Hugging Face's logo

JerryFan011018
/
Qwen-Code-7B_2

TensorBoard
Safetensors
qwen2
4-bit precision
bitsandbytes
Model card Files
xet
Metrics Community
JerryFan011018 commited on
Commit
0f60832
·
verified ·
1 Parent(s): b38ada8

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +15 -0
  2. checkpoint-1050/README.md +202 -0
  3. checkpoint-1050/adapter_config.json +37 -0
  4. checkpoint-1050/adapter_model.safetensors +3 -0
  5. checkpoint-1050/added_tokens.json +24 -0
  6. checkpoint-1050/merges.txt +0 -0
  7. checkpoint-1050/optimizer.pt +3 -0
  8. checkpoint-1050/rng_state.pth +3 -0
  9. checkpoint-1050/scheduler.pt +3 -0
  10. checkpoint-1050/special_tokens_map.json +31 -0
  11. checkpoint-1050/tokenizer.json +3 -0
  12. checkpoint-1050/tokenizer_config.json +208 -0
  13. checkpoint-1050/trainer_state.json +1119 -0
  14. checkpoint-1050/training_args.bin +3 -0
  15. checkpoint-1050/vocab.json +0 -0
  16. checkpoint-1125/README.md +202 -0
  17. checkpoint-1125/adapter_config.json +37 -0
  18. checkpoint-1125/adapter_model.safetensors +3 -0
  19. checkpoint-1125/added_tokens.json +24 -0
  20. checkpoint-1125/merges.txt +0 -0
  21. checkpoint-1125/optimizer.pt +3 -0
  22. checkpoint-1125/rng_state.pth +3 -0
  23. checkpoint-1125/scheduler.pt +3 -0
  24. checkpoint-1125/special_tokens_map.json +31 -0
  25. checkpoint-1125/tokenizer.json +3 -0
  26. checkpoint-1125/tokenizer_config.json +208 -0
  27. checkpoint-1125/trainer_state.json +1192 -0
  28. checkpoint-1125/training_args.bin +3 -0
  29. checkpoint-1125/vocab.json +0 -0
  30. checkpoint-150/README.md +202 -0
  31. checkpoint-150/adapter_config.json +37 -0
  32. checkpoint-150/adapter_model.safetensors +3 -0
  33. checkpoint-150/added_tokens.json +24 -0
  34. checkpoint-150/merges.txt +0 -0
  35. checkpoint-150/optimizer.pt +3 -0
  36. checkpoint-150/rng_state.pth +3 -0
  37. checkpoint-150/scheduler.pt +3 -0
  38. checkpoint-150/special_tokens_map.json +31 -0
  39. checkpoint-150/tokenizer.json +3 -0
  40. checkpoint-150/tokenizer_config.json +208 -0
  41. checkpoint-150/trainer_state.json +189 -0
  42. checkpoint-150/training_args.bin +3 -0
  43. checkpoint-150/vocab.json +0 -0
  44. checkpoint-225/README.md +202 -0
  45. checkpoint-225/adapter_config.json +37 -0
  46. checkpoint-225/adapter_model.safetensors +3 -0
  47. checkpoint-225/added_tokens.json +24 -0
  48. checkpoint-225/merges.txt +0 -0
  49. checkpoint-225/optimizer.pt +3 -0
  50. checkpoint-225/rng_state.pth +3 -0
.gitattributes CHANGED
@@ -33,3 +33,18 @@ 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
+ checkpoint-1050/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-1125/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ checkpoint-150/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ checkpoint-225/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
+ checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
+ checkpoint-375/tokenizer.json filter=lfs diff=lfs merge=lfs -text
42
+ checkpoint-450/tokenizer.json filter=lfs diff=lfs merge=lfs -text
43
+ checkpoint-525/tokenizer.json filter=lfs diff=lfs merge=lfs -text
44
+ checkpoint-600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
45
+ checkpoint-675/tokenizer.json filter=lfs diff=lfs merge=lfs -text
46
+ checkpoint-75/tokenizer.json filter=lfs diff=lfs merge=lfs -text
47
+ checkpoint-750/tokenizer.json filter=lfs diff=lfs merge=lfs -text
48
+ checkpoint-825/tokenizer.json filter=lfs diff=lfs merge=lfs -text
49
+ checkpoint-900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
50
+ checkpoint-975/tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoint-1050/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-7B-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
checkpoint-1050/adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-7B-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": 0.1,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 16,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "down_proj",
27
+ "k_proj",
28
+ "up_proj",
29
+ "o_proj",
30
+ "v_proj",
31
+ "gate_proj",
32
+ "q_proj"
33
+ ],
34
+ "task_type": "CAUSAL_LM",
35
+ "use_dora": false,
36
+ "use_rslora": false
37
+ }
checkpoint-1050/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7894cb4a70bebe35dd788cc5f5fe36a54dec88ce996c4d49595b711d662c70f
3
+ size 161533192
checkpoint-1050/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
+ }
checkpoint-1050/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1050/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:213748181183adb3451f6cae7b80a243a63b0646bef8f3c2ffdc2f399ec2f176
3
+ size 82461044
checkpoint-1050/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c232116e8837e4cb94bd94366c699fe0d6b41a79d2a34bd1aa84d10ba364c8db
3
+ size 14244
checkpoint-1050/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef5652852026467d6003252bdb9856e1cf1344352461aeb3920751180095e667
3
+ size 1064
checkpoint-1050/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
checkpoint-1050/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
checkpoint-1050/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": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
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": null,
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
+ }
checkpoint-1050/trainer_state.json ADDED
@@ -0,0 +1,1119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 225,
3
+ "best_metric": 0.36194586753845215,
4
+ "best_model_checkpoint": "/content/output/checkpoint-225",
5
+ "epoch": 14.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1050,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.13333333333333333,
14
+ "grad_norm": 1.7940553426742554,
15
+ "learning_rate": 5.917159763313609e-06,
16
+ "loss": 1.3972,
17
+ "mean_token_accuracy": 0.7618847399950027,
18
+ "num_tokens": 31152.0,
19
+ "step": 10
20
+ },
21
+ {
22
+ "epoch": 0.26666666666666666,
23
+ "grad_norm": 1.0511088371276855,
24
+ "learning_rate": 1.1834319526627219e-05,
25
+ "loss": 1.2288,
26
+ "mean_token_accuracy": 0.7673537939786911,
27
+ "num_tokens": 61773.0,
28
+ "step": 20
29
+ },
30
+ {
31
+ "epoch": 0.4,
32
+ "grad_norm": 0.8096975088119507,
33
+ "learning_rate": 1.7751479289940828e-05,
34
+ "loss": 0.9255,
35
+ "mean_token_accuracy": 0.7948055118322372,
36
+ "num_tokens": 94758.0,
37
+ "step": 30
38
+ },
39
+ {
40
+ "epoch": 0.5333333333333333,
41
+ "grad_norm": 0.6213255524635315,
42
+ "learning_rate": 2.3668639053254438e-05,
43
+ "loss": 0.7366,
44
+ "mean_token_accuracy": 0.8212289035320282,
45
+ "num_tokens": 125915.0,
46
+ "step": 40
47
+ },
48
+ {
49
+ "epoch": 0.6666666666666666,
50
+ "grad_norm": 0.42887863516807556,
51
+ "learning_rate": 2.958579881656805e-05,
52
+ "loss": 0.5556,
53
+ "mean_token_accuracy": 0.8463607966899872,
54
+ "num_tokens": 159364.0,
55
+ "step": 50
56
+ },
57
+ {
58
+ "epoch": 0.8,
59
+ "grad_norm": 0.5108550786972046,
60
+ "learning_rate": 3.5502958579881656e-05,
61
+ "loss": 0.4676,
62
+ "mean_token_accuracy": 0.8614094287157059,
63
+ "num_tokens": 190374.0,
64
+ "step": 60
65
+ },
66
+ {
67
+ "epoch": 0.9333333333333333,
68
+ "grad_norm": 0.4310983121395111,
69
+ "learning_rate": 4.142011834319527e-05,
70
+ "loss": 0.4214,
71
+ "mean_token_accuracy": 0.8710317760705948,
72
+ "num_tokens": 222156.0,
73
+ "step": 70
74
+ },
75
+ {
76
+ "epoch": 1.0,
77
+ "eval_loss": 0.4043419659137726,
78
+ "eval_mean_token_accuracy": 0.8734077858924866,
79
+ "eval_num_tokens": 238011.0,
80
+ "eval_runtime": 50.8925,
81
+ "eval_samples_per_second": 1.965,
82
+ "eval_steps_per_second": 0.491,
83
+ "step": 75
84
+ },
85
+ {
86
+ "epoch": 1.0666666666666667,
87
+ "grad_norm": 0.35767048597335815,
88
+ "learning_rate": 4.7337278106508875e-05,
89
+ "loss": 0.3901,
90
+ "mean_token_accuracy": 0.8787548273801804,
91
+ "num_tokens": 255825.0,
92
+ "step": 80
93
+ },
94
+ {
95
+ "epoch": 1.2,
96
+ "grad_norm": 0.3684692680835724,
97
+ "learning_rate": 5.3254437869822495e-05,
98
+ "loss": 0.3956,
99
+ "mean_token_accuracy": 0.8787799149751663,
100
+ "num_tokens": 287370.0,
101
+ "step": 90
102
+ },
103
+ {
104
+ "epoch": 1.3333333333333333,
105
+ "grad_norm": 0.35148611664772034,
106
+ "learning_rate": 5.91715976331361e-05,
107
+ "loss": 0.3822,
108
+ "mean_token_accuracy": 0.8814697057008744,
109
+ "num_tokens": 315883.0,
110
+ "step": 100
111
+ },
112
+ {
113
+ "epoch": 1.4666666666666668,
114
+ "grad_norm": 0.39074671268463135,
115
+ "learning_rate": 6.50887573964497e-05,
116
+ "loss": 0.3703,
117
+ "mean_token_accuracy": 0.8836676925420761,
118
+ "num_tokens": 347324.0,
119
+ "step": 110
120
+ },
121
+ {
122
+ "epoch": 1.6,
123
+ "grad_norm": 0.38130292296409607,
124
+ "learning_rate": 7.100591715976331e-05,
125
+ "loss": 0.3762,
126
+ "mean_token_accuracy": 0.8851484537124634,
127
+ "num_tokens": 379374.0,
128
+ "step": 120
129
+ },
130
+ {
131
+ "epoch": 1.7333333333333334,
132
+ "grad_norm": 0.4091486632823944,
133
+ "learning_rate": 7.692307692307693e-05,
134
+ "loss": 0.3446,
135
+ "mean_token_accuracy": 0.8894414573907852,
136
+ "num_tokens": 411843.0,
137
+ "step": 130
138
+ },
139
+ {
140
+ "epoch": 1.8666666666666667,
141
+ "grad_norm": 0.361017644405365,
142
+ "learning_rate": 8.284023668639054e-05,
143
+ "loss": 0.3494,
144
+ "mean_token_accuracy": 0.8915452778339386,
145
+ "num_tokens": 444017.0,
146
+ "step": 140
147
+ },
148
+ {
149
+ "epoch": 2.0,
150
+ "grad_norm": 0.3487047851085663,
151
+ "learning_rate": 8.875739644970414e-05,
152
+ "loss": 0.3674,
153
+ "mean_token_accuracy": 0.8846240967512131,
154
+ "num_tokens": 476022.0,
155
+ "step": 150
156
+ },
157
+ {
158
+ "epoch": 2.0,
159
+ "eval_loss": 0.3620273470878601,
160
+ "eval_mean_token_accuracy": 0.8875497984886169,
161
+ "eval_num_tokens": 476022.0,
162
+ "eval_runtime": 50.8961,
163
+ "eval_samples_per_second": 1.965,
164
+ "eval_steps_per_second": 0.491,
165
+ "step": 150
166
+ },
167
+ {
168
+ "epoch": 2.1333333333333333,
169
+ "grad_norm": 0.480814665555954,
170
+ "learning_rate": 9.467455621301775e-05,
171
+ "loss": 0.2974,
172
+ "mean_token_accuracy": 0.9050114572048187,
