Hugging Face's logo

FINGU-AI
/
Qwen2.5-32B-3000

PEFT
Safetensors
qwen2
Model card Files
xet
 Community
1
FINGU-AI commited on
Commit
4578f05
·
verified ·
1 Parent(s): 4174988

Upload folder using huggingface_hub

Browse files
Files changed (18) hide show
  1. .gitattributes +1 -0
  2. README.md +202 -3
  3. adapter_config.json +37 -0
  4. adapter_model.safetensors +3 -0
  5. added_tokens.json +24 -0
  6. merges.txt +0 -0
  7. optimizer.pt +3 -0
  8. rng_state_0.pth +3 -0
  9. rng_state_1.pth +3 -0
  10. rng_state_2.pth +3 -0
  11. rng_state_3.pth +3 -0
  12. scheduler.pt +3 -0
  13. special_tokens_map.json +32 -0
  14. tokenizer.json +3 -0
  15. tokenizer_config.json +208 -0
  16. trainer_state.json +2921 -0
  17. training_args.bin +3 -0
  18. vocab.json +0 -0
.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 CHANGED
@@ -1,3 +1,202 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-32B-Instruct
3
+ library_name: peft
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 0.14.0
adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-32B-Instruct",
5
+ "bias": "none",
6
+ "eva_config": null,
7
+ "exclude_modules": null,
8
+ "fan_in_fan_out": false,
9
+ "inference_mode": true,
10
+ "init_lora_weights": true,
11
+ "layer_replication": null,
12
+ "layers_pattern": null,
13
+ "layers_to_transform": null,
14
+ "loftq_config": {},
15
+ "lora_alpha": 32,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 32,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "gate_proj",
27
+ "up_proj",
28
+ "o_proj",
29
+ "k_proj",
30
+ "v_proj",
31
+ "down_proj",
32
+ "q_proj"
33
+ ],
34
+ "task_type": "CAUSAL_LM",
35
+ "use_dora": false,
36
+ "use_rslora": false
37
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:386949c36fe1a64abca6fcf3fa0126e1c8ad22fec172ea73c6bba480438cf597
3
+ size 1073863208
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47278a9b0c4d0d43ad98088dd8af050a61fd782c33a0f5489dc9fbb199588a03
3
+ size 2148241810
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:304ea729d1101e4b5081d298c4787f6e44d8eb835c3cfcd793c8528a3890d070
3
+ size 14960
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ed1b050b0403dca8776d7c71a5870865e5fef8759b67c995af6ebe4ed004d8b
3
+ size 14960
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1920ce4c262b018adbd7092eebe5728a603bae119f0d088f7fd201aef8b17e16
3
+ size 14960
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c31f7e6e7930a095327c50eba06bc3a414b966eb5621f17423b678b4ddf0ebb6
3
+ size 14960
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5722287aa0c035b931cf86a8af54e34e8eb46745bc11ec7e0098100f1598fc4
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "bos_token": "<|im_start|>",
18
+ "eos_token": {
19
+ "content": "<|im_end|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "pad_token": {
26
+ "content": "<|endoftext|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ }
32
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eccfe8446b814d6120eec3f96528c1faf44f51410f2524c11cac30fda10c9ee9
3
+ size 11421896
tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": false
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": "<|im_start|>",
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "extra_special_tokens": {},
203
+ "model_max_length": 131072,
204
+ "pad_token": "<|endoftext|>",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
trainer_state.json ADDED
@@ -0,0 +1,2921 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.934950385887541,
5
+ "eval_steps": 50,
6
+ "global_step": 3360,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01470047776552738,
13
+ "grad_norm": 0.5667821168899536,
14
+ "learning_rate": 0.0003,
15
+ "loss": 14.1829,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.02940095553105476,
20
+ "grad_norm": 0.34381482005119324,
21
+ "learning_rate": 0.0002995581737849779,
22
+ "loss": 10.6392,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.044101433296582136,
27
+ "grad_norm": 0.4359741806983948,
28
+ "learning_rate": 0.00029911634756995577,
29
+ "loss": 9.822,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.05880191106210952,
34
+ "grad_norm": 0.4812168478965759,
35
+ "learning_rate": 0.0002986745213549337,
36
+ "loss": 9.5543,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.07350238882763689,
41
+ "grad_norm": 0.5038645267486572,
42
+ "learning_rate": 0.0002982326951399116,
43
+ "loss": 9.2649,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.07350238882763689,
48
+ "eval_loss": 1.1481549739837646,
49
+ "eval_runtime": 122.7544,
50
+ "eval_samples_per_second": 7.079,
51
+ "eval_steps_per_second": 0.888,
52
+ "step": 50
53
+ },
54
+ {
55
+ "epoch": 0.08820286659316427,
56
+ "grad_norm": 0.5140169858932495,
57
+ "learning_rate": 0.00029779086892488954,
58
+ "loss": 9.0792,
59
+ "step": 60
60
+ },
61
+ {
62
+ "epoch": 0.10290334435869165,
63
+ "grad_norm": 0.5402693152427673,
64
+ "learning_rate": 0.0002973490427098674,
65
+ "loss": 8.9419,
66
+ "step": 70
67
+ },
68
+ {
69
+ "epoch": 0.11760382212421903,
70
+ "grad_norm": 0.5764286518096924,
71
+ "learning_rate": 0.00029690721649484533,
72
+ "loss": 8.8216,
73
+ "step": 80
74
+ },
75
+ {
76
+ "epoch": 0.13230429988974643,
77
+ "grad_norm": 0.5907140374183655,
78
+ "learning_rate": 0.00029646539027982326,
79
+ "loss": 8.7672,
80
+ "step": 90
81
+ },
82
+ {
83
+ "epoch": 0.14700477765527378,
84
+ "grad_norm": 0.6670350432395935,
85
+ "learning_rate": 0.0002960235640648012,
86
+ "loss": 8.6517,
87
+ "step": 100
88
+ },
89
+ {
90
+ "epoch": 0.14700477765527378,
91
+ "eval_loss": 1.0773104429244995,
92
+ "eval_runtime": 122.6477,
93
+ "eval_samples_per_second": 7.085,
94
+ "eval_steps_per_second": 0.889,
95
+ "step": 100
96
+ },
97
+ {
98
+ "epoch": 0.16170525542080116,
99
+ "grad_norm": 0.6163733601570129,
100
+ "learning_rate": 0.00029558173784977905,
101
+ "loss": 8.514,
102
+ "step": 110
103
+ },
104
+ {
105
+ "epoch": 0.17640573318632854,
106
+ "grad_norm": 0.6671579480171204,
107
+ "learning_rate": 0.000295139911634757,
108
+ "loss": 8.453,
109
+ "step": 120
110
+ },
111
+ {
112
+ "epoch": 0.19110621095185593,
113
+ "grad_norm": 0.6266494989395142,
114
+ "learning_rate": 0.00029469808541973485,
115
+ "loss": 8.432,
116
+ "step": 130
117
+ },
118
+ {
119
+ "epoch": 0.2058066887173833,
120
+ "grad_norm": 0.6384584307670593,
121
+ "learning_rate": 0.00029425625920471277,
122
+ "loss": 8.4165,
123
+ "step": 140
124
+ },
125
+ {
126
+ "epoch": 0.2205071664829107,
127
+ "grad_norm": 0.6454419493675232,
128
+ "learning_rate": 0.0002938144329896907,
129
+ "loss": 8.3296,
130
+ "step": 150
131
+ },
132
+ {
133
+ "epoch": 0.2205071664829107,
134
+ "eval_loss": 1.0390021800994873,
135
+ "eval_runtime": 122.6855,
136
+ "eval_samples_per_second": 7.083,
137
+ "eval_steps_per_second": 0.888,
138
+ "step": 150
139
+ },
140
+ {
141
+ "epoch": 0.23520764424843807,
142
+ "grad_norm": 0.7196301817893982,
143
+ "learning_rate": 0.0002933726067746686,
144
+ "loss": 8.3398,
145
+ "step": 160
146
+ },
147
+ {
148
+ "epoch": 0.24990812201396545,
149
+ "grad_norm": 0.6549277305603027,
150
+ "learning_rate": 0.0002929307805596465,
151
+ "loss": 8.2129,
152
+ "step": 170
153
+ },
154
+ {
155
+ "epoch": 0.26460859977949286,
156
+ "grad_norm": 0.7620148062705994,
157
+ "learning_rate": 0.0002924889543446244,
158
+ "loss": 8.1606,
159
+ "step": 180
160
+ },
161
+ {
162
+ "epoch": 0.2793090775450202,
163
+ "grad_norm": 0.7137699723243713,
164
+ "learning_rate": 0.00029204712812960234,
165
+ "loss": 8.149,
166
+ "step": 190
167
+ },
168
+ {
169
+ "epoch": 0.29400955531054757,
170
+ "grad_norm": 0.8829444050788879,
171
+ "learning_rate": 0.00029160530191458026,
172
+ "loss": 8.1411,
173
+ "step": 200
174
+ },
175
+ {
176
+ "epoch": 0.29400955531054757,
177
+ "eval_loss": 1.013519048690796,
178
+ "eval_runtime": 122.7693,
179
+ "eval_samples_per_second": 7.078,
180
+ "eval_steps_per_second": 0.888,
181
+ "step": 200
182
+ },
183
+ {
184
+ "epoch": 0.308710033076075,
185
+ "grad_norm": 0.7682989239692688,
186
+ "learning_rate": 0.00029116347569955813,
187
+ "loss": 8.0776,
188
+ "step": 210
189
+ },
190
+ {
191
+ "epoch": 0.32341051084160233,
192
+ "grad_norm": 0.7389448285102844,
193
+ "learning_rate": 0.00029072164948453606,
194
+ "loss": 8.0282,
195
+ "step": 220
196
+ },
197
+ {
198
+ "epoch": 0.33811098860712974,
199
+ "grad_norm": 0.6548839211463928,
200
+ "learning_rate": 0.000290279823269514,
201
+ "loss": 7.9301,
202
+ "step": 230
203
+ },
204
+ {
205
+ "epoch": 0.3528114663726571,
206
+ "grad_norm": 0.6590954065322876,
207
+ "learning_rate": 0.0002898379970544919,
208
+ "loss": 7.9751,
209
+ "step": 240
210
+ },
211
+ {
212
+ "epoch": 0.3675119441381845,
213
+ "grad_norm": 0.6717875003814697,
214
+ "learning_rate": 0.0002893961708394698,
215
+ "loss": 7.9119,
216
+ "step": 250
217
+ },
218
+ {
219
+ "epoch": 0.3675119441381845,
220
+ "eval_loss": 0.9925356507301331,
221
+ "eval_runtime": 122.9342,
222
+ "eval_samples_per_second": 7.069,
223
+ "eval_steps_per_second": 0.887,
224
+ "step": 250
225
+ },
226
+ {
227
+ "epoch": 0.38221242190371185,
228
+ "grad_norm": 0.7246499061584473,
229
+ "learning_rate": 0.0002889543446244477,
230
+ "loss": 7.967,
231
+ "step": 260
232
+ },
233
+ {
234
+ "epoch": 0.39691289966923926,
235
+ "grad_norm": 0.6811556220054626,
236
+ "learning_rate": 0.0002885125184094256,
237
+ "loss": 7.8876,
238
+ "step": 270
239
+ },
240
+ {
241
+ "epoch": 0.4116133774347666,
242
+ "grad_norm": 0.6982465386390686,
243
+ "learning_rate": 0.0002880706921944035,
244
+ "loss": 7.7926,
245
+ "step": 280
246
+ },
247
+ {
248
+ "epoch": 0.426313855200294,
249
+ "grad_norm": 0.7146357893943787,
250
+ "learning_rate": 0.0002876288659793814,
251
+ "loss": 7.8198,
252
+ "step": 290
253
+ },
254
+ {
255
+ "epoch": 0.4410143329658214,
256
+ "grad_norm": 0.6905196309089661,
257
+ "learning_rate": 0.00028718703976435934,
258
+ "loss": 7.8613,
259
+ "step": 300
260
+ },
261
+ {
262
+ "epoch": 0.4410143329658214,
263
+ "eval_loss": 0.9757246971130371,
264
+ "eval_runtime": 122.6633,
265
+ "eval_samples_per_second": 7.084,
266
