,
|
349 |
+
"grad_norm": 0.5831142067909241,
|
350 |
+
"learning_rate": 0.0002,
|
351 |
+
"loss": 1.768,
|
352 |
+
"step": 4900
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 2.0,
|
356 |
+
"grad_norm": 0.5329481959342957,
|
357 |
+
"learning_rate": 0.0002,
|
358 |
+
"loss": 1.8615,
|
359 |
+
"step": 5000
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 2.04,
|
363 |
+
"grad_norm": 0.5874722599983215,
|
364 |
+
"learning_rate": 0.0002,
|
365 |
+
"loss": 1.6998,
|
366 |
+
"step": 5100
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 2.08,
|
370 |
+
"grad_norm": 0.5984659194946289,
|
371 |
+
"learning_rate": 0.0002,
|
372 |
+
"loss": 1.7303,
|
373 |
+
"step": 5200
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 2.12,
|
377 |
+
"grad_norm": 0.7614981532096863,
|
378 |
+
"learning_rate": 0.0002,
|
379 |
+
"loss": 1.6637,
|
380 |
+
"step": 5300
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 2.16,
|
384 |
+
"grad_norm": 0.8689171671867371,
|
385 |
+
"learning_rate": 0.0002,
|
386 |
+
"loss": 1.7,
|
387 |
+
"step": 5400
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 2.2,
|
391 |
+
"grad_norm": 0.8071489334106445,
|
392 |
+
"learning_rate": 0.0002,
|
393 |
+
"loss": 1.6588,
|
394 |
+
"step": 5500
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 2.24,
|
398 |
+
"grad_norm": 0.7306439280509949,
|
399 |
+
"learning_rate": 0.0002,
|
400 |
+
"loss": 1.7062,
|
401 |
+
"step": 5600
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 2.2800000000000002,
|
405 |
+
"grad_norm": 0.483328253030777,
|
406 |
+
"learning_rate": 0.0002,
|
407 |
+
"loss": 1.705,
|
408 |
+
"step": 5700
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 2.32,
|
412 |
+
"grad_norm": 0.9662113189697266,
|
413 |
+
"learning_rate": 0.0002,
|
414 |
+
"loss": 1.6375,
|
415 |
+
"step": 5800
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 2.36,
|
419 |
+
"grad_norm": 0.6570947766304016,
|
420 |
+
"learning_rate": 0.0002,
|
421 |
+
"loss": 1.6495,
|
422 |
+
"step": 5900
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 2.4,
|
426 |
+
"grad_norm": 0.6682040691375732,
|
427 |
+
"learning_rate": 0.0002,
|
428 |
+
"loss": 1.6971,
|
429 |
+
"step": 6000
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 2.44,
|
433 |
+
"grad_norm": 0.6937342286109924,
|
434 |
+
"learning_rate": 0.0002,
|
435 |
+
"loss": 1.6179,
|
436 |
+
"step": 6100
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 2.48,
|
440 |
+
"grad_norm": 0.6113543510437012,
|
441 |
+
"learning_rate": 0.0002,
|
442 |
+
"loss": 1.6769,
|
443 |
+
"step": 6200
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 2.52,
|
447 |
+
"grad_norm": 0.6734089851379395,
|
448 |
+
"learning_rate": 0.0002,
|
449 |
+
"loss": 1.6866,
|
450 |
+
"step": 6300
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 2.56,
|
454 |
+
"grad_norm": 0.6203577518463135,
|
455 |
+
"learning_rate": 0.0002,
|
456 |
+
"loss": 1.6999,
|
457 |
+
"step": 6400
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 2.6,
|
461 |
+
"grad_norm": 0.8067578077316284,
|
462 |
+
"learning_rate": 0.0002,
|
463 |
+
"loss": 1.6294,
|
464 |
+
"step": 6500
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 2.64,
|
468 |
+
"grad_norm": 0.7386764883995056,
|
469 |
+
"learning_rate": 0.0002,
|
470 |
+
"loss": 1.6841,
|
471 |
+
"step": 6600
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 2.68,
|
475 |
+
"grad_norm": 0.9529528617858887,
|
476 |
+
"learning_rate": 0.0002,
|
477 |
+
"loss": 1.665,
|
478 |
+
"step": 6700
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 2.7199999999999998,
|
482 |
+
"grad_norm": 0.5639382600784302,
|
483 |
+
"learning_rate": 0.0002,
|
484 |
+
"loss": 1.6756,
|
485 |
+
"step": 6800
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 2.76,
|
489 |
+
"grad_norm": 0.8711239695549011,
|
490 |
+
"learning_rate": 0.0002,
|
491 |
+
"loss": 1.5953,
|
492 |
+
"step": 6900
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 2.8,
|
496 |
+
"grad_norm": 0.6677307486534119,
|
497 |
+
"learning_rate": 0.0002,
|
498 |
+
"loss": 1.6708,
|
499 |
+
"step": 7000
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 2.84,
|
503 |
+
"grad_norm": 0.6820212006568909,
|
504 |
+
"learning_rate": 0.0002,
|
505 |
+
"loss": 1.6722,
|
506 |
+
"step": 7100
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 2.88,
|
510 |
+
"grad_norm": 0.6516992449760437,
|
511 |
+
"learning_rate": 0.0002,
|
512 |
+
"loss": 1.6407,
|
513 |
+
"step": 7200
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 2.92,
|
517 |
+
"grad_norm": 0.6071237325668335,
|
518 |
+
"learning_rate": 0.0002,
|
519 |
+
"loss": 1.6273,
|
520 |
+
"step": 7300
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 2.96,
|
524 |
+
"grad_norm": 0.6759991645812988,
|
525 |
+
"learning_rate": 0.0002,
|
526 |
+
"loss": 1.6218,
|
527 |
+
"step": 7400
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 3.0,
|
531 |
+
"grad_norm": 0.6260673403739929,
|
532 |
+
"learning_rate": 0.0002,
|
533 |
+
"loss": 1.7184,
|
534 |
+
"step": 7500
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 3.04,
|
538 |
+
"grad_norm": 0.6020120978355408,
|
539 |
+
"learning_rate": 0.0002,
|
540 |
+
"loss": 1.4686,
|
541 |
+
"step": 7600
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 3.08,
|
545 |
+
"grad_norm": 0.9953874945640564,
|
546 |
+
"learning_rate": 0.0002,
|
547 |
+
"loss": 1.5124,
|
548 |
+
"step": 7700
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 3.12,
|
552 |
+
"grad_norm": 0.7787545323371887,
|
553 |
+
"learning_rate": 0.0002,
|
554 |
+
"loss": 1.5184,
|
555 |
+
"step": 7800
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 3.16,
|
559 |
+
"grad_norm": 0.9334218502044678,
|
560 |
+
"learning_rate": 0.0002,
|
561 |
+
"loss": 1.5031,
|
562 |
+
"step": 7900
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 3.2,
|
566 |
+
"grad_norm": 0.9822279214859009,
|
567 |
+
"learning_rate": 0.0002,
|
568 |
+
"loss": 1.504,
|
569 |
+
"step": 8000
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 3.24,
|
573 |
+
"grad_norm": 0.8602248430252075,
|
574 |
+
"learning_rate": 0.0002,
|
575 |
+
"loss": 1.5348,
|
576 |
+
"step": 8100
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 3.2800000000000002,
|
580 |
+
"grad_norm": 0.88422691822052,
|
581 |
+
"learning_rate": 0.0002,
|
582 |
+
"loss": 1.4788,
|
583 |
+
"step": 8200
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 3.32,
|
587 |
+
"grad_norm": 0.8250532746315002,
|
588 |
+
"learning_rate": 0.0002,
|
589 |
+
"loss": 1.5258,
|
590 |
+
"step": 8300
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 3.36,
|
594 |
+
"grad_norm": 1.3689357042312622,
|
595 |
+
"learning_rate": 0.0002,
|
596 |
+
"loss": 1.53,
|
597 |
+
