Hugging Face's logo

oodeh
/
eco-gotests-tag-model-only-tests-checkpoints

Safetensors
Model card Files Community
oodeh commited on
Commit
edb8f02
·
verified ·
1 Parent(s): 6c6da7a

Add files using upload-large-folder tool

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 +8 -0
  2. checkpoint-120/README.md +202 -0
  3. checkpoint-120/adapter_config.json +34 -0
  4. checkpoint-120/adapter_model.safetensors +3 -0
  5. checkpoint-120/added_tokens.json +24 -0
  6. checkpoint-120/merges.txt +0 -0
  7. checkpoint-120/optimizer.pt +3 -0
  8. checkpoint-120/rng_state_0.pth +3 -0
  9. checkpoint-120/rng_state_1.pth +3 -0
  10. checkpoint-120/scheduler.pt +3 -0
  11. checkpoint-120/special_tokens_map.json +31 -0
  12. checkpoint-120/tokenizer.json +3 -0
  13. checkpoint-120/tokenizer_config.json +209 -0
  14. checkpoint-120/trainer_state.json +993 -0
  15. checkpoint-120/training_args.bin +3 -0
  16. checkpoint-120/vocab.json +0 -0
  17. checkpoint-180/README.md +202 -0
  18. checkpoint-180/adapter_config.json +34 -0
  19. checkpoint-180/adapter_model.safetensors +3 -0
  20. checkpoint-180/added_tokens.json +24 -0
  21. checkpoint-180/merges.txt +0 -0
  22. checkpoint-180/optimizer.pt +3 -0
  23. checkpoint-180/rng_state_0.pth +3 -0
  24. checkpoint-180/rng_state_1.pth +3 -0
  25. checkpoint-180/scheduler.pt +3 -0
  26. checkpoint-180/special_tokens_map.json +31 -0
  27. checkpoint-180/tokenizer.json +3 -0
  28. checkpoint-180/tokenizer_config.json +209 -0
  29. checkpoint-180/trainer_state.json +1473 -0
  30. checkpoint-180/training_args.bin +3 -0
  31. checkpoint-180/vocab.json +0 -0
  32. checkpoint-240/README.md +202 -0
  33. checkpoint-240/adapter_config.json +34 -0
  34. checkpoint-240/adapter_model.safetensors +3 -0
  35. checkpoint-240/added_tokens.json +24 -0
  36. checkpoint-240/merges.txt +0 -0
  37. checkpoint-240/optimizer.pt +3 -0
  38. checkpoint-240/rng_state_0.pth +3 -0
  39. checkpoint-240/rng_state_1.pth +3 -0
  40. checkpoint-240/scheduler.pt +3 -0
  41. checkpoint-240/special_tokens_map.json +31 -0
  42. checkpoint-240/tokenizer.json +3 -0
  43. checkpoint-240/tokenizer_config.json +209 -0
  44. checkpoint-240/trainer_state.json +1953 -0
  45. checkpoint-240/training_args.bin +3 -0
  46. checkpoint-240/vocab.json +0 -0
  47. checkpoint-300/README.md +202 -0
  48. checkpoint-300/adapter_config.json +34 -0
  49. checkpoint-300/adapter_model.safetensors +3 -0
  50. checkpoint-300/added_tokens.json +24 -0
.gitattributes CHANGED
@@ -33,3 +33,11 @@ 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-360/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ checkpoint-420/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ checkpoint-480/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
+ checkpoint-60/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
+ checkpoint-120/tokenizer.json filter=lfs diff=lfs merge=lfs -text
42
+ checkpoint-240/tokenizer.json filter=lfs diff=lfs merge=lfs -text
43
+ checkpoint-180/tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoint-120/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-Coder-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 0.12.0
checkpoint-120/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-Coder-7B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "down_proj",
24
+ "k_proj",
25
+ "v_proj",
26
+ "q_proj",
27
+ "o_proj",
28
+ "gate_proj",
29
+ "up_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-120/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36e44a66c0b25d2204417e5cb0612fc3115226db2b610ba3a7faa16eaa9721db
3
+ size 161533192
checkpoint-120/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-120/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-120/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f80cabc84bfad36bd4dd6e2a99965406b50b77c02af179e1b4a53ac466ac4044
3
+ size 323290986
checkpoint-120/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40245830296e0325962211fbc9328be302d2c3db64330baed83c0212334f76ac
3
+ size 14512
checkpoint-120/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65df254e1019f54e1386eadf76d4cdb870f1dd0e41ebb21db1a25015c7f3139f
3
+ size 14512
checkpoint-120/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dd9baf01246fc9627263131baa26325e9df03b1eeb9500344dfbddaeedf522a
3
+ size 1064
checkpoint-120/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-120/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
checkpoint-120/tokenizer_config.json ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 17000,
204
+ "pad_token": "<|endoftext|>",
205
+ "padding_side": "right",
206
+ "split_special_tokens": false,
207
+ "tokenizer_class": "Qwen2Tokenizer",
208
+ "unk_token": null
209
+ }
checkpoint-120/trainer_state.json ADDED
@@ -0,0 +1,993 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.980269989615784,
5
+ "eval_steps": 500,
6
+ "global_step": 120,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.016614745586708203,
13
+ "grad_norm": 0.061364494264125824,
14
+ "learning_rate": 4.999991432639962e-05,
15
+ "loss": 0.5857,
16
+ "num_input_tokens_seen": 70408,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.033229491173416406,
21
+ "grad_norm": 0.0613991804420948,
22
+ "learning_rate": 4.999965730618567e-05,
23
+ "loss": 0.5331,
24
+ "num_input_tokens_seen": 139640,
25
+ "step": 2
26
+ },
27
+ {
28
+ "epoch": 0.04984423676012461,
29
+ "grad_norm": 0.06351307034492493,
30
+ "learning_rate": 4.9999228941119745e-05,
31
+ "loss": 0.5852,
32
+ "num_input_tokens_seen": 223656,
33
+ "step": 3
34
+ },
35
+ {
36
+ "epoch": 0.06645898234683281,
37
+ "grad_norm": 0.05762802064418793,
38
+ "learning_rate": 4.999862923413781e-05,
39
+ "loss": 0.5384,
40
+ "num_input_tokens_seen": 300688,
41
+ "step": 4
42
+ },
43
+ {
44
+ "epoch": 0.08307372793354102,
45
+ "grad_norm": 0.0632179006934166,
46
+ "learning_rate": 4.999785818935018e-05,
47
+ "loss": 0.5273,
48
+ "num_input_tokens_seen": 366368,
49
+ "step": 5
50
+ },
51
+ {
52
+ "epoch": 0.09968847352024922,
53
+ "grad_norm": 0.056689903140068054,
54
+ "learning_rate": 4.999691581204152e-05,
55
+ "loss": 0.5145,
56
+ "num_input_tokens_seen": 445808,
57
+ "step": 6
58
+ },
59
+ {
60
+ "epoch": 0.11630321910695743,
61
+ "grad_norm": 0.06574171781539917,
62
+ "learning_rate": 4.9995802108670775e-05,
63
+ "loss": 0.5301,
64
+ "num_input_tokens_seen": 522800,
65
+ "step": 7
66
+ },
67
+ {
68
+ "epoch": 0.13291796469366562,
69
+ "grad_norm": 0.06367070972919464,
70
+ "learning_rate": 4.999451708687114e-05,
71
+ "loss": 0.5552,
72
+ "num_input_tokens_seen": 599608,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.14953271028037382,
77
+ "grad_norm": 0.0585966520011425,
78
+ "learning_rate": 4.9993060755450015e-05,
79
+ "loss": 0.5999,
80
+ "num_input_tokens_seen": 681424,
81
+ "step": 9
82
+ },
83
+ {
84
+ "epoch": 0.16614745586708204,
85
+ "grad_norm": 0.05650574713945389,
86
+ "learning_rate": 4.999143312438893e-05,
87
+ "loss": 0.4535,
88
+ "num_input_tokens_seen": 756744,
89
+ "step": 10
90
+ },
91
+ {
92
+ "epoch": 0.18276220145379024,
93
+ "grad_norm": 0.05954223498702049,
94
+ "learning_rate": 4.998963420484349e-05,
95
+ "loss": 0.4674,
96
+ "num_input_tokens_seen": 842576,
97
+ "step": 11
98
+ },
99
+ {
100
+ "epoch": 0.19937694704049844,
101
+ "grad_norm": 0.0663776770234108,
102
+ "learning_rate": 4.998766400914329e-05,
103
+ "loss": 0.4703,
104
+ "num_input_tokens_seen": 917232,
105
+ "step": 12
106
+ },
107
+ {
108
+ "epoch": 0.21599169262720663,
109
+ "grad_norm": 0.056374579668045044,
110
+ "learning_rate": 4.9985522550791825e-05,
111
+ "loss": 0.3725,
112
+ "num_input_tokens_seen": 1006800,
113
+ "step": 13
114
+ },
115
+ {
116
+ "epoch": 0.23260643821391486,
117
+ "grad_norm": 0.06437493115663528,
118
+ "learning_rate": 4.998320984446641e-05,
119
+ "loss": 0.4653,
120
+ "num_input_tokens_seen": 1085824,
121
+ "step": 14
122
+ },
123
+ {
124
+ "epoch": 0.24922118380062305,
125
+ "grad_norm": 0.06560757756233215,
126
+ "learning_rate": 4.9980725906018074e-05,
127
+ "loss": 0.5026,
128
+ "num_input_tokens_seen": 1164160,
129
+ "step": 15
130
+ },
131
+ {
132
+ "epoch": 0.26583592938733125,
133
+ "grad_norm": 0.06942517310380936,
134
+ "learning_rate": 4.997807075247146e-05,
135
+ "loss": 0.5401,
136
+ "num_input_tokens_seen": 1242264,
137
+ "step": 16
138
+ },
139
+ {
140
+ "epoch": 0.2824506749740395,
141
+ "grad_norm": 0.06349828094244003,
142
+ "learning_rate": 4.997524440202469e-05,
143
+ "loss": 0.4713,
144
+ "num_input_tokens_seen": 1325904,
145
+ "step": 17
146
+ },
147
+ {
148
+ "epoch": 0.29906542056074764,
149
+ "grad_norm": 0.08846385776996613,
150
+ "learning_rate": 4.9972246874049254e-05,
151
+ "loss": 0.5834,
152
+ "num_input_tokens_seen": 1385632,
153
+ "step": 18
154
+ },
155
+ {
156
+ "epoch": 0.31568016614745587,
157
+ "grad_norm": 0.062130190432071686,
158
+ "learning_rate": 4.996907818908987e-05,
159
+ "loss": 0.4045,
160
+ "num_input_tokens_seen": 1470632,
161
+ "step": 19
162
+ },
163
+ {
164
+ "epoch": 0.3322949117341641,
165
+ "grad_norm": 0.07743565738201141,
166
+ "learning_rate": 4.996573836886435e-05,
167
+ "loss": 0.5283,
168
+ "num_input_tokens_seen": 1547536,
169
+ "step": 20
170
+ },
171
+ {
172
+ "epoch": 0.34890965732087226,
173
+ "grad_norm": 0.06756695359945297,
174
+ "learning_rate": 4.9962227436263453e-05,
175
+ "loss": 0.4199,
176
+ "num_input_tokens_seen": 1615528,
177
+ "step": 21
178
+ },
179
+ {
180
+ "epoch": 0.3655244029075805,
181
+ "grad_norm": 0.08662309497594833,
182
+ "learning_rate": 4.995854541535071e-05,
183
+ "loss": 0.4775,
184
+ "num_input_tokens_seen": 1694352,
185
+ "step": 22
186
+ },
187
+ {
188
+ "epoch": 0.3821391484942887,
189
+ "grad_norm": 0.08380820602178574,
190
+ "learning_rate": 4.9954692331362294e-05,
191
+ "loss": 0.4871,
192
+ "num_input_tokens_seen": 1753776,
193
+ "step": 23
194
+ },
195
+ {
196
+ "epoch": 0.3987538940809969,
197
+ "grad_norm": 0.09967435896396637,
198
+ "learning_rate": 4.995066821070679e-05,
199
+ "loss": 0.4871,
200
+ "num_input_tokens_seen": 1809048,
201
+ "step": 24
202
+ },
203
+ {
204
+ "epoch": 0.4153686396677051,
205
+ "grad_norm": 0.0871267095208168,
206
+ "learning_rate": 4.994647308096509e-05,
207
+ "loss": 0.5461,
208
+ "num_input_tokens_seen": 1884264,
209
+ "step": 25
210
+ },
211
+ {
212
+ "epoch": 0.43198338525441327,
213
+ "grad_norm": 0.065020851790905,
214
+ "learning_rate": 4.994210697089014e-05,
215
+ "loss": 0.405,
216
+ "num_input_tokens_seen": 1981704,
217
+ "step": 26
218
+ },
219
+ {
220
+ "epoch": 0.4485981308411215,
221
+ "grad_norm": 0.09853450953960419,
222
+ "learning_rate": 4.9937569910406756e-05,
223
+ "loss": 0.4487,
224
+ "num_input_tokens_seen": 2044144,
225
+ "step": 27
226
+ },
227
+ {
228
+ "epoch": 0.4652128764278297,
229
+ "grad_norm": 0.08763110637664795,
230
+ "learning_rate": 4.9932861930611454e-05,
231
+ "loss": 0.3946,
232
+ "num_input_tokens_seen": 2107584,
233
+ "step": 28
234
+ },
235
+ {
236
+ "epoch": 0.4818276220145379,
237
+ "grad_norm": 0.08950547873973846,
238
+ "learning_rate": 4.9927983063772196e-05,
239
+ "loss": 0.4257,
240
+ "num_input_tokens_seen": 2169248,
241
+ "step": 29
242
+ },
243
+ {
244
+ "epoch": 0.4984423676012461,
245
+ "grad_norm": 0.09980211406946182,
246
+ "learning_rate": 4.99229333433282e-05,
247
+ "loss": 0.3911,
248
+ "num_input_tokens_seen": 2230344,
249
+ "step": 30
250
+ },
251
+ {
252
+ "epoch": 0.5150571131879543,
253
+ "grad_norm": 0.092055544257164,
254
+ "learning_rate": 4.9917712803889674e-05,
255
+ "loss": 0.3749,
256
+ "num_input_tokens_seen": 2302368,
257
+ "step": 31
258
+ },
259
+ {
260
+ "epoch": 0.5316718587746625,
261
+ "grad_norm": 0.10067818313837051,
262
+ "learning_rate": 4.991232148123761e-05,
263
+ "loss": 0.4761,
264
+ "num_input_tokens_seen": 2369984,
265
+ "step": 32
266
+ },
267
+ {
268
+ "epoch": 0.5482866043613707,
269
+ "grad_norm": 0.0717971920967102,
270
+ "learning_rate": 4.990675941232353e-05,
271
+ "loss": 0.4328,
272
+ "num_input_tokens_seen": 2453032,
273
+ "step": 33
274
+ },
275
+ {
276
+ "epoch": 0.564901349948079,
277
+ "grad_norm": 0.07436250895261765,
278
+ "learning_rate": 4.990102663526924e-05,
279
+ "loss": 0.417,
280
+ "num_input_tokens_seen": 2527464,
281
+ "step": 34
282
+ },
283
+ {
284
+ "epoch": 0.5815160955347871,
285
+ "grad_norm": 0.09256689995527267,
286
+ "learning_rate": 4.989512318936655e-05,
287
+ "loss": 0.4097,
288
+ "num_input_tokens_seen": 2597032,
289
+ "step": 35
290
+ },
291
+ {
292
+ "epoch": 0.5981308411214953,
293
+ "grad_norm": 0.09964177012443542,
294
+ "learning_rate": 4.9889049115077005e-05,
295
+ "loss": 0.4065,
296
+ "num_input_tokens_seen": 2671704,
297
+ "step": 36
298
+ },
299
+ {
300
+ "epoch": 0.6147455867082036,
301
+ "grad_norm": 0.06627887487411499,