+ "eval_steps_per_second": 0.889,
267
+ "step": 300
268
+ },
269
+ {
270
+ "epoch": 0.4557148107313488,
271
+ "grad_norm": 0.7458569407463074,
272
+ "learning_rate": 0.00028674521354933726,
273
+ "loss": 7.753,
274
+ "step": 310
275
+ },
276
+ {
277
+ "epoch": 0.47041528849687614,
278
+ "grad_norm": 0.6701686382293701,
279
+ "learning_rate": 0.00028630338733431513,
280
+ "loss": 7.7493,
281
+ "step": 320
282
+ },
283
+ {
284
+ "epoch": 0.48511576626240355,
285
+ "grad_norm": 0.6544702053070068,
286
+ "learning_rate": 0.00028586156111929306,
287
+ "loss": 7.7707,
288
+ "step": 330
289
+ },
290
+ {
291
+ "epoch": 0.4998162440279309,
292
+ "grad_norm": 0.7933269739151001,
293
+ "learning_rate": 0.00028541973490427093,
294
+ "loss": 7.6491,
295
+ "step": 340
296
+ },
297
+ {
298
+ "epoch": 0.5145167217934583,
299
+ "grad_norm": 0.9241804480552673,
300
+ "learning_rate": 0.00028497790868924885,
301
+ "loss": 7.654,
302
+ "step": 350
303
+ },
304
+ {
305
+ "epoch": 0.5145167217934583,
306
+ "eval_loss": 0.9614924788475037,
307
+ "eval_runtime": 122.7436,
308
+ "eval_samples_per_second": 7.08,
309
+ "eval_steps_per_second": 0.888,
310
+ "step": 350
311
+ },
312
+ {
313
+ "epoch": 0.5292171995589857,
314
+ "grad_norm": 0.7038714289665222,
315
+ "learning_rate": 0.0002845360824742268,
316
+ "loss": 7.6464,
317
+ "step": 360
318
+ },
319
+ {
320
+ "epoch": 0.543917677324513,
321
+ "grad_norm": 0.6981613636016846,
322
+ "learning_rate": 0.0002840942562592047,
323
+ "loss": 7.7035,
324
+ "step": 370
325
+ },
326
+ {
327
+ "epoch": 0.5586181550900404,
328
+ "grad_norm": 0.7330546379089355,
329
+ "learning_rate": 0.00028365243004418257,
330
+ "loss": 7.5588,
331
+ "step": 380
332
+ },
333
+ {
334
+ "epoch": 0.5733186328555678,
335
+ "grad_norm": 0.7032233476638794,
336
+ "learning_rate": 0.0002832106038291605,
337
+ "loss": 7.558,
338
+ "step": 390
339
+ },
340
+ {
341
+ "epoch": 0.5880191106210951,
342
+ "grad_norm": 0.6604267358779907,
343
+ "learning_rate": 0.0002827687776141384,
344
+ "loss": 7.5529,
345
+ "step": 400
346
+ },
347
+ {
348
+ "epoch": 0.5880191106210951,
349
+ "eval_loss": 0.9492942094802856,
350
+ "eval_runtime": 122.7734,
351
+ "eval_samples_per_second": 7.078,
352
+ "eval_steps_per_second": 0.888,
353
+ "step": 400
354
+ },
355
+ {
356
+ "epoch": 0.6027195883866225,
357
+ "grad_norm": 0.6671615839004517,
358
+ "learning_rate": 0.00028232695139911634,
359
+ "loss": 7.5444,
360
+ "step": 410
361
+ },
362
+ {
363
+ "epoch": 0.61742006615215,
364
+ "grad_norm": 0.8184302449226379,
365
+ "learning_rate": 0.0002818851251840942,
366
+ "loss": 7.55,
367
+ "step": 420
368
+ },
369
+ {
370
+ "epoch": 0.6321205439176774,
371
+ "grad_norm": 0.7789945006370544,
372
+ "learning_rate": 0.00028144329896907214,
373
+ "loss": 7.5528,
374
+ "step": 430
375
+ },
376
+ {
377
+ "epoch": 0.6468210216832047,
378
+ "grad_norm": 0.6673751473426819,
379
+ "learning_rate": 0.00028100147275405006,
380
+ "loss": 7.5363,
381
+ "step": 440
382
+ },
383
+ {
384
+ "epoch": 0.6615214994487321,
385
+ "grad_norm": 0.6923938989639282,
386
+ "learning_rate": 0.000280559646539028,
387
+ "loss": 7.4971,
388
+ "step": 450
389
+ },
390
+ {
391
+ "epoch": 0.6615214994487321,
392
+ "eval_loss": 0.9389350414276123,
393
+ "eval_runtime": 122.7652,
394
+ "eval_samples_per_second": 7.079,
395
+ "eval_steps_per_second": 0.888,
396
+ "step": 450
397
+ },
398
+ {
399
+ "epoch": 0.6762219772142595,
400
+ "grad_norm": 0.7583535313606262,
401
+ "learning_rate": 0.00028011782032400586,
402
+ "loss": 7.5674,
403
+ "step": 460
404
+ },
405
+ {
406
+ "epoch": 0.6909224549797869,
407
+ "grad_norm": 0.8926804065704346,
408
+ "learning_rate": 0.0002796759941089838,
409
+ "loss": 7.494,
410
+ "step": 470
411
+ },
412
+ {
413
+ "epoch": 0.7056229327453142,
414
+ "grad_norm": 0.6774755716323853,
415
+ "learning_rate": 0.0002792341678939617,
416
+ "loss": 7.4429,
417
+ "step": 480
418
+ },
419
+ {
420
+ "epoch": 0.7203234105108416,
421
+ "grad_norm": 0.7251358032226562,
422
+ "learning_rate": 0.00027879234167893963,
423
+ "loss": 7.4177,
424
+ "step": 490
425
+ },
426
+ {
427
+ "epoch": 0.735023888276369,
428
+ "grad_norm": 0.7453545928001404,
429
+ "learning_rate": 0.0002783505154639175,
430
+ "loss": 7.4214,
431
+ "step": 500
432
+ },
433
+ {
434
+ "epoch": 0.735023888276369,
435
+ "eval_loss": 0.9294928312301636,
436
+ "eval_runtime": 122.745,
437
+ "eval_samples_per_second": 7.08,
438
+ "eval_steps_per_second": 0.888,
439
+ "step": 500
440
+ },
441
+ {
442
+ "epoch": 0.7497243660418964,
443
+ "grad_norm": 0.7907696962356567,
444
+ "learning_rate": 0.0002779086892488954,
445
+ "loss": 7.4205,
446
+ "step": 510
447
+ },
448
+ {
449
+ "epoch": 0.7644248438074237,
450
+ "grad_norm": 0.8346834182739258,
451
+ "learning_rate": 0.00027746686303387335,
452
+ "loss": 7.3813,
453
+ "step": 520
454
+ },
455
+ {
456
+ "epoch": 0.7791253215729511,
457
+ "grad_norm": 0.6804636120796204,
458
+ "learning_rate": 0.0002770250368188512,
459
+ "loss": 7.381,
460
+ "step": 530
461
+ },
462
+ {
463
+ "epoch": 0.7938257993384785,
464
+ "grad_norm": 0.6866320371627808,
465
+ "learning_rate": 0.00027658321060382914,
466
+ "loss": 7.3764,
467
+ "step": 540
468
+ },
469
+ {
470
+ "epoch": 0.8085262771040059,
471
+ "grad_norm": 0.669920027256012,
472
+ "learning_rate": 0.000276141384388807,
473
+ "loss": 7.3525,
474
+ "step": 550
475
+ },
476
+ {
477
+ "epoch": 0.8085262771040059,
478
+ "eval_loss": 0.9208266735076904,
479
+ "eval_runtime": 122.7608,
480
+ "eval_samples_per_second": 7.079,
481
+ "eval_steps_per_second": 0.888,
482
+ "step": 550
483
+ },
484
+ {
485
+ "epoch": 0.8232267548695332,
486
+ "grad_norm": 0.6660575866699219,
487
+ "learning_rate": 0.00027569955817378493,
488
+ "loss": 7.3205,
489
+ "step": 560
490
+ },
491
+ {
492
+ "epoch": 0.8379272326350606,
493
+ "grad_norm": 0.6585595011711121,
494
+ "learning_rate": 0.00027525773195876286,
495
+ "loss": 7.3378,
496
+ "step": 570
497
+ },
498
+ {
499
+ "epoch": 0.852627710400588,
500
+ "grad_norm": 0.6798352003097534,
501
+ "learning_rate": 0.0002748159057437408,
502
+ "loss": 7.3742,
503
+ "step": 580
504
+ },
505
+ {
506
+ "epoch": 0.8673281881661153,
507
+ "grad_norm": 0.6834390759468079,
508
+ "learning_rate": 0.00027437407952871865,
509
+ "loss": 7.3129,
510
+ "step": 590
511
+ },
512
+ {
513
+ "epoch": 0.8820286659316428,
514
+ "grad_norm": 0.6835374236106873,
515
+ "learning_rate": 0.0002739322533136966,
516
+ "loss": 7.3155,
517
+ "step": 600
518
+ },
519
+ {
520
+ "epoch": 0.8820286659316428,
521
+ "eval_loss": 0.914364218711853,
522
+ "eval_runtime": 122.6825,
523
+ "eval_samples_per_second": 7.083,
524
+ "eval_steps_per_second": 0.888,
525
+ "step": 600
526
+ },
527
+ {
528
+ "epoch": 0.8967291436971702,
529
+ "grad_norm": 0.6754274368286133,
530
+ "learning_rate": 0.0002734904270986745,
531
+ "loss": 7.2469,
532
+ "step": 610
533
+ },
534
+ {
535
+ "epoch": 0.9114296214626976,
536
+ "grad_norm": 0.685310959815979,
537
+ "learning_rate": 0.0002730486008836524,
538
+ "loss": 7.2842,
539
+ "step": 620
540
+ },
541
+ {
542
+ "epoch": 0.9261300992282249,
543
+ "grad_norm": 0.6500253081321716,
544
+ "learning_rate": 0.0002726067746686303,
545
+ "loss": 7.2391,
546
+ "step": 630
547
+ },
548
+ {
549
+ "epoch": 0.9408305769937523,
550
+ "grad_norm": 0.6883764863014221,
551
+ "learning_rate": 0.0002721649484536082,
552
+ "loss": 7.2422,
553
+ "step": 640
554
+ },
555
+ {
556
+ "epoch": 0.9555310547592797,
557
+ "grad_norm": 0.6952683329582214,
558
+ "learning_rate": 0.00027172312223858614,
559
+ "loss": 7.2299,
560
+ "step": 650
561
+ },
562
+ {
563
+ "epoch": 0.9555310547592797,
564
+ "eval_loss": 0.9077203273773193,
565
+ "eval_runtime": 122.8456,
566
+ "eval_samples_per_second": 7.074,
567
+ "eval_steps_per_second": 0.887,
568
+ "step": 650
569
+ },
570
+ {
571
+ "epoch": 0.9702315325248071,
572
+ "grad_norm": 0.689813494682312,
573
+ "learning_rate": 0.00027128129602356407,
574
+ "loss": 7.195,
575
+ "step": 660
576
+ },
577
+ {
578
+ "epoch": 0.9849320102903344,
579
+ "grad_norm": 0.7432010173797607,
580
+ "learning_rate": 0.00027083946980854194,
581
+ "loss": 7.2269,
582
+ "step": 670
583
+ },
584
+ {
585
+ "epoch": 0.9996324880558618,
586
+ "grad_norm": 0.6559237837791443,
587
+ "learning_rate": 0.00027039764359351986,
588
+ "loss": 7.2033,
589
+ "step": 680
590
+ },
591
+ {
592
+ "epoch": 1.0132304299889747,
593
+ "grad_norm": 0.6594626307487488,
594
+ "learning_rate": 0.0002699558173784978,
595
+ "loss": 6.3891,
596
+ "step": 690
597
+ },
598
+ {
599
+ "epoch": 1.027930907754502,
600
+ "grad_norm": 0.7604880928993225,
601
+ "learning_rate": 0.0002695139911634757,
602
+ "loss": 6.9323,
603
+ "step": 700
604
+ },
605
+ {
606
+ "epoch": 1.027930907754502,
607
+ "eval_loss": 0.9017989039421082,
608
+ "eval_runtime": 122.7598,
609
+ "eval_samples_per_second": 7.079,
610
+ "eval_steps_per_second": 0.888,
611
+ "step": 700
612
+ },
613
+ {
614
+ "epoch": 1.0426313855200293,
615
+ "grad_norm": 0.6518153548240662,
616
+ "learning_rate": 0.0002690721649484536,
617
+ "loss": 6.8683,
618
+ "step": 710
619
+ },
620
+ {
621
+ "epoch": 1.0573318632855568,
622
+ "grad_norm": 0.6659955978393555,
623
+ "learning_rate": 0.0002686303387334315,
624
+ "loss": 6.8752,
625
+ "step": 720
626
+ },
627
+ {
628
+ "epoch": 1.0720323410510841,
629
+ "grad_norm": 0.6533622145652771,
630
+ "learning_rate": 0.00026818851251840943,
631
+ "loss": 6.9249,
632
+ "step": 730
633
+ },
634
+ {
635
+ "epoch": 1.0867328188166114,
636
+ "grad_norm": 0.6731697916984558,
637
+ "learning_rate": 0.00026774668630338735,
638
+ "loss": 6.8896,
639
+ "step": 740
640
+ },
641
+ {
642
+ "epoch": 1.101433296582139,
643
+ "grad_norm": 0.6576088070869446,
644
+ "learning_rate": 0.0002673048600883652,
645
+ "loss": 6.9015,
646
+ "step": 750
647
+ },
648
+ {
649
+ "epoch": 1.101433296582139,
650
+ "eval_loss": 0.8985611200332642,
651
+ "eval_runtime": 122.7501,
652
+ "eval_samples_per_second": 7.079,
653
+ "eval_steps_per_second": 0.888,
654
+ "step": 750
655
+ },
656
+ {
657
+ "epoch": 1.1161337743476663,
658
+ "grad_norm": 0.6596420407295227,