"step": 8400
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 3.4,
|
601 |
+
"grad_norm": 1.0472410917282104,
|
602 |
+
"learning_rate": 0.0002,
|
603 |
+
"loss": 1.5347,
|
604 |
+
"step": 8500
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 3.44,
|
608 |
+
"grad_norm": 0.7986043095588684,
|
609 |
+
"learning_rate": 0.0002,
|
610 |
+
"loss": 1.4467,
|
611 |
+
"step": 8600
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 3.48,
|
615 |
+
"grad_norm": 0.8166589736938477,
|
616 |
+
"learning_rate": 0.0002,
|
617 |
+
"loss": 1.6207,
|
618 |
+
"step": 8700
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 3.52,
|
622 |
+
"grad_norm": 0.7566811442375183,
|
623 |
+
"learning_rate": 0.0002,
|
624 |
+
"loss": 1.5238,
|
625 |
+
"step": 8800
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 3.56,
|
629 |
+
"grad_norm": 0.9338216185569763,
|
630 |
+
"learning_rate": 0.0002,
|
631 |
+
"loss": 1.5801,
|
632 |
+
"step": 8900
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 3.6,
|
636 |
+
"grad_norm": 0.9602301716804504,
|
637 |
+
"learning_rate": 0.0002,
|
638 |
+
"loss": 1.4506,
|
639 |
+
"step": 9000
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 3.64,
|
643 |
+
"grad_norm": 0.9274515509605408,
|
644 |
+
"learning_rate": 0.0002,
|
645 |
+
"loss": 1.5574,
|
646 |
+
"step": 9100
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 3.68,
|
650 |
+
"grad_norm": 1.6966444253921509,
|
651 |
+
"learning_rate": 0.0002,
|
652 |
+
"loss": 1.4391,
|
653 |
+
"step": 9200
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 3.7199999999999998,
|
657 |
+
"grad_norm": 0.9805380702018738,
|
658 |
+
"learning_rate": 0.0002,
|
659 |
+
"loss": 1.5071,
|
660 |
+
"step": 9300
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 3.76,
|
664 |
+
"grad_norm": 1.1102324724197388,
|
665 |
+
"learning_rate": 0.0002,
|
666 |
+
"loss": 1.5041,
|
667 |
+
"step": 9400
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 3.8,
|
671 |
+
"grad_norm": 1.1052135229110718,
|
672 |
+
"learning_rate": 0.0002,
|
673 |
+
"loss": 1.504,
|
674 |
+
"step": 9500
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 3.84,
|
678 |
+
"grad_norm": 0.8187786936759949,
|
679 |
+
"learning_rate": 0.0002,
|
680 |
+
"loss": 1.5444,
|
681 |
+
"step": 9600
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 3.88,
|
685 |
+
"grad_norm": 1.5404032468795776,
|
686 |
+
"learning_rate": 0.0002,
|
687 |
+
"loss": 1.5627,
|
688 |
+
"step": 9700
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 3.92,
|
692 |
+
"grad_norm": 0.7880242466926575,
|
693 |
+
"learning_rate": 0.0002,
|
694 |
+
"loss": 1.508,
|
695 |
+
"step": 9800
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 3.96,
|
699 |
+
"grad_norm": 1.2433679103851318,
|
700 |
+
"learning_rate": 0.0002,
|
701 |
+
"loss": 1.5252,
|
702 |
+
"step": 9900
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 4.0,
|
706 |
+
"grad_norm": NaN,
|
707 |
+
"learning_rate": 0.0002,
|
708 |
+
"loss": 1.5194,
|
709 |
+
"step": 10000
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 4.04,
|
713 |
+
"grad_norm": 0.9061052799224854,
|
714 |
+
"learning_rate": 0.0002,
|
715 |
+
"loss": 1.3939,
|
716 |
+
"step": 10100
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 4.08,
|
720 |
+
"grad_norm": 0.9826890230178833,
|
721 |
+
"learning_rate": 0.0002,
|
722 |
+
"loss": 1.3602,
|
723 |
+
"step": 10200
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 4.12,
|
727 |
+
"grad_norm": 1.1164418458938599,
|
728 |
+
"learning_rate": 0.0002,
|
729 |
+
"loss": 1.4036,
|
730 |
+
"step": 10300
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 4.16,
|
734 |
+
"grad_norm": 1.2371020317077637,
|
735 |
+
"learning_rate": 0.0002,
|
736 |
+
"loss": 1.4325,
|
737 |
+
"step": 10400
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 4.2,
|
741 |
+
"grad_norm": 0.9281136393547058,
|
742 |
+
"learning_rate": 0.0002,
|
743 |
+
"loss": 1.3633,
|
744 |
+
"step": 10500
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 4.24,
|
748 |
+
"grad_norm": 1.5267653465270996,
|
749 |
+
"learning_rate": 0.0002,
|
750 |
+
"loss": 1.3531,
|
751 |
+
"step": 10600
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 4.28,
|
755 |
+
"grad_norm": 0.9372194409370422,
|
756 |
+
"learning_rate": 0.0002,
|
757 |
+
"loss": 1.387,
|
758 |
+
"step": 10700
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 4.32,
|
762 |
+
"grad_norm": 1.9180704355239868,
|
763 |
+
"learning_rate": 0.0002,
|
764 |
+
"loss": 1.4049,
|
765 |
+
"step": 10800
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 4.36,
|
769 |
+
"grad_norm": 0.9102849960327148,
|
770 |
+
"learning_rate": 0.0002,
|
771 |
+
"loss": 1.3481,
|
772 |
+
"step": 10900
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 4.4,
|
776 |
+
"grad_norm": 1.3661117553710938,
|
777 |
+
"learning_rate": 0.0002,
|
778 |
+
"loss": 1.3171,
|
779 |
+
"step": 11000
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 4.44,
|
783 |
+
"grad_norm": 0.6796606183052063,
|
784 |
+
"learning_rate": 0.0002,
|
785 |
+
"loss": 1.3776,
|
786 |
+
"step": 11100
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 4.48,
|
790 |
+
"grad_norm": 1.2240846157073975,
|
791 |
+
"learning_rate": 0.0002,
|
792 |
+
"loss": 1.3756,
|
793 |
+
"step": 11200
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 4.52,
|
797 |
+
"grad_norm": 0.7911117672920227,
|
798 |
+
"learning_rate": 0.0002,
|
799 |
+
"loss": 1.3484,
|
800 |
+
"step": 11300
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 4.5600000000000005,
|
804 |
+
"grad_norm": 0.6849353313446045,
|
805 |
+
"learning_rate": 0.0002,
|
806 |
+
"loss": 1.3985,
|
807 |
+
"step": 11400
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 4.6,
|
811 |
+
"grad_norm": 1.292270541191101,
|
812 |
+
"learning_rate": 0.0002,
|
813 |
+
"loss": 1.3338,
|
814 |
+
"step": 11500
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 4.64,
|
818 |
+
"grad_norm": 1.0751451253890991,
|
819 |
+
"learning_rate": 0.0002,
|
820 |
+
"loss": 1.4044,
|
821 |
+
"step": 11600
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 4.68,
|
825 |
+
"grad_norm": 1.391108512878418,
|
826 |
+
"learning_rate": 0.0002,
|
827 |
+
"loss": 1.4003,
|
828 |
+
"step": 11700
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 4.72,
|
832 |
+
"grad_norm": 0.8339885473251343,
|
833 |
+
"learning_rate": 0.0002,
|
834 |
+
"loss": 1.389,
|
835 |
+
"step": 11800
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 4.76,
|
839 |
+
"grad_norm": 0.9836968779563904,
|
840 |
+
"learning_rate": 0.0002,
|
841 |
+
"loss": 1.3732,
|
842 |
+
"step": 11900
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 4.8,
|
846 |
+
"grad_norm": 1.3942408561706543,
|
847 |
+