302
+ "learning_rate": 4.988280445403164e-05,
303
+ "loss": 0.4136,
304
+ "num_input_tokens_seen": 2767640,
305
+ "step": 37
306
+ },
307
+ {
308
+ "epoch": 0.6313603322949117,
309
+ "grad_norm": 0.0746045857667923,
310
+ "learning_rate": 4.987638924903067e-05,
311
+ "loss": 0.4125,
312
+ "num_input_tokens_seen": 2843720,
313
+ "step": 38
314
+ },
315
+ {
316
+ "epoch": 0.6479750778816199,
317
+ "grad_norm": 0.0795741006731987,
318
+ "learning_rate": 4.9869803544043166e-05,
319
+ "loss": 0.3135,
320
+ "num_input_tokens_seen": 2921472,
321
+ "step": 39
322
+ },
323
+ {
324
+ "epoch": 0.6645898234683282,
325
+ "grad_norm": 0.08914181590080261,
326
+ "learning_rate": 4.9863047384206835e-05,
327
+ "loss": 0.4549,
328
+ "num_input_tokens_seen": 2998400,
329
+ "step": 40
330
+ },
331
+ {
332
+ "epoch": 0.6812045690550363,
333
+ "grad_norm": 0.11220043897628784,
334
+ "learning_rate": 4.985612081582764e-05,
335
+ "loss": 0.4135,
336
+ "num_input_tokens_seen": 3059648,
337
+ "step": 41
338
+ },
339
+ {
340
+ "epoch": 0.6978193146417445,
341
+ "grad_norm": 0.08390027284622192,
342
+ "learning_rate": 4.98490238863795e-05,
343
+ "loss": 0.3538,
344
+ "num_input_tokens_seen": 3140184,
345
+ "step": 42
346
+ },
347
+ {
348
+ "epoch": 0.7144340602284528,
349
+ "grad_norm": 0.08858532458543777,
350
+ "learning_rate": 4.984175664450397e-05,
351
+ "loss": 0.3644,
352
+ "num_input_tokens_seen": 3207184,
353
+ "step": 43
354
+ },
355
+ {
356
+ "epoch": 0.731048805815161,
357
+ "grad_norm": 0.07439564168453217,
358
+ "learning_rate": 4.983431914000991e-05,
359
+ "loss": 0.4019,
360
+ "num_input_tokens_seen": 3292344,
361
+ "step": 44
362
+ },
363
+ {
364
+ "epoch": 0.7476635514018691,
365
+ "grad_norm": 0.08694300055503845,
366
+ "learning_rate": 4.982671142387316e-05,
367
+ "loss": 0.4238,
368
+ "num_input_tokens_seen": 3365384,
369
+ "step": 45
370
+ },
371
+ {
372
+ "epoch": 0.7642782969885774,
373
+ "grad_norm": 0.0867784395813942,
374
+ "learning_rate": 4.981893354823614e-05,
375
+ "loss": 0.3702,
376
+ "num_input_tokens_seen": 3440720,
377
+ "step": 46
378
+ },
379
+ {
380
+ "epoch": 0.7808930425752856,
381
+ "grad_norm": 0.06278439611196518,
382
+ "learning_rate": 4.9810985566407544e-05,
383
+ "loss": 0.3354,
384
+ "num_input_tokens_seen": 3533576,
385
+ "step": 47
386
+ },
387
+ {
388
+ "epoch": 0.7975077881619937,
389
+ "grad_norm": 0.08999717980623245,
390
+ "learning_rate": 4.980286753286195e-05,
391
+ "loss": 0.4981,
392
+ "num_input_tokens_seen": 3599744,
393
+ "step": 48
394
+ },
395
+ {
396
+ "epoch": 0.814122533748702,
397
+ "grad_norm": 0.07938859611749649,
398
+ "learning_rate": 4.979457950323945e-05,
399
+ "loss": 0.4016,
400
+ "num_input_tokens_seen": 3689520,
401
+ "step": 49
402
+ },
403
+ {
404
+ "epoch": 0.8307372793354102,
405
+ "grad_norm": 0.1045590192079544,
406
+ "learning_rate": 4.9786121534345265e-05,
407
+ "loss": 0.388,
408
+ "num_input_tokens_seen": 3751808,
409
+ "step": 50
410
+ },
411
+ {
412
+ "epoch": 0.8473520249221184,
413
+ "grad_norm": 0.07890618592500687,
414
+ "learning_rate": 4.9777493684149375e-05,
415
+ "loss": 0.3674,
416
+ "num_input_tokens_seen": 3839096,
417
+ "step": 51
418
+ },
419
+ {
420
+ "epoch": 0.8639667705088265,
421
+ "grad_norm": 0.07802557945251465,
422
+ "learning_rate": 4.976869601178609e-05,
423
+ "loss": 0.4147,
424
+ "num_input_tokens_seen": 3919824,
425
+ "step": 52
426
+ },
427
+ {
428
+ "epoch": 0.8805815160955348,
429
+ "grad_norm": 0.0913538783788681,
430
+ "learning_rate": 4.975972857755369e-05,
431
+ "loss": 0.2978,
432
+ "num_input_tokens_seen": 3989312,
433
+ "step": 53
434
+ },
435
+ {
436
+ "epoch": 0.897196261682243,
437
+ "grad_norm": 0.08525951951742172,
438
+ "learning_rate": 4.975059144291394e-05,
439
+ "loss": 0.3923,
440
+ "num_input_tokens_seen": 4060528,
441
+ "step": 54
442
+ },
443
+ {
444
+ "epoch": 0.9138110072689511,
445
+ "grad_norm": 0.08649709820747375,
446
+ "learning_rate": 4.974128467049176e-05,
447
+ "loss": 0.3282,
448
+ "num_input_tokens_seen": 4129368,
449
+ "step": 55
450
+ },
451
+ {
452
+ "epoch": 0.9304257528556594,
453
+ "grad_norm": 0.11635593324899673,
454
+ "learning_rate": 4.9731808324074717e-05,
455
+ "loss": 0.3403,
456
+ "num_input_tokens_seen": 4175208,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 0.9470404984423676,
461
+ "grad_norm": 0.1115177720785141,
462
+ "learning_rate": 4.972216246861262e-05,
463
+ "loss": 0.3191,
464
+ "num_input_tokens_seen": 4218096,
465
+ "step": 57
466
+ },
467
+ {
468
+ "epoch": 0.9636552440290758,
469
+ "grad_norm": 0.0986371859908104,
470
+ "learning_rate": 4.971234717021709e-05,
471
+ "loss": 0.3745,
472
+ "num_input_tokens_seen": 4275968,
473
+ "step": 58
474
+ },
475
+ {
476
+ "epoch": 0.980269989615784,
477
+ "grad_norm": 0.07860780507326126,
478
+ "learning_rate": 4.9702362496161085e-05,
479
+ "loss": 0.3129,
480
+ "num_input_tokens_seen": 4346616,
481
+ "step": 59
482
+ },
483
+ {
484
+ "epoch": 0.9968847352024922,
485
+ "grad_norm": 0.08581527322530746,
486
+ "learning_rate": 4.9692208514878444e-05,
487
+ "loss": 0.3324,
488
+ "num_input_tokens_seen": 4425064,
489
+ "step": 60
490
+ },
491
+ {
492
+ "epoch": 1.0,
493
+ "grad_norm": 0.16779834032058716,
494
+ "learning_rate": 4.968188529596342e-05,
495
+ "loss": 0.2814,
496
+ "num_input_tokens_seen": 4435328,
497
+ "step": 61
498
+ },
499
+ {
500
+ "epoch": 1.0166147455867083,
501
+ "grad_norm": 0.08948636800050735,
502
+ "learning_rate": 4.9671392910170185e-05,
503
+ "loss": 0.3467,
504
+ "num_input_tokens_seen": 4500104,
505
+ "step": 62
506
+ },
507
+ {
508
+ "epoch": 1.0332294911734163,
509
+ "grad_norm": 0.07826830446720123,
510
+ "learning_rate": 4.966073142941239e-05,
511
+ "loss": 0.3892,
512
+ "num_input_tokens_seen": 4581976,
513
+ "step": 63
514
+ },
515
+ {
516
+ "epoch": 1.0498442367601246,
517
+ "grad_norm": 0.08562575280666351,
518
+ "learning_rate": 4.964990092676263e-05,
519
+ "loss": 0.3354,
520
+ "num_input_tokens_seen": 4652160,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 1.066458982346833,
525
+ "grad_norm": 0.1057090312242508,
526
+ "learning_rate": 4.9638901476451946e-05,
527
+ "loss": 0.3457,
528
+ "num_input_tokens_seen": 4709368,
529
+ "step": 65
530
+ },
531
+ {
532
+ "epoch": 1.083073727933541,
533
+ "grad_norm": 0.08131146430969238,
534
+ "learning_rate": 4.962773315386935e-05,
535
+ "loss": 0.3672,
536
+ "num_input_tokens_seen": 4798256,
537
+ "step": 66
538
+ },
539
+ {
540
+ "epoch": 1.0996884735202492,
541
+ "grad_norm": 0.09464936703443527,
542
+ "learning_rate": 4.961639603556127e-05,
543
+ "loss": 0.3157,
544
+ "num_input_tokens_seen": 4859200,
545
+ "step": 67
546
+ },
547
+ {
548
+ "epoch": 1.1163032191069575,
549
+ "grad_norm": 0.0999661460518837,
550
+ "learning_rate": 4.960489019923105e-05,
551
+ "loss": 0.3968,
552
+ "num_input_tokens_seen": 4925992,
553
+ "step": 68
554
+ },
555
+ {
556
+ "epoch": 1.1329179646936656,
557
+ "grad_norm": 0.09851639717817307,
558
+ "learning_rate": 4.9593215723738404e-05,
559
+ "loss": 0.329,
560
+ "num_input_tokens_seen": 4998808,
561
+ "step": 69
562
+ },
563
+ {
564
+ "epoch": 1.1495327102803738,
565
+ "grad_norm": 0.08382592350244522,
566
+ "learning_rate": 4.958137268909887e-05,
567
+ "loss": 0.2856,
568
+ "num_input_tokens_seen": 5089672,
569
+ "step": 70
570
+ },
571
+ {
572
+ "epoch": 1.1661474558670821,
573
+ "grad_norm": 0.09073847532272339,
574
+ "learning_rate": 4.9569361176483286e-05,
575
+ "loss": 0.3512,
576
+ "num_input_tokens_seen": 5166744,
577
+ "step": 71
578
+ },
579
+ {
580
+ "epoch": 1.1827622014537902,
581
+ "grad_norm": 0.10290185362100601,
582
+ "learning_rate": 4.9557181268217227e-05,
583
+ "loss": 0.4263,
584
+ "num_input_tokens_seen": 5228264,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 1.1993769470404985,
589
+ "grad_norm": 0.07421435415744781,
590
+ "learning_rate": 4.9544833047780394e-05,
591
+ "loss": 0.3126,
592
+ "num_input_tokens_seen": 5338224,
593
+ "step": 73
594
+ },
595
+ {
596
+ "epoch": 1.2159916926272065,
597
+ "grad_norm": 0.10284842550754547,
598
+ "learning_rate": 4.9532316599806124e-05,
599
+ "loss": 0.3473,
600
+ "num_input_tokens_seen": 5399848,
601
+ "step": 74
602
+ },
603
+ {
604
+ "epoch": 1.2326064382139148,
605
+ "grad_norm": 0.10817047953605652,
606
+ "learning_rate": 4.951963201008076e-05,
607
+ "loss": 0.3275,
608
+ "num_input_tokens_seen": 5468624,
609
+ "step": 75
610
+ },
611
+ {
612
+ "epoch": 1.249221183800623,
613
+ "grad_norm": 0.09662210941314697,
614
+ "learning_rate": 4.9506779365543046e-05,
615
+ "loss": 0.3296,
616
+ "num_input_tokens_seen": 5536776,
617
+ "step": 76
618
+ },
619
+ {
620
+ "epoch": 1.2658359293873311,
621
+ "grad_norm": 0.11193853616714478,
622
+ "learning_rate": 4.949375875428357e-05,
623
+ "loss": 0.3605,
624
+ "num_input_tokens_seen": 5609296,
625
+ "step": 77
626
+ },
627
+ {
628
+ "epoch": 1.2824506749740394,
629
+ "grad_norm": 0.11866679787635803,
630
+ "learning_rate": 4.9480570265544144e-05,
631
+ "loss": 0.3133,
632
+ "num_input_tokens_seen": 5663824,
633
+ "step": 78
634
+ },
635
+ {
636
+ "epoch": 1.2990654205607477,
637
+ "grad_norm": 0.09865846484899521,
638
+ "learning_rate": 4.94672139897172e-05,
639
+ "loss": 0.3464,
640
+ "num_input_tokens_seen": 5742032,
641
+ "step": 79
642
+ },
643
+ {
644
+ "epoch": 1.3156801661474558,
645
+ "grad_norm": 0.09930054098367691,
646
+ "learning_rate": 4.9453690018345144e-05,
647
+ "loss": 0.3346,
648
+ "num_input_tokens_seen": 5816864,
649
+ "step": 80
650
+ },
651
+ {
652
+ "epoch": 1.332294911734164,
653
+ "grad_norm": 0.1085321381688118,
654
+ "learning_rate": 4.943999844411977e-05,
655
+ "loss": 0.3102,
656
+ "num_input_tokens_seen": 5881624,
657
+ "step": 81
658
+ },
659
+ {
660
+ "epoch": 1.3489096573208723,
661
+ "grad_norm": 0.08012478053569794,
662
+ "learning_rate": 4.94261393608816e-05,
663
+ "loss": 0.2853,
664
+ "num_input_tokens_seen": 5970272,
665
+ "step": 82
666
+ },
667
+ {
668
+ "epoch": 1.3655244029075804,
669
+ "grad_norm": 0.10291877388954163,
670
+ "learning_rate": 4.941211286361922e-05,
671
+ "loss": 0.3038,
672
+ "num_input_tokens_seen": 6058752,
673
+ "step": 83
674
+ },
675
+ {
676
+ "epoch": 1.3821391484942886,
677
+ "grad_norm": 0.11999356001615524,
678
+ "learning_rate": 4.939791904846869e-05,
679
+ "loss": 0.3283,
680
+ "num_input_tokens_seen": 6120064,
681
+ "step": 84
682
+ },
683
+ {
684
+ "epoch": 1.398753894080997,
685
+ "grad_norm": 0.10502559691667557,
686
+ "learning_rate": 4.938355801271282e-05,
687
+ "loss": 0.321,
688
+ "num_input_tokens_seen": 6182072,
689
+ "step": 85
690
+ },
691
+ {
692
+ "epoch": 1.415368639667705,
693
+ "grad_norm": 0.12620873749256134,
694
+ "learning_rate": 4.936902985478055e-05,
695
+ "loss": 0.3296,
696
+ "num_input_tokens_seen": 6269680,
697
+ "step": 86
698
+ },
699
+ {
700
+ "epoch": 1.4319833852544133,
701
+ "grad_norm": 0.13212910294532776,
702
+ "learning_rate": 4.935433467424624e-05,
703
+ "loss": 0.3225,
704
+ "num_input_tokens_seen": 6347424,
705
+ "step": 87
706
+ },
707
+ {
708
+ "epoch": 1.4485981308411215,
709
+ "grad_norm": 0.11600925773382187,
710
+ "learning_rate": 4.933947257182901e-05,
711
+ "loss": 0.3479,
712
+ "num_input_tokens_seen": 6412584,
713
+ "step": 88
714
+ },
715
+ {
716
+ "epoch": 1.4652128764278296,
717
+ "grad_norm": 0.11683235317468643,
718
+ "learning_rate": 4.932444364939205e-05,
719
+ "loss": 0.3322,
720
+ "num_input_tokens_seen": 6482728,
721
+ "step": 89
722
+ },
723
+ {
724
+ "epoch": 1.4818276220145379,
725
+ "grad_norm": 0.11446017026901245,
726
+ "learning_rate": 4.9309248009941914e-05,
727
+ "loss": 0.3802,
728
+ "num_input_tokens_seen": 6562104,
729
+ "step": 90
730
+ },
731
+ {
732
+ "epoch": 1.4984423676012462,
733
+ "grad_norm": 0.10500892251729965,
734
+ "learning_rate": 4.929388575762782e-05,
735
+ "loss": 0.3371,
736
+ "num_input_tokens_seen": 6656552,
737
+ "step": 91
738
+ },
739
+ {
740
+ "epoch": 1.5150571131879542,
741
+ "grad_norm": 0.13279151916503906,
742
+ "learning_rate": 4.9278356997740904e-05,
743
+ "loss": 0.293,
744
+ "num_input_tokens_seen": 6714184,
745
+ "step": 92
746
+ },
747
+ {
748
+ "epoch": 1.5316718587746625,
749
+ "grad_norm": 0.107506163418293,
750
+ "learning_rate": 4.9262661836713564e-05,
751
+ "loss": 0.3127,
752
+ "num_input_tokens_seen": 6793552,
753
+ "step": 93
754
+ },
755
+ {
756
+ "epoch": 1.5482866043613708,
757
+ "grad_norm": 0.124021977186203,
758
+ "learning_rate": 4.924680038211867e-05,
759
+ "loss": 0.3263,
760
+ "num_input_tokens_seen": 6865256,
761
+ "step": 94
762
+ },
763
+ {
764
+ "epoch": 1.5649013499480788,
765
+ "grad_norm": 0.14172782003879547,
766
+ "learning_rate": 4.9230772742668866e-05,
767
+ "loss": 0.3204,
768
+ "num_input_tokens_seen": 6931152,
769
+ "step": 95
770
+ },
771
+ {