659
+ "learning_rate": 0.0002668630338733431,
660
+ "loss": 6.9081,
661
+ "step": 760
662
+ },
663
+ {
664
+ "epoch": 1.1308342521131938,
665
+ "grad_norm": 0.6679617762565613,
666
+ "learning_rate": 0.000266421207658321,
667
+ "loss": 6.8619,
668
+ "step": 770
669
+ },
670
+ {
671
+ "epoch": 1.145534729878721,
672
+ "grad_norm": 0.6485927700996399,
673
+ "learning_rate": 0.00026597938144329894,
674
+ "loss": 6.9068,
675
+ "step": 780
676
+ },
677
+ {
678
+ "epoch": 1.1602352076442484,
679
+ "grad_norm": 0.679757297039032,
680
+ "learning_rate": 0.00026553755522827686,
681
+ "loss": 6.9091,
682
+ "step": 790
683
+ },
684
+ {
685
+ "epoch": 1.1749356854097759,
686
+ "grad_norm": 0.7027860879898071,
687
+ "learning_rate": 0.00026509572901325473,
688
+ "loss": 6.9184,
689
+ "step": 800
690
+ },
691
+ {
692
+ "epoch": 1.1749356854097759,
693
+ "eval_loss": 0.8939267992973328,
694
+ "eval_runtime": 122.7304,
695
+ "eval_samples_per_second": 7.081,
696
+ "eval_steps_per_second": 0.888,
697
+ "step": 800
698
+ },
699
+ {
700
+ "epoch": 1.1896361631753032,
701
+ "grad_norm": 0.651599645614624,
702
+ "learning_rate": 0.00026465390279823266,
703
+ "loss": 6.8758,
704
+ "step": 810
705
+ },
706
+ {
707
+ "epoch": 1.2043366409408305,
708
+ "grad_norm": 0.6500714421272278,
709
+ "learning_rate": 0.0002642120765832106,
710
+ "loss": 6.8177,
711
+ "step": 820
712
+ },
713
+ {
714
+ "epoch": 1.219037118706358,
715
+ "grad_norm": 0.7008342146873474,
716
+ "learning_rate": 0.0002637702503681885,
717
+ "loss": 6.8862,
718
+ "step": 830
719
+ },
720
+ {
721
+ "epoch": 1.2337375964718853,
722
+ "grad_norm": 0.6531012058258057,
723
+ "learning_rate": 0.0002633284241531664,
724
+ "loss": 6.8651,
725
+ "step": 840
726
+ },
727
+ {
728
+ "epoch": 1.2484380742374128,
729
+ "grad_norm": 0.6673538684844971,
730
+ "learning_rate": 0.0002628865979381443,
731
+ "loss": 6.8483,
732
+ "step": 850
733
+ },
734
+ {
735
+ "epoch": 1.2484380742374128,
736
+ "eval_loss": 0.8902646899223328,
737
+ "eval_runtime": 122.8026,
738
+ "eval_samples_per_second": 7.076,
739
+ "eval_steps_per_second": 0.888,
740
+ "step": 850
741
+ },
742
+ {
743
+ "epoch": 1.2631385520029401,
744
+ "grad_norm": 0.6538046002388,
745
+ "learning_rate": 0.0002624447717231222,
746
+ "loss": 6.8312,
747
+ "step": 860
748
+ },
749
+ {
750
+ "epoch": 1.2778390297684674,
751
+ "grad_norm": 0.7091453671455383,
752
+ "learning_rate": 0.00026200294550810015,
753
+ "loss": 6.8254,
754
+ "step": 870
755
+ },
756
+ {
757
+ "epoch": 1.292539507533995,
758
+ "grad_norm": 0.6591873168945312,
759
+ "learning_rate": 0.000261561119293078,
760
+ "loss": 6.8611,
761
+ "step": 880
762
+ },
763
+ {
764
+ "epoch": 1.3072399852995222,
765
+ "grad_norm": 0.6869573593139648,
766
+ "learning_rate": 0.00026111929307805594,
767
+ "loss": 6.8559,
768
+ "step": 890
769
+ },
770
+ {
771
+ "epoch": 1.3219404630650495,
772
+ "grad_norm": 0.6487476229667664,
773
+ "learning_rate": 0.00026067746686303387,
774
+ "loss": 6.841,
775
+ "step": 900
776
+ },
777
+ {
778
+ "epoch": 1.3219404630650495,
779
+ "eval_loss": 0.8851333260536194,
780
+ "eval_runtime": 122.7209,
781
+ "eval_samples_per_second": 7.081,
782
+ "eval_steps_per_second": 0.888,
783
+ "step": 900
784
+ },
785
+ {
786
+ "epoch": 1.336640940830577,
787
+ "grad_norm": 0.957991361618042,
788
+ "learning_rate": 0.0002602356406480118,
789
+ "loss": 6.8572,
790
+ "step": 910
791
+ },
792
+ {
793
+ "epoch": 1.3513414185961043,
794
+ "grad_norm": 0.6700526475906372,
795
+ "learning_rate": 0.00025979381443298966,
796
+ "loss": 6.8354,
797
+ "step": 920
798
+ },
799
+ {
800
+ "epoch": 1.3660418963616316,
801
+ "grad_norm": 0.6402295827865601,
802
+ "learning_rate": 0.0002593519882179676,
803
+ "loss": 6.7743,
804
+ "step": 930
805
+ },
806
+ {
807
+ "epoch": 1.3807423741271592,
808
+ "grad_norm": 0.6479661464691162,
809
+ "learning_rate": 0.0002589101620029455,
810
+ "loss": 6.8425,
811
+ "step": 940
812
+ },
813
+ {
814
+ "epoch": 1.3954428518926865,
815
+ "grad_norm": 0.638687789440155,
816
+ "learning_rate": 0.00025846833578792343,
817
+ "loss": 6.8481,
818
+ "step": 950
819
+ },
820
+ {
821
+ "epoch": 1.3954428518926865,
822
+ "eval_loss": 0.881273627281189,
823
+ "eval_runtime": 122.7019,
824
+ "eval_samples_per_second": 7.082,
825
+ "eval_steps_per_second": 0.888,
826
+ "step": 950
827
+ },
828
+ {
829
+ "epoch": 1.4101433296582138,
830
+ "grad_norm": 0.6479136347770691,
831
+ "learning_rate": 0.0002580265095729013,
832
+ "loss": 6.851,
833
+ "step": 960
834
+ },
835
+ {
836
+ "epoch": 1.4248438074237413,
837
+ "grad_norm": 0.6393547654151917,
838
+ "learning_rate": 0.0002575846833578792,
839
+ "loss": 6.7861,
840
+ "step": 970
841
+ },
842
+ {
843
+ "epoch": 1.4395442851892686,
844
+ "grad_norm": 0.6324586272239685,
845
+ "learning_rate": 0.0002571428571428571,
846
+ "loss": 6.8184,
847
+ "step": 980
848
+ },
849
+ {
850
+ "epoch": 1.454244762954796,
851
+ "grad_norm": 0.6082057952880859,
852
+ "learning_rate": 0.000256701030927835,
853
+ "loss": 6.7677,
854
+ "step": 990
855
+ },
856
+ {
857
+ "epoch": 1.4689452407203234,
858
+ "grad_norm": 0.6476999521255493,
859
+ "learning_rate": 0.00025625920471281295,
860
+ "loss": 6.846,
861
+ "step": 1000
862
+ },
863
+ {
864
+ "epoch": 1.4689452407203234,
865
+ "eval_loss": 0.877618134021759,
866
+ "eval_runtime": 122.7086,
867
+ "eval_samples_per_second": 7.082,
868
+ "eval_steps_per_second": 0.888,
869
+ "step": 1000
870
+ },
871
+ {
872
+ "epoch": 1.483645718485851,
873
+ "grad_norm": 0.6280727386474609,
874
+ "learning_rate": 0.0002558173784977908,
875
+ "loss": 6.785,
876
+ "step": 1010
877
+ },
878
+ {
879
+ "epoch": 1.4983461962513782,
880
+ "grad_norm": 0.6497882604598999,
881
+ "learning_rate": 0.00025537555228276874,
882
+ "loss": 6.7953,
883
+ "step": 1020
884
+ },
885
+ {
886
+ "epoch": 1.5130466740169055,
887
+ "grad_norm": 0.6304103136062622,
888
+ "learning_rate": 0.00025493372606774666,
889
+ "loss": 6.7844,
890
+ "step": 1030
891
+ },
892
+ {
893
+ "epoch": 1.527747151782433,
894
+ "grad_norm": 0.6390955448150635,
895
+ "learning_rate": 0.0002544918998527246,
896
+ "loss": 6.8057,
897
+ "step": 1040
898
+ },
899
+ {
900
+ "epoch": 1.5424476295479603,
901
+ "grad_norm": 0.6420630812644958,
902
+ "learning_rate": 0.00025405007363770246,
903
+ "loss": 6.772,
904
+ "step": 1050
905
+ },
906
+ {
907
+ "epoch": 1.5424476295479603,
908
+ "eval_loss": 0.8740328550338745,
909
+ "eval_runtime": 122.7668,
910
+ "eval_samples_per_second": 7.078,
911
+ "eval_steps_per_second": 0.888,
912
+ "step": 1050
913
+ },
914
+ {
915
+ "epoch": 1.5571481073134876,
916
+ "grad_norm": 0.6527525186538696,
917
+ "learning_rate": 0.0002536082474226804,
918
+ "loss": 6.7597,
919
+ "step": 1060
920
+ },
921
+ {
922
+ "epoch": 1.5718485850790151,
923
+ "grad_norm": 0.63811856508255,
924
+ "learning_rate": 0.0002531664212076583,
925
+ "loss": 6.7273,
926
+ "step": 1070
927
+ },
928
+ {
929
+ "epoch": 1.5865490628445424,
930
+ "grad_norm": 0.6332401037216187,
931
+ "learning_rate": 0.00025272459499263623,
932
+ "loss": 6.7035,
933
+ "step": 1080
934
+ },
935
+ {
936
+ "epoch": 1.6012495406100697,
937
+ "grad_norm": 0.631254255771637,
938
+ "learning_rate": 0.0002522827687776141,
939
+ "loss": 6.7374,
940
+ "step": 1090
941
+ },
942
+ {
943
+ "epoch": 1.6159500183755973,
944
+ "grad_norm": 0.5980453491210938,
945
+ "learning_rate": 0.000251840942562592,
946
+ "loss": 6.7379,
947
+ "step": 1100
948
+ },
949
+ {
950
+ "epoch": 1.6159500183755973,
951
+ "eval_loss": 0.8703284859657288,
952
+ "eval_runtime": 122.7173,
953
+ "eval_samples_per_second": 7.081,
954
+ "eval_steps_per_second": 0.888,
955
+ "step": 1100
956
+ },
957
+ {
958
+ "epoch": 1.6306504961411246,
959
+ "grad_norm": 0.6735087633132935,
960
+ "learning_rate": 0.00025139911634756995,
961
+ "loss": 6.729,
962
+ "step": 1110
963
+ },
964
+ {
965
+ "epoch": 1.6453509739066519,
966
+ "grad_norm": 0.629978597164154,
967
+ "learning_rate": 0.00025095729013254787,
968
+ "loss": 6.7366,
969
+ "step": 1120
970
+ },
971
+ {
972
+ "epoch": 1.6600514516721794,
973
+ "grad_norm": 0.6302997469902039,
974
+ "learning_rate": 0.00025051546391752574,
975
+ "loss": 6.743,
976
+ "step": 1130
977
+ },
978
+ {
979
+ "epoch": 1.6747519294377067,
980
+ "grad_norm": 0.6438983082771301,
981
+ "learning_rate": 0.00025007363770250367,
982
+ "loss": 6.7066,
983
+ "step": 1140
984
+ },
985
+ {
986
+ "epoch": 1.689452407203234,
987
+ "grad_norm": 0.6278811097145081,
988
+ "learning_rate": 0.0002496318114874816,
989
+ "loss": 6.7407,
990
+ "step": 1150
991
+ },
992
+ {
993
+ "epoch": 1.689452407203234,
994
+ "eval_loss": 0.8671343922615051,
995
+ "eval_runtime": 122.7608,
996
+ "eval_samples_per_second": 7.079,
997
+ "eval_steps_per_second": 0.888,
998
+ "step": 1150
999
+ },
1000
+ {
1001
+ "epoch": 1.7041528849687615,
1002
+ "grad_norm": 0.625558614730835,
1003
+ "learning_rate": 0.0002491899852724595,
1004
+ "loss": 6.7356,
1005
+ "step": 1160
1006
+ },
1007
+ {
1008
+ "epoch": 1.718853362734289,
1009
+ "grad_norm": 0.6096333861351013,
1010
+ "learning_rate": 0.0002487481590574374,
1011
+ "loss": 6.7057,
1012
+ "step": 1170
1013
+ },
1014
+ {
1015
+ "epoch": 1.733553840499816,
1016
+ "grad_norm": 0.619067370891571,
1017
+ "learning_rate": 0.00024830633284241525,
1018
+ "loss": 6.6987,
1019
+ "step": 1180
1020
+ },
1021
+ {
1022
+ "epoch": 1.7482543182653436,
1023
+ "grad_norm": 0.6105065941810608,
1024
+ "learning_rate": 0.0002478645066273932,
1025
+ "loss": 6.6905,
1026
+ "step": 1190
1027
+ },
1028
+ {
1029
+ "epoch": 1.7629547960308711,
1030
+ "grad_norm": 0.6466421484947205,
1031
+ "learning_rate": 0.0002474226804123711,
1032
+ "loss": 6.714,
1033
+ "step": 1200
1034
+ },
1035
+ {
1036
+ "epoch": 1.7629547960308711,
1037
+ "eval_loss": 0.8641793131828308,
1038
+ "eval_runtime": 122.7219,
1039
+ "eval_samples_per_second": 7.081,
1040
+ "eval_steps_per_second": 0.888,
1041
+ "step": 1200
1042
+ },
1043
+ {
1044
+ "epoch": 1.7776552737963984,
1045
+ "grad_norm": 0.6360054612159729,
1046
+ "learning_rate": 0.000246980854197349,
1047
+ "loss": 6.7256,