"learning_rate": 0.0002,
|
848 |
+
"loss": 1.3763,
|
849 |
+
"step": 12000
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 4.84,
|
853 |
+
"grad_norm": 0.8473936915397644,
|
854 |
+
"learning_rate": 0.0002,
|
855 |
+
"loss": 1.3675,
|
856 |
+
"step": 12100
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 4.88,
|
860 |
+
"grad_norm": 1.1180263757705688,
|
861 |
+
"learning_rate": 0.0002,
|
862 |
+
"loss": 1.3018,
|
863 |
+
"step": 12200
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 4.92,
|
867 |
+
"grad_norm": 1.0825896263122559,
|
868 |
+
"learning_rate": 0.0002,
|
869 |
+
"loss": 1.3935,
|
870 |
+
"step": 12300
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 4.96,
|
874 |
+
"grad_norm": 1.7957453727722168,
|
875 |
+
"learning_rate": 0.0002,
|
876 |
+
"loss": 1.4167,
|
877 |
+
"step": 12400
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 5.0,
|
881 |
+
"grad_norm": 1.4984807968139648,
|
882 |
+
"learning_rate": 0.0002,
|
883 |
+
"loss": 1.3562,
|
884 |
+
"step": 12500
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 5.04,
|
888 |
+
"grad_norm": 1.2871723175048828,
|
889 |
+
"learning_rate": 0.0002,
|
890 |
+
"loss": 1.2327,
|
891 |
+
"step": 12600
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 5.08,
|
895 |
+
"grad_norm": 0.5957996249198914,
|
896 |
+
"learning_rate": 0.0002,
|
897 |
+
"loss": 1.1613,
|
898 |
+
"step": 12700
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 5.12,
|
902 |
+
"grad_norm": 1.0731712579727173,
|
903 |
+
"learning_rate": 0.0002,
|
904 |
+
"loss": 1.2683,
|
905 |
+
"step": 12800
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 5.16,
|
909 |
+
"grad_norm": 1.2785401344299316,
|
910 |
+
"learning_rate": 0.0002,
|
911 |
+
"loss": 1.2215,
|
912 |
+
"step": 12900
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 5.2,
|
916 |
+
"grad_norm": 0.6945757269859314,
|
917 |
+
"learning_rate": 0.0002,
|
918 |
+
"loss": 1.2665,
|
919 |
+
"step": 13000
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 5.24,
|
923 |
+
"grad_norm": 0.8779969215393066,
|
924 |
+
"learning_rate": 0.0002,
|
925 |
+
"loss": 1.2028,
|
926 |
+
"step": 13100
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 5.28,
|
930 |
+
"grad_norm": 0.9905422329902649,
|
931 |
+
"learning_rate": 0.0002,
|
932 |
+
"loss": 1.2691,
|
933 |
+
"step": 13200
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 5.32,
|
937 |
+
"grad_norm": 0.7267619967460632,
|
938 |
+
"learning_rate": 0.0002,
|
939 |
+
"loss": 1.2794,
|
940 |
+
"step": 13300
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 5.36,
|
944 |
+
"grad_norm": 1.1280577182769775,
|
945 |
+
"learning_rate": 0.0002,
|
946 |
+
"loss": 1.2608,
|
947 |
+
"step": 13400
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 5.4,
|
951 |
+
"grad_norm": 1.3053045272827148,
|
952 |
+
"learning_rate": 0.0002,
|
953 |
+
"loss": 1.253,
|
954 |
+
"step": 13500
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 5.44,
|
958 |
+
"grad_norm": 1.1373580694198608,
|
959 |
+
"learning_rate": 0.0002,
|
960 |
+
"loss": 1.2236,
|
961 |
+
"step": 13600
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 5.48,
|
965 |
+
"grad_norm": 0.9823132753372192,
|
966 |
+
"learning_rate": 0.0002,
|
967 |
+
"loss": 1.2841,
|
968 |
+
"step": 13700
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 5.52,
|
972 |
+
"grad_norm": 1.0225436687469482,
|
973 |
+
"learning_rate": 0.0002,
|
974 |
+
"loss": 1.2052,
|
975 |
+
"step": 13800
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 5.5600000000000005,
|
979 |
+
"grad_norm": 1.6617635488510132,
|
980 |
+
"learning_rate": 0.0002,
|
981 |
+
"loss": 1.2314,
|
982 |
+
"step": 13900
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 5.6,
|
986 |
+
"grad_norm": 1.0195096731185913,
|
987 |
+
"learning_rate": 0.0002,
|
988 |
+
"loss": 1.2959,
|
989 |
+
"step": 14000
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 5.64,
|
993 |
+
"grad_norm": 1.3563017845153809,
|
994 |
+
"learning_rate": 0.0002,
|
995 |
+
"loss": 1.2683,
|
996 |
+
"step": 14100
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 5.68,
|
1000 |
+
"grad_norm": 2.1966164112091064,
|
1001 |
+
"learning_rate": 0.0002,
|
1002 |
+
"loss": 1.2247,
|
1003 |
+
"step": 14200
|
1004 |
+
},
|
1005 |
+
{
|
1006 |
+
"epoch": 5.72,
|
1007 |
+
"grad_norm": 1.057099461555481,
|
1008 |
+
"learning_rate": 0.0002,
|
1009 |
+
"loss": 1.2577,
|
1010 |
+
"step": 14300
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 5.76,
|
1014 |
+
"grad_norm": 1.2523263692855835,
|
1015 |
+
"learning_rate": 0.0002,
|
1016 |
+
"loss": 1.2865,
|
1017 |
+
"step": 14400
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 5.8,
|
1021 |
+
"grad_norm": 1.7607208490371704,
|
1022 |
+
"learning_rate": 0.0002,
|
1023 |
+
"loss": 1.2205,
|
1024 |
+
"step": 14500
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 5.84,
|
1028 |
+
"grad_norm": 1.9455257654190063,
|
1029 |
+
"learning_rate": 0.0002,
|
1030 |
+
"loss": 1.2829,
|
1031 |
+
"step": 14600
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 5.88,
|
1035 |
+
"grad_norm": 1.0618771314620972,
|
1036 |
+
"learning_rate": 0.0002,
|
1037 |
+
"loss": 1.3037,
|
1038 |
+
"step": 14700
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 5.92,
|
1042 |
+
"grad_norm": 1.0242942571640015,
|
1043 |
+
"learning_rate": 0.0002,
|
1044 |
+
"loss": 1.2165,
|
1045 |
+
"step": 14800
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 5.96,
|
1049 |
+
"grad_norm": 1.2692897319793701,
|
1050 |
+
"learning_rate": 0.0002,
|
1051 |
+
"loss": 1.2873,
|
1052 |
+
"step": 14900
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 6.0,
|
1056 |
+
"grad_norm": 1.0533056259155273,
|
1057 |
+
"learning_rate": 0.0002,
|
1058 |
+
"loss": 1.2528,
|
1059 |
+
"step": 15000
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 6.04,
|
1063 |
+
"grad_norm": 0.8311458230018616,
|
1064 |
+
"learning_rate": 0.0002,
|
1065 |
+
"loss": 1.0705,
|
1066 |
+
"step": 15100
|
1067 |
+
},
|
1068 |
+
{
|
1069 |
+
"epoch": 6.08,
|
1070 |
+
"grad_norm": 1.0614266395568848,
|
1071 |
+
"learning_rate": 0.0002,
|
1072 |
+
"loss": 1.0803,
|
1073 |
+
"step": 15200
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 6.12,
|
1077 |
+
"grad_norm": 1.4157719612121582,
|
1078 |
+
"learning_rate": 0.0002,
|
1079 |
+
"loss": 1.0864,
|
1080 |
+
"step": 15300
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 6.16,
|
1084 |
+
"grad_norm": 1.0785095691680908,
|
1085 |
+
"learning_rate": 0.0002,
|
1086 |
+
"loss": 1.1076,
|
1087 |
+
"step": 15400
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 6.2,
|
1091 |
+
"grad_norm": 1.3798463344573975,
|
1092 |
+
"learning_rate": 0.0002,
|
1093 |
+
"loss": 1.1038,
|
1094 |
+