772
+ "epoch": 1.5815160955347871,
773
+ "grad_norm": 0.12229758501052856,
774
+ "learning_rate": 4.9214579028215776e-05,
775
+ "loss": 0.326,
776
+ "num_input_tokens_seen": 6998408,
777
+ "step": 96
778
+ },
779
+ {
780
+ "epoch": 1.5981308411214954,
781
+ "grad_norm": 0.1242135688662529,
782
+ "learning_rate": 4.919821934974933e-05,
783
+ "loss": 0.2814,
784
+ "num_input_tokens_seen": 7053008,
785
+ "step": 97
786
+ },
787
+ {
788
+ "epoch": 1.6147455867082035,
789
+ "grad_norm": 0.12830108404159546,
790
+ "learning_rate": 4.918169381939692e-05,
791
+ "loss": 0.3254,
792
+ "num_input_tokens_seen": 7106440,
793
+ "step": 98
794
+ },
795
+ {
796
+ "epoch": 1.6313603322949117,
797
+ "grad_norm": 0.12180659174919128,
798
+ "learning_rate": 4.916500255042268e-05,
799
+ "loss": 0.3228,
800
+ "num_input_tokens_seen": 7167032,
801
+ "step": 99
802
+ },
803
+ {
804
+ "epoch": 1.64797507788162,
805
+ "grad_norm": 0.10792312026023865,
806
+ "learning_rate": 4.914814565722671e-05,
807
+ "loss": 0.2729,
808
+ "num_input_tokens_seen": 7245720,
809
+ "step": 100
810
+ },
811
+ {
812
+ "epoch": 1.664589823468328,
813
+ "grad_norm": 0.18523500859737396,
814
+ "learning_rate": 4.913112325534426e-05,
815
+ "loss": 0.3462,
816
+ "num_input_tokens_seen": 7326320,
817
+ "step": 101
818
+ },
819
+ {
820
+ "epoch": 1.6812045690550363,
821
+ "grad_norm": 0.09529964625835419,
822
+ "learning_rate": 4.9113935461444955e-05,
823
+ "loss": 0.3096,
824
+ "num_input_tokens_seen": 7442232,
825
+ "step": 102
826
+ },
827
+ {
828
+ "epoch": 1.6978193146417446,
829
+ "grad_norm": 0.14481183886528015,
830
+ "learning_rate": 4.9096582393332025e-05,
831
+ "loss": 0.3014,
832
+ "num_input_tokens_seen": 7502496,
833
+ "step": 103
834
+ },
835
+ {
836
+ "epoch": 1.7144340602284527,
837
+ "grad_norm": 0.14645016193389893,
838
+ "learning_rate": 4.907906416994146e-05,
839
+ "loss": 0.3336,
840
+ "num_input_tokens_seen": 7566496,
841
+ "step": 104
842
+ },
843
+ {
844
+ "epoch": 1.731048805815161,
845
+ "grad_norm": 0.1306885927915573,
846
+ "learning_rate": 4.906138091134118e-05,
847
+ "loss": 0.3911,
848
+ "num_input_tokens_seen": 7629056,
849
+ "step": 105
850
+ },
851
+ {
852
+ "epoch": 1.7476635514018692,
853
+ "grad_norm": 0.10863160341978073,
854
+ "learning_rate": 4.9043532738730284e-05,
855
+ "loss": 0.3201,
856
+ "num_input_tokens_seen": 7706096,
857
+ "step": 106
858
+ },
859
+ {
860
+ "epoch": 1.7642782969885773,
861
+ "grad_norm": 0.11725673079490662,
862
+ "learning_rate": 4.9025519774438136e-05,
863
+ "loss": 0.2783,
864
+ "num_input_tokens_seen": 7780072,
865
+ "step": 107
866
+ },
867
+ {
868
+ "epoch": 1.7808930425752856,
869
+ "grad_norm": 0.1243867501616478,
870
+ "learning_rate": 4.900734214192358e-05,
871
+ "loss": 0.3044,
872
+ "num_input_tokens_seen": 7857712,
873
+ "step": 108
874
+ },
875
+ {
876
+ "epoch": 1.7975077881619939,
877
+ "grad_norm": 0.13539955019950867,
878
+ "learning_rate": 4.898899996577407e-05,
879
+ "loss": 0.3009,
880
+ "num_input_tokens_seen": 7916832,
881
+ "step": 109
882
+ },
883
+ {
884
+ "epoch": 1.814122533748702,
885
+ "grad_norm": 0.11198178678750992,
886
+ "learning_rate": 4.8970493371704826e-05,
887
+ "loss": 0.3229,
888
+ "num_input_tokens_seen": 7993056,
889
+ "step": 110
890
+ },
891
+ {
892
+ "epoch": 1.8307372793354102,
893
+ "grad_norm": 0.11881165206432343,
894
+ "learning_rate": 4.8951822486557986e-05,
895
+ "loss": 0.3414,
896
+ "num_input_tokens_seen": 8090056,
897
+ "step": 111
898
+ },
899
+ {
900
+ "epoch": 1.8473520249221185,
901
+ "grad_norm": 0.12841404974460602,
902
+ "learning_rate": 4.893298743830168e-05,
903
+ "loss": 0.2907,
904
+ "num_input_tokens_seen": 8164808,
905
+ "step": 112
906
+ },
907
+ {
908
+ "epoch": 1.8639667705088265,
909
+ "grad_norm": 0.14767521619796753,
910
+ "learning_rate": 4.891398835602925e-05,
911
+ "loss": 0.2901,
912
+ "num_input_tokens_seen": 8223568,
913
+ "step": 113
914
+ },
915
+ {
916
+ "epoch": 1.8805815160955348,
917
+ "grad_norm": 0.15326914191246033,
918
+ "learning_rate": 4.8894825369958255e-05,
919
+ "loss": 0.2918,
920
+ "num_input_tokens_seen": 8276160,
921
+ "step": 114
922
+ },
923
+ {
924
+ "epoch": 1.897196261682243,
925
+ "grad_norm": 0.1210051029920578,
926
+ "learning_rate": 4.8875498611429674e-05,
927
+ "loss": 0.3074,
928
+ "num_input_tokens_seen": 8354904,
929
+ "step": 115
930
+ },
931
+ {
932
+ "epoch": 1.9138110072689511,
933
+ "grad_norm": 0.13544373214244843,
934
+ "learning_rate": 4.8856008212906925e-05,
935
+ "loss": 0.3461,
936
+ "num_input_tokens_seen": 8442584,
937
+ "step": 116
938
+ },
939
+ {
940
+ "epoch": 1.9304257528556594,
941
+ "grad_norm": 0.13535892963409424,
942
+ "learning_rate": 4.8836354307975026e-05,
943
+ "loss": 0.3078,
944
+ "num_input_tokens_seen": 8506688,
945
+ "step": 117
946
+ },
947
+ {
948
+ "epoch": 1.9470404984423677,
949
+ "grad_norm": 0.10383590310811996,
950
+ "learning_rate": 4.881653703133966e-05,
951
+ "loss": 0.2432,
952
+ "num_input_tokens_seen": 8610712,
953
+ "step": 118
954
+ },
955
+ {
956
+ "epoch": 1.9636552440290758,
957
+ "grad_norm": 0.12125886976718903,
958
+ "learning_rate": 4.87965565188262e-05,
959
+ "loss": 0.2915,
960
+ "num_input_tokens_seen": 8692624,
961
+ "step": 119
962
+ },
963
+ {
964
+ "epoch": 1.980269989615784,
965
+ "grad_norm": 0.1351424902677536,
966
+ "learning_rate": 4.877641290737884e-05,
967
+ "loss": 0.3006,
968
+ "num_input_tokens_seen": 8772208,
969
+ "step": 120
970
+ }
971
+ ],
972
+ "logging_steps": 1.0,
973
+ "max_steps": 1200,
974
+ "num_input_tokens_seen": 8772208,
975
+ "num_train_epochs": 20,
976
+ "save_steps": 60,
977
+ "stateful_callbacks": {
978
+ "TrainerControl": {
979
+ "args": {
980
+ "should_epoch_stop": false,
981
+ "should_evaluate": false,
982
+ "should_log": false,
983
+ "should_save": true,
984
+ "should_training_stop": false
985
+ },
986
+ "attributes": {}
987
+ }
988
+ },
989
+ "total_flos": 3.742744632748933e+17,
990
+ "train_batch_size": 1,
991
+ "trial_name": null,
992
+ "trial_params": null
993
+ }
checkpoint-120/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9746167dc82a516aeee83c5731c4b250770d2cfb0fb68a7cd590dc02bd3eb0d6
3
+ size 5688
checkpoint-120/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-180/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-Coder-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 0.12.0
checkpoint-180/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-Coder-7B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "down_proj",
24
+ "k_proj",
25
+ "v_proj",
26
+ "q_proj",
27
+ "o_proj",
28
+ "gate_proj",
29
+ "up_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-180/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4da19006dbaed50dc99f03a9e0b338c05b479a3d4d2c5bdf806717104305a99f
3
+ size 161533192
checkpoint-180/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-180/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-180/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92c6196b0c2d6d684a8397bea658132db03de809816fc510448d7934d7712f4a
3
+ size 323290986
checkpoint-180/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9e8d0c20559c89162d6b25d21ed76a3461d85ad3c424d93b9a1ae6a104cad0a
3
+ size 14512
checkpoint-180/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ee3da34bf6a485879e2d4435e55bc169240515e4202101561db89ec5a4ed16d
3
+ size 14512
checkpoint-180/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:243a9836b3d970c6c41c2092c03d3e8d49dfad7f975032e627f0fd298aca20f9
3
+ size 1064
checkpoint-180/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-180/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
checkpoint-180/tokenizer_config.json ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 17000,
204
+ "pad_token": "<|endoftext|>",
205
+ "padding_side": "right",
206
+ "split_special_tokens": false,
207
+ "tokenizer_class": "Qwen2Tokenizer",
208
+ "unk_token": null
209
+ }
checkpoint-180/trainer_state.json ADDED
@@ -0,0 +1,1473 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9636552440290758,
5
+ "eval_steps": 500,
6
+ "global_step": 180,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.016614745586708203,
13
+ "grad_norm": 0.061364494264125824,
14
+ "learning_rate": 4.999991432639962e-05,
15
+ "loss": 0.5857,
16
+ "num_input_tokens_seen": 70408,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.033229491173416406,
21
+ "grad_norm": 0.0613991804420948,
22
+ "learning_rate": 4.999965730618567e-05,
23
+ "loss": 0.5331,
24
+ "num_input_tokens_seen": 139640,
25
+ "step": 2
26
+ },
27
+ {
28
+ "epoch": 0.04984423676012461,
29
+ "grad_norm": 0.06351307034492493,
30
+ "learning_rate": 4.9999228941119745e-05,
31
+ "loss": 0.5852,
32
+ "num_input_tokens_seen": 223656,
33
+ "step": 3
34
+ },
35
+ {
36
+ "epoch": 0.06645898234683281,
37
+ "grad_norm": 0.05762802064418793,
38
+ "learning_rate": 4.999862923413781e-05,
39
+ "loss": 0.5384,
40
+ "num_input_tokens_seen": 300688,
41
+ "step": 4
42
+ },
43
+ {
44
+ "epoch": 0.08307372793354102,
45
+ "grad_norm": 0.0632179006934166,
46
+ "learning_rate": 4.999785818935018e-05,
47
+ "loss": 0.5273,
48
+ "num_input_tokens_seen": 366368,
49
+ "step": 5
50
+ },
51
+ {
52
+ "epoch": 0.09968847352024922,
53
+ "grad_norm": 0.056689903140068054,
54
+ "learning_rate": 4.999691581204152e-05,
55
+ "loss": 0.5145,
56
+ "num_input_tokens_seen": 445808,
57
+ "step": 6
58
+ },
59
+ {
60
+ "epoch": 0.11630321910695743,
61
+ "grad_norm": 0.06574171781539917,
62
+ "learning_rate": 4.9995802108670775e-05,
63
+ "loss": 0.5301,
64
+ "num_input_tokens_seen": 522800,
65
+ "step": 7
66
+ },
67
+ {
68
+ "epoch": 0.13291796469366562,
69
+ "grad_norm": 0.06367070972919464,
70
+ "learning_rate": 4.999451708687114e-05,
71
+ "loss": 0.5552,
72
+ "num_input_tokens_seen": 599608,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.14953271028037382,
77
+ "grad_norm": 0.0585966520011425,
78
+ "learning_rate": 4.9993060755450015e-05,
79
+ "loss": 0.5999,
80
+ "num_input_tokens_seen": 681424,
81
+ "step": 9
82
+ },
83
+ {
84
+ "epoch": 0.16614745586708204,
85
+ "grad_norm": 0.05650574713945389,
86
+ "learning_rate": 4.999143312438893e-05,
87
+ "loss": 0.4535,
88
+ "num_input_tokens_seen": 756744,
89
+ "step": 10
90
+ },
91
+ {
92
+ "epoch": 0.18276220145379024,
93
+ "grad_norm": 0.05954223498702049,
94
+ "learning_rate": 4.998963420484349e-05,
95
+ "loss": 0.4674,
96
+ "num_input_tokens_seen": 842576,
97
+ "step": 11
98
+ },
99
+ {
100
+ "epoch": 0.19937694704049844,
101
+ "grad_norm": 0.0663776770234108,
102
+ "learning_rate": 4.998766400914329e-05,
103
+ "loss": 0.4703,
104
+ "num_input_tokens_seen": 917232,
105
+ "step": 12
106
+ },
107
+ {
108
+ "epoch": 0.21599169262720663,
109
+ "grad_norm": 0.056374579668045044,
110
+ "learning_rate": 4.9985522550791825e-05,
111
+ "loss": 0.3725,
112
+ "num_input_tokens_seen": 1006800,
113
+ "step": 13
114
+ },
115
+ {
116
+ "epoch": 0.23260643821391486,
117
+ "grad_norm": 0.06437493115663528,
118
+ "learning_rate": 4.998320984446641e-05,
119
+ "loss": 0.4653,
120
+ "num_input_tokens_seen": 1085824,
121
+ "step": 14
122
+ },
123
+ {
124
+ "epoch": 0.24922118380062305,
125
+ "grad_norm": 0.06560757756233215,
126
+ "learning_rate": 4.9980725906018074e-05,
127
+ "loss": 0.5026,
128
+ "num_input_tokens_seen": 1164160,
129
+ "step": 15
130
+ },
131
+ {
132
+ "epoch": 0.26583592938733125,
133
+ "grad_norm": 0.06942517310380936,
134
+ "learning_rate": 4.997807075247146e-05,
135
+ "loss": 0.5401,
136
+ "num_input_tokens_seen": 1242264,
137
+ "step": 16
138
+ },
139
+ {
140
+ "epoch": 0.2824506749740395,
141
+ "grad_norm": 0.06349828094244003,
142
+ "learning_rate": 4.997524440202469e-05,
143
+ "loss": 0.4713,
144
+ "num_input_tokens_seen": 1325904,
145
+ "step": 17
146
+ },
147
+ {
148
+ "epoch": 0.29906542056074764,
149
+ "grad_norm": 0.08846385776996613,
150
+ "learning_rate": 4.9972246874049254e-05,
151
+ "loss": 0.5834,
152
+ "num_input_tokens_seen": 1385632,
153
+ "step": 18
154
+ },
155
+ {
156
+ "epoch": 0.31568016614745587,
157
+ "grad_norm": 0.062130190432071686,
158
+ "learning_rate": 4.996907818908987e-05,
159
+ "loss": 0.4045,
160
+ "num_input_tokens_seen": 1470632,
161
+ "step": 19
162
+ },
163
+ {
164
+ "epoch": 0.3322949117341641,
165
+ "grad_norm": 0.07743565738201141,
166
+ "learning_rate": 4.996573836886435e-05,
167
+ "loss": 0.5283,
168
+ "num_input_tokens_seen": 1547536,
169
+ "step": 20
170
+ },
171
+ {
172
+ "epoch": 0.34890965732087226,
173
+ "grad_norm": 0.06756695359945297,
174
+ "learning_rate": 4.9962227436263453e-05,
175
+ "loss": 0.4199,
176
+ "num_input_tokens_seen": 1615528,
177
+ "step": 21
178
+ },
179
+ {
180
+ "epoch": 0.3655244029075805,
181
+ "grad_norm": 0.08662309497594833,
182
+ "learning_rate": 4.995854541535071e-05,
183
+ "loss": 0.4775,
184