173
+ "num_tokens": 508445.0,
174
+ "step": 160
175
+ },
176
+ {
177
+ "epoch": 2.2666666666666666,
178
+ "grad_norm": 0.40775951743125916,
179
+ "learning_rate": 9.989539748953976e-05,
180
+ "loss": 0.2896,
181
+ "mean_token_accuracy": 0.9084265738725662,
182
+ "num_tokens": 541530.0,
183
+ "step": 170
184
+ },
185
+ {
186
+ "epoch": 2.4,
187
+ "grad_norm": 0.5174453854560852,
188
+ "learning_rate": 9.884937238493725e-05,
189
+ "loss": 0.29,
190
+ "mean_token_accuracy": 0.9073476493358612,
191
+ "num_tokens": 572212.0,
192
+ "step": 180
193
+ },
194
+ {
195
+ "epoch": 2.533333333333333,
196
+ "grad_norm": 0.5889921188354492,
197
+ "learning_rate": 9.780334728033474e-05,
198
+ "loss": 0.2828,
199
+ "mean_token_accuracy": 0.909446981549263,
200
+ "num_tokens": 603269.0,
201
+ "step": 190
202
+ },
203
+ {
204
+ "epoch": 2.6666666666666665,
205
+ "grad_norm": 0.5635319352149963,
206
+ "learning_rate": 9.675732217573223e-05,
207
+ "loss": 0.2744,
208
+ "mean_token_accuracy": 0.9101487964391708,
209
+ "num_tokens": 635792.0,
210
+ "step": 200
211
+ },
212
+ {
213
+ "epoch": 2.8,
214
+ "grad_norm": 0.609230637550354,
215
+ "learning_rate": 9.571129707112972e-05,
216
+ "loss": 0.2863,
217
+ "mean_token_accuracy": 0.9104649156332016,
218
+ "num_tokens": 666470.0,
219
+ "step": 210
220
+ },
221
+ {
222
+ "epoch": 2.9333333333333336,
223
+ "grad_norm": 0.5209991931915283,
224
+ "learning_rate": 9.46652719665272e-05,
225
+ "loss": 0.3027,
226
+ "mean_token_accuracy": 0.9050683736801147,
227
+ "num_tokens": 699119.0,
228
+ "step": 220
229
+ },
230
+ {
231
+ "epoch": 3.0,
232
+ "eval_loss": 0.36194586753845215,
233
+ "eval_mean_token_accuracy": 0.8886684679985046,
234
+ "eval_num_tokens": 714033.0,
235
+ "eval_runtime": 50.8962,
236
+ "eval_samples_per_second": 1.965,
237
+ "eval_steps_per_second": 0.491,
238
+ "step": 225
239
+ },
240
+ {
241
+ "epoch": 3.066666666666667,
242
+ "grad_norm": 0.5214265584945679,
243
+ "learning_rate": 9.361924686192469e-05,
244
+ "loss": 0.2371,
245
+ "mean_token_accuracy": 0.9248212277889252,
246
+ "num_tokens": 729520.0,
247
+ "step": 230
248
+ },
249
+ {
250
+ "epoch": 3.2,
251
+ "grad_norm": 0.7459234595298767,
252
+ "learning_rate": 9.257322175732218e-05,
253
+ "loss": 0.1874,
254
+ "mean_token_accuracy": 0.939895498752594,
255
+ "num_tokens": 759510.0,
256
+ "step": 240
257
+ },
258
+ {
259
+ "epoch": 3.3333333333333335,
260
+ "grad_norm": 0.614969789981842,
261
+ "learning_rate": 9.152719665271967e-05,
262
+ "loss": 0.1754,
263
+ "mean_token_accuracy": 0.943790751695633,
264
+ "num_tokens": 791875.0,
265
+ "step": 250
266
+ },
267
+ {
268
+ "epoch": 3.466666666666667,
269
+ "grad_norm": 0.8585807085037231,
270
+ "learning_rate": 9.048117154811716e-05,
271
+ "loss": 0.1794,
272
+ "mean_token_accuracy": 0.9401535421609879,
273
+ "num_tokens": 821467.0,
274
+ "step": 260
275
+ },
276
+ {
277
+ "epoch": 3.6,
278
+ "grad_norm": 0.6798614263534546,
279
+ "learning_rate": 8.943514644351465e-05,
280
+ "loss": 0.1754,
281
+ "mean_token_accuracy": 0.9439484149217605,
282
+ "num_tokens": 854000.0,
283
+ "step": 270
284
+ },
285
+ {
286
+ "epoch": 3.7333333333333334,
287
+ "grad_norm": 0.6594717502593994,
288
+ "learning_rate": 8.838912133891214e-05,
289
+ "loss": 0.179,
290
+ "mean_token_accuracy": 0.9433883309364319,
291
+ "num_tokens": 885296.0,
292
+ "step": 280
293
+ },
294
+ {
295
+ "epoch": 3.8666666666666667,
296
+ "grad_norm": 0.6909582614898682,
297
+ "learning_rate": 8.734309623430963e-05,
298
+ "loss": 0.1855,
299
+ "mean_token_accuracy": 0.9395292073488235,
300
+ "num_tokens": 919387.0,
301
+ "step": 290
302
+ },
303
+ {
304
+ "epoch": 4.0,
305
+ "grad_norm": 0.7755655646324158,
306
+ "learning_rate": 8.629707112970712e-05,
307
+ "loss": 0.1851,
308
+ "mean_token_accuracy": 0.9409447878599166,
309
+ "num_tokens": 952044.0,
310
+ "step": 300
311
+ },
312
+ {
313
+ "epoch": 4.0,
314
+ "eval_loss": 0.39551886916160583,
315
+ "eval_mean_token_accuracy": 0.887341833114624,
316
+ "eval_num_tokens": 952044.0,
317
+ "eval_runtime": 50.8937,
318
+ "eval_samples_per_second": 1.965,
319
+ "eval_steps_per_second": 0.491,
320
+ "step": 300
321
+ },
322
+ {
323
+ "epoch": 4.133333333333334,
324
+ "grad_norm": 0.6951614022254944,
325
+ "learning_rate": 8.525104602510461e-05,
326
+ "loss": 0.0942,
327
+ "mean_token_accuracy": 0.9724623709917068,
328
+ "num_tokens": 984335.0,
329
+ "step": 310
330
+ },
331
+ {
332
+ "epoch": 4.266666666666667,
333
+ "grad_norm": 0.6803505420684814,
334
+ "learning_rate": 8.42050209205021e-05,
335
+ "loss": 0.1073,
336
+ "mean_token_accuracy": 0.9653927534818649,
337
+ "num_tokens": 1014854.0,
338
+ "step": 320
339
+ },
340
+ {
341
+ "epoch": 4.4,
342
+ "grad_norm": 0.7284913063049316,
343
+ "learning_rate": 8.315899581589958e-05,
344
+ "loss": 0.1054,
345
+ "mean_token_accuracy": 0.9662943929433823,
346
+ "num_tokens": 1047986.0,
347
+ "step": 330
348
+ },
349
+ {
350
+ "epoch": 4.533333333333333,
351
+ "grad_norm": 0.6803147792816162,
352
+ "learning_rate": 8.211297071129707e-05,
353
+ "loss": 0.1065,
354
+ "mean_token_accuracy": 0.9682819366455078,
355
+ "num_tokens": 1079663.0,
356
+ "step": 340
357
+ },
358
+ {
359
+ "epoch": 4.666666666666667,
360
+ "grad_norm": 0.6864665150642395,
361
+ "learning_rate": 8.106694560669456e-05,
362
+ "loss": 0.1085,
363
+ "mean_token_accuracy": 0.9646553307771683,
364
+ "num_tokens": 1109495.0,
365
+ "step": 350
366
+ },
367
+ {
368
+ "epoch": 4.8,
369
+ "grad_norm": 0.7594568729400635,
370
+ "learning_rate": 8.002092050209205e-05,
371
+ "loss": 0.1079,
372
+ "mean_token_accuracy": 0.9674631506204605,
373
+ "num_tokens": 1141598.0,
374
+ "step": 360
375
+ },
376
+ {
377
+ "epoch": 4.933333333333334,
378
+ "grad_norm": 0.6360507607460022,
379
+ "learning_rate": 7.897489539748954e-05,
380
+ "loss": 0.118,
381
+ "mean_token_accuracy": 0.9628556370735168,
382
+ "num_tokens": 1172834.0,
383
+ "step": 370
384
+ },
385
+ {
386
+ "epoch": 5.0,
387
+ "eval_loss": 0.45760437846183777,
388
+ "eval_mean_token_accuracy": 0.8874933505058289,
389
+ "eval_num_tokens": 1190055.0,
390
+ "eval_runtime": 50.9015,
391
+ "eval_samples_per_second": 1.965,
392
+ "eval_steps_per_second": 0.491,
393
+ "step": 375
394
+ },
395
+ {
396
+ "epoch": 5.066666666666666,
397
+ "grad_norm": 0.4860494136810303,
398
+ "learning_rate": 7.792887029288704e-05,
399
+ "loss": 0.0845,
400
+ "mean_token_accuracy": 0.9751860290765763,
401
+ "num_tokens": 1206554.0,
402
+ "step": 380
403
+ },
404
+ {
405
+ "epoch": 5.2,
406
+ "grad_norm": 0.6970198750495911,
407
+ "learning_rate": 7.688284518828453e-05,
408
+ "loss": 0.065,
409
+ "mean_token_accuracy": 0.9810720026493073,
410
+ "num_tokens": 1237792.0,
411
+ "step": 390
412
+ },
413
+ {
414
+ "epoch": 5.333333333333333,
415
+ "grad_norm": 0.8283060193061829,
416
+ "learning_rate": 7.583682008368202e-05,
417
+ "loss": 0.0663,
418
+ "mean_token_accuracy": 0.9797625124454499,
419
+ "num_tokens": 1270203.0,
420
+ "step": 400
421
+ },
422
+ {
423
+ "epoch": 5.466666666666667,
424
+ "grad_norm": 0.8080848455429077,
425
+ "learning_rate": 7.479079497907951e-05,
426
+ "loss": 0.0712,
427
+ "mean_token_accuracy": 0.9780115723609925,
428
+ "num_tokens": 1301414.0,
429
+ "step": 410
430
+ },
431
+ {
432
+ "epoch": 5.6,
433
+ "grad_norm": 0.7461147904396057,
434
+ "learning_rate": 7.3744769874477e-05,
435
+ "loss": 0.0678,
436
+ "mean_token_accuracy": 0.9800621330738067,
437
+ "num_tokens": 1332421.0,
438
+ "step": 420
439
+ },
440
+ {
441
+ "epoch": 5.733333333333333,
442
+ "grad_norm": 0.5786488056182861,
443
+ "learning_rate": 7.269874476987449e-05,
444
+ "loss": 0.067,
445
+ "mean_token_accuracy": 0.980746528506279,
446
+ "num_tokens": 1365542.0,
447
+ "step": 430
448
+ },
449
+ {
450
+ "epoch": 5.866666666666667,
451
+ "grad_norm": 0.6561855673789978,
452
+ "learning_rate": 7.165271966527197e-05,
453
+ "loss": 0.0702,
454
+ "mean_token_accuracy": 0.9795888513326645,
455
+ "num_tokens": 1396981.0,
456
+ "step": 440
457
+ },
458
+ {
459
+ "epoch": 6.0,
460
+ "grad_norm": 0.8029749989509583,
461
+ "learning_rate": 7.060669456066946e-05,
462
+ "loss": 0.0721,
463
+ "mean_token_accuracy": 0.9787283718585968,
464
+ "num_tokens": 1428066.0,
465
+ "step": 450
466
+ },
467
+ {
468
+ "epoch": 6.0,
469
+ "eval_loss": 0.5095443725585938,
470
+ "eval_mean_token_accuracy": 0.8847648048400879,
471
+ "eval_num_tokens": 1428066.0,
472
+ "eval_runtime": 50.9006,
473
+ "eval_samples_per_second": 1.965,
474
+ "eval_steps_per_second": 0.491,
475
+ "step": 450
476
+ },
477
+ {
478
+ "epoch": 6.133333333333334,
479
+ "grad_norm": 0.5984286665916443,
480
+ "learning_rate": 6.956066945606695e-05,
481
+ "loss": 0.0439,
482
+ "mean_token_accuracy": 0.9883647084236145,
483
+ "num_tokens": 1459612.0,
484
+ "step": 460
485
+ },
486
+ {
487
+ "epoch": 6.266666666666667,
488
+ "grad_norm": 0.7371001839637756,
489
+ "learning_rate": 6.851464435146444e-05,
490
+ "loss": 0.0497,
491
+ "mean_token_accuracy": 0.9854195445775986,
492
+ "num_tokens": 1490815.0,
493
+ "step": 470
494
+ },
495
+ {
496
+ "epoch": 6.4,
497
+ "grad_norm": 0.5508085489273071,
498
+ "learning_rate": 6.746861924686193e-05,
499
+ "loss": 0.0477,
500
+ "mean_token_accuracy": 0.9866609632968902,
501
+ "num_tokens": 1520943.0,
502
+ "step": 480
503
+ },
504
+ {
505
+ "epoch": 6.533333333333333,
506
+ "grad_norm": 0.7761865854263306,
507
+ "learning_rate": 6.642259414225942e-05,
508
+ "loss": 0.0449,
509
+ "mean_token_accuracy": 0.9868600249290467,
510
+ "num_tokens": 1552633.0,
511
+ "step": 490
512
+ },
513
+ {
514
+ "epoch": 6.666666666666667,
515
+ "grad_norm": 0.6642009615898132,
516
+ "learning_rate": 6.537656903765691e-05,
517
+ "loss": 0.0472,
518
+ "mean_token_accuracy": 0.9871610105037689,
519
+ "num_tokens": 1587798.0,
520
+ "step": 500
521
+ },
522
+ {
523
+ "epoch": 6.8,
524
+ "grad_norm": 0.6801927089691162,
525
+ "learning_rate": 6.43305439330544e-05,
526
+ "loss": 0.0527,
527
+ "mean_token_accuracy": 0.9849318206310272,
528
+ "num_tokens": 1617597.0,
529
+ "step": 510
530
+ },
531
+ {
532
+ "epoch": 6.933333333333334,
533
+ "grad_norm": 0.6705682873725891,