1048
+ "step": 1210
1049
+ },
1050
+ {
1051
+ "epoch": 1.7923557515619257,
1052
+ "grad_norm": 0.604234516620636,
1053
+ "learning_rate": 0.0002465390279823269,
1054
+ "loss": 6.7378,
1055
+ "step": 1220
1056
+ },
1057
+ {
1058
+ "epoch": 1.8070562293274532,
1059
+ "grad_norm": 0.5942307710647583,
1060
+ "learning_rate": 0.0002460972017673048,
1061
+ "loss": 6.6839,
1062
+ "step": 1230
1063
+ },
1064
+ {
1065
+ "epoch": 1.8217567070929805,
1066
+ "grad_norm": 0.6054413318634033,
1067
+ "learning_rate": 0.00024565537555228275,
1068
+ "loss": 6.6793,
1069
+ "step": 1240
1070
+ },
1071
+ {
1072
+ "epoch": 1.8364571848585078,
1073
+ "grad_norm": 0.6159862279891968,
1074
+ "learning_rate": 0.00024521354933726067,
1075
+ "loss": 6.7124,
1076
+ "step": 1250
1077
+ },
1078
+ {
1079
+ "epoch": 1.8364571848585078,
1080
+ "eval_loss": 0.8611465096473694,
1081
+ "eval_runtime": 122.7049,
1082
+ "eval_samples_per_second": 7.082,
1083
+ "eval_steps_per_second": 0.888,
1084
+ "step": 1250
1085
+ },
1086
+ {
1087
+ "epoch": 1.8511576626240354,
1088
+ "grad_norm": 0.6350423693656921,
1089
+ "learning_rate": 0.00024477172312223854,
1090
+ "loss": 6.6738,
1091
+ "step": 1260
1092
+ },
1093
+ {
1094
+ "epoch": 1.8658581403895627,
1095
+ "grad_norm": 0.6083235740661621,
1096
+ "learning_rate": 0.00024432989690721646,
1097
+ "loss": 6.6895,
1098
+ "step": 1270
1099
+ },
1100
+ {
1101
+ "epoch": 1.88055861815509,
1102
+ "grad_norm": 0.6661822199821472,
1103
+ "learning_rate": 0.0002438880706921944,
1104
+ "loss": 6.6935,
1105
+ "step": 1280
1106
+ },
1107
+ {
1108
+ "epoch": 1.8952590959206175,
1109
+ "grad_norm": 0.6287885308265686,
1110
+ "learning_rate": 0.00024344624447717228,
1111
+ "loss": 6.6507,
1112
+ "step": 1290
1113
+ },
1114
+ {
1115
+ "epoch": 1.9099595736861448,
1116
+ "grad_norm": 0.6344292759895325,
1117
+ "learning_rate": 0.0002430044182621502,
1118
+ "loss": 6.6706,
1119
+ "step": 1300
1120
+ },
1121
+ {
1122
+ "epoch": 1.9099595736861448,
1123
+ "eval_loss": 0.8582596778869629,
1124
+ "eval_runtime": 122.7802,
1125
+ "eval_samples_per_second": 7.078,
1126
+ "eval_steps_per_second": 0.888,
1127
+ "step": 1300
1128
+ },
1129
+ {
1130
+ "epoch": 1.924660051451672,
1131
+ "grad_norm": 0.6139386892318726,
1132
+ "learning_rate": 0.0002425625920471281,
1133
+ "loss": 6.6578,
1134
+ "step": 1310
1135
+ },
1136
+ {
1137
+ "epoch": 1.9393605292171996,
1138
+ "grad_norm": 0.6080993413925171,
1139
+ "learning_rate": 0.00024212076583210603,
1140
+ "loss": 6.6478,
1141
+ "step": 1320
1142
+ },
1143
+ {
1144
+ "epoch": 1.954061006982727,
1145
+ "grad_norm": 0.6097526550292969,
1146
+ "learning_rate": 0.00024167893961708393,
1147
+ "loss": 6.6307,
1148
+ "step": 1330
1149
+ },
1150
+ {
1151
+ "epoch": 1.9687614847482542,
1152
+ "grad_norm": 0.603585958480835,
1153
+ "learning_rate": 0.00024123711340206185,
1154
+ "loss": 6.6696,
1155
+ "step": 1340
1156
+ },
1157
+ {
1158
+ "epoch": 1.9834619625137817,
1159
+ "grad_norm": 0.6306211948394775,
1160
+ "learning_rate": 0.00024079528718703975,
1161
+ "loss": 6.6335,
1162
+ "step": 1350
1163
+ },
1164
+ {
1165
+ "epoch": 1.9834619625137817,
1166
+ "eval_loss": 0.8551880121231079,
1167
+ "eval_runtime": 122.671,
1168
+ "eval_samples_per_second": 7.084,
1169
+ "eval_steps_per_second": 0.889,
1170
+ "step": 1350
1171
+ },
1172
+ {
1173
+ "epoch": 1.9981624402793092,
1174
+ "grad_norm": 0.6002718806266785,
1175
+ "learning_rate": 0.00024035346097201767,
1176
+ "loss": 6.6681,
1177
+ "step": 1360
1178
+ },
1179
+ {
1180
+ "epoch": 2.011760382212422,
1181
+ "grad_norm": 0.609912097454071,
1182
+ "learning_rate": 0.00023991163475699557,
1183
+ "loss": 5.7921,
1184
+ "step": 1370
1185
+ },
1186
+ {
1187
+ "epoch": 2.0264608599779494,
1188
+ "grad_norm": 0.631758451461792,
1189
+ "learning_rate": 0.0002394698085419735,
1190
+ "loss": 6.2318,
1191
+ "step": 1380
1192
+ },
1193
+ {
1194
+ "epoch": 2.0411613377434765,
1195
+ "grad_norm": 0.6468050479888916,
1196
+ "learning_rate": 0.00023902798232695136,
1197
+ "loss": 6.2074,
1198
+ "step": 1390
1199
+ },
1200
+ {
1201
+ "epoch": 2.055861815509004,
1202
+ "grad_norm": 0.6332272887229919,
1203
+ "learning_rate": 0.00023858615611192926,
1204
+ "loss": 6.2245,
1205
+ "step": 1400
1206
+ },
1207
+ {
1208
+ "epoch": 2.055861815509004,
1209
+ "eval_loss": 0.8581995368003845,
1210
+ "eval_runtime": 122.7582,
1211
+ "eval_samples_per_second": 7.079,
1212
+ "eval_steps_per_second": 0.888,
1213
+ "step": 1400
1214
+ },
1215
+ {
1216
+ "epoch": 2.0705622932745316,
1217
+ "grad_norm": 0.6591159105300903,
1218
+ "learning_rate": 0.00023814432989690718,
1219
+ "loss": 6.1981,
1220
+ "step": 1410
1221
+ },
1222
+ {
1223
+ "epoch": 2.0852627710400586,
1224
+ "grad_norm": 0.634479820728302,
1225
+ "learning_rate": 0.00023770250368188508,
1226
+ "loss": 6.2003,
1227
+ "step": 1420
1228
+ },
1229
+ {
1230
+ "epoch": 2.099963248805586,
1231
+ "grad_norm": 0.6693385243415833,
1232
+ "learning_rate": 0.000237260677466863,
1233
+ "loss": 6.2305,
1234
+ "step": 1430
1235
+ },
1236
+ {
1237
+ "epoch": 2.1146637265711137,
1238
+ "grad_norm": 0.68646639585495,
1239
+ "learning_rate": 0.0002368188512518409,
1240
+ "loss": 6.2214,
1241
+ "step": 1440
1242
+ },
1243
+ {
1244
+ "epoch": 2.1293642043366408,
1245
+ "grad_norm": 0.6264299750328064,
1246
+ "learning_rate": 0.00023637702503681883,
1247
+ "loss": 6.1968,
1248
+ "step": 1450
1249
+ },
1250
+ {
1251
+ "epoch": 2.1293642043366408,
1252
+ "eval_loss": 0.8580149412155151,
1253
+ "eval_runtime": 122.7321,
1254
+ "eval_samples_per_second": 7.08,
1255
+ "eval_steps_per_second": 0.888,
1256
+ "step": 1450
1257
+ },
1258
+ {
1259
+ "epoch": 2.1440646821021683,
1260
+ "grad_norm": 0.6439588069915771,
1261
+ "learning_rate": 0.00023593519882179672,
1262
+ "loss": 6.2362,
1263
+ "step": 1460
1264
+ },
1265
+ {
1266
+ "epoch": 2.158765159867696,
1267
+ "grad_norm": 0.6767362952232361,
1268
+ "learning_rate": 0.00023549337260677465,
1269
+ "loss": 6.2137,
1270
+ "step": 1470
1271
+ },
1272
+ {
1273
+ "epoch": 2.173465637633223,
1274
+ "grad_norm": 0.6421840786933899,
1275
+ "learning_rate": 0.00023505154639175254,
1276
+ "loss": 6.2331,
1277
+ "step": 1480
1278
+ },
1279
+ {
1280
+ "epoch": 2.1881661153987504,
1281
+ "grad_norm": 0.6356670260429382,
1282
+ "learning_rate": 0.00023460972017673047,
1283
+ "loss": 6.1292,
1284
+ "step": 1490
1285
+ },
1286
+ {
1287
+ "epoch": 2.202866593164278,
1288
+ "grad_norm": 0.6405894756317139,
1289
+ "learning_rate": 0.00023416789396170837,
1290
+ "loss": 6.212,
1291
+ "step": 1500
1292
+ },
1293
+ {
1294
+ "epoch": 2.202866593164278,
1295
+ "eval_loss": 0.8558148741722107,
1296
+ "eval_runtime": 122.8325,
1297
+ "eval_samples_per_second": 7.075,
1298
+ "eval_steps_per_second": 0.887,
1299
+ "step": 1500
1300
+ },
1301
+ {
1302
+ "epoch": 2.217567070929805,
1303
+ "grad_norm": 0.640738308429718,
1304
+ "learning_rate": 0.0002337260677466863,
1305
+ "loss": 6.2344,
1306
+ "step": 1510
1307
+ },
1308
+ {
1309
+ "epoch": 2.2322675486953325,
1310
+ "grad_norm": 0.6253748536109924,
1311
+ "learning_rate": 0.0002332842415316642,
1312
+ "loss": 6.2409,
1313
+ "step": 1520
1314
+ },
1315
+ {
1316
+ "epoch": 2.24696802646086,
1317
+ "grad_norm": 0.6264599561691284,
1318
+ "learning_rate": 0.0002328424153166421,
1319
+ "loss": 6.2622,
1320
+ "step": 1530
1321
+ },
1322
+ {
1323
+ "epoch": 2.2616685042263875,
1324
+ "grad_norm": 0.6570128202438354,
1325
+ "learning_rate": 0.00023240058910162,
1326
+ "loss": 6.2325,
1327
+ "step": 1540
1328
+ },
1329
+ {
1330
+ "epoch": 2.2763689819919146,
1331
+ "grad_norm": 0.6414036750793457,
1332
+ "learning_rate": 0.00023195876288659793,
1333
+ "loss": 6.2025,
1334
+ "step": 1550
1335
+ },
1336
+ {
1337
+ "epoch": 2.2763689819919146,
1338
+ "eval_loss": 0.8544706702232361,
1339
+ "eval_runtime": 122.7389,
1340
+ "eval_samples_per_second": 7.08,
1341
+ "eval_steps_per_second": 0.888,
1342
+ "step": 1550
1343
+ },
1344
+ {
1345
+ "epoch": 2.291069459757442,
1346
+ "grad_norm": 0.6400018930435181,
1347
+ "learning_rate": 0.00023151693667157583,
1348
+ "loss": 6.2232,
1349
+ "step": 1560
1350
+ },
1351
+ {
1352
+ "epoch": 2.3057699375229697,
1353
+ "grad_norm": 0.657616376876831,
1354
+ "learning_rate": 0.00023107511045655375,
1355
+ "loss": 6.1867,
1356
+ "step": 1570
1357
+ },
1358
+ {
1359
+ "epoch": 2.3204704152884967,
1360
+ "grad_norm": 0.6157673001289368,
1361
+ "learning_rate": 0.00023063328424153165,
1362
+ "loss": 6.2029,
1363
+ "step": 1580
1364
+ },
1365
+ {
1366
+ "epoch": 2.3351708930540243,
1367
+ "grad_norm": 0.6498163342475891,
1368
+ "learning_rate": 0.00023019145802650957,
1369
+ "loss": 6.2112,
1370
+ "step": 1590
1371
+ },
1372
+ {
1373
+ "epoch": 2.3498713708195518,
1374
+ "grad_norm": 0.6593335866928101,
1375
+ "learning_rate": 0.00022974963181148747,
1376
+ "loss": 6.1991,
1377
+ "step": 1600
1378
+ },
1379
+ {
1380
+ "epoch": 2.3498713708195518,
1381
+ "eval_loss": 0.8528178930282593,
1382
+ "eval_runtime": 122.9309,
1383
+ "eval_samples_per_second": 7.069,
1384
+ "eval_steps_per_second": 0.887,
1385
+ "step": 1600
1386
+ },
1387
+ {
1388
+ "epoch": 2.364571848585079,
1389
+ "grad_norm": 0.6478355526924133,
1390
+ "learning_rate": 0.00022930780559646534,
1391
+ "loss": 6.2688,
1392
+ "step": 1610
1393
+ },
1394
+ {
1395
+ "epoch": 2.3792723263506064,
1396
+ "grad_norm": 0.6342290043830872,
1397
+ "learning_rate": 0.00022886597938144327,
1398
+ "loss": 6.2411,
1399
+ "step": 1620
1400
+ },
1401
+ {
1402
+ "epoch": 2.393972804116134,
1403
+ "grad_norm": 0.6611024737358093,
1404
+ "learning_rate": 0.00022842415316642116,
1405
+ "loss": 6.233,
1406
+ "step": 1630
1407
+ },
1408
+ {
1409
+ "epoch": 2.408673281881661,
1410
+ "grad_norm": 0.6265544295310974,
1411
+ "learning_rate": 0.0002279823269513991,
1412
+ "loss": 6.1916,
1413
+ "step": 1640
1414
+ },
1415
+ {
1416
+ "epoch": 2.4233737596471885,
1417
+ "grad_norm": 0.6478269696235657,
1418
+ "learning_rate": 0.00022754050073637698,
1419
+ "loss": 6.1738,
1420
+ "step": 1650
1421
+ },
1422
+ {
1423
+ "epoch": 2.4233737596471885,
1424