+ "num_input_tokens_seen": 1694352,
185
+ "step": 22
186
+ },
187
+ {
188
+ "epoch": 0.3821391484942887,
189
+ "grad_norm": 0.08380820602178574,
190
+ "learning_rate": 4.9954692331362294e-05,
191
+ "loss": 0.4871,
192
+ "num_input_tokens_seen": 1753776,
193
+ "step": 23
194
+ },
195
+ {
196
+ "epoch": 0.3987538940809969,
197
+ "grad_norm": 0.09967435896396637,
198
+ "learning_rate": 4.995066821070679e-05,
199
+ "loss": 0.4871,
200
+ "num_input_tokens_seen": 1809048,
201
+ "step": 24
202
+ },
203
+ {
204
+ "epoch": 0.4153686396677051,
205
+ "grad_norm": 0.0871267095208168,
206
+ "learning_rate": 4.994647308096509e-05,
207
+ "loss": 0.5461,
208
+ "num_input_tokens_seen": 1884264,
209
+ "step": 25
210
+ },
211
+ {
212
+ "epoch": 0.43198338525441327,
213
+ "grad_norm": 0.065020851790905,
214
+ "learning_rate": 4.994210697089014e-05,
215
+ "loss": 0.405,
216
+ "num_input_tokens_seen": 1981704,
217
+ "step": 26
218
+ },
219
+ {
220
+ "epoch": 0.4485981308411215,
221
+ "grad_norm": 0.09853450953960419,
222
+ "learning_rate": 4.9937569910406756e-05,
223
+ "loss": 0.4487,
224
+ "num_input_tokens_seen": 2044144,
225
+ "step": 27
226
+ },
227
+ {
228
+ "epoch": 0.4652128764278297,
229
+ "grad_norm": 0.08763110637664795,
230
+ "learning_rate": 4.9932861930611454e-05,
231
+ "loss": 0.3946,
232
+ "num_input_tokens_seen": 2107584,
233
+ "step": 28
234
+ },
235
+ {
236
+ "epoch": 0.4818276220145379,
237
+ "grad_norm": 0.08950547873973846,
238
+ "learning_rate": 4.9927983063772196e-05,
239
+ "loss": 0.4257,
240
+ "num_input_tokens_seen": 2169248,
241
+ "step": 29
242
+ },
243
+ {
244
+ "epoch": 0.4984423676012461,
245
+ "grad_norm": 0.09980211406946182,
246
+ "learning_rate": 4.99229333433282e-05,
247
+ "loss": 0.3911,
248
+ "num_input_tokens_seen": 2230344,
249
+ "step": 30
250
+ },
251
+ {
252
+ "epoch": 0.5150571131879543,
253
+ "grad_norm": 0.092055544257164,
254
+ "learning_rate": 4.9917712803889674e-05,
255
+ "loss": 0.3749,
256
+ "num_input_tokens_seen": 2302368,
257
+ "step": 31
258
+ },
259
+ {
260
+ "epoch": 0.5316718587746625,
261
+ "grad_norm": 0.10067818313837051,
262
+ "learning_rate": 4.991232148123761e-05,
263
+ "loss": 0.4761,
264
+ "num_input_tokens_seen": 2369984,
265
+ "step": 32
266
+ },
267
+ {
268
+ "epoch": 0.5482866043613707,
269
+ "grad_norm": 0.0717971920967102,
270
+ "learning_rate": 4.990675941232353e-05,
271
+ "loss": 0.4328,
272
+ "num_input_tokens_seen": 2453032,
273
+ "step": 33
274
+ },
275
+ {
276
+ "epoch": 0.564901349948079,
277
+ "grad_norm": 0.07436250895261765,
278
+ "learning_rate": 4.990102663526924e-05,
279
+ "loss": 0.417,
280
+ "num_input_tokens_seen": 2527464,
281
+ "step": 34
282
+ },
283
+ {
284
+ "epoch": 0.5815160955347871,
285
+ "grad_norm": 0.09256689995527267,
286
+ "learning_rate": 4.989512318936655e-05,
287
+ "loss": 0.4097,
288
+ "num_input_tokens_seen": 2597032,
289
+ "step": 35
290
+ },
291
+ {
292
+ "epoch": 0.5981308411214953,
293
+ "grad_norm": 0.09964177012443542,
294
+ "learning_rate": 4.9889049115077005e-05,
295
+ "loss": 0.4065,
296
+ "num_input_tokens_seen": 2671704,
297
+ "step": 36
298
+ },
299
+ {
300
+ "epoch": 0.6147455867082036,
301
+ "grad_norm": 0.06627887487411499,
302
+ "learning_rate": 4.988280445403164e-05,
303
+ "loss": 0.4136,
304
+ "num_input_tokens_seen": 2767640,
305
+ "step": 37
306
+ },
307
+ {
308
+ "epoch": 0.6313603322949117,
309
+ "grad_norm": 0.0746045857667923,
310
+ "learning_rate": 4.987638924903067e-05,
311
+ "loss": 0.4125,
312
+ "num_input_tokens_seen": 2843720,
313
+ "step": 38
314
+ },
315
+ {
316
+ "epoch": 0.6479750778816199,
317
+ "grad_norm": 0.0795741006731987,
318
+ "learning_rate": 4.9869803544043166e-05,
319
+ "loss": 0.3135,
320
+ "num_input_tokens_seen": 2921472,
321
+ "step": 39
322
+ },
323
+ {
324
+ "epoch": 0.6645898234683282,
325
+ "grad_norm": 0.08914181590080261,
326
+ "learning_rate": 4.9863047384206835e-05,
327
+ "loss": 0.4549,
328
+ "num_input_tokens_seen": 2998400,
329
+ "step": 40
330
+ },
331
+ {
332
+ "epoch": 0.6812045690550363,
333
+ "grad_norm": 0.11220043897628784,
334
+ "learning_rate": 4.985612081582764e-05,
335
+ "loss": 0.4135,
336
+ "num_input_tokens_seen": 3059648,
337
+ "step": 41
338
+ },
339
+ {
340
+ "epoch": 0.6978193146417445,
341
+ "grad_norm": 0.08390027284622192,
342
+ "learning_rate": 4.98490238863795e-05,
343
+ "loss": 0.3538,
344
+ "num_input_tokens_seen": 3140184,
345
+ "step": 42
346
+ },
347
+ {
348
+ "epoch": 0.7144340602284528,
349
+ "grad_norm": 0.08858532458543777,
350
+ "learning_rate": 4.984175664450397e-05,
351
+ "loss": 0.3644,
352
+ "num_input_tokens_seen": 3207184,
353
+ "step": 43
354
+ },
355
+ {
356
+ "epoch": 0.731048805815161,
357
+ "grad_norm": 0.07439564168453217,
358
+ "learning_rate": 4.983431914000991e-05,
359
+ "loss": 0.4019,
360
+ "num_input_tokens_seen": 3292344,
361
+ "step": 44
362
+ },
363
+ {
364
+ "epoch": 0.7476635514018691,
365
+ "grad_norm": 0.08694300055503845,
366
+ "learning_rate": 4.982671142387316e-05,
367
+ "loss": 0.4238,
368
+ "num_input_tokens_seen": 3365384,
369
+ "step": 45
370
+ },
371
+ {
372
+ "epoch": 0.7642782969885774,
373
+ "grad_norm": 0.0867784395813942,
374
+ "learning_rate": 4.981893354823614e-05,
375
+ "loss": 0.3702,
376
+ "num_input_tokens_seen": 3440720,
377
+ "step": 46
378
+ },
379
+ {
380
+ "epoch": 0.7808930425752856,
381
+ "grad_norm": 0.06278439611196518,
382
+ "learning_rate": 4.9810985566407544e-05,
383
+ "loss": 0.3354,
384
+ "num_input_tokens_seen": 3533576,
385
+ "step": 47
386
+ },
387
+ {
388
+ "epoch": 0.7975077881619937,
389
+ "grad_norm": 0.08999717980623245,
390
+ "learning_rate": 4.980286753286195e-05,
391
+ "loss": 0.4981,
392
+ "num_input_tokens_seen": 3599744,
393
+ "step": 48
394
+ },
395
+ {
396
+ "epoch": 0.814122533748702,
397
+ "grad_norm": 0.07938859611749649,
398
+ "learning_rate": 4.979457950323945e-05,
399
+ "loss": 0.4016,
400
+ "num_input_tokens_seen": 3689520,
401
+ "step": 49
402
+ },
403
+ {
404
+ "epoch": 0.8307372793354102,
405
+ "grad_norm": 0.1045590192079544,
406
+ "learning_rate": 4.9786121534345265e-05,
407
+ "loss": 0.388,
408
+ "num_input_tokens_seen": 3751808,
409
+ "step": 50
410
+ },
411
+ {
412
+ "epoch": 0.8473520249221184,
413
+ "grad_norm": 0.07890618592500687,
414
+ "learning_rate": 4.9777493684149375e-05,
415
+ "loss": 0.3674,
416
+ "num_input_tokens_seen": 3839096,
417
+ "step": 51
418
+ },
419
+ {
420
+ "epoch": 0.8639667705088265,
421
+ "grad_norm": 0.07802557945251465,
422
+ "learning_rate": 4.976869601178609e-05,
423
+ "loss": 0.4147,
424
+ "num_input_tokens_seen": 3919824,
425
+ "step": 52
426
+ },
427
+ {
428
+ "epoch": 0.8805815160955348,
429
+ "grad_norm": 0.0913538783788681,
430
+ "learning_rate": 4.975972857755369e-05,
431
+ "loss": 0.2978,
432
+ "num_input_tokens_seen": 3989312,
433
+ "step": 53
434
+ },
435
+ {
436
+ "epoch": 0.897196261682243,
437
+ "grad_norm": 0.08525951951742172,
438
+ "learning_rate": 4.975059144291394e-05,
439
+ "loss": 0.3923,
440
+ "num_input_tokens_seen": 4060528,
441
+ "step": 54
442
+ },
443
+ {
444
+ "epoch": 0.9138110072689511,
445
+ "grad_norm": 0.08649709820747375,
446
+ "learning_rate": 4.974128467049176e-05,
447
+ "loss": 0.3282,
448
+ "num_input_tokens_seen": 4129368,
449
+ "step": 55
450
+ },
451
+ {
452
+ "epoch": 0.9304257528556594,
453
+ "grad_norm": 0.11635593324899673,
454
+ "learning_rate": 4.9731808324074717e-05,
455
+ "loss": 0.3403,
456
+ "num_input_tokens_seen": 4175208,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 0.9470404984423676,
461
+ "grad_norm": 0.1115177720785141,
462
+ "learning_rate": 4.972216246861262e-05,
463
+ "loss": 0.3191,
464
+ "num_input_tokens_seen": 4218096,
465
+ "step": 57
466
+ },
467
+ {
468
+ "epoch": 0.9636552440290758,
469
+ "grad_norm": 0.0986371859908104,
470
+ "learning_rate": 4.971234717021709e-05,
471
+ "loss": 0.3745,
472
+ "num_input_tokens_seen": 4275968,
473
+ "step": 58
474
+ },
475
+ {
476
+ "epoch": 0.980269989615784,
477
+ "grad_norm": 0.07860780507326126,
478
+ "learning_rate": 4.9702362496161085e-05,
479
+ "loss": 0.3129,
480
+ "num_input_tokens_seen": 4346616,
481
+ "step": 59
482
+ },
483
+ {
484
+ "epoch": 0.9968847352024922,
485
+ "grad_norm": 0.08581527322530746,
486
+ "learning_rate": 4.9692208514878444e-05,
487
+ "loss": 0.3324,
488
+ "num_input_tokens_seen": 4425064,
489
+ "step": 60
490
+ },
491
+ {
492
+ "epoch": 1.0,
493
+ "grad_norm": 0.16779834032058716,
494
+ "learning_rate": 4.968188529596342e-05,
495
+ "loss": 0.2814,
496
+ "num_input_tokens_seen": 4435328,
497
+ "step": 61
498
+ },
499
+ {
500
+ "epoch": 1.0166147455867083,
501
+ "grad_norm": 0.08948636800050735,
502
+ "learning_rate": 4.9671392910170185e-05,
503
+ "loss": 0.3467,
504
+ "num_input_tokens_seen": 4500104,
505
+ "step": 62
506
+ },
507
+ {
508
+ "epoch": 1.0332294911734163,
509
+ "grad_norm": 0.07826830446720123,
510
+ "learning_rate": 4.966073142941239e-05,
511
+ "loss": 0.3892,
512
+ "num_input_tokens_seen": 4581976,
513
+ "step": 63
514
+ },
515
+ {
516
+ "epoch": 1.0498442367601246,
517
+ "grad_norm": 0.08562575280666351,
518
+ "learning_rate": 4.964990092676263e-05,
519
+ "loss": 0.3354,
520
+ "num_input_tokens_seen": 4652160,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 1.066458982346833,
525
+ "grad_norm": 0.1057090312242508,
526
+ "learning_rate": 4.9638901476451946e-05,
527
+ "loss": 0.3457,
528
+ "num_input_tokens_seen": 4709368,
529
+ "step": 65
530
+ },
531
+ {
532
+ "epoch": 1.083073727933541,
533
+ "grad_norm": 0.08131146430969238,
534
+ "learning_rate": 4.962773315386935e-05,
535
+ "loss": 0.3672,
536
+ "num_input_tokens_seen": 4798256,
537
+ "step": 66
538
+ },
539
+ {
540
+ "epoch": 1.0996884735202492,
541
+ "grad_norm": 0.09464936703443527,
542
+ "learning_rate": 4.961639603556127e-05,
543
+ "loss": 0.3157,
544
+ "num_input_tokens_seen": 4859200,
545
+ "step": 67
546
+ },
547
+ {
548
+ "epoch": 1.1163032191069575,
549
+ "grad_norm": 0.0999661460518837,
550
+ "learning_rate": 4.960489019923105e-05,
551
+ "loss": 0.3968,
552
+ "num_input_tokens_seen": 4925992,
553
+ "step": 68
554
+ },
555
+ {
556
+ "epoch": 1.1329179646936656,
557
+ "grad_norm": 0.09851639717817307,
558
+ "learning_rate": 4.9593215723738404e-05,
559
+ "loss": 0.329,
560
+ "num_input_tokens_seen": 4998808,
561
+ "step": 69
562
+ },
563
+ {
564
+ "epoch": 1.1495327102803738,
565
+ "grad_norm": 0.08382592350244522,
566
+ "learning_rate": 4.958137268909887e-05,
567
+ "loss": 0.2856,
568
+ "num_input_tokens_seen": 5089672,
569
+ "step": 70
570
+ },
571
+ {
572
+ "epoch": 1.1661474558670821,
573
+ "grad_norm": 0.09073847532272339,
574
+ "learning_rate": 4.9569361176483286e-05,
575
+ "loss": 0.3512,
576
+ "num_input_tokens_seen": 5166744,
577
+ "step": 71
578
+ },
579
+ {
580
+ "epoch": 1.1827622014537902,
581
+ "grad_norm": 0.10290185362100601,
582
+ "learning_rate": 4.9557181268217227e-05,
583
+ "loss": 0.4263,
584
+ "num_input_tokens_seen": 5228264,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 1.1993769470404985,
589
+ "grad_norm": 0.07421435415744781,
590
+ "learning_rate": 4.9544833047780394e-05,
591
+ "loss": 0.3126,
592
+ "num_input_tokens_seen": 5338224,
593
+ "step": 73
594
+ },
595
+ {
596
+ "epoch": 1.2159916926272065,
597
+ "grad_norm": 0.10284842550754547,
598
+ "learning_rate": 4.9532316599806124e-05,
599
+ "loss": 0.3473,
600
+ "num_input_tokens_seen": 5399848,
601
+ "step": 74
602
+ },
603
+ {
604
+ "epoch": 1.2326064382139148,
605
+ "grad_norm": 0.10817047953605652,
606
+ "learning_rate": 4.951963201008076e-05,
607
+ "loss": 0.3275,
608
+ "num_input_tokens_seen": 5468624,
609
+ "step": 75
610
+ },
611
+ {
612
+ "epoch": 1.249221183800623,
613
+ "grad_norm": 0.09662210941314697,
614
+ "learning_rate": 4.9506779365543046e-05,
615
+ "loss": 0.3296,
616
+ "num_input_tokens_seen": 5536776,
617
+ "step": 76
618
+ },
619
+ {
620
+ "epoch": 1.2658359293873311,
621
+ "grad_norm": 0.11193853616714478,
622
+ "learning_rate": 4.949375875428357e-05,
623
+ "loss": 0.3605,
624
+ "num_input_tokens_seen": 5609296,
625
+ "step": 77
626
+ },
627
+ {
628
+ "epoch": 1.2824506749740394,
629
+ "grad_norm": 0.11866679787635803,
630
+ "learning_rate": 4.9480570265544144e-05,
631
+ "loss": 0.3133,
632
+ "num_input_tokens_seen": 5663824,
633
+ "step": 78
634
+ },
635
+ {
636
+ "epoch": 1.2990654205607477,
637
+ "grad_norm": 0.09865846484899521,
638
+ "learning_rate": 4.94672139897172e-05,
639
+ "loss": 0.3464,
640
+ "num_input_tokens_seen": 5742032,
641
+ "step": 79
642
+ },
643
+ {
644
+ "epoch": 1.3156801661474558,
645
+ "grad_norm": 0.09930054098367691,
646
+ "learning_rate": 4.9453690018345144e-05,
647
+ "loss": 0.3346,
648
+ "num_input_tokens_seen": 5816864,
649
+ "step": 80
650
+ },
651
+ {
652
+ "epoch": 1.332294911734164,
653
+ "grad_norm": 0.1085321381688118,
654