534
+ "learning_rate": 6.32845188284519e-05,
535
+ "loss": 0.0505,
536
+ "mean_token_accuracy": 0.9851646542549133,
537
+ "num_tokens": 1648212.0,
538
+ "step": 520
539
+ },
540
+ {
541
+ "epoch": 7.0,
542
+ "eval_loss": 0.5524249076843262,
543
+ "eval_mean_token_accuracy": 0.8823326063156128,
544
+ "eval_num_tokens": 1666077.0,
545
+ "eval_runtime": 50.8934,
546
+ "eval_samples_per_second": 1.965,
547
+ "eval_steps_per_second": 0.491,
548
+ "step": 525
549
+ },
550
+ {
551
+ "epoch": 7.066666666666666,
552
+ "grad_norm": 1.0225543975830078,
553
+ "learning_rate": 6.223849372384938e-05,
554
+ "loss": 0.0441,
555
+ "mean_token_accuracy": 0.9876838475465775,
556
+ "num_tokens": 1682282.0,
557
+ "step": 530
558
+ },
559
+ {
560
+ "epoch": 7.2,
561
+ "grad_norm": 0.7063732743263245,
562
+ "learning_rate": 6.119246861924686e-05,
563
+ "loss": 0.0314,
564
+ "mean_token_accuracy": 0.9909861594438553,
565
+ "num_tokens": 1714966.0,
566
+ "step": 540
567
+ },
568
+ {
569
+ "epoch": 7.333333333333333,
570
+ "grad_norm": 0.4836845099925995,
571
+ "learning_rate": 6.014644351464436e-05,
572
+ "loss": 0.0346,
573
+ "mean_token_accuracy": 0.9898746073246002,
574
+ "num_tokens": 1745662.0,
575
+ "step": 550
576
+ },
577
+ {
578
+ "epoch": 7.466666666666667,
579
+ "grad_norm": 0.5448402166366577,
580
+ "learning_rate": 5.910041841004185e-05,
581
+ "loss": 0.0375,
582
+ "mean_token_accuracy": 0.9898856014013291,
583
+ "num_tokens": 1778368.0,
584
+ "step": 560
585
+ },
586
+ {
587
+ "epoch": 7.6,
588
+ "grad_norm": 0.4760727882385254,
589
+ "learning_rate": 5.8054393305439334e-05,
590
+ "loss": 0.0357,
591
+ "mean_token_accuracy": 0.9897664040327072,
592
+ "num_tokens": 1810571.0,
593
+ "step": 570
594
+ },
595
+ {
596
+ "epoch": 7.733333333333333,
597
+ "grad_norm": 0.43467867374420166,
598
+ "learning_rate": 5.7008368200836825e-05,
599
+ "loss": 0.0388,
600
+ "mean_token_accuracy": 0.9894861280918121,
601
+ "num_tokens": 1842310.0,
602
+ "step": 580
603
+ },
604
+ {
605
+ "epoch": 7.866666666666667,
606
+ "grad_norm": 0.8253856897354126,
607
+ "learning_rate": 5.5962343096234316e-05,
608
+ "loss": 0.0398,
609
+ "mean_token_accuracy": 0.9881662368774414,
610
+ "num_tokens": 1873435.0,
611
+ "step": 590
612
+ },
613
+ {
614
+ "epoch": 8.0,
615
+ "grad_norm": 0.5036665797233582,
616
+ "learning_rate": 5.4916317991631806e-05,
617
+ "loss": 0.0421,
618
+ "mean_token_accuracy": 0.9883299976587295,
619
+ "num_tokens": 1904088.0,
620
+ "step": 600
621
+ },
622
+ {
623
+ "epoch": 8.0,
624
+ "eval_loss": 0.5785043239593506,
625
+ "eval_mean_token_accuracy": 0.8845841264724732,
626
+ "eval_num_tokens": 1904088.0,
627
+ "eval_runtime": 50.8908,
628
+ "eval_samples_per_second": 1.965,
629
+ "eval_steps_per_second": 0.491,
630
+ "step": 600
631
+ },
632
+ {
633
+ "epoch": 8.133333333333333,
634
+ "grad_norm": 0.24711328744888306,
635
+ "learning_rate": 5.38702928870293e-05,
636
+ "loss": 0.0273,
637
+ "mean_token_accuracy": 0.9923271119594574,
638
+ "num_tokens": 1936241.0,
639
+ "step": 610
640
+ },
641
+ {
642
+ "epoch": 8.266666666666667,
643
+ "grad_norm": 0.44961780309677124,
644
+ "learning_rate": 5.282426778242678e-05,
645
+ "loss": 0.0291,
646
+ "mean_token_accuracy": 0.9920144468545914,
647
+ "num_tokens": 1969247.0,
648
+ "step": 620
649
+ },
650
+ {
651
+ "epoch": 8.4,
652
+ "grad_norm": 0.3607077896595001,
653
+ "learning_rate": 5.177824267782427e-05,
654
+ "loss": 0.032,
655
+ "mean_token_accuracy": 0.9911372780799865,
656
+ "num_tokens": 2001136.0,
657
+ "step": 630
658
+ },
659
+ {
660
+ "epoch": 8.533333333333333,
661
+ "grad_norm": 0.34154054522514343,
662
+ "learning_rate": 5.073221757322176e-05,
663
+ "loss": 0.0308,
664
+ "mean_token_accuracy": 0.9917692422866822,
665
+ "num_tokens": 2033446.0,
666
+ "step": 640
667
+ },
668
+ {
669
+ "epoch": 8.666666666666666,
670
+ "grad_norm": 0.5010355710983276,
671
+ "learning_rate": 4.968619246861925e-05,
672
+ "loss": 0.0341,
673
+ "mean_token_accuracy": 0.9908981770277023,
674
+ "num_tokens": 2064800.0,
675
+ "step": 650
676
+ },
677
+ {
678
+ "epoch": 8.8,
679
+ "grad_norm": 0.47791624069213867,
680
+ "learning_rate": 4.864016736401674e-05,
681
+ "loss": 0.0302,
682
+ "mean_token_accuracy": 0.9913896471261978,
683
+ "num_tokens": 2095573.0,
684
+ "step": 660
685
+ },
686
+ {
687
+ "epoch": 8.933333333333334,
688
+ "grad_norm": 0.45093876123428345,
689
+ "learning_rate": 4.759414225941423e-05,
690
+ "loss": 0.0371,
691
+ "mean_token_accuracy": 0.9898908942937851,
692
+ "num_tokens": 2126001.0,
693
+ "step": 670
694
+ },
695
+ {
696
+ "epoch": 9.0,
697
+ "eval_loss": 0.6148654222488403,
698
+ "eval_mean_token_accuracy": 0.8842980313301086,
699
+ "eval_num_tokens": 2142099.0,
700
+ "eval_runtime": 50.8928,
701
+ "eval_samples_per_second": 1.965,
702
+ "eval_steps_per_second": 0.491,
703
+ "step": 675
704
+ },
705
+ {
706
+ "epoch": 9.066666666666666,
707
+ "grad_norm": 0.5800787806510925,
708
+ "learning_rate": 4.654811715481171e-05,
709
+ "loss": 0.0291,
710
+ "mean_token_accuracy": 0.9921304136514664,
711
+ "num_tokens": 2157400.0,
712
+ "step": 680
713
+ },
714
+ {
715
+ "epoch": 9.2,
716
+ "grad_norm": 0.6982473731040955,
717
+ "learning_rate": 4.5502092050209203e-05,
718
+ "loss": 0.0239,
719
+ "mean_token_accuracy": 0.9932474166154861,
720
+ "num_tokens": 2189379.0,
721
+ "step": 690
722
+ },
723
+ {
724
+ "epoch": 9.333333333333334,
725
+ "grad_norm": 0.3595369756221771,
726
+ "learning_rate": 4.4456066945606694e-05,
727
+ "loss": 0.0265,
728
+ "mean_token_accuracy": 0.9921673446893692,
729
+ "num_tokens": 2219752.0,
730
+ "step": 700
731
+ },
732
+ {
733
+ "epoch": 9.466666666666667,
734
+ "grad_norm": 0.27210283279418945,
735
+ "learning_rate": 4.3410041841004185e-05,
736
+ "loss": 0.0276,
737
+ "mean_token_accuracy": 0.9919114917516708,
738
+ "num_tokens": 2251801.0,
739
+ "step": 710
740
+ },
741
+ {
742
+ "epoch": 9.6,
743
+ "grad_norm": 0.45378750562667847,
744
+ "learning_rate": 4.2364016736401676e-05,
745
+ "loss": 0.0267,
746
+ "mean_token_accuracy": 0.9923428118228912,
747
+ "num_tokens": 2283166.0,
748
+ "step": 720
749
+ },
750
+ {
751
+ "epoch": 9.733333333333333,
752
+ "grad_norm": 0.21831561625003815,
753
+ "learning_rate": 4.131799163179916e-05,
754
+ "loss": 0.0265,
755
+ "mean_token_accuracy": 0.9930205404758453,
756
+ "num_tokens": 2315753.0,
757
+ "step": 730
758
+ },
759
+ {
760
+ "epoch": 9.866666666666667,
761
+ "grad_norm": 0.3201010525226593,
762
+ "learning_rate": 4.027196652719665e-05,
763
+ "loss": 0.0293,
764
+ "mean_token_accuracy": 0.9924349457025528,
765
+ "num_tokens": 2348020.0,
766
+ "step": 740
767
+ },
768
+ {
769
+ "epoch": 10.0,
770
+ "grad_norm": 0.25126612186431885,
771
+ "learning_rate": 3.922594142259414e-05,
772
+ "loss": 0.0285,
773
+ "mean_token_accuracy": 0.9927875697612762,
774
+ "num_tokens": 2380110.0,
775
+ "step": 750
776
+ },
777
+ {
778
+ "epoch": 10.0,
779
+ "eval_loss": 0.6573454141616821,
780
+ "eval_mean_token_accuracy": 0.8831826686859131,
781
+ "eval_num_tokens": 2380110.0,
782
+ "eval_runtime": 50.8906,
783
+ "eval_samples_per_second": 1.965,
784
+ "eval_steps_per_second": 0.491,
785
+ "step": 750
786
+ },
787
+ {
788
+ "epoch": 10.133333333333333,
789
+ "grad_norm": 0.5593218803405762,
790
+ "learning_rate": 3.817991631799163e-05,
791
+ "loss": 0.0216,
792
+ "mean_token_accuracy": 0.9936788022518158,
793
+ "num_tokens": 2412729.0,
794
+ "step": 760
795
+ },
796
+ {
797
+ "epoch": 10.266666666666667,
798
+ "grad_norm": 0.3219089210033417,
799
+ "learning_rate": 3.713389121338912e-05,
800
+ "loss": 0.0228,
801
+ "mean_token_accuracy": 0.9932976424694061,
802
+ "num_tokens": 2443952.0,
803
+ "step": 770
804
+ },
805
+ {
806
+ "epoch": 10.4,
807
+ "grad_norm": 0.14705878496170044,
808
+ "learning_rate": 3.6087866108786614e-05,
809
+ "loss": 0.0226,
810
+ "mean_token_accuracy": 0.9936914265155792,
811
+ "num_tokens": 2475185.0,
812
+ "step": 780
813
+ },
814
+ {
815
+ "epoch": 10.533333333333333,
816
+ "grad_norm": 0.2050597369670868,
817
+ "learning_rate": 3.50418410041841e-05,
818
+ "loss": 0.024,
819
+ "mean_token_accuracy": 0.9928701817989349,
820
+ "num_tokens": 2506064.0,
821
+ "step": 790
822
+ },
823
+ {
824
+ "epoch": 10.666666666666666,
825
+ "grad_norm": 0.30800071358680725,
826
+ "learning_rate": 3.399581589958159e-05,
827
+ "loss": 0.0231,
828
+ "mean_token_accuracy": 0.9936599344015121,
829
+ "num_tokens": 2537568.0,
830
+ "step": 800
831
+ },
832
+ {
833
+ "epoch": 10.8,
834
+ "grad_norm": 0.6075056195259094,
835
+ "learning_rate": 3.294979079497908e-05,
836
+ "loss": 0.0252,
837
+ "mean_token_accuracy": 0.9924876004457474,
838
+ "num_tokens": 2568278.0,
839
+ "step": 810
840
+ },
841
+ {
842
+ "epoch": 10.933333333333334,
843
+ "grad_norm": 0.46507900953292847,
844
+ "learning_rate": 3.190376569037657e-05,
845
+ "loss": 0.0233,
846
+ "mean_token_accuracy": 0.9935177505016327,
847
+ "num_tokens": 2601290.0,
848
+ "step": 820
849
+ },
850
+ {
851
+ "epoch": 11.0,
852
+ "eval_loss": 0.7078420519828796,
853
+ "eval_mean_token_accuracy": 0.8819138598442078,
854
+ "eval_num_tokens": 2618121.0,
855
+ "eval_runtime": 50.8936,
856
+ "eval_samples_per_second": 1.965,
857
+ "eval_steps_per_second": 0.491,
858
+ "step": 825
859
+ },
860
+ {
861
+ "epoch": 11.066666666666666,
862
+ "grad_norm": 0.13493098318576813,
863
+ "learning_rate": 3.085774058577406e-05,
864
+ "loss": 0.0227,
865
+ "mean_token_accuracy": 0.9937657356262207,
866
+ "num_tokens": 2631945.0,
867
+ "step": 830
868
+ },
869
+ {
870
+ "epoch": 11.2,
871
+ "grad_norm": 0.27274149656295776,
872
+ "learning_rate": 2.981171548117155e-05,
873
+ "loss": 0.0202,
874
+ "mean_token_accuracy": 0.9939479857683182,
875
+ "num_tokens": 2664278.0,
876
+ "step": 840
877
+ },
878
+ {
879
+ "epoch": 11.333333333333334,
880
+ "grad_norm": 0.12694329023361206,
881
+ "learning_rate": 2.8765690376569036e-05,
882
+ "loss": 0.0217,
883
+ "mean_token_accuracy": 0.9940280497074128,
884
+ "num_tokens": 2697487.0,
885
+ "step": 850
886
+ },
887
+ {
888
+ "epoch": 11.466666666666667,
889
+ "grad_norm": 0.30919721722602844,
890
+ "learning_rate": 2.7719665271966527e-05,