"step": 15500
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 6.24,
|
1098 |
+
"grad_norm": 0.9821926355361938,
|
1099 |
+
"learning_rate": 0.0002,
|
1100 |
+
"loss": 1.1482,
|
1101 |
+
"step": 15600
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 6.28,
|
1105 |
+
"grad_norm": 2.189770221710205,
|
1106 |
+
"learning_rate": 0.0002,
|
1107 |
+
"loss": 1.1154,
|
1108 |
+
"step": 15700
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 6.32,
|
1112 |
+
"grad_norm": 5.5393500328063965,
|
1113 |
+
"learning_rate": 0.0002,
|
1114 |
+
"loss": 1.1186,
|
1115 |
+
"step": 15800
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 6.36,
|
1119 |
+
"grad_norm": 1.2127723693847656,
|
1120 |
+
"learning_rate": 0.0002,
|
1121 |
+
"loss": 1.1888,
|
1122 |
+
"step": 15900
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 6.4,
|
1126 |
+
"grad_norm": 2.876635789871216,
|
1127 |
+
"learning_rate": 0.0002,
|
1128 |
+
"loss": 1.1029,
|
1129 |
+
"step": 16000
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 6.44,
|
1133 |
+
"grad_norm": 1.3155653476715088,
|
1134 |
+
"learning_rate": 0.0002,
|
1135 |
+
"loss": 1.1092,
|
1136 |
+
"step": 16100
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 6.48,
|
1140 |
+
"grad_norm": 1.1871975660324097,
|
1141 |
+
"learning_rate": 0.0002,
|
1142 |
+
"loss": 1.1488,
|
1143 |
+
"step": 16200
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 6.52,
|
1147 |
+
"grad_norm": 1.6706851720809937,
|
1148 |
+
"learning_rate": 0.0002,
|
1149 |
+
"loss": 1.153,
|
1150 |
+
"step": 16300
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 6.5600000000000005,
|
1154 |
+
"grad_norm": 2.3989503383636475,
|
1155 |
+
"learning_rate": 0.0002,
|
1156 |
+
"loss": 1.1049,
|
1157 |
+
"step": 16400
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 6.6,
|
1161 |
+
"grad_norm": 1.0962737798690796,
|
1162 |
+
"learning_rate": 0.0002,
|
1163 |
+
"loss": 1.182,
|
1164 |
+
"step": 16500
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 6.64,
|
1168 |
+
"grad_norm": 1.2321207523345947,
|
1169 |
+
"learning_rate": 0.0002,
|
1170 |
+
"loss": 1.1196,
|
1171 |
+
"step": 16600
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 6.68,
|
1175 |
+
"grad_norm": 1.6745890378952026,
|
1176 |
+
"learning_rate": 0.0002,
|
1177 |
+
"loss": 1.1776,
|
1178 |
+
"step": 16700
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 6.72,
|
1182 |
+
"grad_norm": 3.3587148189544678,
|
1183 |
+
"learning_rate": 0.0002,
|
1184 |
+
"loss": 1.1335,
|
1185 |
+
"step": 16800
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 6.76,
|
1189 |
+
"grad_norm": 1.2802035808563232,
|
1190 |
+
"learning_rate": 0.0002,
|
1191 |
+
"loss": 1.2144,
|
1192 |
+
"step": 16900
|
1193 |
+
},
|
1194 |
+
{
|
1195 |
+
"epoch": 6.8,
|
1196 |
+
"grad_norm": 1.5999842882156372,
|
1197 |
+
"learning_rate": 0.0002,
|
1198 |
+
"loss": 1.1143,
|
1199 |
+
"step": 17000
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 6.84,
|
1203 |
+
"grad_norm": 1.5529465675354004,
|
1204 |
+
"learning_rate": 0.0002,
|
1205 |
+
"loss": 1.1503,
|
1206 |
+
"step": 17100
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 6.88,
|
1210 |
+
"grad_norm": 0.9041572213172913,
|
1211 |
+
"learning_rate": 0.0002,
|
1212 |
+
"loss": 1.1681,
|
1213 |
+
"step": 17200
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 6.92,
|
1217 |
+
"grad_norm": 1.2176377773284912,
|
1218 |
+
"learning_rate": 0.0002,
|
1219 |
+
"loss": 1.1284,
|
1220 |
+
"step": 17300
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 6.96,
|
1224 |
+
"grad_norm": 1.1047685146331787,
|
1225 |
+
"learning_rate": 0.0002,
|
1226 |
+
"loss": 1.1622,
|
1227 |
+
"step": 17400
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 7.0,
|
1231 |
+
"grad_norm": 2.3316566944122314,
|
1232 |
+
"learning_rate": 0.0002,
|
1233 |
+
"loss": 1.149,
|
1234 |
+
"step": 17500
|
1235 |
+
},
|
1236 |
+
{
|
1237 |
+
"epoch": 7.04,
|
1238 |
+
"grad_norm": 0.9057099223136902,
|
1239 |
+
"learning_rate": 0.0002,
|
1240 |
+
"loss": 0.9952,
|
1241 |
+
"step": 17600
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 7.08,
|
1245 |
+
"grad_norm": 2.2556183338165283,
|
1246 |
+
"learning_rate": 0.0002,
|
1247 |
+
"loss": 0.9667,
|
1248 |
+
"step": 17700
|
1249 |
+
},
|
1250 |
+
{
|
1251 |
+
"epoch": 7.12,
|
1252 |
+
"grad_norm": 1.2181649208068848,
|
1253 |
+
"learning_rate": 0.0002,
|
1254 |
+
"loss": 0.9606,
|
1255 |
+
"step": 17800
|
1256 |
+
},
|
1257 |
+
{
|
1258 |
+
"epoch": 7.16,
|
1259 |
+
"grad_norm": 1.1756635904312134,
|
1260 |
+
"learning_rate": 0.0002,
|
1261 |
+
"loss": 1.0176,
|
1262 |
+
"step": 17900
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 7.2,
|
1266 |
+
"grad_norm": 1.3955613374710083,
|
1267 |
+
"learning_rate": 0.0002,
|
1268 |
+
"loss": 1.0423,
|
1269 |
+
"step": 18000
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 7.24,
|
1273 |
+
"grad_norm": 2.0451719760894775,
|
1274 |
+
"learning_rate": 0.0002,
|
1275 |
+
"loss": 1.0152,
|
1276 |
+
"step": 18100
|
1277 |
+
},
|
1278 |
+
{
|
1279 |
+
"epoch": 7.28,
|
1280 |
+
"grad_norm": 1.8395252227783203,
|
1281 |
+
"learning_rate": 0.0002,
|
1282 |
+
"loss": 0.9896,
|
1283 |
+
"step": 18200
|
1284 |
+
},
|
1285 |
+
{
|
1286 |
+
"epoch": 7.32,
|
1287 |
+
"grad_norm": 0.8587050437927246,
|
1288 |
+
"learning_rate": 0.0002,
|
1289 |
+
"loss": 0.9976,
|
1290 |
+
"step": 18300
|
1291 |
+
},
|
1292 |
+
{
|
1293 |
+
"epoch": 7.36,
|
1294 |
+
"grad_norm": 1.848895788192749,
|
1295 |
+
"learning_rate": 0.0002,
|
1296 |
+
"loss": 0.9711,
|
1297 |
+
"step": 18400
|
1298 |
+
},
|
1299 |
+
{
|
1300 |
+
"epoch": 7.4,
|
1301 |
+
"grad_norm": 0.8069963455200195,
|
1302 |
+
"learning_rate": 0.0002,
|
1303 |
+
"loss": 1.02,
|
1304 |
+
"step": 18500
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 7.44,
|
1308 |
+
"grad_norm": 1.0655219554901123,
|
1309 |
+
"learning_rate": 0.0002,
|
1310 |
+
"loss": 1.0069,
|
1311 |
+
"step": 18600
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 7.48,
|
1315 |
+
"grad_norm": 1.474328637123108,
|
1316 |
+
"learning_rate": 0.0002,
|
1317 |
+
"loss": 1.0311,
|
1318 |
+
"step": 18700
|
1319 |
+
},
|
1320 |
+
{
|
1321 |
+
"epoch": 7.52,
|
1322 |
+
"grad_norm": 1.3253296613693237,
|
1323 |
+
"learning_rate": 0.0002,
|
1324 |
+
"loss": 1.0158,
|
1325 |
+
"step": 18800
|
1326 |
+
},
|
1327 |
+
{
|
1328 |
+
"epoch": 7.5600000000000005,
|
1329 |
+
"grad_norm": 1.1345421075820923,
|
1330 |
+
"learning_rate": 0.0002,
|
1331 |
+
"loss": 1.0391,
|
1332 |
+
"step": 18900
|
1333 |
+
},
|
1334 |
+
{
|
1335 |
+
"epoch": 7.6,
|
1336 |
+
"grad_norm": 1.0736902952194214,
|
1337 |
+
"learning_rate": 0.0002,
|
1338 |
+
"loss": 1.0498,
|
1339 |
+
"step": 19000
|
1340 |
+
},
|