+ "eval_loss": 0.8510602712631226,
1425
+ "eval_runtime": 122.8125,
1426
+ "eval_samples_per_second": 7.076,
1427
+ "eval_steps_per_second": 0.888,
1428
+ "step": 1650
1429
+ },
1430
+ {
1431
+ "epoch": 2.438074237412716,
1432
+ "grad_norm": 0.6446574926376343,
1433
+ "learning_rate": 0.0002270986745213549,
1434
+ "loss": 6.2713,
1435
+ "step": 1660
1436
+ },
1437
+ {
1438
+ "epoch": 2.4527747151782435,
1439
+ "grad_norm": 0.6360475420951843,
1440
+ "learning_rate": 0.0002266568483063328,
1441
+ "loss": 6.2584,
1442
+ "step": 1670
1443
+ },
1444
+ {
1445
+ "epoch": 2.4674751929437706,
1446
+ "grad_norm": 0.6492727398872375,
1447
+ "learning_rate": 0.00022621502209131073,
1448
+ "loss": 6.2234,
1449
+ "step": 1680
1450
+ },
1451
+ {
1452
+ "epoch": 2.482175670709298,
1453
+ "grad_norm": 0.6489901542663574,
1454
+ "learning_rate": 0.00022577319587628863,
1455
+ "loss": 6.2155,
1456
+ "step": 1690
1457
+ },
1458
+ {
1459
+ "epoch": 2.4968761484748256,
1460
+ "grad_norm": 0.6320230960845947,
1461
+ "learning_rate": 0.00022533136966126655,
1462
+ "loss": 6.1839,
1463
+ "step": 1700
1464
+ },
1465
+ {
1466
+ "epoch": 2.4968761484748256,
1467
+ "eval_loss": 0.8486818075180054,
1468
+ "eval_runtime": 122.741,
1469
+ "eval_samples_per_second": 7.08,
1470
+ "eval_steps_per_second": 0.888,
1471
+ "step": 1700
1472
+ },
1473
+ {
1474
+ "epoch": 2.5115766262403527,
1475
+ "grad_norm": 0.642189621925354,
1476
+ "learning_rate": 0.00022488954344624445,
1477
+ "loss": 6.1757,
1478
+ "step": 1710
1479
+ },
1480
+ {
1481
+ "epoch": 2.5262771040058802,
1482
+ "grad_norm": 0.6360085010528564,
1483
+ "learning_rate": 0.00022444771723122237,
1484
+ "loss": 6.2302,
1485
+ "step": 1720
1486
+ },
1487
+ {
1488
+ "epoch": 2.5409775817714078,
1489
+ "grad_norm": 0.6216627359390259,
1490
+ "learning_rate": 0.00022400589101620027,
1491
+ "loss": 6.2138,
1492
+ "step": 1730
1493
+ },
1494
+ {
1495
+ "epoch": 2.555678059536935,
1496
+ "grad_norm": 0.6285056471824646,
1497
+ "learning_rate": 0.0002235640648011782,
1498
+ "loss": 6.2394,
1499
+ "step": 1740
1500
+ },
1501
+ {
1502
+ "epoch": 2.5703785373024624,
1503
+ "grad_norm": 0.6265233755111694,
1504
+ "learning_rate": 0.0002231222385861561,
1505
+ "loss": 6.2358,
1506
+ "step": 1750
1507
+ },
1508
+ {
1509
+ "epoch": 2.5703785373024624,
1510
+ "eval_loss": 0.846447765827179,
1511
+ "eval_runtime": 122.9508,
1512
+ "eval_samples_per_second": 7.068,
1513
+ "eval_steps_per_second": 0.887,
1514
+ "step": 1750
1515
+ },
1516
+ {
1517
+ "epoch": 2.58507901506799,
1518
+ "grad_norm": 0.6178449988365173,
1519
+ "learning_rate": 0.00022268041237113401,
1520
+ "loss": 6.2289,
1521
+ "step": 1760
1522
+ },
1523
+ {
1524
+ "epoch": 2.599779492833517,
1525
+ "grad_norm": 0.6336231827735901,
1526
+ "learning_rate": 0.0002222385861561119,
1527
+ "loss": 6.1892,
1528
+ "step": 1770
1529
+ },
1530
+ {
1531
+ "epoch": 2.6144799705990445,
1532
+ "grad_norm": 0.6177706718444824,
1533
+ "learning_rate": 0.00022179675994108984,
1534
+ "loss": 6.2211,
1535
+ "step": 1780
1536
+ },
1537
+ {
1538
+ "epoch": 2.629180448364572,
1539
+ "grad_norm": 0.6471459269523621,
1540
+ "learning_rate": 0.00022135493372606773,
1541
+ "loss": 6.2231,
1542
+ "step": 1790
1543
+ },
1544
+ {
1545
+ "epoch": 2.643880926130099,
1546
+ "grad_norm": 0.6517642140388489,
1547
+ "learning_rate": 0.00022091310751104566,
1548
+ "loss": 6.2072,
1549
+ "step": 1800
1550
+ },
1551
+ {
1552
+ "epoch": 2.643880926130099,
1553
+ "eval_loss": 0.8459606170654297,
1554
+ "eval_runtime": 122.7829,
1555
+ "eval_samples_per_second": 7.078,
1556
+ "eval_steps_per_second": 0.888,
1557
+ "step": 1800
1558
+ },
1559
+ {
1560
+ "epoch": 2.6585814038956266,
1561
+ "grad_norm": 0.6251035332679749,
1562
+ "learning_rate": 0.00022047128129602355,
1563
+ "loss": 6.2043,
1564
+ "step": 1810
1565
+ },
1566
+ {
1567
+ "epoch": 2.673281881661154,
1568
+ "grad_norm": 0.6282381415367126,
1569
+ "learning_rate": 0.00022002945508100145,
1570
+ "loss": 6.2106,
1571
+ "step": 1820
1572
+ },
1573
+ {
1574
+ "epoch": 2.687982359426681,
1575
+ "grad_norm": 0.6424158811569214,
1576
+ "learning_rate": 0.00021958762886597935,
1577
+ "loss": 6.1704,
1578
+ "step": 1830
1579
+ },
1580
+ {
1581
+ "epoch": 2.7026828371922087,
1582
+ "grad_norm": 0.6325989365577698,
1583
+ "learning_rate": 0.00021914580265095727,
1584
+ "loss": 6.2082,
1585
+ "step": 1840
1586
+ },
1587
+ {
1588
+ "epoch": 2.717383314957736,
1589
+ "grad_norm": 0.6277638673782349,
1590
+ "learning_rate": 0.00021870397643593517,
1591
+ "loss": 6.2104,
1592
+ "step": 1850
1593
+ },
1594
+ {
1595
+ "epoch": 2.717383314957736,
1596
+ "eval_loss": 0.8437173366546631,
1597
+ "eval_runtime": 122.7354,
1598
+ "eval_samples_per_second": 7.08,
1599
+ "eval_steps_per_second": 0.888,
1600
+ "step": 1850
1601
+ },
1602
+ {
1603
+ "epoch": 2.7320837927232633,
1604
+ "grad_norm": 0.59511798620224,
1605
+ "learning_rate": 0.00021826215022091307,
1606
+ "loss": 6.2104,
1607
+ "step": 1860
1608
+ },
1609
+ {
1610
+ "epoch": 2.746784270488791,
1611
+ "grad_norm": 0.6076375246047974,
1612
+ "learning_rate": 0.000217820324005891,
1613
+ "loss": 6.2272,
1614
+ "step": 1870
1615
+ },
1616
+ {
1617
+ "epoch": 2.7614847482543183,
1618
+ "grad_norm": 0.6336222290992737,
1619
+ "learning_rate": 0.0002173784977908689,
1620
+ "loss": 6.2629,
1621
+ "step": 1880
1622
+ },
1623
+ {
1624
+ "epoch": 2.7761852260198454,
1625
+ "grad_norm": 0.6477245092391968,
1626
+ "learning_rate": 0.0002169366715758468,
1627
+ "loss": 6.2086,
1628
+ "step": 1890
1629
+ },
1630
+ {
1631
+ "epoch": 2.790885703785373,
1632
+ "grad_norm": 0.63583904504776,
1633
+ "learning_rate": 0.0002164948453608247,
1634
+ "loss": 6.2289,
1635
+ "step": 1900
1636
+ },
1637
+ {
1638
+ "epoch": 2.790885703785373,
1639
+ "eval_loss": 0.8419505953788757,
1640
+ "eval_runtime": 122.7793,
1641
+ "eval_samples_per_second": 7.078,
1642
+ "eval_steps_per_second": 0.888,
1643
+ "step": 1900
1644
+ },
1645
+ {
1646
+ "epoch": 2.8055861815509004,
1647
+ "grad_norm": 0.6694473028182983,
1648
+ "learning_rate": 0.00021605301914580263,
1649
+ "loss": 6.2386,
1650
+ "step": 1910
1651
+ },
1652
+ {
1653
+ "epoch": 2.8202866593164275,
1654
+ "grad_norm": 0.6175634860992432,
1655
+ "learning_rate": 0.00021561119293078053,
1656
+ "loss": 6.1825,
1657
+ "step": 1920
1658
+ },
1659
+ {
1660
+ "epoch": 2.834987137081955,
1661
+ "grad_norm": 0.6627750992774963,
1662
+ "learning_rate": 0.00021516936671575845,
1663
+ "loss": 6.204,
1664
+ "step": 1930
1665
+ },
1666
+ {
1667
+ "epoch": 2.8496876148474826,
1668
+ "grad_norm": 0.6206278800964355,
1669
+ "learning_rate": 0.00021472754050073635,
1670
+ "loss": 6.1706,
1671
+ "step": 1940
1672
+ },
1673
+ {
1674
+ "epoch": 2.86438809261301,
1675
+ "grad_norm": 0.6408950686454773,
1676
+ "learning_rate": 0.00021428571428571427,
1677
+ "loss": 6.2532,
1678
+ "step": 1950
1679
+ },
1680
+ {
1681
+ "epoch": 2.86438809261301,
1682
+ "eval_loss": 0.8408024907112122,
1683
+ "eval_runtime": 122.8418,
1684
+ "eval_samples_per_second": 7.074,
1685
+ "eval_steps_per_second": 0.887,
1686
+ "step": 1950
1687
+ },
1688
+ {
1689
+ "epoch": 2.879088570378537,
1690
+ "grad_norm": 0.6331806778907776,
1691
+ "learning_rate": 0.00021384388807069217,
1692
+ "loss": 6.1977,
1693
+ "step": 1960
1694
+ },
1695
+ {
1696
+ "epoch": 2.8937890481440647,
1697
+ "grad_norm": 0.6263200640678406,
1698
+ "learning_rate": 0.0002134020618556701,
1699
+ "loss": 6.2267,
1700
+ "step": 1970
1701
+ },
1702
+ {
1703
+ "epoch": 2.908489525909592,
1704
+ "grad_norm": 0.6077616214752197,
1705
+ "learning_rate": 0.000212960235640648,
1706
+ "loss": 6.2016,
1707
+ "step": 1980
1708
+ },
1709
+ {
1710
+ "epoch": 2.9231900036751193,
1711
+ "grad_norm": 0.6300930976867676,
1712
+ "learning_rate": 0.00021251840942562592,
1713
+ "loss": 6.1878,
1714
+ "step": 1990
1715
+ },
1716
+ {
1717
+ "epoch": 2.937890481440647,
1718
+ "grad_norm": 0.6281541585922241,
1719
+ "learning_rate": 0.00021207658321060381,
1720
+ "loss": 6.2084,
1721
+ "step": 2000
1722
+ },
1723
+ {
1724
+ "epoch": 2.937890481440647,
1725
+ "eval_loss": 0.8391561508178711,
1726
+ "eval_runtime": 122.7198,
1727
+ "eval_samples_per_second": 7.081,
1728
+ "eval_steps_per_second": 0.888,
1729
+ "step": 2000
1730
+ },
1731
+ {
1732
+ "epoch": 2.9525909592061743,
1733
+ "grad_norm": 0.6204951405525208,
1734
+ "learning_rate": 0.00021163475699558174,
1735
+ "loss": 6.2271,
1736
+ "step": 2010
1737
+ },
1738
+ {
1739
+ "epoch": 2.967291436971702,
1740
+ "grad_norm": 0.6341344118118286,
1741
+ "learning_rate": 0.00021119293078055964,
1742
+ "loss": 6.2171,
1743
+ "step": 2020
1744
+ },
1745
+ {
1746
+ "epoch": 2.981991914737229,
1747
+ "grad_norm": 0.6163744330406189,
1748
+ "learning_rate": 0.00021075110456553753,
1749
+ "loss": 6.2194,
1750
+ "step": 2030
1751
+ },
1752
+ {
1753
+ "epoch": 2.9966923925027564,
1754
+ "grad_norm": 0.635434627532959,
1755
+ "learning_rate": 0.00021030927835051543,
1756
+ "loss": 6.1609,
1757
+ "step": 2040
1758
+ },
1759
+ {
1760
+ "epoch": 3.010290334435869,
1761
+ "grad_norm": 0.8156677484512329,
1762
+ "learning_rate": 0.00020986745213549335,
1763
+ "loss": 5.3662,
1764
+ "step": 2050
1765
+ },
1766
+ {
1767
+ "epoch": 3.010290334435869,
1768
+ "eval_loss": 0.8518180251121521,
1769
+ "eval_runtime": 122.7832,
1770
+ "eval_samples_per_second": 7.078,
1771
+ "eval_steps_per_second": 0.888,
1772
+ "step": 2050
1773
+ },
1774
+ {
1775
+ "epoch": 3.0249908122013967,
1776
+ "grad_norm": 0.6709501147270203,
1777
+ "learning_rate": 0.00020942562592047125,
1778
+ "loss": 5.657,
1779
+ "step": 2060
1780
+ },
1781
+ {
1782
+ "epoch": 3.0396912899669237,
1783
+ "grad_norm": 0.6364277601242065,
1784
+ "learning_rate": 0.00020898379970544917,
1785
+ "loss": 5.6556,
1786
+ "step": 2070
1787
+ },
1788
+ {
1789
+ "epoch": 3.0543917677324512,
1790
+ "grad_norm": 0.6877652406692505,
1791
+ "learning_rate": 0.00020854197349042707,
1792
+ "loss": 5.6971,
1793
+ "step": 2080
1794
+ },
1795
+ {
1796
+ "epoch": 3.0690922454979788,
1797
+ "grad_norm": 0.6691612005233765,
1798
+ "learning_rate": 0.000208100147275405,
1799