891
+ "loss": 0.0208,
892
+ "mean_token_accuracy": 0.993863531947136,
893
+ "num_tokens": 2729287.0,
894
+ "step": 860
895
+ },
896
+ {
897
+ "epoch": 11.6,
898
+ "grad_norm": 0.346965491771698,
899
+ "learning_rate": 2.6673640167364018e-05,
900
+ "loss": 0.0219,
901
+ "mean_token_accuracy": 0.9938155382871627,
902
+ "num_tokens": 2760283.0,
903
+ "step": 870
904
+ },
905
+ {
906
+ "epoch": 11.733333333333333,
907
+ "grad_norm": 0.22179089486598969,
908
+ "learning_rate": 2.5627615062761505e-05,
909
+ "loss": 0.0198,
910
+ "mean_token_accuracy": 0.9939759701490403,
911
+ "num_tokens": 2793986.0,
912
+ "step": 880
913
+ },
914
+ {
915
+ "epoch": 11.866666666666667,
916
+ "grad_norm": 0.16201026737689972,
917
+ "learning_rate": 2.4581589958158996e-05,
918
+ "loss": 0.0228,
919
+ "mean_token_accuracy": 0.9931929171085357,
920
+ "num_tokens": 2824816.0,
921
+ "step": 890
922
+ },
923
+ {
924
+ "epoch": 12.0,
925
+ "grad_norm": 0.20347487926483154,
926
+ "learning_rate": 2.3535564853556487e-05,
927
+ "loss": 0.0228,
928
+ "mean_token_accuracy": 0.9934813290834427,
929
+ "num_tokens": 2856132.0,
930
+ "step": 900
931
+ },
932
+ {
933
+ "epoch": 12.0,
934
+ "eval_loss": 0.7223861813545227,
935
+ "eval_mean_token_accuracy": 0.8824266290664673,
936
+ "eval_num_tokens": 2856132.0,
937
+ "eval_runtime": 50.8977,
938
+ "eval_samples_per_second": 1.965,
939
+ "eval_steps_per_second": 0.491,
940
+ "step": 900
941
+ },
942
+ {
943
+ "epoch": 12.133333333333333,
944
+ "grad_norm": 0.10506761819124222,
945
+ "learning_rate": 2.2489539748953974e-05,
946
+ "loss": 0.0181,
947
+ "mean_token_accuracy": 0.9947699904441833,
948
+ "num_tokens": 2889294.0,
949
+ "step": 910
950
+ },
951
+ {
952
+ "epoch": 12.266666666666667,
953
+ "grad_norm": 0.22959034144878387,
954
+ "learning_rate": 2.1443514644351465e-05,
955
+ "loss": 0.0191,
956
+ "mean_token_accuracy": 0.9941918909549713,
957
+ "num_tokens": 2920564.0,
958
+ "step": 920
959
+ },
960
+ {
961
+ "epoch": 12.4,
962
+ "grad_norm": 0.14024658501148224,
963
+ "learning_rate": 2.0397489539748953e-05,
964
+ "loss": 0.0193,
965
+ "mean_token_accuracy": 0.9944606810808182,
966
+ "num_tokens": 2952215.0,
967
+ "step": 930
968
+ },
969
+ {
970
+ "epoch": 12.533333333333333,
971
+ "grad_norm": 0.1049821749329567,
972
+ "learning_rate": 1.9351464435146444e-05,
973
+ "loss": 0.0187,
974
+ "mean_token_accuracy": 0.9942614287137985,
975
+ "num_tokens": 2984367.0,
976
+ "step": 940
977
+ },
978
+ {
979
+ "epoch": 12.666666666666666,
980
+ "grad_norm": 0.14182651042938232,
981
+ "learning_rate": 1.8305439330543934e-05,
982
+ "loss": 0.0199,
983
+ "mean_token_accuracy": 0.9938604891300201,
984
+ "num_tokens": 3015120.0,
985
+ "step": 950
986
+ },
987
+ {
988
+ "epoch": 12.8,
989
+ "grad_norm": 0.13577786087989807,
990
+ "learning_rate": 1.7259414225941422e-05,
991
+ "loss": 0.0197,
992
+ "mean_token_accuracy": 0.9941955178976059,
993
+ "num_tokens": 3046751.0,
994
+ "step": 960
995
+ },
996
+ {
997
+ "epoch": 12.933333333333334,
998
+ "grad_norm": 0.18529069423675537,
999
+ "learning_rate": 1.6213389121338913e-05,
1000
+ "loss": 0.0201,
1001
+ "mean_token_accuracy": 0.9938661843538285,
1002
+ "num_tokens": 3078212.0,
1003
+ "step": 970
1004
+ },
1005
+ {
1006
+ "epoch": 13.0,
1007
+ "eval_loss": 0.7834702134132385,
1008
+ "eval_mean_token_accuracy": 0.8812357115745545,
1009
+ "eval_num_tokens": 3094143.0,
1010
+ "eval_runtime": 50.9004,
1011
+ "eval_samples_per_second": 1.965,
1012
+ "eval_steps_per_second": 0.491,
1013
+ "step": 975
1014
+ },
1015
+ {
1016
+ "epoch": 13.066666666666666,
1017
+ "grad_norm": 0.07987310737371445,
1018
+ "learning_rate": 1.5167364016736402e-05,
1019
+ "loss": 0.0193,
1020
+ "mean_token_accuracy": 0.9944200098514557,
1021
+ "num_tokens": 3109895.0,
1022
+ "step": 980
1023
+ },
1024
+ {
1025
+ "epoch": 13.2,
1026
+ "grad_norm": 0.09330923855304718,
1027
+ "learning_rate": 1.412133891213389e-05,
1028
+ "loss": 0.0181,
1029
+ "mean_token_accuracy": 0.9943874269723892,
1030
+ "num_tokens": 3141209.0,
1031
+ "step": 990
1032
+ },
1033
+ {
1034
+ "epoch": 13.333333333333334,
1035
+ "grad_norm": 0.11167001724243164,
1036
+ "learning_rate": 1.307531380753138e-05,
1037
+ "loss": 0.018,
1038
+ "mean_token_accuracy": 0.9946882605552674,
1039
+ "num_tokens": 3173385.0,
1040
+ "step": 1000
1041
+ },
1042
+ {
1043
+ "epoch": 13.466666666666667,
1044
+ "grad_norm": 0.16363947093486786,
1045
+ "learning_rate": 1.202928870292887e-05,
1046
+ "loss": 0.0192,
1047
+ "mean_token_accuracy": 0.994058096408844,
1048
+ "num_tokens": 3203081.0,
1049
+ "step": 1010
1050
+ },
1051
+ {
1052
+ "epoch": 13.6,
1053
+ "grad_norm": 0.15829868614673615,
1054
+ "learning_rate": 1.098326359832636e-05,
1055
+ "loss": 0.0192,
1056
+ "mean_token_accuracy": 0.993596938252449,
1057
+ "num_tokens": 3234247.0,
1058
+ "step": 1020
1059
+ },
1060
+ {
1061
+ "epoch": 13.733333333333333,
1062
+ "grad_norm": 0.11582522094249725,
1063
+ "learning_rate": 9.937238493723849e-06,
1064
+ "loss": 0.0183,
1065
+ "mean_token_accuracy": 0.9946052461862565,
1066
+ "num_tokens": 3265780.0,
1067
+ "step": 1030
1068
+ },
1069
+ {
1070
+ "epoch": 13.866666666666667,
1071
+ "grad_norm": 0.09746014326810837,
1072
+ "learning_rate": 8.891213389121338e-06,
1073
+ "loss": 0.0179,
1074
+ "mean_token_accuracy": 0.9942047536373139,
1075
+ "num_tokens": 3299307.0,
1076
+ "step": 1040
1077
+ },
1078
+ {
1079
+ "epoch": 14.0,
1080
+ "grad_norm": 0.09180562198162079,
1081
+ "learning_rate": 7.845188284518829e-06,
1082
+ "loss": 0.018,
1083
+ "mean_token_accuracy": 0.9945183902978897,
1084
+ "num_tokens": 3332154.0,
1085
+ "step": 1050
1086
+ },
1087
+ {
1088
+ "epoch": 14.0,
1089
+ "eval_loss": 0.8125747442245483,
1090
+ "eval_mean_token_accuracy": 0.8807920503616333,
1091
+ "eval_num_tokens": 3332154.0,
1092
+ "eval_runtime": 50.8913,
1093
+ "eval_samples_per_second": 1.965,
1094
+ "eval_steps_per_second": 0.491,
1095
+ "step": 1050
1096
+ }
1097
+ ],
1098
+ "logging_steps": 10,
1099
+ "max_steps": 1125,
1100
+ "num_input_tokens_seen": 0,
1101
+ "num_train_epochs": 15,
1102
+ "save_steps": 500,
1103
+ "stateful_callbacks": {
1104
+ "TrainerControl": {
1105
+ "args": {
1106
+ "should_epoch_stop": false,
1107
+ "should_evaluate": false,
1108
+ "should_log": false,
1109
+ "should_save": true,
1110
+ "should_training_stop": false
1111
+ },
1112
+ "attributes": {}
1113
+ }
1114
+ },
1115
+ "total_flos": 1.9974535736958566e+17,
1116
+ "train_batch_size": 4,
1117
+ "trial_name": null,
1118
+ "trial_params": null
1119
+ }
checkpoint-1050/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62870f24a4207eea4af3eb1d98603c25ccfec3a861c88478569c8265a81dc3de
3
+ size 5624
checkpoint-1050/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1125/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-7B-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
checkpoint-1125/adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-7B-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": 0.1,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 16,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "down_proj",
27
+ "k_proj",
28
+ "up_proj",
29
+ "o_proj",
30
+ "v_proj",
31
+ "gate_proj",
32
+ "q_proj"
33
+ ],
34
+ "task_type": "CAUSAL_LM",
35
+ "use_dora": false,
36
+ "use_rslora": false
37
+ }
checkpoint-1125/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cdd6ce91c41a7b9a9da13797e96b882babc0df7bc6f7fb888ab78b556464d94
3
+ size 161533192
checkpoint-1125/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
+ }
checkpoint-1125/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1125/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29c26c77dc380f8e0e6df4345a857bfb131ab9b23c113350b81ff5bed37bf089
3
+ size 82461044
checkpoint-1125/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d25ebdc79469f6e623cfa822c999c874dafbbea7e85dfc8d741c0fc259db3176
3
+ size 14244
checkpoint-1125/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10a5c0903aa41376be2e7e08598d576931d26fb1dedc7d0c5140f9d591e1debc
3
+ size 1064
checkpoint-1125/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
checkpoint-1125/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
checkpoint-1125/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": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
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": null,
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
+ }
checkpoint-1125/trainer_state.json ADDED
@@ -0,0 +1,1192 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 225,
3
+ "best_metric": 0.36194586753845215,
4
+ "best_model_checkpoint": "/content/output/checkpoint-225",
5
+ "epoch": 15.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1125,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.13333333333333333,
14
+ "grad_norm": 1.7940553426742554,
15
+ "learning_rate": 5.917159763313609e-06,
16
+ "loss": 1.3972,
17
+ "mean_token_accuracy": 0.7618847399950027,
18
+ "num_tokens": 31152.0,
19
+ "step": 10
20
+ },
21
+ {
22
+ "epoch": 0.26666666666666666,
23
+ "grad_norm": 1.0511088371276855,
24
+ "learning_rate": 1.1834319526627219e-05,
25
+ "loss": 1.2288,
26
+ "mean_token_accuracy": 0.7673537939786911,
27
+ "num_tokens": 61773.0,
28
+ "step": 20
29
+ },
30
+ {
31
+ "epoch": 0.4,
32
+ "grad_norm": 0.8096975088119507,
33
+ "learning_rate": 1.7751479289940828e-05,
34
+ "loss": 0.9255,
35
+ "mean_token_accuracy": 0.7948055118322372,
36
+ "num_tokens": 94758.0,
37
+ "step": 30
38
+ },
39
+ {
40
+ "epoch": 0.5333333333333333,
41
+ "grad_norm": 0.6213255524635315,
42
+ "learning_rate": 2.3668639053254438e-05,
43
+ "loss": 0.7366,
44
+ "mean_token_accuracy": 0.8212289035320282,
45
+ "num_tokens": 125915.0,
46
+ "step": 40
47
+ },
48
+ {
49
+ "epoch": 0.6666666666666666,
50
+ "grad_norm": 0.42887863516807556,
51
+ "learning_rate": 2.958579881656805e-05,
52
+ "loss": 0.5556,
53
+ "mean_token_accuracy": 0.8463607966899872,
54
+ "num_tokens": 159364.0,
55
+ "step": 50
56
+ },
57
+ {
58
+ "epoch": 0.8,
59
+ "grad_norm": 0.5108550786972046,
60
+ "learning_rate": 3.5502958579881656e-05,
61