+ "learning_rate": 4.943999844411977e-05,
655
+ "loss": 0.3102,
656
+ "num_input_tokens_seen": 5881624,
657
+ "step": 81
658
+ },
659
+ {
660
+ "epoch": 1.3489096573208723,
661
+ "grad_norm": 0.08012478053569794,
662
+ "learning_rate": 4.94261393608816e-05,
663
+ "loss": 0.2853,
664
+ "num_input_tokens_seen": 5970272,
665
+ "step": 82
666
+ },
667
+ {
668
+ "epoch": 1.3655244029075804,
669
+ "grad_norm": 0.10291877388954163,
670
+ "learning_rate": 4.941211286361922e-05,
671
+ "loss": 0.3038,
672
+ "num_input_tokens_seen": 6058752,
673
+ "step": 83
674
+ },
675
+ {
676
+ "epoch": 1.3821391484942886,
677
+ "grad_norm": 0.11999356001615524,
678
+ "learning_rate": 4.939791904846869e-05,
679
+ "loss": 0.3283,
680
+ "num_input_tokens_seen": 6120064,
681
+ "step": 84
682
+ },
683
+ {
684
+ "epoch": 1.398753894080997,
685
+ "grad_norm": 0.10502559691667557,
686
+ "learning_rate": 4.938355801271282e-05,
687
+ "loss": 0.321,
688
+ "num_input_tokens_seen": 6182072,
689
+ "step": 85
690
+ },
691
+ {
692
+ "epoch": 1.415368639667705,
693
+ "grad_norm": 0.12620873749256134,
694
+ "learning_rate": 4.936902985478055e-05,
695
+ "loss": 0.3296,
696
+ "num_input_tokens_seen": 6269680,
697
+ "step": 86
698
+ },
699
+ {
700
+ "epoch": 1.4319833852544133,
701
+ "grad_norm": 0.13212910294532776,
702
+ "learning_rate": 4.935433467424624e-05,
703
+ "loss": 0.3225,
704
+ "num_input_tokens_seen": 6347424,
705
+ "step": 87
706
+ },
707
+ {
708
+ "epoch": 1.4485981308411215,
709
+ "grad_norm": 0.11600925773382187,
710
+ "learning_rate": 4.933947257182901e-05,
711
+ "loss": 0.3479,
712
+ "num_input_tokens_seen": 6412584,
713
+ "step": 88
714
+ },
715
+ {
716
+ "epoch": 1.4652128764278296,
717
+ "grad_norm": 0.11683235317468643,
718
+ "learning_rate": 4.932444364939205e-05,
719
+ "loss": 0.3322,
720
+ "num_input_tokens_seen": 6482728,
721
+ "step": 89
722
+ },
723
+ {
724
+ "epoch": 1.4818276220145379,
725
+ "grad_norm": 0.11446017026901245,
726
+ "learning_rate": 4.9309248009941914e-05,
727
+ "loss": 0.3802,
728
+ "num_input_tokens_seen": 6562104,
729
+ "step": 90
730
+ },
731
+ {
732
+ "epoch": 1.4984423676012462,
733
+ "grad_norm": 0.10500892251729965,
734
+ "learning_rate": 4.929388575762782e-05,
735
+ "loss": 0.3371,
736
+ "num_input_tokens_seen": 6656552,
737
+ "step": 91
738
+ },
739
+ {
740
+ "epoch": 1.5150571131879542,
741
+ "grad_norm": 0.13279151916503906,
742
+ "learning_rate": 4.9278356997740904e-05,
743
+ "loss": 0.293,
744
+ "num_input_tokens_seen": 6714184,
745
+ "step": 92
746
+ },
747
+ {
748
+ "epoch": 1.5316718587746625,
749
+ "grad_norm": 0.107506163418293,
750
+ "learning_rate": 4.9262661836713564e-05,
751
+ "loss": 0.3127,
752
+ "num_input_tokens_seen": 6793552,
753
+ "step": 93
754
+ },
755
+ {
756
+ "epoch": 1.5482866043613708,
757
+ "grad_norm": 0.124021977186203,
758
+ "learning_rate": 4.924680038211867e-05,
759
+ "loss": 0.3263,
760
+ "num_input_tokens_seen": 6865256,
761
+ "step": 94
762
+ },
763
+ {
764
+ "epoch": 1.5649013499480788,
765
+ "grad_norm": 0.14172782003879547,
766
+ "learning_rate": 4.9230772742668866e-05,
767
+ "loss": 0.3204,
768
+ "num_input_tokens_seen": 6931152,
769
+ "step": 95
770
+ },
771
+ {
772
+ "epoch": 1.5815160955347871,
773
+ "grad_norm": 0.12229758501052856,
774
+ "learning_rate": 4.9214579028215776e-05,
775
+ "loss": 0.326,
776
+ "num_input_tokens_seen": 6998408,
777
+ "step": 96
778
+ },
779
+ {
780
+ "epoch": 1.5981308411214954,
781
+ "grad_norm": 0.1242135688662529,
782
+ "learning_rate": 4.919821934974933e-05,
783
+ "loss": 0.2814,
784
+ "num_input_tokens_seen": 7053008,
785
+ "step": 97
786
+ },
787
+ {
788
+ "epoch": 1.6147455867082035,
789
+ "grad_norm": 0.12830108404159546,
790
+ "learning_rate": 4.918169381939692e-05,
791
+ "loss": 0.3254,
792
+ "num_input_tokens_seen": 7106440,
793
+ "step": 98
794
+ },
795
+ {
796
+ "epoch": 1.6313603322949117,
797
+ "grad_norm": 0.12180659174919128,
798
+ "learning_rate": 4.916500255042268e-05,
799
+ "loss": 0.3228,
800
+ "num_input_tokens_seen": 7167032,
801
+ "step": 99
802
+ },
803
+ {
804
+ "epoch": 1.64797507788162,
805
+ "grad_norm": 0.10792312026023865,
806
+ "learning_rate": 4.914814565722671e-05,
807
+ "loss": 0.2729,
808
+ "num_input_tokens_seen": 7245720,
809
+ "step": 100
810
+ },
811
+ {
812
+ "epoch": 1.664589823468328,
813
+ "grad_norm": 0.18523500859737396,
814
+ "learning_rate": 4.913112325534426e-05,
815
+ "loss": 0.3462,
816
+ "num_input_tokens_seen": 7326320,
817
+ "step": 101
818
+ },
819
+ {
820
+ "epoch": 1.6812045690550363,
821
+ "grad_norm": 0.09529964625835419,
822
+ "learning_rate": 4.9113935461444955e-05,
823
+ "loss": 0.3096,
824
+ "num_input_tokens_seen": 7442232,
825
+ "step": 102
826
+ },
827
+ {
828
+ "epoch": 1.6978193146417446,
829
+ "grad_norm": 0.14481183886528015,
830
+ "learning_rate": 4.9096582393332025e-05,
831
+ "loss": 0.3014,
832
+ "num_input_tokens_seen": 7502496,
833
+ "step": 103
834
+ },
835
+ {
836
+ "epoch": 1.7144340602284527,
837
+ "grad_norm": 0.14645016193389893,
838
+ "learning_rate": 4.907906416994146e-05,
839
+ "loss": 0.3336,
840
+ "num_input_tokens_seen": 7566496,
841
+ "step": 104
842
+ },
843
+ {
844
+ "epoch": 1.731048805815161,
845
+ "grad_norm": 0.1306885927915573,
846
+ "learning_rate": 4.906138091134118e-05,
847
+ "loss": 0.3911,
848
+ "num_input_tokens_seen": 7629056,
849
+ "step": 105
850
+ },
851
+ {
852
+ "epoch": 1.7476635514018692,
853
+ "grad_norm": 0.10863160341978073,
854
+ "learning_rate": 4.9043532738730284e-05,
855
+ "loss": 0.3201,
856
+ "num_input_tokens_seen": 7706096,
857
+ "step": 106
858
+ },
859
+ {
860
+ "epoch": 1.7642782969885773,
861
+ "grad_norm": 0.11725673079490662,
862
+ "learning_rate": 4.9025519774438136e-05,
863
+ "loss": 0.2783,
864
+ "num_input_tokens_seen": 7780072,
865
+ "step": 107
866
+ },
867
+ {
868
+ "epoch": 1.7808930425752856,
869
+ "grad_norm": 0.1243867501616478,
870
+ "learning_rate": 4.900734214192358e-05,
871
+ "loss": 0.3044,
872
+ "num_input_tokens_seen": 7857712,
873
+ "step": 108
874
+ },
875
+ {
876
+ "epoch": 1.7975077881619939,
877
+ "grad_norm": 0.13539955019950867,
878
+ "learning_rate": 4.898899996577407e-05,
879
+ "loss": 0.3009,
880
+ "num_input_tokens_seen": 7916832,
881
+ "step": 109
882
+ },
883
+ {
884
+ "epoch": 1.814122533748702,
885
+ "grad_norm": 0.11198178678750992,
886
+ "learning_rate": 4.8970493371704826e-05,
887
+ "loss": 0.3229,
888
+ "num_input_tokens_seen": 7993056,
889
+ "step": 110
890
+ },
891
+ {
892
+ "epoch": 1.8307372793354102,
893
+ "grad_norm": 0.11881165206432343,
894
+ "learning_rate": 4.8951822486557986e-05,
895
+ "loss": 0.3414,
896
+ "num_input_tokens_seen": 8090056,
897
+ "step": 111
898
+ },
899
+ {
900
+ "epoch": 1.8473520249221185,
901
+ "grad_norm": 0.12841404974460602,
902
+ "learning_rate": 4.893298743830168e-05,
903
+ "loss": 0.2907,
904
+ "num_input_tokens_seen": 8164808,
905
+ "step": 112
906
+ },
907
+ {
908
+ "epoch": 1.8639667705088265,
909
+ "grad_norm": 0.14767521619796753,
910
+ "learning_rate": 4.891398835602925e-05,
911
+ "loss": 0.2901,
912
+ "num_input_tokens_seen": 8223568,
913
+ "step": 113
914
+ },
915
+ {
916
+ "epoch": 1.8805815160955348,
917
+ "grad_norm": 0.15326914191246033,
918
+ "learning_rate": 4.8894825369958255e-05,
919
+ "loss": 0.2918,
920
+ "num_input_tokens_seen": 8276160,
921
+ "step": 114
922
+ },
923
+ {
924
+ "epoch": 1.897196261682243,
925
+ "grad_norm": 0.1210051029920578,
926
+ "learning_rate": 4.8875498611429674e-05,
927
+ "loss": 0.3074,
928
+ "num_input_tokens_seen": 8354904,
929
+ "step": 115
930
+ },
931
+ {
932
+ "epoch": 1.9138110072689511,
933
+ "grad_norm": 0.13544373214244843,
934
+ "learning_rate": 4.8856008212906925e-05,
935
+ "loss": 0.3461,
936
+ "num_input_tokens_seen": 8442584,
937
+ "step": 116
938
+ },
939
+ {
940
+ "epoch": 1.9304257528556594,
941
+ "grad_norm": 0.13535892963409424,
942
+ "learning_rate": 4.8836354307975026e-05,
943
+ "loss": 0.3078,
944
+ "num_input_tokens_seen": 8506688,
945
+ "step": 117
946
+ },
947
+ {
948
+ "epoch": 1.9470404984423677,
949
+ "grad_norm": 0.10383590310811996,
950
+ "learning_rate": 4.881653703133966e-05,
951
+ "loss": 0.2432,
952
+ "num_input_tokens_seen": 8610712,
953
+ "step": 118
954
+ },
955
+ {
956
+ "epoch": 1.9636552440290758,
957
+ "grad_norm": 0.12125886976718903,
958
+ "learning_rate": 4.87965565188262e-05,
959
+ "loss": 0.2915,
960
+ "num_input_tokens_seen": 8692624,
961
+ "step": 119
962
+ },
963
+ {
964
+ "epoch": 1.980269989615784,
965
+ "grad_norm": 0.1351424902677536,
966
+ "learning_rate": 4.877641290737884e-05,
967
+ "loss": 0.3006,
968
+ "num_input_tokens_seen": 8772208,
969
+ "step": 120
970
+ },
971
+ {
972
+ "epoch": 1.9968847352024923,
973
+ "grad_norm": 0.11472523212432861,
974
+ "learning_rate": 4.8756106335059646e-05,
975
+ "loss": 0.2774,
976
+ "num_input_tokens_seen": 8854904,
977
+ "step": 121
978
+ },
979
+ {
980
+ "epoch": 2.0,
981
+ "grad_norm": 0.3606414794921875,
982
+ "learning_rate": 4.87356369410476e-05,
983
+ "loss": 0.2786,
984
+ "num_input_tokens_seen": 8872656,
985
+ "step": 122
986
+ },
987
+ {
988
+ "epoch": 2.016614745586708,
989
+ "grad_norm": 0.13124766945838928,
990
+ "learning_rate": 4.8715004865637614e-05,
991
+ "loss": 0.294,
992
+ "num_input_tokens_seen": 8946480,
993
+ "step": 123
994
+ },
995
+ {
996
+ "epoch": 2.0332294911734166,
997
+ "grad_norm": 0.12415049225091934,
998
+ "learning_rate": 4.869421025023965e-05,
999
+ "loss": 0.2931,
1000
+ "num_input_tokens_seen": 9023328,
1001
+ "step": 124
1002
+ },
1003
+ {
1004
+ "epoch": 2.0498442367601246,
1005
+ "grad_norm": 0.16626115143299103,
1006
+ "learning_rate": 4.867325323737765e-05,
1007
+ "loss": 0.2887,
1008
+ "num_input_tokens_seen": 9074320,
1009
+ "step": 125
1010
+ },
1011
+ {
1012
+ "epoch": 2.0664589823468327,
1013
+ "grad_norm": 0.153628870844841,
1014
+ "learning_rate": 4.8652133970688636e-05,
1015
+ "loss": 0.2776,
1016
+ "num_input_tokens_seen": 9148784,
1017
+ "step": 126
1018
+ },
1019
+ {
1020
+ "epoch": 2.083073727933541,
1021
+ "grad_norm": 0.12231138348579407,
1022
+ "learning_rate": 4.8630852594921706e-05,
1023
+ "loss": 0.3091,
1024
+ "num_input_tokens_seen": 9246624,
1025
+ "step": 127
1026
+ },
1027
+ {
1028
+ "epoch": 2.0996884735202492,
1029
+ "grad_norm": 0.15192057192325592,
1030
+ "learning_rate": 4.860940925593703e-05,
1031
+ "loss": 0.3354,
1032
+ "num_input_tokens_seen": 9328176,
1033
+ "step": 128
1034
+ },
1035
+ {
1036
+ "epoch": 2.1163032191069573,
1037
+ "grad_norm": 0.13820070028305054,
1038
+ "learning_rate": 4.8587804100704845e-05,
1039
+ "loss": 0.282,
1040
+ "num_input_tokens_seen": 9388936,
1041
+ "step": 129
1042
+ },
1043
+ {
1044
+ "epoch": 2.132917964693666,
1045
+ "grad_norm": 0.14466816186904907,
1046
+ "learning_rate": 4.856603727730447e-05,
1047
+ "loss": 0.2801,
1048
+ "num_input_tokens_seen": 9461664,
1049
+ "step": 130
1050
+ },
1051
+ {
1052
+ "epoch": 2.149532710280374,
1053
+ "grad_norm": 0.14671838283538818,
1054
+ "learning_rate": 4.854410893492326e-05,
1055
+ "loss": 0.2927,
1056
+ "num_input_tokens_seen": 9535000,
1057
+ "step": 131
1058
+ },
1059
+ {
1060
+ "epoch": 2.166147455867082,
1061
+ "grad_norm": 0.1757712960243225,
1062
+ "learning_rate": 4.852201922385564e-05,
1063
+ "loss": 0.2807,
1064
+ "num_input_tokens_seen": 9600296,
1065
+ "step": 132
1066
+ },
1067
+ {
1068
+ "epoch": 2.1827622014537904,
1069
+ "grad_norm": 0.17755423486232758,
1070
+ "learning_rate": 4.8499768295502004e-05,
1071
+ "loss": 0.2765,
1072
+ "num_input_tokens_seen": 9686784,
1073
+ "step": 133
1074
+ },
1075
+ {
1076
+ "epoch": 2.1993769470404985,
1077
+ "grad_norm": 0.13321827352046967,
1078
+ "learning_rate": 4.847735630236773e-05,
1079
+ "loss": 0.3068,
1080
+ "num_input_tokens_seen": 9781112,
1081
+ "step": 134
1082
+ },
1083
+ {
1084
+ "epoch": 2.2159916926272065,
1085
+ "grad_norm": 0.15012745559215546,
1086
+ "learning_rate": 4.8454783398062106e-05,
1087
+ "loss": 0.2737,
1088
+ "num_input_tokens_seen": 9849528,
1089
+ "step": 135
1090
+ },
1091
+ {
1092
+ "epoch": 2.232606438213915,
1093
+ "grad_norm": 0.14000360667705536,
1094
+ "learning_rate": 4.843204973729729e-05,
1095
+ "loss": 0.2831,
1096
+ "num_input_tokens_seen": 9931080,
1097
+ "step": 136
1098
+ },
1099
+ {
1100
+ "epoch": 2.249221183800623,
1101
+ "grad_norm": 0.14742712676525116,
1102
+ "learning_rate": 4.840915547588725e-05,
1103
+ "loss": 0.3047,
1104
+ "num_input_tokens_seen": 10011176,
1105
+ "step": 137
1106
+ },
1107
+ {
1108
+ "epoch": 2.265835929387331,
1109
+ "grad_norm": 0.16192346811294556,
1110
+ "learning_rate": 4.838610077074669e-05,
1111
+ "loss": 0.2759,
1112
+ "num_input_tokens_seen": 10084128,
1113
+ "step": 138
1114
+ },
1115
+ {
1116
+ "epoch": 2.2824506749740396,
1117
+ "grad_norm": 0.1502583771944046,
1118