1341 |
+
{
|
1342 |
+
"epoch": 7.64,
|
1343 |
+
"grad_norm": 1.6537193059921265,
|
1344 |
+
"learning_rate": 0.0002,
|
1345 |
+
"loss": 1.0235,
|
1346 |
+
"step": 19100
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 7.68,
|
1350 |
+
"grad_norm": 1.3010786771774292,
|
1351 |
+
"learning_rate": 0.0002,
|
1352 |
+
"loss": 1.0307,
|
1353 |
+
"step": 19200
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 7.72,
|
1357 |
+
"grad_norm": 0.9209179282188416,
|
1358 |
+
"learning_rate": 0.0002,
|
1359 |
+
"loss": 1.0111,
|
1360 |
+
"step": 19300
|
1361 |
+
},
|
1362 |
+
{
|
1363 |
+
"epoch": 7.76,
|
1364 |
+
"grad_norm": 5.0836310386657715,
|
1365 |
+
"learning_rate": 0.0002,
|
1366 |
+
"loss": 1.059,
|
1367 |
+
"step": 19400
|
1368 |
+
},
|
1369 |
+
{
|
1370 |
+
"epoch": 7.8,
|
1371 |
+
"grad_norm": 1.7362360954284668,
|
1372 |
+
"learning_rate": 0.0002,
|
1373 |
+
"loss": 1.0704,
|
1374 |
+
"step": 19500
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 7.84,
|
1378 |
+
"grad_norm": 1.692413330078125,
|
1379 |
+
"learning_rate": 0.0002,
|
1380 |
+
"loss": 1.0618,
|
1381 |
+
"step": 19600
|
1382 |
+
},
|
1383 |
+
{
|
1384 |
+
"epoch": 7.88,
|
1385 |
+
"grad_norm": 3.538470506668091,
|
1386 |
+
"learning_rate": 0.0002,
|
1387 |
+
"loss": 1.0778,
|
1388 |
+
"step": 19700
|
1389 |
+
},
|
1390 |
+
{
|
1391 |
+
"epoch": 7.92,
|
1392 |
+
"grad_norm": 2.578237533569336,
|
1393 |
+
"learning_rate": 0.0002,
|
1394 |
+
"loss": 1.1153,
|
1395 |
+
"step": 19800
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 7.96,
|
1399 |
+
"grad_norm": 1.356609582901001,
|
1400 |
+
"learning_rate": 0.0002,
|
1401 |
+
"loss": 1.0597,
|
1402 |
+
"step": 19900
|
1403 |
+
},
|
1404 |
+
{
|
1405 |
+
"epoch": 8.0,
|
1406 |
+
"grad_norm": 0.89506995677948,
|
1407 |
+
"learning_rate": 0.0002,
|
1408 |
+
"loss": 1.0892,
|
1409 |
+
"step": 20000
|
1410 |
+
},
|
1411 |
+
{
|
1412 |
+
"epoch": 8.04,
|
1413 |
+
"grad_norm": 1.5506243705749512,
|
1414 |
+
"learning_rate": 0.0002,
|
1415 |
+
"loss": 0.8659,
|
1416 |
+
"step": 20100
|
1417 |
+
},
|
1418 |
+
{
|
1419 |
+
"epoch": 8.08,
|
1420 |
+
"grad_norm": 1.69996178150177,
|
1421 |
+
"learning_rate": 0.0002,
|
1422 |
+
"loss": 0.9142,
|
1423 |
+
"step": 20200
|
1424 |
+
},
|
1425 |
+
{
|
1426 |
+
"epoch": 8.12,
|
1427 |
+
"grad_norm": 2.0094783306121826,
|
1428 |
+
"learning_rate": 0.0002,
|
1429 |
+
"loss": 0.8807,
|
1430 |
+
"step": 20300
|
1431 |
+
},
|
1432 |
+
{
|
1433 |
+
"epoch": 8.16,
|
1434 |
+
"grad_norm": 1.6503652334213257,
|
1435 |
+
"learning_rate": 0.0002,
|
1436 |
+
"loss": 0.857,
|
1437 |
+
"step": 20400
|
1438 |
+
},
|
1439 |
+
{
|
1440 |
+
"epoch": 8.2,
|
1441 |
+
"grad_norm": 0.933527410030365,
|
1442 |
+
"learning_rate": 0.0002,
|
1443 |
+
"loss": 0.8855,
|
1444 |
+
"step": 20500
|
1445 |
+
},
|
1446 |
+
{
|
1447 |
+
"epoch": 8.24,
|
1448 |
+
"grad_norm": 1.6827526092529297,
|
1449 |
+
"learning_rate": 0.0002,
|
1450 |
+
"loss": 0.9295,
|
1451 |
+
"step": 20600
|
1452 |
+
},
|
1453 |
+
{
|
1454 |
+
"epoch": 8.28,
|
1455 |
+
"grad_norm": 2.89079213142395,
|
1456 |
+
"learning_rate": 0.0002,
|
1457 |
+
"loss": 0.9146,
|
1458 |
+
"step": 20700
|
1459 |
+
},
|
1460 |
+
{
|
1461 |
+
"epoch": 8.32,
|
1462 |
+
"grad_norm": 1.0603892803192139,
|
1463 |
+
"learning_rate": 0.0002,
|
1464 |
+
"loss": 0.9279,
|
1465 |
+
"step": 20800
|
1466 |
+
},
|
1467 |
+
{
|
1468 |
+
"epoch": 8.36,
|
1469 |
+
"grad_norm": 3.3014211654663086,
|
1470 |
+
"learning_rate": 0.0002,
|
1471 |
+
"loss": 0.9406,
|
1472 |
+
"step": 20900
|
1473 |
+
},
|
1474 |
+
{
|
1475 |
+
"epoch": 8.4,
|
1476 |
+
"grad_norm": 0.8049854040145874,
|
1477 |
+
"learning_rate": 0.0002,
|
1478 |
+
"loss": 0.907,
|
1479 |
+
"step": 21000
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 8.44,
|
1483 |
+
"grad_norm": 2.991314649581909,
|
1484 |
+
"learning_rate": 0.0002,
|
1485 |
+
"loss": 0.9721,
|
1486 |
+
"step": 21100
|
1487 |
+
},
|
1488 |
+
{
|
1489 |
+
"epoch": 8.48,
|
1490 |
+
"grad_norm": 1.043578028678894,
|
1491 |
+
"learning_rate": 0.0002,
|
1492 |
+
"loss": 0.9557,
|
1493 |
+
"step": 21200
|
1494 |
+
},
|
1495 |
+
{
|
1496 |
+
"epoch": 8.52,
|
1497 |
+
"grad_norm": 1.6888822317123413,
|
1498 |
+
"learning_rate": 0.0002,
|
1499 |
+
"loss": 0.9477,
|
1500 |
+
"step": 21300
|
1501 |
+
},
|
1502 |
+
{
|
1503 |
+
"epoch": 8.56,
|
1504 |
+
"grad_norm": 1.4089540243148804,
|
1505 |
+
"learning_rate": 0.0002,
|
1506 |
+
"loss": 0.9424,
|
1507 |
+
"step": 21400
|
1508 |
+
},
|
1509 |
+
{
|
1510 |
+
"epoch": 8.6,
|
1511 |
+
"grad_norm": 7.123160362243652,
|
1512 |
+
"learning_rate": 0.0002,
|
1513 |
+
"loss": 0.9232,
|
1514 |
+
"step": 21500
|
1515 |
+
},
|
1516 |
+
{
|
1517 |
+
"epoch": 8.64,
|
1518 |
+
"grad_norm": 1.149699091911316,
|
1519 |
+
"learning_rate": 0.0002,
|
1520 |
+
"loss": 0.9189,
|
1521 |
+
"step": 21600
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 8.68,
|
1525 |
+
"grad_norm": 1.3870540857315063,
|
1526 |
+
"learning_rate": 0.0002,
|
1527 |
+
"loss": 0.9318,
|
1528 |
+
"step": 21700
|
1529 |
+
},
|
1530 |
+
{
|
1531 |
+
"epoch": 8.72,
|
1532 |
+
"grad_norm": 1.4124248027801514,
|
1533 |
+
"learning_rate": 0.0002,
|
1534 |
+
"loss": 0.9657,
|
1535 |
+
"step": 21800
|
1536 |
+
},
|
1537 |
+
{
|
1538 |
+
"epoch": 8.76,
|
1539 |
+
"grad_norm": 0.6599737405776978,
|
1540 |
+
"learning_rate": 0.0002,
|
1541 |
+
"loss": 0.9493,
|
1542 |
+
"step": 21900
|
1543 |
+
},
|
1544 |
+
{
|
1545 |
+
"epoch": 8.8,
|
1546 |
+
"grad_norm": 1.0088489055633545,
|
1547 |
+
"learning_rate": 0.0002,
|
1548 |
+
"loss": 0.9739,
|
1549 |
+
"step": 22000
|
1550 |
+
},
|
1551 |
+
{
|
1552 |
+
"epoch": 8.84,
|
1553 |
+
"grad_norm": 0.7540724873542786,
|
1554 |
+
"learning_rate": 0.0002,
|
1555 |
+
"loss": 0.9492,
|
1556 |
+
"step": 22100
|
1557 |
+
},
|
1558 |
+
{
|
1559 |
+
"epoch": 8.88,
|
1560 |
+
"grad_norm": 1.0838185548782349,
|
1561 |
+
"learning_rate": 0.0002,
|
1562 |
+
"loss": 1.0105,
|
1563 |
+
"step": 22200
|
1564 |
+
},
|
1565 |
+
{
|
1566 |
+
"epoch": 8.92,
|
1567 |
+
"grad_norm": 0.8989962935447693,
|
1568 |
+
"learning_rate": 0.0002,
|
1569 |
+
"loss": 0.9256,
|
1570 |
+
"step": 22300
|
1571 |
+
},
|
1572 |
+
{
|
1573 |
+
"epoch": 8.96,
|
1574 |
+
"grad_norm": 0.9646226167678833,
|
1575 |
+
"learning_rate": 0.0002,
|
1576 |
+
"loss": 0.9766,
|
1577 |
+
"step": 22400
|
1578 |
+
},
|
1579 |
+
{
|
1580 |
+
"epoch": 9.0,
|
1581 |
+
"grad_norm": 1.0363638401031494,
|
1582 |
+
"learning_rate": 0.0002,
|
1583 |
+
"loss": 0.9676,
|
1584 |
+
"step": 22500
|
1585 |
+
},
|
1586 |
+
{
|
1587 |
+
"epoch": 9.04,
|
1588 |
+
"grad_norm": 1.2631175518035889,
|
1589 |
+
"learning_rate": 0.0002,
|
1590 |
+
"loss": 0.7845,
|
1591 |
+
"step": 22600
|
1592 |
+
},
|
1593 |
+
{