+ "loss": 0.4676,
62
+ "mean_token_accuracy": 0.8614094287157059,
63
+ "num_tokens": 190374.0,
64
+ "step": 60
65
+ },
66
+ {
67
+ "epoch": 0.9333333333333333,
68
+ "grad_norm": 0.4310983121395111,
69
+ "learning_rate": 4.142011834319527e-05,
70
+ "loss": 0.4214,
71
+ "mean_token_accuracy": 0.8710317760705948,
72
+ "num_tokens": 222156.0,
73
+ "step": 70
74
+ },
75
+ {
76
+ "epoch": 1.0,
77
+ "eval_loss": 0.4043419659137726,
78
+ "eval_mean_token_accuracy": 0.8734077858924866,
79
+ "eval_num_tokens": 238011.0,
80
+ "eval_runtime": 50.8925,
81
+ "eval_samples_per_second": 1.965,
82
+ "eval_steps_per_second": 0.491,
83
+ "step": 75
84
+ },
85
+ {
86
+ "epoch": 1.0666666666666667,
87
+ "grad_norm": 0.35767048597335815,
88
+ "learning_rate": 4.7337278106508875e-05,
89
+ "loss": 0.3901,
90
+ "mean_token_accuracy": 0.8787548273801804,
91
+ "num_tokens": 255825.0,
92
+ "step": 80
93
+ },
94
+ {
95
+ "epoch": 1.2,
96
+ "grad_norm": 0.3684692680835724,
97
+ "learning_rate": 5.3254437869822495e-05,
98
+ "loss": 0.3956,
99
+ "mean_token_accuracy": 0.8787799149751663,
100
+ "num_tokens": 287370.0,
101
+ "step": 90
102
+ },
103
+ {
104
+ "epoch": 1.3333333333333333,
105
+ "grad_norm": 0.35148611664772034,
106
+ "learning_rate": 5.91715976331361e-05,
107
+ "loss": 0.3822,
108
+ "mean_token_accuracy": 0.8814697057008744,
109
+ "num_tokens": 315883.0,
110
+ "step": 100
111
+ },
112
+ {
113
+ "epoch": 1.4666666666666668,
114
+ "grad_norm": 0.39074671268463135,
115
+ "learning_rate": 6.50887573964497e-05,
116
+ "loss": 0.3703,
117
+ "mean_token_accuracy": 0.8836676925420761,
118
+ "num_tokens": 347324.0,
119
+ "step": 110
120
+ },
121
+ {
122
+ "epoch": 1.6,
123
+ "grad_norm": 0.38130292296409607,
124
+ "learning_rate": 7.100591715976331e-05,
125
+ "loss": 0.3762,
126
+ "mean_token_accuracy": 0.8851484537124634,
127
+ "num_tokens": 379374.0,
128
+ "step": 120
129
+ },
130
+ {
131
+ "epoch": 1.7333333333333334,
132
+ "grad_norm": 0.4091486632823944,
133
+ "learning_rate": 7.692307692307693e-05,
134
+ "loss": 0.3446,
135
+ "mean_token_accuracy": 0.8894414573907852,
136
+ "num_tokens": 411843.0,
137
+ "step": 130
138
+ },
139
+ {
140
+ "epoch": 1.8666666666666667,
141
+ "grad_norm": 0.361017644405365,
142
+ "learning_rate": 8.284023668639054e-05,
143
+ "loss": 0.3494,
144
+ "mean_token_accuracy": 0.8915452778339386,
145
+ "num_tokens": 444017.0,
146
+ "step": 140
147
+ },
148
+ {
149
+ "epoch": 2.0,
150
+ "grad_norm": 0.3487047851085663,
151
+ "learning_rate": 8.875739644970414e-05,
152
+ "loss": 0.3674,
153
+ "mean_token_accuracy": 0.8846240967512131,
154
+ "num_tokens": 476022.0,
155
+ "step": 150
156
+ },
157
+ {
158
+ "epoch": 2.0,
159
+ "eval_loss": 0.3620273470878601,
160
+ "eval_mean_token_accuracy": 0.8875497984886169,
161
+ "eval_num_tokens": 476022.0,
162
+ "eval_runtime": 50.8961,
163
+ "eval_samples_per_second": 1.965,
164
+ "eval_steps_per_second": 0.491,
165
+ "step": 150
166
+ },
167
+ {
168
+ "epoch": 2.1333333333333333,
169
+ "grad_norm": 0.480814665555954,
170
+ "learning_rate": 9.467455621301775e-05,
171
+ "loss": 0.2974,
172
+ "mean_token_accuracy": 0.9050114572048187,
173
+ "num_tokens": 508445.0,
174
+ "step": 160
175
+ },
176
+ {
177
+ "epoch": 2.2666666666666666,
178
+ "grad_norm": 0.40775951743125916,
179
+ "learning_rate": 9.989539748953976e-05,
180
+ "loss": 0.2896,
181
+ "mean_token_accuracy": 0.9084265738725662,
182
+ "num_tokens": 541530.0,
183
+ "step": 170
184
+ },
185
+ {
186
+ "epoch": 2.4,
187
+ "grad_norm": 0.5174453854560852,
188
+ "learning_rate": 9.884937238493725e-05,
189
+ "loss": 0.29,
190
+ "mean_token_accuracy": 0.9073476493358612,
191
+ "num_tokens": 572212.0,
192
+ "step": 180
193
+ },
194
+ {
195
+ "epoch": 2.533333333333333,
196
+ "grad_norm": 0.5889921188354492,
197
+ "learning_rate": 9.780334728033474e-05,
198
+ "loss": 0.2828,
199
+ "mean_token_accuracy": 0.909446981549263,
200
+ "num_tokens": 603269.0,
201
+ "step": 190
202
+ },
203
+ {
204
+ "epoch": 2.6666666666666665,
205
+ "grad_norm": 0.5635319352149963,
206
+ "learning_rate": 9.675732217573223e-05,
207
+ "loss": 0.2744,
208
+ "mean_token_accuracy": 0.9101487964391708,
209
+ "num_tokens": 635792.0,
210
+ "step": 200
211
+ },
212
+ {
213
+ "epoch": 2.8,
214
+ "grad_norm": 0.609230637550354,
215
+ "learning_rate": 9.571129707112972e-05,
216
+ "loss": 0.2863,
217
+ "mean_token_accuracy": 0.9104649156332016,
218
+ "num_tokens": 666470.0,
219
+ "step": 210
220
+ },
221
+ {
222
+ "epoch": 2.9333333333333336,
223
+ "grad_norm": 0.5209991931915283,
224
+ "learning_rate": 9.46652719665272e-05,
225
+ "loss": 0.3027,
226
+ "mean_token_accuracy": 0.9050683736801147,
227
+ "num_tokens": 699119.0,
228
+ "step": 220
229
+ },
230
+ {
231
+ "epoch": 3.0,
232
+ "eval_loss": 0.36194586753845215,
233
+ "eval_mean_token_accuracy": 0.8886684679985046,
234
+ "eval_num_tokens": 714033.0,
235
+ "eval_runtime": 50.8962,
236
+ "eval_samples_per_second": 1.965,
237
+ "eval_steps_per_second": 0.491,
238
+ "step": 225
239
+ },
240
+ {
241
+ "epoch": 3.066666666666667,
242
+ "grad_norm": 0.5214265584945679,
243
+ "learning_rate": 9.361924686192469e-05,
244
+ "loss": 0.2371,
245
+ "mean_token_accuracy": 0.9248212277889252,
246
+ "num_tokens": 729520.0,
247
+ "step": 230
248
+ },
249
+ {
250
+ "epoch": 3.2,
251
+ "grad_norm": 0.7459234595298767,
252
+ "learning_rate": 9.257322175732218e-05,
253
+ "loss": 0.1874,
254
+ "mean_token_accuracy": 0.939895498752594,
255
+ "num_tokens": 759510.0,
256
+ "step": 240
257
+ },
258
+ {
259
+ "epoch": 3.3333333333333335,
260
+ "grad_norm": 0.614969789981842,
261
+ "learning_rate": 9.152719665271967e-05,
262
+ "loss": 0.1754,
263
+ "mean_token_accuracy": 0.943790751695633,
264
+ "num_tokens": 791875.0,
265
+ "step": 250
266
+ },
267
+ {
268
+ "epoch": 3.466666666666667,
269
+ "grad_norm": 0.8585807085037231,
270
+ "learning_rate": 9.048117154811716e-05,
271
+ "loss": 0.1794,
272
+ "mean_token_accuracy": 0.9401535421609879,
273
+ "num_tokens": 821467.0,
274
+ "step": 260
275
+ },
276
+ {
277
+ "epoch": 3.6,
278
+ "grad_norm": 0.6798614263534546,
279
+ "learning_rate": 8.943514644351465e-05,
280
+ "loss": 0.1754,
281
+ "mean_token_accuracy": 0.9439484149217605,
282
+ "num_tokens": 854000.0,
283
+ "step": 270
284
+ },
285
+ {
286
+ "epoch": 3.7333333333333334,
287
+ "grad_norm": 0.6594717502593994,
288
+ "learning_rate": 8.838912133891214e-05,
289
+ "loss": 0.179,
290
+ "mean_token_accuracy": 0.9433883309364319,
291
+ "num_tokens": 885296.0,
292
+ "step": 280
293
+ },
294
+ {
295
+ "epoch": 3.8666666666666667,
296
+ "grad_norm": 0.6909582614898682,
297
+ "learning_rate": 8.734309623430963e-05,
298
+ "loss": 0.1855,
299
+ "mean_token_accuracy": 0.9395292073488235,
300
+ "num_tokens": 919387.0,
301
+ "step": 290
302
+ },
303
+ {
304
+ "epoch": 4.0,
305
+ "grad_norm": 0.7755655646324158,
306
+ "learning_rate": 8.629707112970712e-05,
307
+ "loss": 0.1851,
308
+ "mean_token_accuracy": 0.9409447878599166,
309
+ "num_tokens": 952044.0,
310
+ "step": 300
311
+ },
312
+ {
313
+ "epoch": 4.0,
314
+ "eval_loss": 0.39551886916160583,
315
+ "eval_mean_token_accuracy": 0.887341833114624,
316
+ "eval_num_tokens": 952044.0,
317
+ "eval_runtime": 50.8937,
318
+ "eval_samples_per_second": 1.965,
319
+ "eval_steps_per_second": 0.491,
320
+ "step": 300
321
+ },
322
+ {
323
+ "epoch": 4.133333333333334,
324
+ "grad_norm": 0.6951614022254944,
325
+ "learning_rate": 8.525104602510461e-05,
326
+ "loss": 0.0942,
327
+ "mean_token_accuracy": 0.9724623709917068,
328
+ "num_tokens": 984335.0,
329
+ "step": 310
330
+ },
331
+ {
332
+ "epoch": 4.266666666666667,
333
+ "grad_norm": 0.6803505420684814,
334
+ "learning_rate": 8.42050209205021e-05,
335
+ "loss": 0.1073,
336
+ "mean_token_accuracy": 0.9653927534818649,
337
+ "num_tokens": 1014854.0,
338
+ "step": 320
339
+ },
340
+ {
341
+ "epoch": 4.4,
342
+ "grad_norm": 0.7284913063049316,
343
+ "learning_rate": 8.315899581589958e-05,
344
+ "loss": 0.1054,
345
+ "mean_token_accuracy": 0.9662943929433823,
346
+ "num_tokens": 1047986.0,
347
+ "step": 330
348
+ },
349
+ {
350
+ "epoch": 4.533333333333333,
351
+ "grad_norm": 0.6803147792816162,
352
+ "learning_rate": 8.211297071129707e-05,
353
+ "loss": 0.1065,
354
+ "mean_token_accuracy": 0.9682819366455078,
355
+ "num_tokens": 1079663.0,
356
+ "step": 340
357
+ },
358
+ {
359
+ "epoch": 4.666666666666667,
360
+ "grad_norm": 0.6864665150642395,
361
+ "learning_rate": 8.106694560669456e-05,
362
+ "loss": 0.1085,
363
+ "mean_token_accuracy": 0.9646553307771683,
364
+ "num_tokens": 1109495.0,
365
+ "step": 350
366
+ },
367
+ {
368
+ "epoch": 4.8,
369
+ "grad_norm": 0.7594568729400635,
370
+ "learning_rate": 8.002092050209205e-05,
371
+ "loss": 0.1079,
372
+ "mean_token_accuracy": 0.9674631506204605,
373
+ "num_tokens": 1141598.0,
374
+ "step": 360
375
+ },
376
+ {
377
+ "epoch": 4.933333333333334,
378
+ "grad_norm": 0.6360507607460022,
379
+ "learning_rate": 7.897489539748954e-05,
380
+ "loss": 0.118,
381
+ "mean_token_accuracy": 0.9628556370735168,
382
+ "num_tokens": 1172834.0,
383
+ "step": 370
384
+ },
385
+ {
386
+ "epoch": 5.0,
387
+ "eval_loss": 0.45760437846183777,
388
+ "eval_mean_token_accuracy": 0.8874933505058289,
389
+ "eval_num_tokens": 1190055.0,
390
+ "eval_runtime": 50.9015,
391
+ "eval_samples_per_second": 1.965,
392
+ "eval_steps_per_second": 0.491,
393
+ "step": 375
394
+ },
395
+ {
396
+ "epoch": 5.066666666666666,
397
+ "grad_norm": 0.4860494136810303,
398
+ "learning_rate": 7.792887029288704e-05,
399
+ "loss": 0.0845,
400
+ "mean_token_accuracy": 0.9751860290765763,
401
+ "num_tokens": 1206554.0,
402
+ "step": 380
403
+ },
404
+ {
405
+ "epoch": 5.2,
406
+ "grad_norm": 0.6970198750495911,
407
+ "learning_rate": 7.688284518828453e-05,
408
+ "loss": 0.065,
409
+ "mean_token_accuracy": 0.9810720026493073,
410
+ "num_tokens": 1237792.0,
411
+ "step": 390
412
+ },
413
+ {
414
+ "epoch": 5.333333333333333,
415
+ "grad_norm": 0.8283060193061829,
416
+ "learning_rate": 7.583682008368202e-05,
417
+ "loss": 0.0663,
418
+ "mean_token_accuracy": 0.9797625124454499,
419
+ "num_tokens": 1270203.0,
420
+ "step": 400
421
+ },
422
+ {