+ "learning_rate": 4.836288577988996e-05,
1119
+ "loss": 0.298,
1120
+ "num_input_tokens_seen": 10155536,
1121
+ "step": 139
1122
+ },
1123
+ {
1124
+ "epoch": 2.2990654205607477,
1125
+ "grad_norm": 0.12661044299602509,
1126
+ "learning_rate": 4.8339510662430046e-05,
1127
+ "loss": 0.255,
1128
+ "num_input_tokens_seen": 10251160,
1129
+ "step": 140
1130
+ },
1131
+ {
1132
+ "epoch": 2.3156801661474558,
1133
+ "grad_norm": 0.14002998173236847,
1134
+ "learning_rate": 4.8315975578577355e-05,
1135
+ "loss": 0.2566,
1136
+ "num_input_tokens_seen": 10345864,
1137
+ "step": 141
1138
+ },
1139
+ {
1140
+ "epoch": 2.3322949117341643,
1141
+ "grad_norm": 0.17870523035526276,
1142
+ "learning_rate": 4.8292280689638725e-05,
1143
+ "loss": 0.4367,
1144
+ "num_input_tokens_seen": 10417616,
1145
+ "step": 142
1146
+ },
1147
+ {
1148
+ "epoch": 2.3489096573208723,
1149
+ "grad_norm": 0.17209866642951965,
1150
+ "learning_rate": 4.826842615801628e-05,
1151
+ "loss": 0.2954,
1152
+ "num_input_tokens_seen": 10481816,
1153
+ "step": 143
1154
+ },
1155
+ {
1156
+ "epoch": 2.3655244029075804,
1157
+ "grad_norm": 0.1665940284729004,
1158
+ "learning_rate": 4.8244412147206284e-05,
1159
+ "loss": 0.341,
1160
+ "num_input_tokens_seen": 10562056,
1161
+ "step": 144
1162
+ },
1163
+ {
1164
+ "epoch": 2.382139148494289,
1165
+ "grad_norm": 0.18919898569583893,
1166
+ "learning_rate": 4.822023882179811e-05,
1167
+ "loss": 0.2716,
1168
+ "num_input_tokens_seen": 10612808,
1169
+ "step": 145
1170
+ },
1171
+ {
1172
+ "epoch": 2.398753894080997,
1173
+ "grad_norm": 0.1681865006685257,
1174
+ "learning_rate": 4.8195906347473e-05,
1175
+ "loss": 0.2716,
1176
+ "num_input_tokens_seen": 10682328,
1177
+ "step": 146
1178
+ },
1179
+ {
1180
+ "epoch": 2.415368639667705,
1181
+ "grad_norm": 0.13141104578971863,
1182
+ "learning_rate": 4.817141489100302e-05,
1183
+ "loss": 0.2829,
1184
+ "num_input_tokens_seen": 10771912,
1185
+ "step": 147
1186
+ },
1187
+ {
1188
+ "epoch": 2.431983385254413,
1189
+ "grad_norm": 0.16544249653816223,
1190
+ "learning_rate": 4.814676462024988e-05,
1191
+ "loss": 0.3038,
1192
+ "num_input_tokens_seen": 10842232,
1193
+ "step": 148
1194
+ },
1195
+ {
1196
+ "epoch": 2.4485981308411215,
1197
+ "grad_norm": 0.17946277558803558,
1198
+ "learning_rate": 4.8121955704163745e-05,
1199
+ "loss": 0.2792,
1200
+ "num_input_tokens_seen": 10902264,
1201
+ "step": 149
1202
+ },
1203
+ {
1204
+ "epoch": 2.4652128764278296,
1205
+ "grad_norm": 0.14012685418128967,
1206
+ "learning_rate": 4.8096988312782174e-05,
1207
+ "loss": 0.2403,
1208
+ "num_input_tokens_seen": 10992744,
1209
+ "step": 150
1210
+ },
1211
+ {
1212
+ "epoch": 2.4818276220145377,
1213
+ "grad_norm": 0.103813536465168,
1214
+ "learning_rate": 4.8071862617228855e-05,
1215
+ "loss": 0.1605,
1216
+ "num_input_tokens_seen": 11090064,
1217
+ "step": 151
1218
+ },
1219
+ {
1220
+ "epoch": 2.498442367601246,
1221
+ "grad_norm": 0.1596001833677292,
1222
+ "learning_rate": 4.8046578789712515e-05,
1223
+ "loss": 0.2547,
1224
+ "num_input_tokens_seen": 11162864,
1225
+ "step": 152
1226
+ },
1227
+ {
1228
+ "epoch": 2.515057113187954,
1229
+ "grad_norm": 0.17366129159927368,
1230
+ "learning_rate": 4.8021137003525664e-05,
1231
+ "loss": 0.2676,
1232
+ "num_input_tokens_seen": 11224368,
1233
+ "step": 153
1234
+ },
1235
+ {
1236
+ "epoch": 2.5316718587746623,
1237
+ "grad_norm": 0.1615227609872818,
1238
+ "learning_rate": 4.7995537433043446e-05,
1239
+ "loss": 0.2898,
1240
+ "num_input_tokens_seen": 11291056,
1241
+ "step": 154
1242
+ },
1243
+ {
1244
+ "epoch": 2.5482866043613708,
1245
+ "grad_norm": 0.1951528787612915,
1246
+ "learning_rate": 4.796978025372246e-05,
1247
+ "loss": 0.2546,
1248
+ "num_input_tokens_seen": 11345464,
1249
+ "step": 155
1250
+ },
1251
+ {
1252
+ "epoch": 2.564901349948079,
1253
+ "grad_norm": 0.15065862238407135,
1254
+ "learning_rate": 4.794386564209953e-05,
1255
+ "loss": 0.3134,
1256
+ "num_input_tokens_seen": 11418912,
1257
+ "step": 156
1258
+ },
1259
+ {
1260
+ "epoch": 2.581516095534787,
1261
+ "grad_norm": 0.17094938457012177,
1262
+ "learning_rate": 4.79177937757905e-05,
1263
+ "loss": 0.2689,
1264
+ "num_input_tokens_seen": 11491216,
1265
+ "step": 157
1266
+ },
1267
+ {
1268
+ "epoch": 2.5981308411214954,
1269
+ "grad_norm": 0.16850312054157257,
1270
+ "learning_rate": 4.7891564833489035e-05,
1271
+ "loss": 0.2359,
1272
+ "num_input_tokens_seen": 11558016,
1273
+ "step": 158
1274
+ },
1275
+ {
1276
+ "epoch": 2.6147455867082035,
1277
+ "grad_norm": 0.16789822280406952,
1278
+ "learning_rate": 4.7865178994965344e-05,
1279
+ "loss": 0.2735,
1280
+ "num_input_tokens_seen": 11630432,
1281
+ "step": 159
1282
+ },
1283
+ {
1284
+ "epoch": 2.6313603322949115,
1285
+ "grad_norm": 0.19538354873657227,
1286
+ "learning_rate": 4.783863644106502e-05,
1287
+ "loss": 0.254,
1288
+ "num_input_tokens_seen": 11684624,
1289
+ "step": 160
1290
+ },
1291
+ {
1292
+ "epoch": 2.64797507788162,
1293
+ "grad_norm": 0.1609475016593933,
1294
+ "learning_rate": 4.781193735370777e-05,
1295
+ "loss": 0.2763,
1296
+ "num_input_tokens_seen": 11770232,
1297
+ "step": 161
1298
+ },
1299
+ {
1300
+ "epoch": 2.664589823468328,
1301
+ "grad_norm": 0.1964447796344757,
1302
+ "learning_rate": 4.7785081915886134e-05,
1303
+ "loss": 0.2663,
1304
+ "num_input_tokens_seen": 11828360,
1305
+ "step": 162
1306
+ },
1307
+ {
1308
+ "epoch": 2.681204569055036,
1309
+ "grad_norm": 0.18869946897029877,
1310
+ "learning_rate": 4.775807031166428e-05,
1311
+ "loss": 0.2625,
1312
+ "num_input_tokens_seen": 11915944,
1313
+ "step": 163
1314
+ },
1315
+ {
1316
+ "epoch": 2.6978193146417446,
1317
+ "grad_norm": 0.20539921522140503,
1318
+ "learning_rate": 4.773090272617672e-05,
1319
+ "loss": 0.2615,
1320
+ "num_input_tokens_seen": 11981792,
1321
+ "step": 164
1322
+ },
1323
+ {
1324
+ "epoch": 2.7144340602284527,
1325
+ "grad_norm": 0.1616145521402359,
1326
+ "learning_rate": 4.7703579345627035e-05,
1327
+ "loss": 0.3453,
1328
+ "num_input_tokens_seen": 12044024,
1329
+ "step": 165
1330
+ },
1331
+ {
1332
+ "epoch": 2.7310488058151607,
1333
+ "grad_norm": 0.22601978480815887,
1334
+ "learning_rate": 4.7676100357286624e-05,
1335
+ "loss": 0.3036,
1336
+ "num_input_tokens_seen": 12093424,
1337
+ "step": 166
1338
+ },
1339
+ {
1340
+ "epoch": 2.7476635514018692,
1341
+ "grad_norm": 0.15262462198734283,
1342
+ "learning_rate": 4.76484659494934e-05,
1343
+ "loss": 0.2523,
1344
+ "num_input_tokens_seen": 12167792,
1345
+ "step": 167
1346
+ },
1347
+ {
1348
+ "epoch": 2.7642782969885773,
1349
+ "grad_norm": 0.17928001284599304,
1350
+ "learning_rate": 4.762067631165049e-05,
1351
+ "loss": 0.2791,
1352
+ "num_input_tokens_seen": 12233712,
1353
+ "step": 168
1354
+ },
1355
+ {
1356
+ "epoch": 2.7808930425752854,
1357
+ "grad_norm": 0.15228766202926636,
1358
+ "learning_rate": 4.7592731634224966e-05,
1359
+ "loss": 0.2291,
1360
+ "num_input_tokens_seen": 12310544,
1361
+ "step": 169
1362
+ },
1363
+ {
1364
+ "epoch": 2.797507788161994,
1365
+ "grad_norm": 0.18862110376358032,
1366
+ "learning_rate": 4.756463210874652e-05,
1367
+ "loss": 0.2628,
1368
+ "num_input_tokens_seen": 12400160,
1369
+ "step": 170
1370
+ },
1371
+ {
1372
+ "epoch": 2.814122533748702,
1373
+ "grad_norm": 0.16640189290046692,
1374
+ "learning_rate": 4.753637792780614e-05,
1375
+ "loss": 0.2824,
1376
+ "num_input_tokens_seen": 12480432,
1377
+ "step": 171
1378
+ },
1379
+ {
1380
+ "epoch": 2.83073727933541,
1381
+ "grad_norm": 0.151117205619812,
1382
+ "learning_rate": 4.7507969285054845e-05,
1383
+ "loss": 0.2663,
1384
+ "num_input_tokens_seen": 12568064,
1385
+ "step": 172
1386
+ },
1387
+ {
1388
+ "epoch": 2.8473520249221185,
1389
+ "grad_norm": 0.26551589369773865,
1390
+ "learning_rate": 4.7479406375202264e-05,
1391
+ "loss": 0.28,
1392
+ "num_input_tokens_seen": 12647400,
1393
+ "step": 173
1394
+ },
1395
+ {
1396
+ "epoch": 2.8639667705088265,
1397
+ "grad_norm": 0.22416891157627106,
1398
+ "learning_rate": 4.745068939401539e-05,
1399
+ "loss": 0.2424,
1400
+ "num_input_tokens_seen": 12698208,
1401
+ "step": 174
1402
+ },
1403
+ {
1404
+ "epoch": 2.8805815160955346,
1405
+ "grad_norm": 0.2024654597043991,
1406
+ "learning_rate": 4.742181853831721e-05,
1407
+ "loss": 0.2518,
1408
+ "num_input_tokens_seen": 12758528,
1409
+ "step": 175
1410
+ },
1411
+ {
1412
+ "epoch": 2.897196261682243,
1413
+ "grad_norm": 0.18288369476795197,
1414
+ "learning_rate": 4.7392794005985326e-05,
1415
+ "loss": 0.259,
1416
+ "num_input_tokens_seen": 12837264,
1417
+ "step": 176
1418
+ },
1419
+ {
1420
+ "epoch": 2.913811007268951,
1421
+ "grad_norm": 0.18088208138942719,
1422
+ "learning_rate": 4.7363615995950626e-05,
1423
+ "loss": 0.247,
1424
+ "num_input_tokens_seen": 12902368,
1425
+ "step": 177
1426
+ },
1427
+ {
1428
+ "epoch": 2.930425752855659,
1429
+ "grad_norm": 0.16595424711704254,
1430
+ "learning_rate": 4.733428470819594e-05,
1431
+ "loss": 0.2438,
1432
+ "num_input_tokens_seen": 12974296,
1433
+ "step": 178
1434
+ },
1435
+ {
1436
+ "epoch": 2.9470404984423677,
1437
+ "grad_norm": 0.17989091575145721,
1438
+ "learning_rate": 4.730480034375462e-05,
1439
+ "loss": 0.2708,
1440
+ "num_input_tokens_seen": 13057280,
1441
+ "step": 179
1442
+ },
1443
+ {
1444
+ "epoch": 2.9636552440290758,
1445
+ "grad_norm": 0.16136637330055237,
1446
+ "learning_rate": 4.72751631047092e-05,
1447
+ "loss": 0.3171,
1448
+ "num_input_tokens_seen": 13158232,
1449
+ "step": 180
1450
+ }
1451
+ ],
1452
+ "logging_steps": 1.0,
1453
+ "max_steps": 1200,
1454
+ "num_input_tokens_seen": 13158232,
1455
+ "num_train_epochs": 20,
1456
+ "save_steps": 60,
1457
+ "stateful_callbacks": {
1458
+ "TrainerControl": {
1459
+ "args": {
1460
+ "should_epoch_stop": false,
1461
+ "should_evaluate": false,
1462
+ "should_log": false,
1463
+ "should_save": true,
1464
+ "should_training_stop": false
1465
+ },
1466
+ "attributes": {}
1467
+ }
1468
+ },
1469
+ "total_flos": 5.614082820239524e+17,
1470
+ "train_batch_size": 1,
1471
+ "trial_name": null,
1472
+ "trial_params": null
1473
+ }
checkpoint-180/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9746167dc82a516aeee83c5731c4b250770d2cfb0fb68a7cd590dc02bd3eb0d6
3
+ size 5688
checkpoint-180/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-240/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-Coder-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 0.12.0
checkpoint-240/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-Coder-7B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "down_proj",
24
+ "k_proj",
25
+ "v_proj",
26
+ "q_proj",
27
+ "o_proj",
28
+ "gate_proj",
29
+ "up_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-240/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaee62e114b1142e27a6e659ac3372857c41a913d49f1a99a1b011951cf28902
3
+ size 161533192
checkpoint-240/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-240/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-240/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a7dc9f63e1166fce2eb3448271b3a8375141040657d780c91427a75977d2fec
3
+ size 323290986
checkpoint-240/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ad5c27b199fa194b39d04afec866a2e311b35a3782ae0a03b96741b7d8a6d18
3
+ size 14512
checkpoint-240/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e0f6f7ff801e3f59484846afc5d50ec7c71ea31ea35c6ad03e787ab8e194c28
3
+ size 14512
checkpoint-240/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3de8199cf9d6d12153e18123cf96dc2b84397b2c8e869fab2d188b1c5614bc21
3
+ size 1064
checkpoint-240/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-240/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
checkpoint-240/tokenizer_config.json ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 17000,
204
+ "pad_token": "<|endoftext|>",
205
+ "padding_side": "right",
206
+ "split_special_tokens": false,
207
+ "tokenizer_class": "Qwen2Tokenizer",
208
+ "unk_token": null
209
+ }
checkpoint-240/trainer_state.json ADDED
@@ -0,0 +1,1953 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.9470404984423677,
5
+ "eval_steps": 500,
6
+ "global_step": 240,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.016614745586708203,
13
+ "grad_norm": 0.061364494264125824,
14
+ "learning_rate": 4.999991432639962e-05,
15
+ "loss": 0.5857,
16
+ "num_input_tokens_seen": 70408,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.033229491173416406,
21
+ "grad_norm": 0.0613991804420948,
22
+ "learning_rate": 4.999965730618567e-05,
23
+ "loss": 0.5331,
24
+ "num_input_tokens_seen": 139640,
25
+ "step": 2
26
+ },
27
+ {
28
+ "epoch": 0.04984423676012461,
29
+ "grad_norm": 0.06351307034492493,
30
+ "learning_rate": 4.9999228941119745e-05,
31
+ "loss": 0.5852,
32
+ "num_input_tokens_seen": 223656,
33
+ "step": 3
34
+ },
35
+ {
36