+ "loss": 5.6758,
1800
+ "step": 2090
1801
+ },
1802
+ {
1803
+ "epoch": 3.083792723263506,
1804
+ "grad_norm": 0.6702853441238403,
1805
+ "learning_rate": 0.0002076583210603829,
1806
+ "loss": 5.6567,
1807
+ "step": 2100
1808
+ },
1809
+ {
1810
+ "epoch": 3.083792723263506,
1811
+ "eval_loss": 0.8499862551689148,
1812
+ "eval_runtime": 122.6921,
1813
+ "eval_samples_per_second": 7.083,
1814
+ "eval_steps_per_second": 0.888,
1815
+ "step": 2100
1816
+ },
1817
+ {
1818
+ "epoch": 3.0984932010290334,
1819
+ "grad_norm": 0.6671494245529175,
1820
+ "learning_rate": 0.0002072164948453608,
1821
+ "loss": 5.6459,
1822
+ "step": 2110
1823
+ },
1824
+ {
1825
+ "epoch": 3.113193678794561,
1826
+ "grad_norm": 0.6615011692047119,
1827
+ "learning_rate": 0.00020677466863033871,
1828
+ "loss": 5.6901,
1829
+ "step": 2120
1830
+ },
1831
+ {
1832
+ "epoch": 3.1278941565600884,
1833
+ "grad_norm": 0.6596587300300598,
1834
+ "learning_rate": 0.0002063328424153166,
1835
+ "loss": 5.6881,
1836
+ "step": 2130
1837
+ },
1838
+ {
1839
+ "epoch": 3.1425946343256155,
1840
+ "grad_norm": 0.66860032081604,
1841
+ "learning_rate": 0.00020589101620029454,
1842
+ "loss": 5.6988,
1843
+ "step": 2140
1844
+ },
1845
+ {
1846
+ "epoch": 3.157295112091143,
1847
+ "grad_norm": 0.6529964208602905,
1848
+ "learning_rate": 0.00020544918998527243,
1849
+ "loss": 5.7,
1850
+ "step": 2150
1851
+ },
1852
+ {
1853
+ "epoch": 3.157295112091143,
1854
+ "eval_loss": 0.8492234945297241,
1855
+ "eval_runtime": 122.695,
1856
+ "eval_samples_per_second": 7.083,
1857
+ "eval_steps_per_second": 0.888,
1858
+ "step": 2150
1859
+ },
1860
+ {
1861
+ "epoch": 3.1719955898566705,
1862
+ "grad_norm": 0.6981674432754517,
1863
+ "learning_rate": 0.00020500736377025036,
1864
+ "loss": 5.6757,
1865
+ "step": 2160
1866
+ },
1867
+ {
1868
+ "epoch": 3.1866960676221976,
1869
+ "grad_norm": 0.6831721067428589,
1870
+ "learning_rate": 0.00020456553755522825,
1871
+ "loss": 5.7149,
1872
+ "step": 2170
1873
+ },
1874
+ {
1875
+ "epoch": 3.201396545387725,
1876
+ "grad_norm": 0.6813935041427612,
1877
+ "learning_rate": 0.00020412371134020618,
1878
+ "loss": 5.6557,
1879
+ "step": 2180
1880
+ },
1881
+ {
1882
+ "epoch": 3.2160970231532526,
1883
+ "grad_norm": 0.6628422737121582,
1884
+ "learning_rate": 0.00020368188512518407,
1885
+ "loss": 5.6812,
1886
+ "step": 2190
1887
+ },
1888
+ {
1889
+ "epoch": 3.2307975009187797,
1890
+ "grad_norm": 0.6785872578620911,
1891
+ "learning_rate": 0.000203240058910162,
1892
+ "loss": 5.74,
1893
+ "step": 2200
1894
+ },
1895
+ {
1896
+ "epoch": 3.2307975009187797,
1897
+ "eval_loss": 0.8484858870506287,
1898
+ "eval_runtime": 122.7176,
1899
+ "eval_samples_per_second": 7.081,
1900
+ "eval_steps_per_second": 0.888,
1901
+ "step": 2200
1902
+ },
1903
+ {
1904
+ "epoch": 3.2454979786843072,
1905
+ "grad_norm": 0.6826450228691101,
1906
+ "learning_rate": 0.0002027982326951399,
1907
+ "loss": 5.7303,
1908
+ "step": 2210
1909
+ },
1910
+ {
1911
+ "epoch": 3.2601984564498347,
1912
+ "grad_norm": 0.6782203912734985,
1913
+ "learning_rate": 0.00020235640648011782,
1914
+ "loss": 5.7306,
1915
+ "step": 2220
1916
+ },
1917
+ {
1918
+ "epoch": 3.274898934215362,
1919
+ "grad_norm": 0.7322261929512024,
1920
+ "learning_rate": 0.00020191458026509572,
1921
+ "loss": 5.7121,
1922
+ "step": 2230
1923
+ },
1924
+ {
1925
+ "epoch": 3.2895994119808893,
1926
+ "grad_norm": 0.676398754119873,
1927
+ "learning_rate": 0.00020147275405007361,
1928
+ "loss": 5.676,
1929
+ "step": 2240
1930
+ },
1931
+ {
1932
+ "epoch": 3.304299889746417,
1933
+ "grad_norm": 0.6796535849571228,
1934
+ "learning_rate": 0.0002010309278350515,
1935
+ "loss": 5.6793,
1936
+ "step": 2250
1937
+ },
1938
+ {
1939
+ "epoch": 3.304299889746417,
1940
+ "eval_loss": 0.8485282063484192,
1941
+ "eval_runtime": 122.7649,
1942
+ "eval_samples_per_second": 7.079,
1943
+ "eval_steps_per_second": 0.888,
1944
+ "step": 2250
1945
+ },
1946
+ {
1947
+ "epoch": 3.3190003675119444,
1948
+ "grad_norm": 0.6691915392875671,
1949
+ "learning_rate": 0.00020058910162002944,
1950
+ "loss": 5.7447,
1951
+ "step": 2260
1952
+ },
1953
+ {
1954
+ "epoch": 3.3337008452774715,
1955
+ "grad_norm": 0.6691219210624695,
1956
+ "learning_rate": 0.00020014727540500733,
1957
+ "loss": 5.7213,
1958
+ "step": 2270
1959
+ },
1960
+ {
1961
+ "epoch": 3.348401323042999,
1962
+ "grad_norm": 0.691150963306427,
1963
+ "learning_rate": 0.00019970544918998526,
1964
+ "loss": 5.7139,
1965
+ "step": 2280
1966
+ },
1967
+ {
1968
+ "epoch": 3.3631018008085265,
1969
+ "grad_norm": 0.6797978281974792,
1970
+ "learning_rate": 0.00019926362297496315,
1971
+ "loss": 5.7259,
1972
+ "step": 2290
1973
+ },
1974
+ {
1975
+ "epoch": 3.3778022785740536,
1976
+ "grad_norm": 0.680253803730011,
1977
+ "learning_rate": 0.00019882179675994108,
1978
+ "loss": 5.729,
1979
+ "step": 2300
1980
+ },
1981
+ {
1982
+ "epoch": 3.3778022785740536,
1983
+ "eval_loss": 0.8467084765434265,
1984
+ "eval_runtime": 122.7168,
1985
+ "eval_samples_per_second": 7.081,
1986
+ "eval_steps_per_second": 0.888,
1987
+ "step": 2300
1988
+ },
1989
+ {
1990
+ "epoch": 3.392502756339581,
1991
+ "grad_norm": 0.6667632460594177,
1992
+ "learning_rate": 0.00019837997054491897,
1993
+ "loss": 5.7414,
1994
+ "step": 2310
1995
+ },
1996
+ {
1997
+ "epoch": 3.4072032341051086,
1998
+ "grad_norm": 0.6695231795310974,
1999
+ "learning_rate": 0.0001979381443298969,
2000
+ "loss": 5.6706,
2001
+ "step": 2320
2002
+ },
2003
+ {
2004
+ "epoch": 3.4219037118706357,
2005
+ "grad_norm": 0.6954268217086792,
2006
+ "learning_rate": 0.0001974963181148748,
2007
+ "loss": 5.786,
2008
+ "step": 2330
2009
+ },
2010
+ {
2011
+ "epoch": 3.436604189636163,
2012
+ "grad_norm": 0.6876401901245117,
2013
+ "learning_rate": 0.00019705449189985272,
2014
+ "loss": 5.7293,
2015
+ "step": 2340
2016
+ },
2017
+ {
2018
+ "epoch": 3.4513046674016907,
2019
+ "grad_norm": 0.6845841407775879,
2020
+ "learning_rate": 0.00019661266568483062,
2021
+ "loss": 5.7367,
2022
+ "step": 2350
2023
+ },
2024
+ {
2025
+ "epoch": 3.4513046674016907,
2026
+ "eval_loss": 0.8462281823158264,
2027
+ "eval_runtime": 122.7084,
2028
+ "eval_samples_per_second": 7.082,
2029
+ "eval_steps_per_second": 0.888,
2030
+ "step": 2350
2031
+ },
2032
+ {
2033
+ "epoch": 3.466005145167218,
2034
+ "grad_norm": 0.6698250770568848,
2035
+ "learning_rate": 0.00019617083946980851,
2036
+ "loss": 5.7564,
2037
+ "step": 2360
2038
+ },
2039
+ {
2040
+ "epoch": 3.4807056229327453,
2041
+ "grad_norm": 0.691417396068573,
2042
+ "learning_rate": 0.00019572901325478644,
2043
+ "loss": 5.7239,
2044
+ "step": 2370
2045
+ },
2046
+ {
2047
+ "epoch": 3.495406100698273,
2048
+ "grad_norm": 0.69003826379776,
2049
+ "learning_rate": 0.00019528718703976433,
2050
+ "loss": 5.7359,
2051
+ "step": 2380
2052
+ },
2053
+ {
2054
+ "epoch": 3.5101065784638,
2055
+ "grad_norm": 0.665431797504425,
2056
+ "learning_rate": 0.00019484536082474226,
2057
+ "loss": 5.7405,
2058
+ "step": 2390
2059
+ },
2060
+ {
2061
+ "epoch": 3.5248070562293274,
2062
+ "grad_norm": 0.6713572144508362,
2063
+ "learning_rate": 0.00019440353460972016,
2064
+ "loss": 5.7417,
2065
+ "step": 2400
2066
+ },
2067
+ {
2068
+ "epoch": 3.5248070562293274,
2069
+ "eval_loss": 0.8447020053863525,
2070
+ "eval_runtime": 122.7287,
2071
+ "eval_samples_per_second": 7.081,
2072
+ "eval_steps_per_second": 0.888,
2073
+ "step": 2400
2074
+ },
2075
+ {
2076
+ "epoch": 3.539507533994855,
2077
+ "grad_norm": 0.6731536388397217,
2078
+ "learning_rate": 0.00019396170839469808,
2079
+ "loss": 5.7519,
2080
+ "step": 2410
2081
+ },
2082
+ {
2083
+ "epoch": 3.554208011760382,
2084
+ "grad_norm": 0.6862500905990601,
2085
+ "learning_rate": 0.00019351988217967598,
2086
+ "loss": 5.7698,
2087
+ "step": 2420
2088
+ },
2089
+ {
2090
+ "epoch": 3.5689084895259096,
2091
+ "grad_norm": 0.6730573773384094,
2092
+ "learning_rate": 0.0001930780559646539,
2093
+ "loss": 5.7444,
2094
+ "step": 2430
2095
+ },
2096
+ {
2097
+ "epoch": 3.583608967291437,
2098
+ "grad_norm": 0.7046417593955994,
2099
+ "learning_rate": 0.0001926362297496318,
2100
+ "loss": 5.7886,
2101
+ "step": 2440
2102
+ },
2103
+ {
2104
+ "epoch": 3.598309445056964,
2105
+ "grad_norm": 0.6981428265571594,
2106
+ "learning_rate": 0.00019219440353460972,
2107
+ "loss": 5.7708,
2108
+ "step": 2450
2109
+ },
2110
+ {
2111
+ "epoch": 3.598309445056964,
2112
+ "eval_loss": 0.8444002270698547,
2113
+ "eval_runtime": 122.7558,
2114
+ "eval_samples_per_second": 7.079,
2115
+ "eval_steps_per_second": 0.888,
2116
+ "step": 2450
2117
+ },
2118
+ {
2119
+ "epoch": 3.6130099228224917,
2120
+ "grad_norm": 0.6807316541671753,
2121
+ "learning_rate": 0.0001917525773195876,
2122
+ "loss": 5.7589,
2123
+ "step": 2460
2124
+ },
2125
+ {
2126
+ "epoch": 3.627710400588019,
2127
+ "grad_norm": 0.6898190975189209,
2128
+ "learning_rate": 0.00019131075110456552,
2129
+ "loss": 5.716,
2130
+ "step": 2470
2131
+ },
2132
+ {
2133
+ "epoch": 3.6424108783535463,
2134
+ "grad_norm": 0.6854293942451477,
2135
+ "learning_rate": 0.00019086892488954341,
2136
+ "loss": 5.7499,
2137
+ "step": 2480
2138
+ },
2139
+ {
2140
+ "epoch": 3.657111356119074,
2141
+ "grad_norm": 0.6629763245582581,
2142
+ "learning_rate": 0.00019042709867452134,
2143
+ "loss": 5.763,
2144
+ "step": 2490
2145
+ },
2146
+ {
2147
+ "epoch": 3.6718118338846013,
2148
+ "grad_norm": 0.6828572750091553,
2149
+ "learning_rate": 0.00018998527245949923,
2150
+ "loss": 5.748,
2151
+ "step": 2500
2152
+ },
2153
+ {
2154
+ "epoch": 3.6718118338846013,
2155
+ "eval_loss": 0.8433157801628113,
2156
+ "eval_runtime": 122.7268,
2157
+ "eval_samples_per_second": 7.081,
2158
+ "eval_steps_per_second": 0.888,
2159
+ "step": 2500
2160
+ },
2161
+ {
2162
+ "epoch": 3.6865123116501284,
2163
+ "grad_norm": 0.6758775115013123,
2164
+ "learning_rate": 0.00018954344624447716,
2165
+ "loss": 5.8063,
2166
+ "step": 2510
2167
+ },
2168
+ {
2169
+ "epoch": 3.701212789415656,
2170
+ "grad_norm": 0.699603796005249,
2171
+ "learning_rate": 0.00018910162002945506,
2172
+ "loss": 5.7323,
2173
+ "step": 2520
2174
+ },
2175
+ {
2176