423
+ "epoch": 5.466666666666667,
424
+ "grad_norm": 0.8080848455429077,
425
+ "learning_rate": 7.479079497907951e-05,
426
+ "loss": 0.0712,
427
+ "mean_token_accuracy": 0.9780115723609925,
428
+ "num_tokens": 1301414.0,
429
+ "step": 410
430
+ },
431
+ {
432
+ "epoch": 5.6,
433
+ "grad_norm": 0.7461147904396057,
434
+ "learning_rate": 7.3744769874477e-05,
435
+ "loss": 0.0678,
436
+ "mean_token_accuracy": 0.9800621330738067,
437
+ "num_tokens": 1332421.0,
438
+ "step": 420
439
+ },
440
+ {
441
+ "epoch": 5.733333333333333,
442
+ "grad_norm": 0.5786488056182861,
443
+ "learning_rate": 7.269874476987449e-05,
444
+ "loss": 0.067,
445
+ "mean_token_accuracy": 0.980746528506279,
446
+ "num_tokens": 1365542.0,
447
+ "step": 430
448
+ },
449
+ {
450
+ "epoch": 5.866666666666667,
451
+ "grad_norm": 0.6561855673789978,
452
+ "learning_rate": 7.165271966527197e-05,
453
+ "loss": 0.0702,
454
+ "mean_token_accuracy": 0.9795888513326645,
455
+ "num_tokens": 1396981.0,
456
+ "step": 440
457
+ },
458
+ {
459
+ "epoch": 6.0,
460
+ "grad_norm": 0.8029749989509583,
461
+ "learning_rate": 7.060669456066946e-05,
462
+ "loss": 0.0721,
463
+ "mean_token_accuracy": 0.9787283718585968,
464
+ "num_tokens": 1428066.0,
465
+ "step": 450
466
+ },
467
+ {
468
+ "epoch": 6.0,
469
+ "eval_loss": 0.5095443725585938,
470
+ "eval_mean_token_accuracy": 0.8847648048400879,
471
+ "eval_num_tokens": 1428066.0,
472
+ "eval_runtime": 50.9006,
473
+ "eval_samples_per_second": 1.965,
474
+ "eval_steps_per_second": 0.491,
475
+ "step": 450
476
+ },
477
+ {
478
+ "epoch": 6.133333333333334,
479
+ "grad_norm": 0.5984286665916443,
480
+ "learning_rate": 6.956066945606695e-05,
481
+ "loss": 0.0439,
482
+ "mean_token_accuracy": 0.9883647084236145,
483
+ "num_tokens": 1459612.0,
484
+ "step": 460
485
+ },
486
+ {
487
+ "epoch": 6.266666666666667,
488
+ "grad_norm": 0.7371001839637756,
489
+ "learning_rate": 6.851464435146444e-05,
490
+ "loss": 0.0497,
491
+ "mean_token_accuracy": 0.9854195445775986,
492
+ "num_tokens": 1490815.0,
493
+ "step": 470
494
+ },
495
+ {
496
+ "epoch": 6.4,
497
+ "grad_norm": 0.5508085489273071,
498
+ "learning_rate": 6.746861924686193e-05,
499
+ "loss": 0.0477,
500
+ "mean_token_accuracy": 0.9866609632968902,
501
+ "num_tokens": 1520943.0,
502
+ "step": 480
503
+ },
504
+ {
505
+ "epoch": 6.533333333333333,
506
+ "grad_norm": 0.7761865854263306,
507
+ "learning_rate": 6.642259414225942e-05,
508
+ "loss": 0.0449,
509
+ "mean_token_accuracy": 0.9868600249290467,
510
+ "num_tokens": 1552633.0,
511
+ "step": 490
512
+ },
513
+ {
514
+ "epoch": 6.666666666666667,
515
+ "grad_norm": 0.6642009615898132,
516
+ "learning_rate": 6.537656903765691e-05,
517
+ "loss": 0.0472,
518
+ "mean_token_accuracy": 0.9871610105037689,
519
+ "num_tokens": 1587798.0,
520
+ "step": 500
521
+ },
522
+ {
523
+ "epoch": 6.8,
524
+ "grad_norm": 0.6801927089691162,
525
+ "learning_rate": 6.43305439330544e-05,
526
+ "loss": 0.0527,
527
+ "mean_token_accuracy": 0.9849318206310272,
528
+ "num_tokens": 1617597.0,
529
+ "step": 510
530
+ },
531
+ {
532
+ "epoch": 6.933333333333334,
533
+ "grad_norm": 0.6705682873725891,
534
+ "learning_rate": 6.32845188284519e-05,
535
+ "loss": 0.0505,
536
+ "mean_token_accuracy": 0.9851646542549133,
537
+ "num_tokens": 1648212.0,
538
+ "step": 520
539
+ },
540
+ {
541
+ "epoch": 7.0,
542
+ "eval_loss": 0.5524249076843262,
543
+ "eval_mean_token_accuracy": 0.8823326063156128,
544
+ "eval_num_tokens": 1666077.0,
545
+ "eval_runtime": 50.8934,
546
+ "eval_samples_per_second": 1.965,
547
+ "eval_steps_per_second": 0.491,
548
+ "step": 525
549
+ },
550
+ {
551
+ "epoch": 7.066666666666666,
552
+ "grad_norm": 1.0225543975830078,
553
+ "learning_rate": 6.223849372384938e-05,
554
+ "loss": 0.0441,
555
+ "mean_token_accuracy": 0.9876838475465775,
556
+ "num_tokens": 1682282.0,
557
+ "step": 530
558
+ },
559
+ {
560
+ "epoch": 7.2,
561
+ "grad_norm": 0.7063732743263245,
562
+ "learning_rate": 6.119246861924686e-05,
563
+ "loss": 0.0314,
564
+ "mean_token_accuracy": 0.9909861594438553,
565
+ "num_tokens": 1714966.0,
566
+ "step": 540
567
+ },
568
+ {
569
+ "epoch": 7.333333333333333,
570
+ "grad_norm": 0.4836845099925995,
571
+ "learning_rate": 6.014644351464436e-05,
572
+ "loss": 0.0346,
573
+ "mean_token_accuracy": 0.9898746073246002,
574
+ "num_tokens": 1745662.0,
575
+ "step": 550
576
+ },
577
+ {
578
+ "epoch": 7.466666666666667,
579
+ "grad_norm": 0.5448402166366577,
580
+ "learning_rate": 5.910041841004185e-05,
581
+ "loss": 0.0375,
582
+ "mean_token_accuracy": 0.9898856014013291,
583
+ "num_tokens": 1778368.0,
584
+ "step": 560
585
+ },
586
+ {
587
+ "epoch": 7.6,
588
+ "grad_norm": 0.4760727882385254,
589
+ "learning_rate": 5.8054393305439334e-05,
590
+ "loss": 0.0357,
591
+ "mean_token_accuracy": 0.9897664040327072,
592
+ "num_tokens": 1810571.0,
593
+ "step": 570
594
+ },
595
+ {
596
+ "epoch": 7.733333333333333,
597
+ "grad_norm": 0.43467867374420166,
598
+ "learning_rate": 5.7008368200836825e-05,
599
+ "loss": 0.0388,
600
+ "mean_token_accuracy": 0.9894861280918121,
601
+ "num_tokens": 1842310.0,
602
+ "step": 580
603
+ },
604
+ {
605
+ "epoch": 7.866666666666667,
606
+ "grad_norm": 0.8253856897354126,
607
+ "learning_rate": 5.5962343096234316e-05,
608
+ "loss": 0.0398,
609
+ "mean_token_accuracy": 0.9881662368774414,
610
+ "num_tokens": 1873435.0,
611
+ "step": 590
612
+ },
613
+ {
614
+ "epoch": 8.0,
615
+ "grad_norm": 0.5036665797233582,
616
+ "learning_rate": 5.4916317991631806e-05,
617
+ "loss": 0.0421,
618
+ "mean_token_accuracy": 0.9883299976587295,
619
+ "num_tokens": 1904088.0,
620
+ "step": 600
621
+ },
622
+ {
623
+ "epoch": 8.0,
624
+ "eval_loss": 0.5785043239593506,
625
+ "eval_mean_token_accuracy": 0.8845841264724732,
626
+ "eval_num_tokens": 1904088.0,
627
+ "eval_runtime": 50.8908,
628
+ "eval_samples_per_second": 1.965,
629
+ "eval_steps_per_second": 0.491,
630
+ "step": 600
631
+ },
632
+ {
633
+ "epoch": 8.133333333333333,
634
+ "grad_norm": 0.24711328744888306,
635
+ "learning_rate": 5.38702928870293e-05,
636
+ "loss": 0.0273,
637
+ "mean_token_accuracy": 0.9923271119594574,
638
+ "num_tokens": 1936241.0,
639
+ "step": 610
640
+ },
641
+ {
642
+ "epoch": 8.266666666666667,
643
+ "grad_norm": 0.44961780309677124,
644
+ "learning_rate": 5.282426778242678e-05,
645
+ "loss": 0.0291,
646
+ "mean_token_accuracy": 0.9920144468545914,
647
+ "num_tokens": 1969247.0,
648
+ "step": 620
649
+ },
650
+ {
651
+ "epoch": 8.4,
652
+ "grad_norm": 0.3607077896595001,
653
+ "learning_rate": 5.177824267782427e-05,
654
+ "loss": 0.032,
655
+ "mean_token_accuracy": 0.9911372780799865,
656
+ "num_tokens": 2001136.0,
657
+ "step": 630
658
+ },
659
+ {
660
+ "epoch": 8.533333333333333,
661
+ "grad_norm": 0.34154054522514343,
662
+ "learning_rate": 5.073221757322176e-05,
663
+ "loss": 0.0308,
664
+ "mean_token_accuracy": 0.9917692422866822,
665
+ "num_tokens": 2033446.0,
666
+ "step": 640
667
+ },
668
+ {
669
+ "epoch": 8.666666666666666,
670
+ "grad_norm": 0.5010355710983276,
671
+ "learning_rate": 4.968619246861925e-05,
672
+ "loss": 0.0341,
673
+ "mean_token_accuracy": 0.9908981770277023,
674
+ "num_tokens": 2064800.0,
675
+ "step": 650
676
+ },
677
+ {
678
+ "epoch": 8.8,
679
+ "grad_norm": 0.47791624069213867,
680
+ "learning_rate": 4.864016736401674e-05,
681
+ "loss": 0.0302,
682
+ "mean_token_accuracy": 0.9913896471261978,
683
+ "num_tokens": 2095573.0,
684
+ "step": 660
685
+ },
686
+ {
687
+ "epoch": 8.933333333333334,
688
+ "grad_norm": 0.45093876123428345,
689
+ "learning_rate": 4.759414225941423e-05,
690
+ "loss": 0.0371,
691
+ "mean_token_accuracy": 0.9898908942937851,
692
+ "num_tokens": 2126001.0,
693
+ "step": 670
694
+ },
695
+ {
696
+ "epoch": 9.0,
697
+ "eval_loss": 0.6148654222488403,
698
+ "eval_mean_token_accuracy": 0.8842980313301086,
699
+ "eval_num_tokens": 2142099.0,
700
+ "eval_runtime": 50.8928,
701
+ "eval_samples_per_second": 1.965,
702
+ "eval_steps_per_second": 0.491,
703
+ "step": 675
704
+ },
705
+ {
706
+ "epoch": 9.066666666666666,
707
+ "grad_norm": 0.5800787806510925,
708
+ "learning_rate": 4.654811715481171e-05,
709
+ "loss": 0.0291,
710
+ "mean_token_accuracy": 0.9921304136514664,
711
+ "num_tokens": 2157400.0,
712
+ "step": 680
713
+ },
714
+ {
715
+ "epoch": 9.2,
716
+ "grad_norm": 0.6982473731040955,
717
+ "learning_rate": 4.5502092050209203e-05,
718
+ "loss": 0.0239,
719
+ "mean_token_accuracy": 0.9932474166154861,
720
+ "num_tokens": 2189379.0,
721
+ "step": 690
722
+ },
723
+ {
724
+ "epoch": 9.333333333333334,
725
+ "grad_norm": 0.3595369756221771,
726
+ "learning_rate": 4.4456066945606694e-05,
727
+ "loss": 0.0265,
728
+ "mean_token_accuracy": 0.9921673446893692,
729
+ "num_tokens": 2219752.0,
730
+ "step": 700
731
+ },
732
+ {
733
+ "epoch": 9.466666666666667,
734
+ "grad_norm": 0.27210283279418945,
735
+ "learning_rate": 4.3410041841004185e-05,
736
+ "loss": 0.0276,
737
+ "mean_token_accuracy": 0.9919114917516708,
738
+ "num_tokens": 2251801.0,
739
+ "step": 710
740
+ },
741
+ {
742
+ "epoch": 9.6,
743
+ "grad_norm": 0.45378750562667847,
744
+ "learning_rate": 4.2364016736401676e-05,
745
+ "loss": 0.0267,
746
+ "mean_token_accuracy": 0.9923428118228912,
747
+ "num_tokens": 2283166.0,
748
+ "step": 720
749
+ },
750
+ {
751
+ "epoch": 9.733333333333333,
752
+ "grad_norm": 0.21831561625003815,
753
+ "learning_rate": 4.131799163179916e-05,
754
+ "loss": 0.0265,
755
+ "mean_token_accuracy": 0.9930205404758453,
756
+ "num_tokens": 2315753.0,
757
+ "step": 730
758
+ },
759
+ {
760
+ "epoch": 9.866666666666667,
761
+ "grad_norm": 0.3201010525226593,
762
+ "learning_rate": 4.027196652719665e-05,
763
+ "loss": 0.0293,
764
+ "mean_token_accuracy": 0.9924349457025528,
765
+ "num_tokens": 2348020.0,
766
+ "step": 740
767
+ },
768
+ {
769
+ "epoch": 10.0,
770
+ "grad_norm": 0.25126612186431885,
771
+ "learning_rate": 3.922594142259414e-05,
772
+ "loss": 0.0285,
773
+ "mean_token_accuracy": 0.9927875697612762,
774
+ "num_tokens": 2380110.0,
775
+ "step": 750
776
+ },
777
+ {
778
+ "epoch": 10.0,
779
+ "eval_loss": 0.6573454141616821,
780
+ "eval_mean_token_accuracy": 0.8831826686859131,