|
1594 |
+
"epoch": 9.08,
|
1595 |
+
"grad_norm": 1.2183212041854858,
|
1596 |
+
"learning_rate": 0.0002,
|
1597 |
+
"loss": 0.7785,
|
1598 |
+
"step": 22700
|
1599 |
+
},
|
1600 |
+
{
|
1601 |
+
"epoch": 9.12,
|
1602 |
+
"grad_norm": 1.4566229581832886,
|
1603 |
+
"learning_rate": 0.0002,
|
1604 |
+
"loss": 0.7972,
|
1605 |
+
"step": 22800
|
1606 |
+
},
|
1607 |
+
{
|
1608 |
+
"epoch": 9.16,
|
1609 |
+
"grad_norm": 1.2739365100860596,
|
1610 |
+
"learning_rate": 0.0002,
|
1611 |
+
"loss": 0.7729,
|
1612 |
+
"step": 22900
|
1613 |
+
},
|
1614 |
+
{
|
1615 |
+
"epoch": 9.2,
|
1616 |
+
"grad_norm": 1.4455575942993164,
|
1617 |
+
"learning_rate": 0.0002,
|
1618 |
+
"loss": 0.8359,
|
1619 |
+
"step": 23000
|
1620 |
+
},
|
1621 |
+
{
|
1622 |
+
"epoch": 9.24,
|
1623 |
+
"grad_norm": 1.1576048135757446,
|
1624 |
+
"learning_rate": 0.0002,
|
1625 |
+
"loss": 0.8324,
|
1626 |
+
"step": 23100
|
1627 |
+
},
|
1628 |
+
{
|
1629 |
+
"epoch": 9.28,
|
1630 |
+
"grad_norm": 1.3177443742752075,
|
1631 |
+
"learning_rate": 0.0002,
|
1632 |
+
"loss": 0.8223,
|
1633 |
+
"step": 23200
|
1634 |
+
},
|
1635 |
+
{
|
1636 |
+
"epoch": 9.32,
|
1637 |
+
"grad_norm": 4.67700719833374,
|
1638 |
+
"learning_rate": 0.0002,
|
1639 |
+
"loss": 0.8154,
|
1640 |
+
"step": 23300
|
1641 |
+
},
|
1642 |
+
{
|
1643 |
+
"epoch": 9.36,
|
1644 |
+
"grad_norm": 1.2279400825500488,
|
1645 |
+
"learning_rate": 0.0002,
|
1646 |
+
"loss": 0.8047,
|
1647 |
+
"step": 23400
|
1648 |
+
},
|
1649 |
+
{
|
1650 |
+
"epoch": 9.4,
|
1651 |
+
"grad_norm": 0.6378070712089539,
|
1652 |
+
"learning_rate": 0.0002,
|
1653 |
+
"loss": 0.8539,
|
1654 |
+
"step": 23500
|
1655 |
+
},
|
1656 |
+
{
|
1657 |
+
"epoch": 9.44,
|
1658 |
+
"grad_norm": 1.7342982292175293,
|
1659 |
+
"learning_rate": 0.0002,
|
1660 |
+
"loss": 0.8405,
|
1661 |
+
"step": 23600
|
1662 |
+
},
|
1663 |
+
{
|
1664 |
+
"epoch": 9.48,
|
1665 |
+
"grad_norm": 1.534493088722229,
|
1666 |
+
"learning_rate": 0.0002,
|
1667 |
+
"loss": 0.8493,
|
1668 |
+
"step": 23700
|
1669 |
+
},
|
1670 |
+
{
|
1671 |
+
"epoch": 9.52,
|
1672 |
+
"grad_norm": 1.0669933557510376,
|
1673 |
+
"learning_rate": 0.0002,
|
1674 |
+
"loss": 0.8931,
|
1675 |
+
"step": 23800
|
1676 |
+
},
|
1677 |
+
{
|
1678 |
+
"epoch": 9.56,
|
1679 |
+
"grad_norm": 1.2402708530426025,
|
1680 |
+
"learning_rate": 0.0002,
|
1681 |
+
"loss": 0.8689,
|
1682 |
+
"step": 23900
|
1683 |
+
},
|
1684 |
+
{
|
1685 |
+
"epoch": 9.6,
|
1686 |
+
"grad_norm": 1.2599835395812988,
|
1687 |
+
"learning_rate": 0.0002,
|
1688 |
+
"loss": 0.8733,
|
1689 |
+
"step": 24000
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 9.64,
|
1693 |
+
"grad_norm": 2.5779175758361816,
|
1694 |
+
"learning_rate": 0.0002,
|
1695 |
+
"loss": 0.8934,
|
1696 |
+
"step": 24100
|
1697 |
+
},
|
1698 |
+
{
|
1699 |
+
"epoch": 9.68,
|
1700 |
+
"grad_norm": 1.8797070980072021,
|
1701 |
+
"learning_rate": 0.0002,
|
1702 |
+
"loss": 0.8536,
|
1703 |
+
"step": 24200
|
1704 |
+
},
|
1705 |
+
{
|
1706 |
+
"epoch": 9.72,
|
1707 |
+
"grad_norm": 1.3404995203018188,
|
1708 |
+
"learning_rate": 0.0002,
|
1709 |
+
"loss": 0.9191,
|
1710 |
+
"step": 24300
|
1711 |
+
},
|
1712 |
+
{
|
1713 |
+
"epoch": 9.76,
|
1714 |
+
"grad_norm": 1.4789234399795532,
|
1715 |
+
"learning_rate": 0.0002,
|
1716 |
+
"loss": 0.8198,
|
1717 |
+
"step": 24400
|
1718 |
+
},
|
1719 |
+
{
|
1720 |
+
"epoch": 9.8,
|
1721 |
+
"grad_norm": 0.6044953465461731,
|
1722 |
+
"learning_rate": 0.0002,
|
1723 |
+
"loss": 0.8304,
|
1724 |
+
"step": 24500
|
1725 |
+
},
|
1726 |
+
{
|
1727 |
+
"epoch": 9.84,
|
1728 |
+
"grad_norm": 1.2792354822158813,
|
1729 |
+
"learning_rate": 0.0002,
|
1730 |
+
"loss": 0.9196,
|
1731 |
+
"step": 24600
|
1732 |
+
},
|
1733 |
+
{
|
1734 |
+
"epoch": 9.88,
|
1735 |
+
"grad_norm": 2.047617197036743,
|
1736 |
+
"learning_rate": 0.0002,
|
1737 |
+
"loss": 0.9136,
|
1738 |
+
"step": 24700
|
1739 |
+
},
|
1740 |
+
{
|
1741 |
+
"epoch": 9.92,
|
1742 |
+
"grad_norm": 5.776161193847656,
|
1743 |
+
"learning_rate": 0.0002,
|
1744 |
+
"loss": 0.8715,
|
1745 |
+
"step": 24800
|
1746 |
+
},
|
1747 |
+
{
|
1748 |
+
"epoch": 9.96,
|
1749 |
+
"grad_norm": 1.9059360027313232,
|
1750 |
+
"learning_rate": 0.0002,
|
1751 |
+
"loss": 0.8712,
|
1752 |
+
"step": 24900
|
1753 |
+
},
|
1754 |
+
{
|
1755 |
+
"epoch": 10.0,
|
1756 |
+
"grad_norm": 1.1497496366500854,
|
1757 |
+
"learning_rate": 0.0002,
|
1758 |
+
"loss": 0.8607,
|
1759 |
+
"step": 25000
|
1760 |
+
},
|
1761 |
+
{
|
1762 |
+
"epoch": 10.04,
|
1763 |
+
"grad_norm": 0.6882659792900085,
|
1764 |
+
"learning_rate": 0.0002,
|
1765 |
+
"loss": 0.7556,
|
1766 |
+
"step": 25100
|
1767 |
+
},
|
1768 |
+
{
|
1769 |
+
"epoch": 10.08,
|
1770 |
+
"grad_norm": 0.9709841012954712,
|
1771 |
+
"learning_rate": 0.0002,
|
1772 |
+
"loss": 0.787,
|
1773 |
+
"step": 25200
|
1774 |
+
},
|
1775 |
+
{
|
1776 |
+
"epoch": 10.12,
|
1777 |
+
"grad_norm": 0.9609636664390564,
|
1778 |
+
"learning_rate": 0.0002,
|
1779 |
+
"loss": 0.701,
|
1780 |
+
"step": 25300
|
1781 |
+
},
|
1782 |
+
{
|
1783 |
+
"epoch": 10.16,
|
1784 |
+
"grad_norm": 1.397544026374817,
|
1785 |
+
"learning_rate": 0.0002,
|
1786 |
+
"loss": 0.7548,
|
1787 |
+
"step": 25400
|
1788 |
+
},
|
1789 |
+
{
|
1790 |
+
"epoch": 10.2,
|
1791 |
+
"grad_norm": 2.043348550796509,
|
1792 |
+
"learning_rate": 0.0002,
|
1793 |
+
"loss": 0.7357,
|
1794 |
+
"step": 25500
|
1795 |
+
},
|
1796 |
+
{
|
1797 |
+
"epoch": 10.24,
|
1798 |
+
"grad_norm": 0.7744215726852417,
|
1799 |
+
"learning_rate": 0.0002,
|
1800 |
+
"loss": 0.7481,
|
1801 |
+
"step": 25600
|
1802 |
+
},
|
1803 |
+
{
|
1804 |
+
"epoch": 10.28,
|
1805 |
+
"grad_norm": 0.7471018433570862,
|
1806 |
+
"learning_rate": 0.0002,
|
1807 |
+
"loss": 0.7206,
|
1808 |
+
"step": 25700
|
1809 |
+
},
|
1810 |
+
{
|
1811 |
+
"epoch": 10.32,
|
1812 |
+
"grad_norm": 1.5226207971572876,
|
1813 |
+
"learning_rate": 0.0002,
|
1814 |
+
"loss": 0.7199,
|
1815 |
+
"step": 25800
|
1816 |
+
},
|
1817 |
+
{
|
1818 |
+
"epoch": 10.36,
|
1819 |
+
"grad_norm": 0.9229708313941956,
|
1820 |
+
"learning_rate": 0.0002,
|
1821 |
+
"loss": 0.7449,
|
1822 |
+
"step": 25900
|
1823 |
+
},
|
1824 |
+
{
|
1825 |
+
"epoch": 10.4,
|
1826 |
+
"grad_norm": 0.8783457279205322,
|
1827 |
+
"learning_rate": 0.0002,
|
1828 |
+
"loss": 0.8026,
|
1829 |
+
"step": 26000
|
1830 |
+
},
|
1831 |
+
{
|
1832 |
+
"epoch": 10.44,
|
1833 |
+
"grad_norm": 1.858168125152588,
|
1834 |
+
"learning_rate": 0.0002,
|
1835 |
+
"loss": 0.758,
|
1836 |
+
"step": 26100
|
1837 |
+
},
|
1838 |
+
{
|
1839 |
+
"epoch": 10.48,
|
1840 |
+
"grad_norm": 9.689515113830566,
|
1841 |
+
"learning_rate": 0.0002,
|
1842 |
+
"loss": 0.7394,
|
1843 |
+
"step": 26200
|
1844 |
+
},
|
1845 |
+
{
|
1846 |
+
"epoch": 10.52,