+ "epoch": 3.7159132671811834,
2177
+ "grad_norm": 0.6797698140144348,
2178
+ "learning_rate": 0.00018865979381443298,
2179
+ "loss": 5.7159,
2180
+ "step": 2530
2181
+ },
2182
+ {
2183
+ "epoch": 3.7306137449467105,
2184
+ "grad_norm": 0.7055732011795044,
2185
+ "learning_rate": 0.00018821796759941088,
2186
+ "loss": 5.7788,
2187
+ "step": 2540
2188
+ },
2189
+ {
2190
+ "epoch": 3.745314222712238,
2191
+ "grad_norm": 0.6939615607261658,
2192
+ "learning_rate": 0.0001877761413843888,
2193
+ "loss": 5.8017,
2194
+ "step": 2550
2195
+ },
2196
+ {
2197
+ "epoch": 3.745314222712238,
2198
+ "eval_loss": 0.8415707349777222,
2199
+ "eval_runtime": 122.7864,
2200
+ "eval_samples_per_second": 7.077,
2201
+ "eval_steps_per_second": 0.888,
2202
+ "step": 2550
2203
+ },
2204
+ {
2205
+ "epoch": 3.7600147004777655,
2206
+ "grad_norm": 0.6803593635559082,
2207
+ "learning_rate": 0.0001873343151693667,
2208
+ "loss": 5.7542,
2209
+ "step": 2560
2210
+ },
2211
+ {
2212
+ "epoch": 3.774715178243293,
2213
+ "grad_norm": 0.6966648101806641,
2214
+ "learning_rate": 0.00018689248895434462,
2215
+ "loss": 5.7682,
2216
+ "step": 2570
2217
+ },
2218
+ {
2219
+ "epoch": 3.78941565600882,
2220
+ "grad_norm": 0.6992161870002747,
2221
+ "learning_rate": 0.00018645066273932252,
2222
+ "loss": 5.7216,
2223
+ "step": 2580
2224
+ },
2225
+ {
2226
+ "epoch": 3.8041161337743477,
2227
+ "grad_norm": 0.6834452152252197,
2228
+ "learning_rate": 0.00018600883652430044,
2229
+ "loss": 5.7347,
2230
+ "step": 2590
2231
+ },
2232
+ {
2233
+ "epoch": 3.818816611539875,
2234
+ "grad_norm": 0.6835057139396667,
2235
+ "learning_rate": 0.00018556701030927834,
2236
+ "loss": 5.7475,
2237
+ "step": 2600
2238
+ },
2239
+ {
2240
+ "epoch": 3.818816611539875,
2241
+ "eval_loss": 0.8405690789222717,
2242
+ "eval_runtime": 122.7131,
2243
+ "eval_samples_per_second": 7.082,
2244
+ "eval_steps_per_second": 0.888,
2245
+ "step": 2600
2246
+ },
2247
+ {
2248
+ "epoch": 3.8335170893054027,
2249
+ "grad_norm": 0.6868228316307068,
2250
+ "learning_rate": 0.00018512518409425626,
2251
+ "loss": 5.7805,
2252
+ "step": 2610
2253
+ },
2254
+ {
2255
+ "epoch": 3.8482175670709298,
2256
+ "grad_norm": 0.6829861402511597,
2257
+ "learning_rate": 0.00018468335787923416,
2258
+ "loss": 5.7193,
2259
+ "step": 2620
2260
+ },
2261
+ {
2262
+ "epoch": 3.8629180448364573,
2263
+ "grad_norm": 0.6857191920280457,
2264
+ "learning_rate": 0.00018424153166421206,
2265
+ "loss": 5.7893,
2266
+ "step": 2630
2267
+ },
2268
+ {
2269
+ "epoch": 3.877618522601985,
2270
+ "grad_norm": 0.6723675727844238,
2271
+ "learning_rate": 0.00018379970544918998,
2272
+ "loss": 5.7788,
2273
+ "step": 2640
2274
+ },
2275
+ {
2276
+ "epoch": 3.892319000367512,
2277
+ "grad_norm": 0.6871203780174255,
2278
+ "learning_rate": 0.00018335787923416788,
2279
+ "loss": 5.7881,
2280
+ "step": 2650
2281
+ },
2282
+ {
2283
+ "epoch": 3.892319000367512,
2284
+ "eval_loss": 0.8391252160072327,
2285
+ "eval_runtime": 122.6983,
2286
+ "eval_samples_per_second": 7.082,
2287
+ "eval_steps_per_second": 0.888,
2288
+ "step": 2650
2289
+ },
2290
+ {
2291
+ "epoch": 3.9070194781330394,
2292
+ "grad_norm": 0.6965262293815613,
2293
+ "learning_rate": 0.0001829160530191458,
2294
+ "loss": 5.7777,
2295
+ "step": 2660
2296
+ },
2297
+ {
2298
+ "epoch": 3.921719955898567,
2299
+ "grad_norm": 0.6634519696235657,
2300
+ "learning_rate": 0.00018247422680412367,
2301
+ "loss": 5.7385,
2302
+ "step": 2670
2303
+ },
2304
+ {
2305
+ "epoch": 3.936420433664094,
2306
+ "grad_norm": 0.658750593662262,
2307
+ "learning_rate": 0.0001820324005891016,
2308
+ "loss": 5.7514,
2309
+ "step": 2680
2310
+ },
2311
+ {
2312
+ "epoch": 3.9511209114296215,
2313
+ "grad_norm": 0.6765331029891968,
2314
+ "learning_rate": 0.0001815905743740795,
2315
+ "loss": 5.7902,
2316
+ "step": 2690
2317
+ },
2318
+ {
2319
+ "epoch": 3.965821389195149,
2320
+ "grad_norm": 0.684141993522644,
2321
+ "learning_rate": 0.00018114874815905742,
2322
+ "loss": 5.8105,
2323
+ "step": 2700
2324
+ },
2325
+ {
2326
+ "epoch": 3.965821389195149,
2327
+ "eval_loss": 0.8379185795783997,
2328
+ "eval_runtime": 122.8086,
2329
+ "eval_samples_per_second": 7.076,
2330
+ "eval_steps_per_second": 0.888,
2331
+ "step": 2700
2332
+ },
2333
+ {
2334
+ "epoch": 3.980521866960676,
2335
+ "grad_norm": 0.668866753578186,
2336
+ "learning_rate": 0.00018070692194403532,
2337
+ "loss": 5.7643,
2338
+ "step": 2710
2339
+ },
2340
+ {
2341
+ "epoch": 3.9952223447262036,
2342
+ "grad_norm": 0.6660596132278442,
2343
+ "learning_rate": 0.00018026509572901324,
2344
+ "loss": 5.757,
2345
+ "step": 2720
2346
+ },
2347
+ {
2348
+ "epoch": 4.008820286659317,
2349
+ "grad_norm": 1.04069983959198,
2350
+ "learning_rate": 0.00017982326951399114,
2351
+ "loss": 5.0052,
2352
+ "step": 2730
2353
+ },
2354
+ {
2355
+ "epoch": 4.023520764424844,
2356
+ "grad_norm": 0.7606070637702942,
2357
+ "learning_rate": 0.00017938144329896906,
2358
+ "loss": 5.2139,
2359
+ "step": 2740
2360
+ },
2361
+ {
2362
+ "epoch": 4.038221242190371,
2363
+ "grad_norm": 0.743680477142334,
2364
+ "learning_rate": 0.00017893961708394696,
2365
+ "loss": 5.1857,
2366
+ "step": 2750
2367
+ },
2368
+ {
2369
+ "epoch": 4.038221242190371,
2370
+ "eval_loss": 0.8622083067893982,
2371
+ "eval_runtime": 122.732,
2372
+ "eval_samples_per_second": 7.08,
2373
+ "eval_steps_per_second": 0.888,
2374
+ "step": 2750
2375
+ },
2376
+ {
2377
+ "epoch": 4.052921719955899,
2378
+ "grad_norm": 0.7183839678764343,
2379
+ "learning_rate": 0.00017849779086892488,
2380
+ "loss": 5.1678,
2381
+ "step": 2760
2382
+ },
2383
+ {
2384
+ "epoch": 4.067622197721426,
2385
+ "grad_norm": 0.7291563153266907,
2386
+ "learning_rate": 0.00017805596465390278,
2387
+ "loss": 5.2046,
2388
+ "step": 2770
2389
+ },
2390
+ {
2391
+ "epoch": 4.082322675486953,
2392
+ "grad_norm": 0.7452117204666138,
2393
+ "learning_rate": 0.0001776141384388807,
2394
+ "loss": 5.1908,
2395
+ "step": 2780
2396
+ },
2397
+ {
2398
+ "epoch": 4.097023153252481,
2399
+ "grad_norm": 0.730151355266571,
2400
+ "learning_rate": 0.0001771723122238586,
2401
+ "loss": 5.1827,
2402
+ "step": 2790
2403
+ },
2404
+ {
2405
+ "epoch": 4.111723631018008,
2406
+ "grad_norm": 0.7287917137145996,
2407
+ "learning_rate": 0.00017673048600883653,
2408
+ "loss": 5.2302,
2409
+ "step": 2800
2410
+ },
2411
+ {
2412
+ "epoch": 4.111723631018008,
2413
+ "eval_loss": 0.8607571125030518,
2414
+ "eval_runtime": 122.8437,
2415
+ "eval_samples_per_second": 7.074,
2416
+ "eval_steps_per_second": 0.887,
2417
+ "step": 2800
2418
+ },
2419
+ {
2420
+ "epoch": 4.126424108783535,
2421
+ "grad_norm": 0.7352184653282166,
2422
+ "learning_rate": 0.00017628865979381442,
2423
+ "loss": 5.2023,
2424
+ "step": 2810
2425
+ },
2426
+ {
2427
+ "epoch": 4.141124586549063,
2428
+ "grad_norm": 0.7560921311378479,
2429
+ "learning_rate": 0.00017584683357879235,
2430
+ "loss": 5.1905,
2431
+ "step": 2820
2432
+ },
2433
+ {
2434
+ "epoch": 4.15582506431459,
2435
+ "grad_norm": 0.7419695258140564,
2436
+ "learning_rate": 0.00017540500736377024,
2437
+ "loss": 5.187,
2438
+ "step": 2830
2439
+ },
2440
+ {
2441
+ "epoch": 4.170525542080117,
2442
+ "grad_norm": 0.7407976388931274,
2443
+ "learning_rate": 0.00017496318114874817,
2444
+ "loss": 5.2322,
2445
+ "step": 2840
2446
+ },
2447
+ {
2448
+ "epoch": 4.185226019845645,
2449
+ "grad_norm": 0.7482364773750305,
2450
+ "learning_rate": 0.00017452135493372606,
2451
+ "loss": 5.2617,
2452
+ "step": 2850
2453
+ },
2454
+ {
2455
+ "epoch": 4.185226019845645,
2456
+ "eval_loss": 0.8609734177589417,
2457
+ "eval_runtime": 122.7306,
2458
+ "eval_samples_per_second": 7.081,
2459
+ "eval_steps_per_second": 0.888,
2460
+ "step": 2850
2461
+ },
2462
+ {
2463
+ "epoch": 4.199926497611172,
2464
+ "grad_norm": 0.7562023997306824,
2465
+ "learning_rate": 0.000174079528718704,
2466
+ "loss": 5.2432,
2467
+ "step": 2860
2468
+ },
2469
+ {
2470
+ "epoch": 4.214626975376699,
2471
+ "grad_norm": 0.76356440782547,
2472
+ "learning_rate": 0.00017363770250368189,
2473
+ "loss": 5.2342,
2474
+ "step": 2870
2475
+ },
2476
+ {
2477
+ "epoch": 4.229327453142227,
2478
+ "grad_norm": 0.7754319906234741,
2479
+ "learning_rate": 0.00017319587628865976,
2480
+ "loss": 5.2736,
2481
+ "step": 2880
2482
+ },
2483
+ {
2484
+ "epoch": 4.244027930907754,
2485
+ "grad_norm": 0.7472639679908752,
2486
+ "learning_rate": 0.00017275405007363768,
2487
+ "loss": 5.1607,
2488
+ "step": 2890
2489
+ },
2490
+ {
2491
+ "epoch": 4.2587284086732815,
2492
+ "grad_norm": 0.759757936000824,
2493
+ "learning_rate": 0.00017231222385861558,
2494
+ "loss": 5.2299,
2495
+ "step": 2900
2496
+ },
2497
+ {
2498
+ "epoch": 4.2587284086732815,
2499
+ "eval_loss": 0.8612560629844666,
2500
+ "eval_runtime": 122.7459,
2501
+ "eval_samples_per_second": 7.08,
2502
+ "eval_steps_per_second": 0.888,
2503
+ "step": 2900
2504
+ },
2505
+ {
2506
+ "epoch": 4.2734288864388095,
2507
+ "grad_norm": 0.80708247423172,
2508
+ "learning_rate": 0.0001718703976435935,
2509
+ "loss": 5.2688,
2510
+ "step": 2910
2511
+ },
2512
+ {
2513
+ "epoch": 4.2881293642043365,
2514
+ "grad_norm": 0.7704065442085266,
2515
+ "learning_rate": 0.0001714285714285714,
2516
+ "loss": 5.2478,
2517
+ "step": 2920
2518
+ },
2519
+ {
2520
+ "epoch": 4.302829841969864,
2521
+ "grad_norm": 0.7821296453475952,
2522
+ "learning_rate": 0.00017098674521354932,
2523
+ "loss": 5.2805,
2524
+ "step": 2930
2525
+ },
2526
+ {
2527
+ "epoch": 4.317530319735392,
2528
+ "grad_norm": 0.7851975560188293,
2529
+ "learning_rate": 0.00017054491899852722,
2530
+ "loss": 5.246,
2531
+ "step": 2940
2532
+ },
2533
+ {
2534
+ "epoch": 4.332230797500919,
2535
+ "grad_norm": 0.7333672046661377,
2536
+ "learning_rate": 0.00017010309278350514,
2537
+ "loss": 5.2627,
2538
+ "step": 2950
2539
+ },
2540
+ {
2541
+ "epoch": 4.332230797500919,
2542
+ "eval_loss": 0.8597420454025269,
2543
+ "eval_runtime": 122.891,
2544
+ "eval_samples_per_second": 7.071,
2545
+ "eval_steps_per_second": 0.887,
2546
+ "step": 2950
2547
+ },
2548
+ {
2549
+ "epoch": 4.346931275266446,
2550
+ "grad_norm": 0.7573877573013306,
2551