+ "epoch": 0.06645898234683281,
37
+ "grad_norm": 0.05762802064418793,
38
+ "learning_rate": 4.999862923413781e-05,
39
+ "loss": 0.5384,
40
+ "num_input_tokens_seen": 300688,
41
+ "step": 4
42
+ },
43
+ {
44
+ "epoch": 0.08307372793354102,
45
+ "grad_norm": 0.0632179006934166,
46
+ "learning_rate": 4.999785818935018e-05,
47
+ "loss": 0.5273,
48
+ "num_input_tokens_seen": 366368,
49
+ "step": 5
50
+ },
51
+ {
52
+ "epoch": 0.09968847352024922,
53
+ "grad_norm": 0.056689903140068054,
54
+ "learning_rate": 4.999691581204152e-05,
55
+ "loss": 0.5145,
56
+ "num_input_tokens_seen": 445808,
57
+ "step": 6
58
+ },
59
+ {
60
+ "epoch": 0.11630321910695743,
61
+ "grad_norm": 0.06574171781539917,
62
+ "learning_rate": 4.9995802108670775e-05,
63
+ "loss": 0.5301,
64
+ "num_input_tokens_seen": 522800,
65
+ "step": 7
66
+ },
67
+ {
68
+ "epoch": 0.13291796469366562,
69
+ "grad_norm": 0.06367070972919464,
70
+ "learning_rate": 4.999451708687114e-05,
71
+ "loss": 0.5552,
72
+ "num_input_tokens_seen": 599608,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.14953271028037382,
77
+ "grad_norm": 0.0585966520011425,
78
+ "learning_rate": 4.9993060755450015e-05,
79
+ "loss": 0.5999,
80
+ "num_input_tokens_seen": 681424,
81
+ "step": 9
82
+ },
83
+ {
84
+ "epoch": 0.16614745586708204,
85
+ "grad_norm": 0.05650574713945389,
86
+ "learning_rate": 4.999143312438893e-05,
87
+ "loss": 0.4535,
88
+ "num_input_tokens_seen": 756744,
89
+ "step": 10
90
+ },
91
+ {
92
+ "epoch": 0.18276220145379024,
93
+ "grad_norm": 0.05954223498702049,
94
+ "learning_rate": 4.998963420484349e-05,
95
+ "loss": 0.4674,
96
+ "num_input_tokens_seen": 842576,
97
+ "step": 11
98
+ },
99
+ {
100
+ "epoch": 0.19937694704049844,
101
+ "grad_norm": 0.0663776770234108,
102
+ "learning_rate": 4.998766400914329e-05,
103
+ "loss": 0.4703,
104
+ "num_input_tokens_seen": 917232,
105
+ "step": 12
106
+ },
107
+ {
108
+ "epoch": 0.21599169262720663,
109
+ "grad_norm": 0.056374579668045044,
110
+ "learning_rate": 4.9985522550791825e-05,
111
+ "loss": 0.3725,
112
+ "num_input_tokens_seen": 1006800,
113
+ "step": 13
114
+ },
115
+ {
116
+ "epoch": 0.23260643821391486,
117
+ "grad_norm": 0.06437493115663528,
118
+ "learning_rate": 4.998320984446641e-05,
119
+ "loss": 0.4653,
120
+ "num_input_tokens_seen": 1085824,
121
+ "step": 14
122
+ },
123
+ {
124
+ "epoch": 0.24922118380062305,
125
+ "grad_norm": 0.06560757756233215,
126
+ "learning_rate": 4.9980725906018074e-05,
127
+ "loss": 0.5026,
128
+ "num_input_tokens_seen": 1164160,
129
+ "step": 15
130
+ },
131
+ {
132
+ "epoch": 0.26583592938733125,
133
+ "grad_norm": 0.06942517310380936,
134
+ "learning_rate": 4.997807075247146e-05,
135
+ "loss": 0.5401,
136
+ "num_input_tokens_seen": 1242264,
137
+ "step": 16
138
+ },
139
+ {
140
+ "epoch": 0.2824506749740395,
141
+ "grad_norm": 0.06349828094244003,
142
+ "learning_rate": 4.997524440202469e-05,
143
+ "loss": 0.4713,
144
+ "num_input_tokens_seen": 1325904,
145
+ "step": 17
146
+ },
147
+ {
148
+ "epoch": 0.29906542056074764,
149
+ "grad_norm": 0.08846385776996613,
150
+ "learning_rate": 4.9972246874049254e-05,
151
+ "loss": 0.5834,
152
+ "num_input_tokens_seen": 1385632,
153
+ "step": 18
154
+ },
155
+ {
156
+ "epoch": 0.31568016614745587,
157
+ "grad_norm": 0.062130190432071686,
158
+ "learning_rate": 4.996907818908987e-05,
159
+ "loss": 0.4045,
160
+ "num_input_tokens_seen": 1470632,
161
+ "step": 19
162
+ },
163
+ {
164
+ "epoch": 0.3322949117341641,
165
+ "grad_norm": 0.07743565738201141,
166
+ "learning_rate": 4.996573836886435e-05,
167
+ "loss": 0.5283,
168
+ "num_input_tokens_seen": 1547536,
169
+ "step": 20
170
+ },
171
+ {
172
+ "epoch": 0.34890965732087226,
173
+ "grad_norm": 0.06756695359945297,
174
+ "learning_rate": 4.9962227436263453e-05,
175
+ "loss": 0.4199,
176
+ "num_input_tokens_seen": 1615528,
177
+ "step": 21
178
+ },
179
+ {
180
+ "epoch": 0.3655244029075805,
181
+ "grad_norm": 0.08662309497594833,
182
+ "learning_rate": 4.995854541535071e-05,
183
+ "loss": 0.4775,
184
+ "num_input_tokens_seen": 1694352,
185
+ "step": 22
186
+ },
187
+ {
188
+ "epoch": 0.3821391484942887,
189
+ "grad_norm": 0.08380820602178574,
190
+ "learning_rate": 4.9954692331362294e-05,
191
+ "loss": 0.4871,
192
+ "num_input_tokens_seen": 1753776,
193
+ "step": 23
194
+ },
195
+ {
196
+ "epoch": 0.3987538940809969,
197
+ "grad_norm": 0.09967435896396637,
198
+ "learning_rate": 4.995066821070679e-05,
199
+ "loss": 0.4871,
200
+ "num_input_tokens_seen": 1809048,
201
+ "step": 24
202
+ },
203
+ {
204
+ "epoch": 0.4153686396677051,
205
+ "grad_norm": 0.0871267095208168,
206
+ "learning_rate": 4.994647308096509e-05,
207
+ "loss": 0.5461,
208
+ "num_input_tokens_seen": 1884264,
209
+ "step": 25
210
+ },
211
+ {
212
+ "epoch": 0.43198338525441327,
213
+ "grad_norm": 0.065020851790905,
214
+ "learning_rate": 4.994210697089014e-05,
215
+ "loss": 0.405,
216
+ "num_input_tokens_seen": 1981704,
217
+ "step": 26
218
+ },
219
+ {
220
+ "epoch": 0.4485981308411215,
221
+ "grad_norm": 0.09853450953960419,
222
+ "learning_rate": 4.9937569910406756e-05,
223
+ "loss": 0.4487,
224
+ "num_input_tokens_seen": 2044144,
225
+ "step": 27
226
+ },
227
+ {
228
+ "epoch": 0.4652128764278297,
229
+ "grad_norm": 0.08763110637664795,
230
+ "learning_rate": 4.9932861930611454e-05,
231
+ "loss": 0.3946,
232
+ "num_input_tokens_seen": 2107584,
233
+ "step": 28
234
+ },
235
+ {
236
+ "epoch": 0.4818276220145379,
237
+ "grad_norm": 0.08950547873973846,
238
+ "learning_rate": 4.9927983063772196e-05,
239
+ "loss": 0.4257,
240
+ "num_input_tokens_seen": 2169248,
241
+ "step": 29
242
+ },
243
+ {
244
+ "epoch": 0.4984423676012461,
245
+ "grad_norm": 0.09980211406946182,
246
+ "learning_rate": 4.99229333433282e-05,
247
+ "loss": 0.3911,
248
+ "num_input_tokens_seen": 2230344,
249
+ "step": 30
250
+ },
251
+ {
252
+ "epoch": 0.5150571131879543,
253
+ "grad_norm": 0.092055544257164,
254
+ "learning_rate": 4.9917712803889674e-05,
255
+ "loss": 0.3749,
256
+ "num_input_tokens_seen": 2302368,
257
+ "step": 31
258
+ },
259
+ {
260
+ "epoch": 0.5316718587746625,
261
+ "grad_norm": 0.10067818313837051,
262
+ "learning_rate": 4.991232148123761e-05,
263
+ "loss": 0.4761,
264
+ "num_input_tokens_seen": 2369984,
265
+ "step": 32
266
+ },
267
+ {
268
+ "epoch": 0.5482866043613707,
269
+ "grad_norm": 0.0717971920967102,
270
+ "learning_rate": 4.990675941232353e-05,
271
+ "loss": 0.4328,
272
+ "num_input_tokens_seen": 2453032,
273
+ "step": 33
274
+ },
275
+ {
276
+ "epoch": 0.564901349948079,
277
+ "grad_norm": 0.07436250895261765,
278
+ "learning_rate": 4.990102663526924e-05,
279
+ "loss": 0.417,
280
+ "num_input_tokens_seen": 2527464,
281
+ "step": 34
282
+ },
283
+ {
284
+ "epoch": 0.5815160955347871,
285
+ "grad_norm": 0.09256689995527267,
286
+ "learning_rate": 4.989512318936655e-05,
287
+ "loss": 0.4097,
288
+ "num_input_tokens_seen": 2597032,
289
+ "step": 35
290
+ },
291
+ {
292
+ "epoch": 0.5981308411214953,
293
+ "grad_norm": 0.09964177012443542,
294
+ "learning_rate": 4.9889049115077005e-05,
295
+ "loss": 0.4065,
296
+ "num_input_tokens_seen": 2671704,
297
+ "step": 36
298
+ },
299
+ {
300
+ "epoch": 0.6147455867082036,
301
+ "grad_norm": 0.06627887487411499,
302
+ "learning_rate": 4.988280445403164e-05,
303
+ "loss": 0.4136,
304
+ "num_input_tokens_seen": 2767640,
305
+ "step": 37
306
+ },
307
+ {
308
+ "epoch": 0.6313603322949117,
309
+ "grad_norm": 0.0746045857667923,
310
+ "learning_rate": 4.987638924903067e-05,
311
+ "loss": 0.4125,
312
+ "num_input_tokens_seen": 2843720,
313
+ "step": 38
314
+ },
315
+ {
316
+ "epoch": 0.6479750778816199,
317
+ "grad_norm": 0.0795741006731987,
318
+ "learning_rate": 4.9869803544043166e-05,
319
+ "loss": 0.3135,
320
+ "num_input_tokens_seen": 2921472,
321
+ "step": 39
322
+ },
323
+ {
324
+ "epoch": 0.6645898234683282,
325
+ "grad_norm": 0.08914181590080261,
326
+ "learning_rate": 4.9863047384206835e-05,
327
+ "loss": 0.4549,
328
+ "num_input_tokens_seen": 2998400,
329
+ "step": 40
330
+ },
331
+ {
332
+ "epoch": 0.6812045690550363,
333
+ "grad_norm": 0.11220043897628784,
334
+ "learning_rate": 4.985612081582764e-05,
335
+ "loss": 0.4135,
336
+ "num_input_tokens_seen": 3059648,
337
+ "step": 41
338
+ },
339
+ {
340
+ "epoch": 0.6978193146417445,
341
+ "grad_norm": 0.08390027284622192,
342
+ "learning_rate": 4.98490238863795e-05,
343
+ "loss": 0.3538,
344
+ "num_input_tokens_seen": 3140184,
345
+ "step": 42
346
+ },
347
+ {
348
+ "epoch": 0.7144340602284528,
349
+ "grad_norm": 0.08858532458543777,
350
+ "learning_rate": 4.984175664450397e-05,
351
+ "loss": 0.3644,
352
+ "num_input_tokens_seen": 3207184,
353
+ "step": 43
354
+ },
355
+ {
356
+ "epoch": 0.731048805815161,
357
+ "grad_norm": 0.07439564168453217,
358
+ "learning_rate": 4.983431914000991e-05,
359
+ "loss": 0.4019,
360
+ "num_input_tokens_seen": 3292344,
361
+ "step": 44
362
+ },
363
+ {
364
+ "epoch": 0.7476635514018691,
365
+ "grad_norm": 0.08694300055503845,
366
+ "learning_rate": 4.982671142387316e-05,
367
+ "loss": 0.4238,
368
+ "num_input_tokens_seen": 3365384,
369
+ "step": 45
370
+ },
371
+ {
372
+ "epoch": 0.7642782969885774,
373
+ "grad_norm": 0.0867784395813942,
374
+ "learning_rate": 4.981893354823614e-05,
375
+ "loss": 0.3702,
376
+ "num_input_tokens_seen": 3440720,
377
+ "step": 46
378
+ },
379
+ {
380
+ "epoch": 0.7808930425752856,
381
+ "grad_norm": 0.06278439611196518,
382
+ "learning_rate": 4.9810985566407544e-05,
383
+ "loss": 0.3354,
384
+ "num_input_tokens_seen": 3533576,
385
+ "step": 47
386
+ },
387
+ {
388
+ "epoch": 0.7975077881619937,
389
+ "grad_norm": 0.08999717980623245,
390
+ "learning_rate": 4.980286753286195e-05,
391
+ "loss": 0.4981,
392
+ "num_input_tokens_seen": 3599744,
393
+ "step": 48
394
+ },
395
+ {
396
+ "epoch": 0.814122533748702,
397
+ "grad_norm": 0.07938859611749649,
398
+ "learning_rate": 4.979457950323945e-05,
399
+ "loss": 0.4016,
400
+ "num_input_tokens_seen": 3689520,
401
+ "step": 49
402
+ },
403
+ {
404
+ "epoch": 0.8307372793354102,
405
+ "grad_norm": 0.1045590192079544,
406
+ "learning_rate": 4.9786121534345265e-05,
407
+ "loss": 0.388,
408
+ "num_input_tokens_seen": 3751808,
409
+ "step": 50
410
+ },
411
+ {
412
+ "epoch": 0.8473520249221184,
413
+ "grad_norm": 0.07890618592500687,
414
+ "learning_rate": 4.9777493684149375e-05,
415
+ "loss": 0.3674,
416
+ "num_input_tokens_seen": 3839096,
417
+ "step": 51
418
+ },
419
+ {
420
+ "epoch": 0.8639667705088265,
421
+ "grad_norm": 0.07802557945251465,
422
+ "learning_rate": 4.976869601178609e-05,
423
+ "loss": 0.4147,
424
+ "num_input_tokens_seen": 3919824,
425
+ "step": 52
426
+ },
427
+ {
428
+ "epoch": 0.8805815160955348,
429
+ "grad_norm": 0.0913538783788681,
430
+ "learning_rate": 4.975972857755369e-05,
431
+ "loss": 0.2978,
432
+ "num_input_tokens_seen": 3989312,
433
+ "step": 53
434
+ },
435
+ {
436
+ "epoch": 0.897196261682243,
437
+ "grad_norm": 0.08525951951742172,
438
+ "learning_rate": 4.975059144291394e-05,
439
+ "loss": 0.3923,
440
+ "num_input_tokens_seen": 4060528,
441
+ "step": 54
442
+ },
443
+ {
444
+ "epoch": 0.9138110072689511,
445
+ "grad_norm": 0.08649709820747375,
446
+ "learning_rate": 4.974128467049176e-05,
447
+ "loss": 0.3282,
448
+ "num_input_tokens_seen": 4129368,
449
+ "step": 55
450
+ },
451
+ {
452
+ "epoch": 0.9304257528556594,
453
+ "grad_norm": 0.11635593324899673,
454
+ "learning_rate": 4.9731808324074717e-05,
455
+ "loss": 0.3403,
456
+ "num_input_tokens_seen": 4175208,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 0.9470404984423676,
461
+ "grad_norm": 0.1115177720785141,
462
+ "learning_rate": 4.972216246861262e-05,
463
+ "loss": 0.3191,
464
+ "num_input_tokens_seen": 4218096,
465
+ "step": 57
466
+ },
467
+ {
468
+ "epoch": 0.9636552440290758,
469
+ "grad_norm": 0.0986371859908104,
470
+ "learning_rate": 4.971234717021709e-05,
471
+ "loss": 0.3745,
472
+ "num_input_tokens_seen": 4275968,
473
+ "step": 58
474
+ },
475
+ {
476
+ "epoch": 0.980269989615784,
477
+ "grad_norm": 0.07860780507326126,
478
+ "learning_rate": 4.9702362496161085e-05,
479
+ "loss": 0.3129,
480
+ "num_input_tokens_seen": 4346616,
481
+ "step": 59
482
+ },
483
+ {
484
+ "epoch": 0.9968847352024922,
485
+ "grad_norm": 0.08581527322530746,
486
+ "learning_rate": 4.9692208514878444e-05,
487
+ "loss": 0.3324,
488
+ "num_input_tokens_seen": 4425064,
489
+ "step": 60
490
+ },
491
+ {
492
+ "epoch": 1.0,
493
+ "grad_norm": 0.16779834032058716,
494
+ "learning_rate": 4.968188529596342e-05,
495
+ "loss": 0.2814,
496
+ "num_input_tokens_seen": 4435328,
497
+ "step": 61
498
+ },
499
+ {
500
+ "epoch": 1.0166147455867083,
501
+ "grad_norm": 0.08948636800050735,
502
+ "learning_rate": 4.9671392910170185e-05,
503
+ "loss": 0.3467,
504
+ "num_input_tokens_seen": 4500104,
505
+ "step": 62
506
+ },
507