|
1847 |
+
"grad_norm": 1.7214679718017578,
|
1848 |
+
"learning_rate": 0.0002,
|
1849 |
+
"loss": 0.7704,
|
1850 |
+
"step": 26300
|
1851 |
+
},
|
1852 |
+
{
|
1853 |
+
"epoch": 10.56,
|
1854 |
+
"grad_norm": 4.615940570831299,
|
1855 |
+
"learning_rate": 0.0002,
|
1856 |
+
"loss": 0.7957,
|
1857 |
+
"step": 26400
|
1858 |
+
},
|
1859 |
+
{
|
1860 |
+
"epoch": 10.6,
|
1861 |
+
"grad_norm": 1.4114075899124146,
|
1862 |
+
"learning_rate": 0.0002,
|
1863 |
+
"loss": 0.7613,
|
1864 |
+
"step": 26500
|
1865 |
+
},
|
1866 |
+
{
|
1867 |
+
"epoch": 10.64,
|
1868 |
+
"grad_norm": 1.1253297328948975,
|
1869 |
+
"learning_rate": 0.0002,
|
1870 |
+
"loss": 0.8119,
|
1871 |
+
"step": 26600
|
1872 |
+
},
|
1873 |
+
{
|
1874 |
+
"epoch": 10.68,
|
1875 |
+
"grad_norm": 1.9775581359863281,
|
1876 |
+
"learning_rate": 0.0002,
|
1877 |
+
"loss": 0.8083,
|
1878 |
+
"step": 26700
|
1879 |
+
},
|
1880 |
+
{
|
1881 |
+
"epoch": 10.72,
|
1882 |
+
"grad_norm": 0.6344081163406372,
|
1883 |
+
"learning_rate": 0.0002,
|
1884 |
+
"loss": 0.8078,
|
1885 |
+
"step": 26800
|
1886 |
+
},
|
1887 |
+
{
|
1888 |
+
"epoch": 10.76,
|
1889 |
+
"grad_norm": 1.287255048751831,
|
1890 |
+
"learning_rate": 0.0002,
|
1891 |
+
"loss": 0.7732,
|
1892 |
+
"step": 26900
|
1893 |
+
},
|
1894 |
+
{
|
1895 |
+
"epoch": 10.8,
|
1896 |
+
"grad_norm": 0.826394259929657,
|
1897 |
+
"learning_rate": 0.0002,
|
1898 |
+
"loss": 0.7874,
|
1899 |
+
"step": 27000
|
1900 |
+
},
|
1901 |
+
{
|
1902 |
+
"epoch": 10.84,
|
1903 |
+
"grad_norm": 1.9858311414718628,
|
1904 |
+
"learning_rate": 0.0002,
|
1905 |
+
"loss": 0.7672,
|
1906 |
+
"step": 27100
|
1907 |
+
},
|
1908 |
+
{
|
1909 |
+
"epoch": 10.88,
|
1910 |
+
"grad_norm": 2.411587715148926,
|
1911 |
+
"learning_rate": 0.0002,
|
1912 |
+
"loss": 0.7926,
|
1913 |
+
"step": 27200
|
1914 |
+
},
|
1915 |
+
{
|
1916 |
+
"epoch": 10.92,
|
1917 |
+
"grad_norm": 1.1117106676101685,
|
1918 |
+
"learning_rate": 0.0002,
|
1919 |
+
"loss": 0.8031,
|
1920 |
+
"step": 27300
|
1921 |
+
},
|
1922 |
+
{
|
1923 |
+
"epoch": 10.96,
|
1924 |
+
"grad_norm": 0.9955012798309326,
|
1925 |
+
"learning_rate": 0.0002,
|
1926 |
+
"loss": 0.8018,
|
1927 |
+
"step": 27400
|
1928 |
+
},
|
1929 |
+
{
|
1930 |
+
"epoch": 11.0,
|
1931 |
+
"grad_norm": 6.443946838378906,
|
1932 |
+
"learning_rate": 0.0002,
|
1933 |
+
"loss": 0.7974,
|
1934 |
+
"step": 27500
|
1935 |
+
},
|
1936 |
+
{
|
1937 |
+
"epoch": 11.04,
|
1938 |
+
"grad_norm": 0.9066771864891052,
|
1939 |
+
"learning_rate": 0.0002,
|
1940 |
+
"loss": 0.6354,
|
1941 |
+
"step": 27600
|
1942 |
+
},
|
1943 |
+
{
|
1944 |
+
"epoch": 11.08,
|
1945 |
+
"grad_norm": 1.2832303047180176,
|
1946 |
+
"learning_rate": 0.0002,
|
1947 |
+
"loss": 0.6669,
|
1948 |
+
"step": 27700
|
1949 |
+
},
|
1950 |
+
{
|
1951 |
+
"epoch": 11.12,
|
1952 |
+
"grad_norm": 1.3047817945480347,
|
1953 |
+
"learning_rate": 0.0002,
|
1954 |
+
"loss": 0.6408,
|
1955 |
+
"step": 27800
|
1956 |
+
},
|
1957 |
+
{
|
1958 |
+
"epoch": 11.16,
|
1959 |
+
"grad_norm": 1.2970690727233887,
|
1960 |
+
"learning_rate": 0.0002,
|
1961 |
+
"loss": 0.6777,
|
1962 |
+
"step": 27900
|
1963 |
+
},
|
1964 |
+
{
|
1965 |
+
"epoch": 11.2,
|
1966 |
+
"grad_norm": 1.2775633335113525,
|
1967 |
+
"learning_rate": 0.0002,
|
1968 |
+
"loss": 0.6366,
|
1969 |
+
"step": 28000
|
1970 |
+
},
|
1971 |
+
{
|
1972 |
+
"epoch": 11.24,
|
1973 |
+
"grad_norm": 1.1797577142715454,
|
1974 |
+
"learning_rate": 0.0002,
|
1975 |
+
"loss": 0.6618,
|
1976 |
+
"step": 28100
|
1977 |
+
},
|
1978 |
+
{
|
1979 |
+
"epoch": 11.28,
|
1980 |
+
"grad_norm": 0.4641984701156616,
|
1981 |
+
"learning_rate": 0.0002,
|
1982 |
+
"loss": 0.714,
|
1983 |
+
"step": 28200
|
1984 |
+
},
|
1985 |
+
{
|
1986 |
+
"epoch": 11.32,
|
1987 |
+
"grad_norm": 5.440238952636719,
|
1988 |
+
"learning_rate": 0.0002,
|
1989 |
+
"loss": 0.707,
|
1990 |
+
"step": 28300
|
1991 |
+
},
|
1992 |
+
{
|
1993 |
+
"epoch": 11.36,
|
1994 |
+
"grad_norm": 2.7342915534973145,
|
1995 |
+
"learning_rate": 0.0002,
|
1996 |
+
"loss": 0.7155,
|
1997 |
+
"step": 28400
|
1998 |
+
},
|
1999 |
+
{
|
2000 |
+
"epoch": 11.4,
|
2001 |
+
"grad_norm": 1.025922179222107,
|
2002 |
+
"learning_rate": 0.0002,
|
2003 |
+
"loss": 0.6761,
|
2004 |
+
"step": 28500
|
2005 |
+
},
|
2006 |
+
{
|
2007 |
+
"epoch": 11.44,
|
2008 |
+
"grad_norm": 1.4162850379943848,
|
2009 |
+
"learning_rate": 0.0002,
|
2010 |
+
"loss": 0.7079,
|
2011 |
+
"step": 28600
|
2012 |
+
},
|
2013 |
+
{
|
2014 |
+
"epoch": 11.48,
|
2015 |
+
"grad_norm": 1.673281192779541,
|
2016 |
+
"learning_rate": 0.0002,
|
2017 |
+
"loss": 0.6957,
|
2018 |
+
"step": 28700
|
2019 |
+
},
|
2020 |
+
{
|
2021 |
+
"epoch": 11.52,
|
2022 |
+
"grad_norm": 1.6640900373458862,
|
2023 |
+
"learning_rate": 0.0002,
|
2024 |
+
"loss": 0.7616,
|
2025 |
+
"step": 28800
|
2026 |
+
},
|
2027 |
+
{
|
2028 |
+
"epoch": 11.56,
|
2029 |
+
"grad_norm": 0.5658434629440308,
|
2030 |
+
"learning_rate": 0.0002,
|
2031 |
+
"loss": 0.6939,
|
2032 |
+
"step": 28900
|
2033 |
+
},
|
2034 |
+
{
|
2035 |
+
"epoch": 11.6,
|
2036 |
+
"grad_norm": 0.6061828136444092,
|
2037 |
+
"learning_rate": 0.0002,
|
2038 |
+
"loss": 0.7162,
|
2039 |
+
"step": 29000
|
2040 |
+
},
|
2041 |
+
{
|
2042 |
+
"epoch": 11.64,
|
2043 |
+
"grad_norm": 1.6504275798797607,
|
2044 |
+
"learning_rate": 0.0002,
|
2045 |
+
"loss": 0.7266,
|
2046 |
+
"step": 29100
|
2047 |
+
},
|
2048 |
+
{
|
2049 |
+
"epoch": 11.68,
|
2050 |
+
"grad_norm": 2.936732530593872,
|
2051 |
+
"learning_rate": 0.0002,
|
2052 |
+
"loss": 0.7053,
|
2053 |
+
"step": 29200
|
2054 |
+
},
|
2055 |
+
{
|
2056 |
+
"epoch": 11.72,
|
2057 |
+
"grad_norm": 1.2476632595062256,
|
2058 |
+
"learning_rate": 0.0002,
|
2059 |
+
"loss": 0.6966,
|
2060 |
+
"step": 29300
|
2061 |
+
},
|
2062 |
+
{
|
2063 |
+
"epoch": 11.76,
|
2064 |
+
"grad_norm": 0.8274354934692383,
|
2065 |
+
"learning_rate": 0.0002,
|
2066 |
+
"loss": 0.6928,
|
2067 |
+
"step": 29400
|
2068 |
+
},
|
2069 |
+
{
|
2070 |
+
"epoch": 11.8,
|
2071 |
+
"grad_norm": 1.6214333772659302,
|
2072 |
+
"learning_rate": 0.0002,
|
2073 |
+
"loss": 0.7288,
|
2074 |
+
"step": 29500
|
2075 |
+
},
|
2076 |
+
{
|
2077 |
+
"epoch": 11.84,
|
2078 |
+
"grad_norm": 1.2420477867126465,
|
2079 |
+
"learning_rate": 0.0002,
|
2080 |
+
"loss": 0.7501,
|
2081 |
+
"step": 29600
|
2082 |
+
},
|
2083 |
+
{
|
2084 |
+
"epoch": 11.88,
|
2085 |
+
"grad_norm": 1.3407083749771118,
|
2086 |
+
"learning_rate": 0.0002,
|
2087 |
+
"loss": 0.7472,
|
2088 |
+
"step": 29700
|
2089 |
+
},
|
2090 |
+
{
|
2091 |
+
"epoch": 11.92,
|
2092 |
+
"grad_norm": 2.469486951828003,
|
2093 |
+
"learning_rate": 0.0002,
|
2094 |
+
"loss": 0.7077,
|
2095 |
+
"step": 29800
|
2096 |
+
},
|
2097 |
+
{
|
2098 |
+
"epoch": 11.96,
|
2099 |