781
+ "eval_num_tokens": 2380110.0,
782
+ "eval_runtime": 50.8906,
783
+ "eval_samples_per_second": 1.965,
784
+ "eval_steps_per_second": 0.491,
785
+ "step": 750
786
+ },
787
+ {
788
+ "epoch": 10.133333333333333,
789
+ "grad_norm": 0.5593218803405762,
790
+ "learning_rate": 3.817991631799163e-05,
791
+ "loss": 0.0216,
792
+ "mean_token_accuracy": 0.9936788022518158,
793
+ "num_tokens": 2412729.0,
794
+ "step": 760
795
+ },
796
+ {
797
+ "epoch": 10.266666666666667,
798
+ "grad_norm": 0.3219089210033417,
799
+ "learning_rate": 3.713389121338912e-05,
800
+ "loss": 0.0228,
801
+ "mean_token_accuracy": 0.9932976424694061,
802
+ "num_tokens": 2443952.0,
803
+ "step": 770
804
+ },
805
+ {
806
+ "epoch": 10.4,
807
+ "grad_norm": 0.14705878496170044,
808
+ "learning_rate": 3.6087866108786614e-05,
809
+ "loss": 0.0226,
810
+ "mean_token_accuracy": 0.9936914265155792,
811
+ "num_tokens": 2475185.0,
812
+ "step": 780
813
+ },
814
+ {
815
+ "epoch": 10.533333333333333,
816
+ "grad_norm": 0.2050597369670868,
817
+ "learning_rate": 3.50418410041841e-05,
818
+ "loss": 0.024,
819
+ "mean_token_accuracy": 0.9928701817989349,
820
+ "num_tokens": 2506064.0,
821
+ "step": 790
822
+ },
823
+ {
824
+ "epoch": 10.666666666666666,
825
+ "grad_norm": 0.30800071358680725,
826
+ "learning_rate": 3.399581589958159e-05,
827
+ "loss": 0.0231,
828
+ "mean_token_accuracy": 0.9936599344015121,
829
+ "num_tokens": 2537568.0,
830
+ "step": 800
831
+ },
832
+ {
833
+ "epoch": 10.8,
834
+ "grad_norm": 0.6075056195259094,
835
+ "learning_rate": 3.294979079497908e-05,
836
+ "loss": 0.0252,
837
+ "mean_token_accuracy": 0.9924876004457474,
838
+ "num_tokens": 2568278.0,
839
+ "step": 810
840
+ },
841
+ {
842
+ "epoch": 10.933333333333334,
843
+ "grad_norm": 0.46507900953292847,
844
+ "learning_rate": 3.190376569037657e-05,
845
+ "loss": 0.0233,
846
+ "mean_token_accuracy": 0.9935177505016327,
847
+ "num_tokens": 2601290.0,
848
+ "step": 820
849
+ },
850
+ {
851
+ "epoch": 11.0,
852
+ "eval_loss": 0.7078420519828796,
853
+ "eval_mean_token_accuracy": 0.8819138598442078,
854
+ "eval_num_tokens": 2618121.0,
855
+ "eval_runtime": 50.8936,
856
+ "eval_samples_per_second": 1.965,
857
+ "eval_steps_per_second": 0.491,
858
+ "step": 825
859
+ },
860
+ {
861
+ "epoch": 11.066666666666666,
862
+ "grad_norm": 0.13493098318576813,
863
+ "learning_rate": 3.085774058577406e-05,
864
+ "loss": 0.0227,
865
+ "mean_token_accuracy": 0.9937657356262207,
866
+ "num_tokens": 2631945.0,
867
+ "step": 830
868
+ },
869
+ {
870
+ "epoch": 11.2,
871
+ "grad_norm": 0.27274149656295776,
872
+ "learning_rate": 2.981171548117155e-05,
873
+ "loss": 0.0202,
874
+ "mean_token_accuracy": 0.9939479857683182,
875
+ "num_tokens": 2664278.0,
876
+ "step": 840
877
+ },
878
+ {
879
+ "epoch": 11.333333333333334,
880
+ "grad_norm": 0.12694329023361206,
881
+ "learning_rate": 2.8765690376569036e-05,
882
+ "loss": 0.0217,
883
+ "mean_token_accuracy": 0.9940280497074128,
884
+ "num_tokens": 2697487.0,
885
+ "step": 850
886
+ },
887
+ {
888
+ "epoch": 11.466666666666667,
889
+ "grad_norm": 0.30919721722602844,
890
+ "learning_rate": 2.7719665271966527e-05,
891
+ "loss": 0.0208,
892
+ "mean_token_accuracy": 0.993863531947136,
893
+ "num_tokens": 2729287.0,
894
+ "step": 860
895
+ },
896
+ {
897
+ "epoch": 11.6,
898
+ "grad_norm": 0.346965491771698,
899
+ "learning_rate": 2.6673640167364018e-05,
900
+ "loss": 0.0219,
901
+ "mean_token_accuracy": 0.9938155382871627,
902
+ "num_tokens": 2760283.0,
903
+ "step": 870
904
+ },
905
+ {
906
+ "epoch": 11.733333333333333,
907
+ "grad_norm": 0.22179089486598969,
908
+ "learning_rate": 2.5627615062761505e-05,
909
+ "loss": 0.0198,
910
+ "mean_token_accuracy": 0.9939759701490403,
911
+ "num_tokens": 2793986.0,
912
+ "step": 880
913
+ },
914
+ {
915
+ "epoch": 11.866666666666667,
916
+ "grad_norm": 0.16201026737689972,
917
+ "learning_rate": 2.4581589958158996e-05,
918
+ "loss": 0.0228,
919
+ "mean_token_accuracy": 0.9931929171085357,
920
+ "num_tokens": 2824816.0,
921
+ "step": 890
922
+ },
923
+ {
924
+ "epoch": 12.0,
925
+ "grad_norm": 0.20347487926483154,
926
+ "learning_rate": 2.3535564853556487e-05,
927
+ "loss": 0.0228,
928
+ "mean_token_accuracy": 0.9934813290834427,
929
+ "num_tokens": 2856132.0,
930
+ "step": 900
931
+ },
932
+ {
933
+ "epoch": 12.0,
934
+ "eval_loss": 0.7223861813545227,
935
+ "eval_mean_token_accuracy": 0.8824266290664673,
936
+ "eval_num_tokens": 2856132.0,
937
+ "eval_runtime": 50.8977,
938
+ "eval_samples_per_second": 1.965,
939
+ "eval_steps_per_second": 0.491,
940
+ "step": 900
941
+ },
942
+ {
943
+ "epoch": 12.133333333333333,
944
+ "grad_norm": 0.10506761819124222,
945
+ "learning_rate": 2.2489539748953974e-05,
946
+ "loss": 0.0181,
947
+ "mean_token_accuracy": 0.9947699904441833,
948
+ "num_tokens": 2889294.0,
949
+ "step": 910
950
+ },
951
+ {
952
+ "epoch": 12.266666666666667,
953
+ "grad_norm": 0.22959034144878387,
954
+ "learning_rate": 2.1443514644351465e-05,
955
+ "loss": 0.0191,
956
+ "mean_token_accuracy": 0.9941918909549713,
957
+ "num_tokens": 2920564.0,
958
+ "step": 920
959
+ },
960
+ {
961
+ "epoch": 12.4,
962
+ "grad_norm": 0.14024658501148224,
963
+ "learning_rate": 2.0397489539748953e-05,
964
+ "loss": 0.0193,
965
+ "mean_token_accuracy": 0.9944606810808182,
966
+ "num_tokens": 2952215.0,
967
+ "step": 930
968
+ },
969
+ {
970
+ "epoch": 12.533333333333333,
971
+ "grad_norm": 0.1049821749329567,
972
+ "learning_rate": 1.9351464435146444e-05,
973
+ "loss": 0.0187,
974
+ "mean_token_accuracy": 0.9942614287137985,
975
+ "num_tokens": 2984367.0,
976
+ "step": 940
977
+ },
978
+ {
979
+ "epoch": 12.666666666666666,
980
+ "grad_norm": 0.14182651042938232,
981
+ "learning_rate": 1.8305439330543934e-05,
982
+ "loss": 0.0199,
983
+ "mean_token_accuracy": 0.9938604891300201,
984
+ "num_tokens": 3015120.0,
985
+ "step": 950
986
+ },
987
+ {
988
+ "epoch": 12.8,
989
+ "grad_norm": 0.13577786087989807,
990
+ "learning_rate": 1.7259414225941422e-05,
991
+ "loss": 0.0197,
992
+ "mean_token_accuracy": 0.9941955178976059,
993
+ "num_tokens": 3046751.0,
994
+ "step": 960
995
+ },
996
+ {
997
+ "epoch": 12.933333333333334,
998
+ "grad_norm": 0.18529069423675537,
999
+ "learning_rate": 1.6213389121338913e-05,
1000
+ "loss": 0.0201,
1001
+ "mean_token_accuracy": 0.9938661843538285,
1002
+ "num_tokens": 3078212.0,
1003
+ "step": 970
1004
+ },
1005
+ {
1006
+ "epoch": 13.0,
1007
+ "eval_loss": 0.7834702134132385,
1008
+ "eval_mean_token_accuracy": 0.8812357115745545,
1009
+ "eval_num_tokens": 3094143.0,
1010
+ "eval_runtime": 50.9004,
1011
+ "eval_samples_per_second": 1.965,
1012
+ "eval_steps_per_second": 0.491,
1013
+ "step": 975
1014
+ },
1015
+ {
1016
+ "epoch": 13.066666666666666,
1017
+ "grad_norm": 0.07987310737371445,
1018
+ "learning_rate": 1.5167364016736402e-05,
1019
+ "loss": 0.0193,
1020
+ "mean_token_accuracy": 0.9944200098514557,
1021
+ "num_tokens": 3109895.0,
1022
+ "step": 980
1023
+ },
1024
+ {
1025
+ "epoch": 13.2,
1026
+ "grad_norm": 0.09330923855304718,
1027
+ "learning_rate": 1.412133891213389e-05,
1028
+ "loss": 0.0181,
1029
+ "mean_token_accuracy": 0.9943874269723892,
1030
+ "num_tokens": 3141209.0,
1031
+ "step": 990
1032
+ },
1033
+ {
1034
+ "epoch": 13.333333333333334,
1035
+ "grad_norm": 0.11167001724243164,
1036
+ "learning_rate": 1.307531380753138e-05,
1037
+ "loss": 0.018,
1038
+ "mean_token_accuracy": 0.9946882605552674,
1039
+ "num_tokens": 3173385.0,
1040
+ "step": 1000
1041
+ },
1042
+ {
1043
+ "epoch": 13.466666666666667,
1044
+ "grad_norm": 0.16363947093486786,
1045
+ "learning_rate": 1.202928870292887e-05,
1046
+ "loss": 0.0192,
1047
+ "mean_token_accuracy": 0.994058096408844,
1048
+ "num_tokens": 3203081.0,
1049
+ "step": 1010
1050
+ },
1051
+ {
1052
+ "epoch": 13.6,
1053
+ "grad_norm": 0.15829868614673615,
1054
+ "learning_rate": 1.098326359832636e-05,
1055
+ "loss": 0.0192,
1056
+ "mean_token_accuracy": 0.993596938252449,
1057
+ "num_tokens": 3234247.0,
1058
+ "step": 1020
1059
+ },
1060
+ {
1061
+ "epoch": 13.733333333333333,
1062
+ "grad_norm": 0.11582522094249725,
1063
+ "learning_rate": 9.937238493723849e-06,
1064
+ "loss": 0.0183,
1065
+ "mean_token_accuracy": 0.9946052461862565,
1066
+ "num_tokens": 3265780.0,
1067
+ "step": 1030
1068
+ },
1069
+ {
1070
+ "epoch": 13.866666666666667,
1071
+ "grad_norm": 0.09746014326810837,
1072
+ "learning_rate": 8.891213389121338e-06,
1073
+ "loss": 0.0179,
1074
+ "mean_token_accuracy": 0.9942047536373139,
1075
+ "num_tokens": 3299307.0,
1076
+ "step": 1040
1077
+ },
1078
+ {
1079
+ "epoch": 14.0,
1080
+ "grad_norm": 0.09180562198162079,
1081
+ "learning_rate": 7.845188284518829e-06,
1082
+ "loss": 0.018,
1083
+ "mean_token_accuracy": 0.9945183902978897,
1084
+ "num_tokens": 3332154.0,
1085
+ "step": 1050
1086
+ },
1087
+ {
1088
+ "epoch": 14.0,
1089
+ "eval_loss": 0.8125747442245483,
1090
+ "eval_mean_token_accuracy": 0.8807920503616333,
1091
+ "eval_num_tokens": 3332154.0,
1092
+ "eval_runtime": 50.8913,
1093
+ "eval_samples_per_second": 1.965,
1094
+ "eval_steps_per_second": 0.491,
1095
+ "step": 1050
1096
+ },
1097
+ {
1098
+ "epoch": 14.133333333333333,
1099
+ "grad_norm": 0.10202191025018692,
1100
+ "learning_rate": 6.799163179916318e-06,
1101
+ "loss": 0.0183,
1102
+ "mean_token_accuracy": 0.9945108294487,
1103
+ "num_tokens": 3361831.0,
1104
+ "step": 1060
1105
+ },
1106
+ {
1107
+ "epoch": 14.266666666666667,
1108
+ "grad_norm": 0.10076984018087387,
1109
+ "learning_rate": 5.753138075313807e-06,
1110
+ "loss": 0.0185,
1111
+ "mean_token_accuracy": 0.9945613890886307,
1112
+ "num_tokens": 3391208.0,
1113
+ "step": 1070
1114
+ },
1115
+ {
1116
+ "epoch": 14.4,
1117
+ "grad_norm": 0.0787443146109581,
1118
+ "learning_rate": 4.707112970711297e-06,
1119
+ "loss": 0.017,
1120
+ "mean_token_accuracy": 0.9948166966438293,
1121
+ "num_tokens": 3424009.0,
1122
+ "step": 1080
1123
+ },
1124
+ {
1125
+ "epoch": 14.533333333333333,
1126
+ "grad_norm": 0.09680254012346268,
1127
+ "learning_rate": 3.6610878661087868e-06,
1128
+ "loss": 0.0175,
1129
+ "mean_token_accuracy": 0.9944073975086212,
1130
+ "num_tokens": 3455479.0,