+ "learning_rate": 0.00016966126656848304,
2552
+ "loss": 5.2539,
2553
+ "step": 2960
2554
+ },
2555
+ {
2556
+ "epoch": 4.361631753031974,
2557
+ "grad_norm": 0.7531468272209167,
2558
+ "learning_rate": 0.00016921944035346096,
2559
+ "loss": 5.2819,
2560
+ "step": 2970
2561
+ },
2562
+ {
2563
+ "epoch": 4.376332230797501,
2564
+ "grad_norm": 0.7768471837043762,
2565
+ "learning_rate": 0.00016877761413843886,
2566
+ "loss": 5.2684,
2567
+ "step": 2980
2568
+ },
2569
+ {
2570
+ "epoch": 4.391032708563028,
2571
+ "grad_norm": 0.7904699444770813,
2572
+ "learning_rate": 0.00016833578792341679,
2573
+ "loss": 5.2538,
2574
+ "step": 2990
2575
+ },
2576
+ {
2577
+ "epoch": 4.405733186328556,
2578
+ "grad_norm": 0.8030019402503967,
2579
+ "learning_rate": 0.00016789396170839468,
2580
+ "loss": 5.2828,
2581
+ "step": 3000
2582
+ },
2583
+ {
2584
+ "epoch": 4.405733186328556,
2585
+ "eval_loss": 0.8594609498977661,
2586
+ "eval_runtime": 122.7873,
2587
+ "eval_samples_per_second": 7.077,
2588
+ "eval_steps_per_second": 0.888,
2589
+ "step": 3000
2590
+ },
2591
+ {
2592
+ "epoch": 4.420433664094083,
2593
+ "grad_norm": 0.751737117767334,
2594
+ "learning_rate": 0.0001674521354933726,
2595
+ "loss": 5.3038,
2596
+ "step": 3010
2597
+ },
2598
+ {
2599
+ "epoch": 4.43513414185961,
2600
+ "grad_norm": 0.7465061545372009,
2601
+ "learning_rate": 0.0001670103092783505,
2602
+ "loss": 5.2605,
2603
+ "step": 3020
2604
+ },
2605
+ {
2606
+ "epoch": 4.449834619625138,
2607
+ "grad_norm": 0.759131669998169,
2608
+ "learning_rate": 0.00016656848306332843,
2609
+ "loss": 5.2886,
2610
+ "step": 3030
2611
+ },
2612
+ {
2613
+ "epoch": 4.464535097390665,
2614
+ "grad_norm": 0.7656858563423157,
2615
+ "learning_rate": 0.00016612665684830633,
2616
+ "loss": 5.2273,
2617
+ "step": 3040
2618
+ },
2619
+ {
2620
+ "epoch": 4.479235575156193,
2621
+ "grad_norm": 0.7533978223800659,
2622
+ "learning_rate": 0.00016568483063328425,
2623
+ "loss": 5.2777,
2624
+ "step": 3050
2625
+ },
2626
+ {
2627
+ "epoch": 4.479235575156193,
2628
+ "eval_loss": 0.8585497140884399,
2629
+ "eval_runtime": 122.7392,
2630
+ "eval_samples_per_second": 7.08,
2631
+ "eval_steps_per_second": 0.888,
2632
+ "step": 3050
2633
+ },
2634
+ {
2635
+ "epoch": 4.49393605292172,
2636
+ "grad_norm": 0.7555689811706543,
2637
+ "learning_rate": 0.00016524300441826215,
2638
+ "loss": 5.2478,
2639
+ "step": 3060
2640
+ },
2641
+ {
2642
+ "epoch": 4.508636530687247,
2643
+ "grad_norm": 0.7516697645187378,
2644
+ "learning_rate": 0.00016480117820324007,
2645
+ "loss": 5.2559,
2646
+ "step": 3070
2647
+ },
2648
+ {
2649
+ "epoch": 4.523337008452775,
2650
+ "grad_norm": 0.7887890934944153,
2651
+ "learning_rate": 0.00016435935198821797,
2652
+ "loss": 5.3158,
2653
+ "step": 3080
2654
+ },
2655
+ {
2656
+ "epoch": 4.538037486218302,
2657
+ "grad_norm": 0.7691967487335205,
2658
+ "learning_rate": 0.00016391752577319584,
2659
+ "loss": 5.2946,
2660
+ "step": 3090
2661
+ },
2662
+ {
2663
+ "epoch": 4.552737963983829,
2664
+ "grad_norm": 0.7757486701011658,
2665
+ "learning_rate": 0.00016347569955817376,
2666
+ "loss": 5.2849,
2667
+ "step": 3100
2668
+ },
2669
+ {
2670
+ "epoch": 4.552737963983829,
2671
+ "eval_loss": 0.8570435047149658,
2672
+ "eval_runtime": 122.7277,
2673
+ "eval_samples_per_second": 7.081,
2674
+ "eval_steps_per_second": 0.888,
2675
+ "step": 3100
2676
+ },
2677
+ {
2678
+ "epoch": 4.567438441749357,
2679
+ "grad_norm": 0.7805380821228027,
2680
+ "learning_rate": 0.00016303387334315166,
2681
+ "loss": 5.3412,
2682
+ "step": 3110
2683
+ },
2684
+ {
2685
+ "epoch": 4.582138919514884,
2686
+ "grad_norm": 0.7780531048774719,
2687
+ "learning_rate": 0.00016259204712812958,
2688
+ "loss": 5.2718,
2689
+ "step": 3120
2690
+ },
2691
+ {
2692
+ "epoch": 4.596839397280411,
2693
+ "grad_norm": 0.7380784749984741,
2694
+ "learning_rate": 0.00016215022091310748,
2695
+ "loss": 5.3036,
2696
+ "step": 3130
2697
+ },
2698
+ {
2699
+ "epoch": 4.611539875045939,
2700
+ "grad_norm": 0.7692278623580933,
2701
+ "learning_rate": 0.0001617083946980854,
2702
+ "loss": 5.3028,
2703
+ "step": 3140
2704
+ },
2705
+ {
2706
+ "epoch": 4.626240352811466,
2707
+ "grad_norm": 0.7445947527885437,
2708
+ "learning_rate": 0.0001612665684830633,
2709
+ "loss": 5.2811,
2710
+ "step": 3150
2711
+ },
2712
+ {
2713
+ "epoch": 4.626240352811466,
2714
+ "eval_loss": 0.8577845692634583,
2715
+ "eval_runtime": 122.7855,
2716
+ "eval_samples_per_second": 7.077,
2717
+ "eval_steps_per_second": 0.888,
2718
+ "step": 3150
2719
+ },
2720
+ {
2721
+ "epoch": 4.6409408305769935,
2722
+ "grad_norm": 0.7451578974723816,
2723
+ "learning_rate": 0.00016082474226804122,
2724
+ "loss": 5.3035,
2725
+ "step": 3160
2726
+ },
2727
+ {
2728
+ "epoch": 4.655641308342521,
2729
+ "grad_norm": 0.7448246479034424,
2730
+ "learning_rate": 0.00016038291605301912,
2731
+ "loss": 5.2956,
2732
+ "step": 3170
2733
+ },
2734
+ {
2735
+ "epoch": 4.6703417861080485,
2736
+ "grad_norm": 0.7711780071258545,
2737
+ "learning_rate": 0.00015994108983799705,
2738
+ "loss": 5.281,
2739
+ "step": 3180
2740
+ },
2741
+ {
2742
+ "epoch": 4.685042263873576,
2743
+ "grad_norm": 0.7698442339897156,
2744
+ "learning_rate": 0.00015949926362297494,
2745
+ "loss": 5.3382,
2746
+ "step": 3190
2747
+ },
2748
+ {
2749
+ "epoch": 4.6997427416391035,
2750
+ "grad_norm": 0.7665743231773376,
2751
+ "learning_rate": 0.00015905743740795287,
2752
+ "loss": 5.2781,
2753
+ "step": 3200
2754
+ },
2755
+ {
2756
+ "epoch": 4.6997427416391035,
2757
+ "eval_loss": 0.8565701842308044,
2758
+ "eval_runtime": 122.777,
2759
+ "eval_samples_per_second": 7.078,
2760
+ "eval_steps_per_second": 0.888,
2761
+ "step": 3200
2762
+ },
2763
+ {
2764
+ "epoch": 4.714443219404631,
2765
+ "grad_norm": 0.7319465279579163,
2766
+ "learning_rate": 0.00015861561119293076,
2767
+ "loss": 5.3044,
2768
+ "step": 3210
2769
+ },
2770
+ {
2771
+ "epoch": 4.729143697170158,
2772
+ "grad_norm": 0.7576644420623779,
2773
+ "learning_rate": 0.0001581737849779087,
2774
+ "loss": 5.3616,
2775
+ "step": 3220
2776
+ },
2777
+ {
2778
+ "epoch": 4.743844174935686,
2779
+ "grad_norm": 0.7484728693962097,
2780
+ "learning_rate": 0.00015773195876288659,
2781
+ "loss": 5.3121,
2782
+ "step": 3230
2783
+ },
2784
+ {
2785
+ "epoch": 4.758544652701213,
2786
+ "grad_norm": 0.7493030428886414,
2787
+ "learning_rate": 0.0001572901325478645,
2788
+ "loss": 5.2786,
2789
+ "step": 3240
2790
+ },
2791
+ {
2792
+ "epoch": 4.77324513046674,
2793
+ "grad_norm": 0.7527353763580322,
2794
+ "learning_rate": 0.0001568483063328424,
2795
+ "loss": 5.3367,
2796
+ "step": 3250
2797
+ },
2798
+ {
2799
+ "epoch": 4.77324513046674,
2800
+ "eval_loss": 0.8557420372962952,
2801
+ "eval_runtime": 122.7867,
2802
+ "eval_samples_per_second": 7.077,
2803
+ "eval_steps_per_second": 0.888,
2804
+ "step": 3250
2805
+ },
2806
+ {
2807
+ "epoch": 4.787945608232268,
2808
+ "grad_norm": 0.7508755326271057,
2809
+ "learning_rate": 0.00015640648011782033,
2810
+ "loss": 5.3221,
2811
+ "step": 3260
2812
+ },
2813
+ {
2814
+ "epoch": 4.802646085997795,
2815
+ "grad_norm": 0.7572493553161621,
2816
+ "learning_rate": 0.00015596465390279823,
2817
+ "loss": 5.2777,
2818
+ "step": 3270
2819
+ },
2820
+ {
2821
+ "epoch": 4.817346563763322,
2822
+ "grad_norm": 0.7531789541244507,
2823
+ "learning_rate": 0.00015552282768777615,
2824
+ "loss": 5.2999,
2825
+ "step": 3280
2826
+ },
2827
+ {
2828
+ "epoch": 4.83204704152885,
2829
+ "grad_norm": 0.7436636686325073,
2830
+ "learning_rate": 0.00015508100147275405,
2831
+ "loss": 5.2683,
2832
+ "step": 3290
2833
+ },
2834
+ {
2835
+ "epoch": 4.846747519294377,
2836
+ "grad_norm": 0.746624767780304,
2837
+ "learning_rate": 0.00015463917525773192,
2838
+ "loss": 5.3402,
2839
+ "step": 3300
2840
+ },
2841
+ {
2842
+ "epoch": 4.846747519294377,
2843
+ "eval_loss": 0.8542863726615906,
2844
+ "eval_runtime": 122.7376,
2845
+ "eval_samples_per_second": 7.08,
2846
+ "eval_steps_per_second": 0.888,
2847
+ "step": 3300
2848
+ },
2849
+ {
2850
+ "epoch": 4.861447997059905,
2851
+ "grad_norm": 0.7520425319671631,
2852
+ "learning_rate": 0.00015419734904270984,
2853
+ "loss": 5.3424,
2854
+ "step": 3310
2855
+ },
2856
+ {
2857
+ "epoch": 4.876148474825432,
2858
+ "grad_norm": 0.7883239388465881,
2859
+ "learning_rate": 0.00015375552282768774,
2860
+ "loss": 5.3252,
2861
+ "step": 3320
2862
+ },
2863
+ {
2864
+ "epoch": 4.890848952590959,
2865
+ "grad_norm": 0.7612333297729492,
2866
+ "learning_rate": 0.00015331369661266566,
2867
+ "loss": 5.314,
2868
+ "step": 3330
2869
+ },
2870
+ {
2871
+ "epoch": 4.905549430356487,
2872
+ "grad_norm": 0.7855140566825867,
2873
+ "learning_rate": 0.00015287187039764356,
2874
+ "loss": 5.2951,
2875
+ "step": 3340
2876
+ },
2877
+ {
2878
+ "epoch": 4.920249908122014,
2879
+ "grad_norm": 0.7624037861824036,
2880
+ "learning_rate": 0.00015243004418262149,
2881
+ "loss": 5.331,
2882
+ "step": 3350
2883
+ },
2884
+ {
2885
+ "epoch": 4.920249908122014,
2886
+ "eval_loss": 0.8540411591529846,
2887
+ "eval_runtime": 122.7574,
2888
+ "eval_samples_per_second": 7.079,
2889
+ "eval_steps_per_second": 0.888,
2890
+ "step": 3350
2891
+ },
2892
+ {
2893
+ "epoch": 4.934950385887541,
2894
+ "grad_norm": 0.7521130442619324,
2895
+ "learning_rate": 0.00015198821796759938,
2896
+ "loss": 5.2818,
2897
+ "step": 3360
2898
+ }
2899
+ ],
2900
+ "logging_steps": 10,
2901
+ "max_steps": 6800,
2902
+ "num_input_tokens_seen": 0,
2903
+ "num_train_epochs": 10,
2904
+ "save_steps": 120,
2905
+ "stateful_callbacks": {
2906
+ "TrainerControl": {
2907
+ "args": {
2908
+ "should_epoch_stop": false,
2909
+ "should_evaluate": false,
2910
+ "should_log": false,
2911
+ "should_save": true,
2912
+ "should_training_stop": false
2913
+ },
2914
+ "attributes": {}
2915
+ }
2916
+ },
2917
+ "total_flos": 1.7030313392487583e+20,
2918
+ "train_batch_size": 4,
2919
+ "trial_name": null,
2920
+ "trial_params": null
2921
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d183e6b3d7208d685885ae80e03295abde9a377356244073e5851097d4b37bc0
3
+ size 5560
vocab.json ADDED
The diff for this file is too large to render. See raw diff