+
"grad_norm": 2.422231912612915,
|
2100 |
+
"learning_rate": 0.0002,
|
2101 |
+
"loss": 0.7587,
|
2102 |
+
"step": 29900
|
2103 |
+
},
|
2104 |
+
{
|
2105 |
+
"epoch": 12.0,
|
2106 |
+
"grad_norm": 2.655271053314209,
|
2107 |
+
"learning_rate": 0.0002,
|
2108 |
+
"loss": 0.734,
|
2109 |
+
"step": 30000
|
2110 |
+
},
|
2111 |
+
{
|
2112 |
+
"epoch": 12.04,
|
2113 |
+
"grad_norm": 3.5966265201568604,
|
2114 |
+
"learning_rate": 0.0002,
|
2115 |
+
"loss": 0.5812,
|
2116 |
+
"step": 30100
|
2117 |
+
},
|
2118 |
+
{
|
2119 |
+
"epoch": 12.08,
|
2120 |
+
"grad_norm": 0.46480792760849,
|
2121 |
+
"learning_rate": 0.0002,
|
2122 |
+
"loss": 0.589,
|
2123 |
+
"step": 30200
|
2124 |
+
},
|
2125 |
+
{
|
2126 |
+
"epoch": 12.12,
|
2127 |
+
"grad_norm": 0.8438324928283691,
|
2128 |
+
"learning_rate": 0.0002,
|
2129 |
+
"loss": 0.6005,
|
2130 |
+
"step": 30300
|
2131 |
+
},
|
2132 |
+
{
|
2133 |
+
"epoch": 12.16,
|
2134 |
+
"grad_norm": 1.9844694137573242,
|
2135 |
+
"learning_rate": 0.0002,
|
2136 |
+
"loss": 0.6312,
|
2137 |
+
"step": 30400
|
2138 |
+
},
|
2139 |
+
{
|
2140 |
+
"epoch": 12.2,
|
2141 |
+
"grad_norm": 1.1500381231307983,
|
2142 |
+
"learning_rate": 0.0002,
|
2143 |
+
"loss": 0.621,
|
2144 |
+
"step": 30500
|
2145 |
+
},
|
2146 |
+
{
|
2147 |
+
"epoch": 12.24,
|
2148 |
+
"grad_norm": 1.3909460306167603,
|
2149 |
+
"learning_rate": 0.0002,
|
2150 |
+
"loss": 0.6353,
|
2151 |
+
"step": 30600
|
2152 |
+
},
|
2153 |
+
{
|
2154 |
+
"epoch": 12.28,
|
2155 |
+
"grad_norm": 3.504803419113159,
|
2156 |
+
"learning_rate": 0.0002,
|
2157 |
+
"loss": 0.6191,
|
2158 |
+
"step": 30700
|
2159 |
+
},
|
2160 |
+
{
|
2161 |
+
"epoch": 12.32,
|
2162 |
+
"grad_norm": 1.116080641746521,
|
2163 |
+
"learning_rate": 0.0002,
|
2164 |
+
"loss": 0.628,
|
2165 |
+
"step": 30800
|
2166 |
+
},
|
2167 |
+
{
|
2168 |
+
"epoch": 12.36,
|
2169 |
+
"grad_norm": 0.9176204800605774,
|
2170 |
+
"learning_rate": 0.0002,
|
2171 |
+
"loss": 0.6314,
|
2172 |
+
"step": 30900
|
2173 |
+
},
|
2174 |
+
{
|
2175 |
+
"epoch": 12.4,
|
2176 |
+
"grad_norm": 1.0510369539260864,
|
2177 |
+
"learning_rate": 0.0002,
|
2178 |
+
"loss": 0.6532,
|
2179 |
+
"step": 31000
|
2180 |
+
},
|
2181 |
+
{
|
2182 |
+
"epoch": 12.44,
|
2183 |
+
"grad_norm": 0.5242018103599548,
|
2184 |
+
"learning_rate": 0.0002,
|
2185 |
+
"loss": 0.6422,
|
2186 |
+
"step": 31100
|
2187 |
+
},
|
2188 |
+
{
|
2189 |
+
"epoch": 12.48,
|
2190 |
+
"grad_norm": 5.052489280700684,
|
2191 |
+
"learning_rate": 0.0002,
|
2192 |
+
"loss": 0.64,
|
2193 |
+
"step": 31200
|
2194 |
+
},
|
2195 |
+
{
|
2196 |
+
"epoch": 12.52,
|
2197 |
+
"grad_norm": 0.5426860451698303,
|
2198 |
+
"learning_rate": 0.0002,
|
2199 |
+
"loss": 0.6488,
|
2200 |
+
"step": 31300
|
2201 |
+
},
|
2202 |
+
{
|
2203 |
+
"epoch": 12.56,
|
2204 |
+
"grad_norm": 0.7503352165222168,
|
2205 |
+
"learning_rate": 0.0002,
|
2206 |
+
"loss": 0.6764,
|
2207 |
+
"step": 31400
|
2208 |
+
},
|
2209 |
+
{
|
2210 |
+
"epoch": 12.6,
|
2211 |
+
"grad_norm": 2.2711548805236816,
|
2212 |
+
"learning_rate": 0.0002,
|
2213 |
+
"loss": 0.6177,
|
2214 |
+
"step": 31500
|
2215 |
+
},
|
2216 |
+
{
|
2217 |
+
"epoch": 12.64,
|
2218 |
+
"grad_norm": 1.3384021520614624,
|
2219 |
+
"learning_rate": 0.0002,
|
2220 |
+
"loss": 0.6425,
|
2221 |
+
"step": 31600
|
2222 |
+
},
|
2223 |
+
{
|
2224 |
+
"epoch": 12.68,
|
2225 |
+
"grad_norm": 1.098314642906189,
|
2226 |
+
"learning_rate": 0.0002,
|
2227 |
+
"loss": 0.6453,
|
2228 |
+
"step": 31700
|
2229 |
+
},
|
2230 |
+
{
|
2231 |
+
"epoch": 12.72,
|
2232 |
+
"grad_norm": 0.8752951622009277,
|
2233 |
+
"learning_rate": 0.0002,
|
2234 |
+
"loss": 0.6724,
|
2235 |
+
"step": 31800
|
2236 |
+
},
|
2237 |
+
{
|
2238 |
+
"epoch": 12.76,
|
2239 |
+
"grad_norm": 1.700907826423645,
|
2240 |
+
"learning_rate": 0.0002,
|
2241 |
+
"loss": 0.6707,
|
2242 |
+
"step": 31900
|
2243 |
+
},
|
2244 |
+
{
|
2245 |
+
"epoch": 12.8,
|
2246 |
+
"grad_norm": 2.7010860443115234,
|
2247 |
+
"learning_rate": 0.0002,
|
2248 |
+
"loss": 0.6551,
|
2249 |
+
"step": 32000
|
2250 |
+
},
|
2251 |
+
{
|
2252 |
+
"epoch": 12.84,
|
2253 |
+
"grad_norm": 0.9509829878807068,
|
2254 |
+
"learning_rate": 0.0002,
|
2255 |
+
"loss": 0.6766,
|
2256 |
+
"step": 32100
|
2257 |
+
},
|
2258 |
+
{
|
2259 |
+
"epoch": 12.88,
|
2260 |
+
"grad_norm": 1.8936227560043335,
|
2261 |
+
"learning_rate": 0.0002,
|
2262 |
+
"loss": 0.6889,
|
2263 |
+
"step": 32200
|
2264 |
+
},
|
2265 |
+
{
|
2266 |
+
"epoch": 12.92,
|
2267 |
+
"grad_norm": 3.870959997177124,
|
2268 |
+
"learning_rate": 0.0002,
|
2269 |
+
"loss": 0.6526,
|
2270 |
+
"step": 32300
|
2271 |
+
},
|
2272 |
+
{
|
2273 |
+
"epoch": 12.96,
|
2274 |
+
"grad_norm": 0.8048538565635681,
|
2275 |
+
"learning_rate": 0.0002,
|
2276 |
+
"loss": 0.6658,
|
2277 |
+
"step": 32400
|
2278 |
+
},
|
2279 |
+
{
|
2280 |
+
"epoch": 13.0,
|
2281 |
+
"grad_norm": 3.0256259441375732,
|
2282 |
+
"learning_rate": 0.0002,
|
2283 |
+
"loss": 0.6521,
|
2284 |
+
"step": 32500
|
2285 |
+
},
|
2286 |
+
{
|
2287 |
+
"epoch": 13.04,
|
2288 |
+
"grad_norm": 0.5219417810440063,
|
2289 |
+
"learning_rate": 0.0002,
|
2290 |
+
"loss": 0.5415,
|
2291 |
+
"step": 32600
|
2292 |
+
},
|
2293 |
+
{
|
2294 |
+
"epoch": 13.08,
|
2295 |
+
"grad_norm": 0.6729668378829956,
|
2296 |
+
"learning_rate": 0.0002,
|
2297 |
+
"loss": 0.5442,
|
2298 |
+
"step": 32700
|
2299 |
+
},
|
2300 |
+
{
|
2301 |
+
"epoch": 13.12,
|
2302 |
+
"grad_norm": 5.041486740112305,
|
2303 |
+
"learning_rate": 0.0002,
|
2304 |
+
"loss": 0.5794,
|
2305 |
+
"step": 32800
|
2306 |
+
},
|
2307 |
+
{
|
2308 |
+
"epoch": 13.16,
|
2309 |
+
"grad_norm": 0.7740932106971741,
|
2310 |
+
"learning_rate": 0.0002,
|
2311 |
+
"loss": 0.5739,
|
2312 |
+
"step": 32900
|
2313 |
+
},
|
2314 |
+
{
|
2315 |
+
"epoch": 13.2,
|
2316 |
+
"grad_norm": 2.4038619995117188,
|
2317 |
+
"learning_rate": 0.0002,
|
2318 |
+
"loss": 0.5527,
|
2319 |
+
"step": 33000
|
2320 |
+
}
|
2321 |
+
],
|
2322 |
+
"logging_steps": 100,
|
2323 |
+
"max_steps": 125000,
|
2324 |
+
"num_input_tokens_seen": 0,
|
2325 |
+
"num_train_epochs": 50,
|
2326 |
+
"save_steps": 1000,
|
2327 |
+
"stateful_callbacks": {
|
2328 |
+
"TrainerControl": {
|
2329 |
+
"args": {
|
2330 |
+
"should_epoch_stop": false,
|
2331 |
+
"should_evaluate": false,
|
2332 |
+
"should_log": false,
|
2333 |
+
"should_save": true,
|
2334 |
+
"should_training_stop": false
|
2335 |
+
},
|
2336 |
+
"attributes": {}
|
2337 |
+
}
|
2338 |
+
},
|
2339 |
+
"total_flos": 8.330326307619963e+17,
|
2340 |
+
"train_batch_size": 1,
|
2341 |
+
"trial_name": null,
|
2342 |
+
"trial_params": null
|
2343 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac982738137bca95e983e2664b44706868ba9f325f35c6d86a395d9ee7674069
|
3 |
+
size 5368
|