1131
+ "step": 1090
1132
+ },
1133
+ {
1134
+ "epoch": 14.666666666666666,
1135
+ "grad_norm": 0.1012917160987854,
1136
+ "learning_rate": 2.6150627615062763e-06,
1137
+ "loss": 0.0172,
1138
+ "mean_token_accuracy": 0.9949172258377075,
1139
+ "num_tokens": 3488372.0,
1140
+ "step": 1100
1141
+ },
1142
+ {
1143
+ "epoch": 14.8,
1144
+ "grad_norm": 0.12024527043104172,
1145
+ "learning_rate": 1.5690376569037657e-06,
1146
+ "loss": 0.0167,
1147
+ "mean_token_accuracy": 0.9948821812868118,
1148
+ "num_tokens": 3522108.0,
1149
+ "step": 1110
1150
+ },
1151
+ {
1152
+ "epoch": 14.933333333333334,
1153
+ "grad_norm": 0.12410510331392288,
1154
+ "learning_rate": 5.230125523012552e-07,
1155
+ "loss": 0.0169,
1156
+ "mean_token_accuracy": 0.9942798018455505,
1157
+ "num_tokens": 3555212.0,
1158
+ "step": 1120
1159
+ },
1160
+ {
1161
+ "epoch": 15.0,
1162
+ "eval_loss": 0.8290462493896484,
1163
+ "eval_mean_token_accuracy": 0.8807440662384033,
1164
+ "eval_num_tokens": 3570165.0,
1165
+ "eval_runtime": 50.8971,
1166
+ "eval_samples_per_second": 1.965,
1167
+ "eval_steps_per_second": 0.491,
1168
+ "step": 1125
1169
+ }
1170
+ ],
1171
+ "logging_steps": 10,
1172
+ "max_steps": 1125,
1173
+ "num_input_tokens_seen": 0,
1174
+ "num_train_epochs": 15,
1175
+ "save_steps": 500,
1176
+ "stateful_callbacks": {
1177
+ "TrainerControl": {
1178
+ "args": {
1179
+ "should_epoch_stop": false,
1180
+ "should_evaluate": false,
1181
+ "should_log": false,
1182
+ "should_save": true,
1183
+ "should_training_stop": true
1184
+ },
1185
+ "attributes": {}
1186
+ }
1187
+ },
1188
+ "total_flos": 2.14132993600598e+17,
1189
+ "train_batch_size": 4,
1190
+ "trial_name": null,
1191
+ "trial_params": null
1192
+ }
checkpoint-1125/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62870f24a4207eea4af3eb1d98603c25ccfec3a861c88478569c8265a81dc3de
3
+ size 5624
checkpoint-1125/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-150/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-7B-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
checkpoint-150/adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-7B-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": 0.1,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 16,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "down_proj",
27
+ "k_proj",
28
+ "up_proj",
29
+ "o_proj",
30
+ "v_proj",
31
+ "gate_proj",
32
+ "q_proj"
33
+ ],
34
+ "task_type": "CAUSAL_LM",
35
+ "use_dora": false,
36
+ "use_rslora": false
37
+ }
checkpoint-150/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73e57453260f2f64029627aea146702060483f55200e8f9e61b541101f2dacf1
3
+ size 161533192
checkpoint-150/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
+ }
checkpoint-150/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-150/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cc767e835546224917749585ae4c23e9c2376995c6c4590bfdd81938bf12491
3
+ size 82460660
checkpoint-150/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70ac0e2660a962995d46f7ea894a8a7d5aa6221ec60e2b8f6a1365bea5785bf5
3
+ size 14244
checkpoint-150/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9c2c40463630554328064fdab23708482a8449ed82e32b19bdc5292e90d3f82
3
+ size 1064
checkpoint-150/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
checkpoint-150/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
checkpoint-150/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": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
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": null,
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
+ }
checkpoint-150/trainer_state.json ADDED
@@ -0,0 +1,189 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 150,
3
+ "best_metric": 0.3620273470878601,
4
+ "best_model_checkpoint": "/content/output/checkpoint-150",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 150,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.13333333333333333,
14
+ "grad_norm": 1.7940553426742554,
15
+ "learning_rate": 5.917159763313609e-06,
16
+ "loss": 1.3972,
17
+ "mean_token_accuracy": 0.7618847399950027,
18
+ "num_tokens": 31152.0,
19
+ "step": 10
20
+ },
21
+ {
22
+ "epoch": 0.26666666666666666,
23
+ "grad_norm": 1.0511088371276855,
24
+ "learning_rate": 1.1834319526627219e-05,
25
+ "loss": 1.2288,
26
+ "mean_token_accuracy": 0.7673537939786911,
27
+ "num_tokens": 61773.0,
28
+ "step": 20
29
+ },
30
+ {
31
+ "epoch": 0.4,
32
+ "grad_norm": 0.8096975088119507,
33
+ "learning_rate": 1.7751479289940828e-05,
34
+ "loss": 0.9255,
35
+ "mean_token_accuracy": 0.7948055118322372,
36
+ "num_tokens": 94758.0,
37
+ "step": 30
38
+ },
39
+ {
40
+ "epoch": 0.5333333333333333,
41
+ "grad_norm": 0.6213255524635315,
42
+ "learning_rate": 2.3668639053254438e-05,
43
+ "loss": 0.7366,
44
+ "mean_token_accuracy": 0.8212289035320282,
45
+ "num_tokens": 125915.0,
46
+ "step": 40
47
+ },
48
+ {
49
+ "epoch": 0.6666666666666666,
50
+ "grad_norm": 0.42887863516807556,
51
+ "learning_rate": 2.958579881656805e-05,
52
+ "loss": 0.5556,
53
+ "mean_token_accuracy": 0.8463607966899872,
54
+ "num_tokens": 159364.0,
55
+ "step": 50
56
+ },
57
+ {
58
+ "epoch": 0.8,
59
+ "grad_norm": 0.5108550786972046,
60
+ "learning_rate": 3.5502958579881656e-05,
61
+ "loss": 0.4676,
62
+ "mean_token_accuracy": 0.8614094287157059,
63
+ "num_tokens": 190374.0,
64
+ "step": 60
65
+ },
66
+ {
67
+ "epoch": 0.9333333333333333,
68
+ "grad_norm": 0.4310983121395111,
69
+ "learning_rate": 4.142011834319527e-05,
70
+ "loss": 0.4214,
71
+ "mean_token_accuracy": 0.8710317760705948,
72
+ "num_tokens": 222156.0,
73
+ "step": 70
74
+ },
75
+ {
76
+ "epoch": 1.0,
77
+ "eval_loss": 0.4043419659137726,
78
+ "eval_mean_token_accuracy": 0.8734077858924866,
79
+ "eval_num_tokens": 238011.0,
80
+ "eval_runtime": 50.8925,
81
+ "eval_samples_per_second": 1.965,
82
+ "eval_steps_per_second": 0.491,
83
+ "step": 75
84
+ },
85
+ {
86
+ "epoch": 1.0666666666666667,
87
+ "grad_norm": 0.35767048597335815,
88
+ "learning_rate": 4.7337278106508875e-05,
89
+ "loss": 0.3901,
90
+ "mean_token_accuracy": 0.8787548273801804,
91
+ "num_tokens": 255825.0,
92
+ "step": 80
93
+ },
94
+ {
95
+ "epoch": 1.2,
96
+ "grad_norm": 0.3684692680835724,
97
+ "learning_rate": 5.3254437869822495e-05,
98
+ "loss": 0.3956,
99
+ "mean_token_accuracy": 0.8787799149751663,
100
+ "num_tokens": 287370.0,
101
+ "step": 90
102
+ },
103
+ {
104
+ "epoch": 1.3333333333333333,
105
+ "grad_norm": 0.35148611664772034,
106
+ "learning_rate": 5.91715976331361e-05,
107
+ "loss": 0.3822,
108
+ "mean_token_accuracy": 0.8814697057008744,
109
+ "num_tokens": 315883.0,
110
+ "step": 100
111
+ },
112
+ {
113
+ "epoch": 1.4666666666666668,
114
+ "grad_norm": 0.39074671268463135,
115
+ "learning_rate": 6.50887573964497e-05,
116
+ "loss": 0.3703,
117
+ "mean_token_accuracy": 0.8836676925420761,
118
+ "num_tokens": 347324.0,
119
+ "step": 110
120
+ },
121
+ {
122
+ "epoch": 1.6,
123
+ "grad_norm": 0.38130292296409607,
124
+ "learning_rate": 7.100591715976331e-05,
125
+ "loss": 0.3762,
126
+ "mean_token_accuracy": 0.8851484537124634,
127
+ "num_tokens": 379374.0,
128
+ "step": 120
129
+ },
130
+ {
131
+ "epoch": 1.7333333333333334,
132
+ "grad_norm": 0.4091486632823944,
133
+ "learning_rate": 7.692307692307693e-05,
134
+ "loss": 0.3446,
135
+ "mean_token_accuracy": 0.8894414573907852,
136
+ "num_tokens": 411843.0,
137
+ "step": 130
138
+ },
139
+ {
140
+ "epoch": 1.8666666666666667,
141
+ "grad_norm": 0.361017644405365,
142
+ "learning_rate": 8.284023668639054e-05,
143
+ "loss": 0.3494,
144
+ "mean_token_accuracy": 0.8915452778339386,
145
+ "num_tokens": 444017.0,
146
+ "step": 140
147
+ },
148
+ {
149
+ "epoch": 2.0,
150
+ "grad_norm": 0.3487047851085663,
151
+ "learning_rate": 8.875739644970414e-05,
152
+ "loss": 0.3674,
153
+ "mean_token_accuracy": 0.8846240967512131,
154
+ "num_tokens": 476022.0,
155
+ "step": 150
156
+ },
157
+ {
158
+ "epoch": 2.0,
159
+ "eval_loss": 0.3620273470878601,
160
+ "eval_mean_token_accuracy": 0.8875497984886169,
161
+ "eval_num_tokens": 476022.0,
162
+ "eval_runtime": 50.8961,
163
+ "eval_samples_per_second": 1.965,
164
+ "eval_steps_per_second": 0.491,
165
+ "step": 150
166
+ }
167
+ ],
168
+ "logging_steps": 10,
169
+ "max_steps": 1125,
170
+ "num_input_tokens_seen": 0,
171
+ "num_train_epochs": 15,
172
+ "save_steps": 500,
173
+ "stateful_callbacks": {
174
+ "TrainerControl": {
175
+ "args": {
176
+ "should_epoch_stop": false,
177
+ "should_evaluate": false,
178
+ "should_log": false,
179
+ "should_save": true,
180
+ "should_training_stop": false
181
+ },
182
+ "attributes": {}
183
+ }
184
+ },
185
+ "total_flos": 2.842489979664384e+16,
186
+ "train_batch_size": 4,
187
+ "trial_name": null,
188
+ "trial_params": null
189
+ }
checkpoint-150/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62870f24a4207eea4af3eb1d98603c25ccfec3a861c88478569c8265a81dc3de
3
+ size 5624
checkpoint-150/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-225/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-7B-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
checkpoint-225/adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-7B-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": 0.1,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 16,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "down_proj",
27
+ "k_proj",
28
+ "up_proj",
29
+ "o_proj",
30
+ "v_proj",
31
+ "gate_proj",
32
+ "q_proj"
33
+ ],
34
+ "task_type": "CAUSAL_LM",
35
+ "use_dora": false,
36
+ "use_rslora": false
37
+ }
checkpoint-225/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2da8805f4460f7429e7cf7150c435f7371c13368934102a189753fb3dd5a8360
3
+ size 161533192
checkpoint-225/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
+ }
checkpoint-225/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-225/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55c1b28ac70061152c0f2949b0d1ffcdeeeba5e1694ec5e03f855e1b413fdc53
3
+ size 82460660
checkpoint-225/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea74c7b19feed8803cd251b50ad977bce36ebdb687728976060d2d71f416bb3c
3
+ size 14244