+ {
508
+ "epoch": 1.0332294911734163,
509
+ "grad_norm": 0.07826830446720123,
510
+ "learning_rate": 4.966073142941239e-05,
511
+ "loss": 0.3892,
512
+ "num_input_tokens_seen": 4581976,
513
+ "step": 63
514
+ },
515
+ {
516
+ "epoch": 1.0498442367601246,
517
+ "grad_norm": 0.08562575280666351,
518
+ "learning_rate": 4.964990092676263e-05,
519
+ "loss": 0.3354,
520
+ "num_input_tokens_seen": 4652160,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 1.066458982346833,
525
+ "grad_norm": 0.1057090312242508,
526
+ "learning_rate": 4.9638901476451946e-05,
527
+ "loss": 0.3457,
528
+ "num_input_tokens_seen": 4709368,
529
+ "step": 65
530
+ },
531
+ {
532
+ "epoch": 1.083073727933541,
533
+ "grad_norm": 0.08131146430969238,
534
+ "learning_rate": 4.962773315386935e-05,
535
+ "loss": 0.3672,
536
+ "num_input_tokens_seen": 4798256,
537
+ "step": 66
538
+ },
539
+ {
540
+ "epoch": 1.0996884735202492,
541
+ "grad_norm": 0.09464936703443527,
542
+ "learning_rate": 4.961639603556127e-05,
543
+ "loss": 0.3157,
544
+ "num_input_tokens_seen": 4859200,
545
+ "step": 67
546
+ },
547
+ {
548
+ "epoch": 1.1163032191069575,
549
+ "grad_norm": 0.0999661460518837,
550
+ "learning_rate": 4.960489019923105e-05,
551
+ "loss": 0.3968,
552
+ "num_input_tokens_seen": 4925992,
553
+ "step": 68
554
+ },
555
+ {
556
+ "epoch": 1.1329179646936656,
557
+ "grad_norm": 0.09851639717817307,
558
+ "learning_rate": 4.9593215723738404e-05,
559
+ "loss": 0.329,
560
+ "num_input_tokens_seen": 4998808,
561
+ "step": 69
562
+ },
563
+ {
564
+ "epoch": 1.1495327102803738,
565
+ "grad_norm": 0.08382592350244522,
566
+ "learning_rate": 4.958137268909887e-05,
567
+ "loss": 0.2856,
568
+ "num_input_tokens_seen": 5089672,
569
+ "step": 70
570
+ },
571
+ {
572
+ "epoch": 1.1661474558670821,
573
+ "grad_norm": 0.09073847532272339,
574
+ "learning_rate": 4.9569361176483286e-05,
575
+ "loss": 0.3512,
576
+ "num_input_tokens_seen": 5166744,
577
+ "step": 71
578
+ },
579
+ {
580
+ "epoch": 1.1827622014537902,
581
+ "grad_norm": 0.10290185362100601,
582
+ "learning_rate": 4.9557181268217227e-05,
583
+ "loss": 0.4263,
584
+ "num_input_tokens_seen": 5228264,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 1.1993769470404985,
589
+ "grad_norm": 0.07421435415744781,
590
+ "learning_rate": 4.9544833047780394e-05,
591
+ "loss": 0.3126,
592
+ "num_input_tokens_seen": 5338224,
593
+ "step": 73
594
+ },
595
+ {
596
+ "epoch": 1.2159916926272065,
597
+ "grad_norm": 0.10284842550754547,
598
+ "learning_rate": 4.9532316599806124e-05,
599
+ "loss": 0.3473,
600
+ "num_input_tokens_seen": 5399848,
601
+ "step": 74
602
+ },
603
+ {
604
+ "epoch": 1.2326064382139148,
605
+ "grad_norm": 0.10817047953605652,
606
+ "learning_rate": 4.951963201008076e-05,
607
+ "loss": 0.3275,
608
+ "num_input_tokens_seen": 5468624,
609
+ "step": 75
610
+ },
611
+ {
612
+ "epoch": 1.249221183800623,
613
+ "grad_norm": 0.09662210941314697,
614
+ "learning_rate": 4.9506779365543046e-05,
615
+ "loss": 0.3296,
616
+ "num_input_tokens_seen": 5536776,
617
+ "step": 76
618
+ },
619
+ {
620
+ "epoch": 1.2658359293873311,
621
+ "grad_norm": 0.11193853616714478,
622
+ "learning_rate": 4.949375875428357e-05,
623
+ "loss": 0.3605,
624
+ "num_input_tokens_seen": 5609296,
625
+ "step": 77
626
+ },
627
+ {
628
+ "epoch": 1.2824506749740394,
629
+ "grad_norm": 0.11866679787635803,
630
+ "learning_rate": 4.9480570265544144e-05,
631
+ "loss": 0.3133,
632
+ "num_input_tokens_seen": 5663824,
633
+ "step": 78
634
+ },
635
+ {
636
+ "epoch": 1.2990654205607477,
637
+ "grad_norm": 0.09865846484899521,
638
+ "learning_rate": 4.94672139897172e-05,
639
+ "loss": 0.3464,
640
+ "num_input_tokens_seen": 5742032,
641
+ "step": 79
642
+ },
643
+ {
644
+ "epoch": 1.3156801661474558,
645
+ "grad_norm": 0.09930054098367691,
646
+ "learning_rate": 4.9453690018345144e-05,
647
+ "loss": 0.3346,
648
+ "num_input_tokens_seen": 5816864,
649
+ "step": 80
650
+ },
651
+ {
652
+ "epoch": 1.332294911734164,
653
+ "grad_norm": 0.1085321381688118,
654
+ "learning_rate": 4.943999844411977e-05,
655
+ "loss": 0.3102,
656
+ "num_input_tokens_seen": 5881624,
657
+ "step": 81
658
+ },
659
+ {
660
+ "epoch": 1.3489096573208723,
661
+ "grad_norm": 0.08012478053569794,
662
+ "learning_rate": 4.94261393608816e-05,
663
+ "loss": 0.2853,
664
+ "num_input_tokens_seen": 5970272,
665
+ "step": 82
666
+ },
667
+ {
668
+ "epoch": 1.3655244029075804,
669
+ "grad_norm": 0.10291877388954163,
670
+ "learning_rate": 4.941211286361922e-05,
671
+ "loss": 0.3038,
672
+ "num_input_tokens_seen": 6058752,
673
+ "step": 83
674
+ },
675
+ {
676
+ "epoch": 1.3821391484942886,
677
+ "grad_norm": 0.11999356001615524,
678
+ "learning_rate": 4.939791904846869e-05,
679
+ "loss": 0.3283,
680
+ "num_input_tokens_seen": 6120064,
681
+ "step": 84
682
+ },
683
+ {
684
+ "epoch": 1.398753894080997,
685
+ "grad_norm": 0.10502559691667557,
686
+ "learning_rate": 4.938355801271282e-05,
687
+ "loss": 0.321,
688
+ "num_input_tokens_seen": 6182072,
689
+ "step": 85
690
+ },
691
+ {
692
+ "epoch": 1.415368639667705,
693
+ "grad_norm": 0.12620873749256134,
694
+ "learning_rate": 4.936902985478055e-05,
695
+ "loss": 0.3296,
696
+ "num_input_tokens_seen": 6269680,
697
+ "step": 86
698
+ },
699
+ {
700
+ "epoch": 1.4319833852544133,
701
+ "grad_norm": 0.13212910294532776,
702
+ "learning_rate": 4.935433467424624e-05,
703
+ "loss": 0.3225,
704
+ "num_input_tokens_seen": 6347424,
705
+ "step": 87
706
+ },
707
+ {
708
+ "epoch": 1.4485981308411215,
709
+ "grad_norm": 0.11600925773382187,
710
+ "learning_rate": 4.933947257182901e-05,
711
+ "loss": 0.3479,
712
+ "num_input_tokens_seen": 6412584,
713
+ "step": 88
714
+ },
715
+ {
716
+ "epoch": 1.4652128764278296,
717
+ "grad_norm": 0.11683235317468643,
718
+ "learning_rate": 4.932444364939205e-05,
719
+ "loss": 0.3322,
720
+ "num_input_tokens_seen": 6482728,
721
+ "step": 89
722
+ },
723
+ {
724
+ "epoch": 1.4818276220145379,
725
+ "grad_norm": 0.11446017026901245,
726
+ "learning_rate": 4.9309248009941914e-05,
727
+ "loss": 0.3802,
728
+ "num_input_tokens_seen": 6562104,
729
+ "step": 90
730
+ },
731
+ {
732
+ "epoch": 1.4984423676012462,
733
+ "grad_norm": 0.10500892251729965,
734
+ "learning_rate": 4.929388575762782e-05,
735
+ "loss": 0.3371,
736
+ "num_input_tokens_seen": 6656552,
737
+ "step": 91
738
+ },
739
+ {
740
+ "epoch": 1.5150571131879542,
741
+ "grad_norm": 0.13279151916503906,
742
+ "learning_rate": 4.9278356997740904e-05,
743
+ "loss": 0.293,
744
+ "num_input_tokens_seen": 6714184,
745
+ "step": 92
746
+ },
747
+ {
748
+ "epoch": 1.5316718587746625,
749
+ "grad_norm": 0.107506163418293,
750
+ "learning_rate": 4.9262661836713564e-05,
751
+ "loss": 0.3127,
752
+ "num_input_tokens_seen": 6793552,
753
+ "step": 93
754
+ },
755
+ {
756
+ "epoch": 1.5482866043613708,
757
+ "grad_norm": 0.124021977186203,
758
+ "learning_rate": 4.924680038211867e-05,
759
+ "loss": 0.3263,
760
+ "num_input_tokens_seen": 6865256,
761
+ "step": 94
762
+ },
763
+ {
764
+ "epoch": 1.5649013499480788,
765
+ "grad_norm": 0.14172782003879547,
766
+ "learning_rate": 4.9230772742668866e-05,
767
+ "loss": 0.3204,
768
+ "num_input_tokens_seen": 6931152,
769
+ "step": 95
770
+ },
771
+ {
772
+ "epoch": 1.5815160955347871,
773
+ "grad_norm": 0.12229758501052856,
774
+ "learning_rate": 4.9214579028215776e-05,
775
+ "loss": 0.326,
776
+ "num_input_tokens_seen": 6998408,
777
+ "step": 96
778
+ },
779
+ {
780
+ "epoch": 1.5981308411214954,
781
+ "grad_norm": 0.1242135688662529,
782
+ "learning_rate": 4.919821934974933e-05,
783
+ "loss": 0.2814,
784
+ "num_input_tokens_seen": 7053008,
785
+ "step": 97
786
+ },
787
+ {
788
+ "epoch": 1.6147455867082035,
789
+ "grad_norm": 0.12830108404159546,
790
+ "learning_rate": 4.918169381939692e-05,
791
+ "loss": 0.3254,
792
+ "num_input_tokens_seen": 7106440,
793
+ "step": 98
794
+ },
795
+ {
796
+ "epoch": 1.6313603322949117,
797
+ "grad_norm": 0.12180659174919128,
798
+ "learning_rate": 4.916500255042268e-05,
799
+ "loss": 0.3228,
800
+ "num_input_tokens_seen": 7167032,
801
+ "step": 99
802
+ },
803
+ {
804
+ "epoch": 1.64797507788162,
805
+ "grad_norm": 0.10792312026023865,
806
+ "learning_rate": 4.914814565722671e-05,
807
+ "loss": 0.2729,
808
+ "num_input_tokens_seen": 7245720,
809
+ "step": 100
810
+ },
811
+ {
812
+ "epoch": 1.664589823468328,
813
+ "grad_norm": 0.18523500859737396,
814
+ "learning_rate": 4.913112325534426e-05,
815
+ "loss": 0.3462,
816
+ "num_input_tokens_seen": 7326320,
817
+ "step": 101
818
+ },
819
+ {
820
+ "epoch": 1.6812045690550363,
821
+ "grad_norm": 0.09529964625835419,
822
+ "learning_rate": 4.9113935461444955e-05,
823
+ "loss": 0.3096,
824
+ "num_input_tokens_seen": 7442232,
825
+ "step": 102
826
+ },
827
+ {
828
+ "epoch": 1.6978193146417446,
829
+ "grad_norm": 0.14481183886528015,
830
+ "learning_rate": 4.9096582393332025e-05,
831
+ "loss": 0.3014,
832
+ "num_input_tokens_seen": 7502496,
833
+ "step": 103
834
+ },
835
+ {
836
+ "epoch": 1.7144340602284527,
837
+ "grad_norm": 0.14645016193389893,
838
+ "learning_rate": 4.907906416994146e-05,
839
+ "loss": 0.3336,
840
+ "num_input_tokens_seen": 7566496,
841
+ "step": 104
842
+ },
843
+ {
844
+ "epoch": 1.731048805815161,
845
+ "grad_norm": 0.1306885927915573,
846
+ "learning_rate": 4.906138091134118e-05,
847
+ "loss": 0.3911,
848
+ "num_input_tokens_seen": 7629056,
849
+ "step": 105
850
+ },
851
+ {
852
+ "epoch": 1.7476635514018692,
853
+ "grad_norm": 0.10863160341978073,
854
+ "learning_rate": 4.9043532738730284e-05,
855
+ "loss": 0.3201,
856
+ "num_input_tokens_seen": 7706096,
857
+ "step": 106
858
+ },
859
+ {
860
+ "epoch": 1.7642782969885773,
861
+ "grad_norm": 0.11725673079490662,
862
+ "learning_rate": 4.9025519774438136e-05,
863
+ "loss": 0.2783,
864
+ "num_input_tokens_seen": 7780072,
865
+ "step": 107
866
+ },
867
+ {
868
+ "epoch": 1.7808930425752856,
869
+ "grad_norm": 0.1243867501616478,
870
+ "learning_rate": 4.900734214192358e-05,
871
+ "loss": 0.3044,
872
+ "num_input_tokens_seen": 7857712,
873
+ "step": 108
874
+ },
875
+ {
876
+ "epoch": 1.7975077881619939,
877
+ "grad_norm": 0.13539955019950867,
878
+ "learning_rate": 4.898899996577407e-05,
879
+ "loss": 0.3009,
880
+ "num_input_tokens_seen": 7916832,
881
+ "step": 109
882
+ },
883
+ {
884
+ "epoch": 1.814122533748702,
885
+ "grad_norm": 0.11198178678750992,
886
+ "learning_rate": 4.8970493371704826e-05,
887
+ "loss": 0.3229,
888
+ "num_input_tokens_seen": 7993056,
889
+ "step": 110
890
+ },
891
+ {
892
+ "epoch": 1.8307372793354102,
893
+ "grad_norm": 0.11881165206432343,
894
+ "learning_rate": 4.8951822486557986e-05,
895
+ "loss": 0.3414,
896
+ "num_input_tokens_seen": 8090056,
897
+ "step": 111
898
+ },
899
+ {
900
+ "epoch": 1.8473520249221185,
901
+ "grad_norm": 0.12841404974460602,
902
+ "learning_rate": 4.893298743830168e-05,
903
+ "loss": 0.2907,
904
+ "num_input_tokens_seen": 8164808,
905
+ "step": 112
906
+ },
907
+ {
908
+ "epoch": 1.8639667705088265,
909
+ "grad_norm": 0.14767521619796753,
910
+ "learning_rate": 4.891398835602925e-05,
911
+ "loss": 0.2901,
912
+ "num_input_tokens_seen": 8223568,
913
+ "step": 113
914
+ },
915
+ {
916
+ "epoch": 1.8805815160955348,
917
+ "grad_norm": 0.15326914191246033,
918
+ "learning_rate": 4.8894825369958255e-05,
919
+ "loss": 0.2918,
920
+ "num_input_tokens_seen": 8276160,
921
+ "step": 114
922
+ },
923
+ {
924
+ "epoch": 1.897196261682243,
925
+ "grad_norm": 0.1210051029920578,
926
+ "learning_rate": 4.8875498611429674e-05,
927
+ "loss": 0.3074,
928
+ "num_input_tokens_seen": 8354904,
929
+ "step": 115
930
+ },
931
+ {
932
+ "epoch": 1.9138110072689511,
933
+ "grad_norm": 0.13544373214244843,
934
+ "learning_rate": 4.8856008212906925e-05,
935
+ "loss": 0.3461,
936
+ "num_input_tokens_seen": 8442584,
937
+ "step": 116
938
+ },
939
+ {
940
+ "epoch": 1.9304257528556594,
941
+ "grad_norm": 0.13535892963409424,
942
+ "learning_rate": 4.8836354307975026e-05,
943
+ "loss": 0.3078,
944
+ "num_input_tokens_seen": 8506688,
945
+ "step": 117
946
+ },
947
+ {
948
+ "epoch": 1.9470404984423677,
949
+ "grad_norm": 0.10383590310811996,
950
+ "learning_rate": 4.881653703133966e-05,
951
+ "loss": 0.2432,
952
+ "num_input_tokens_seen": 8610712,
953
+ "step": 118
954
+ },
955
+ {
956
+ "epoch": 1.9636552440290758,
957
+ "grad_norm": 0.12125886976718903,
958
+ "learning_rate": 4.87965565188262e-05,
959
+ "loss": 0.2915,
960
+ "num_input_tokens_seen": 8692624,
961
+ "step": 119
962
+ },
963
+ {
964
+ "epoch": 1.980269989615784,
965
+ "grad_norm": 0.1351424902677536,
966
+ "learning_rate": 4.877641290737884e-05,
967
+ "loss": 0.3006,
968
+ "num_input_tokens_seen": 8772208,
969
+ "step": 120
970
+ },
971
+ {
972
+ "epoch": 1.9968847352024923,
973
+ "grad_norm": 0.11472523212432861,
974
+ "learning_rate": 4.8756106335059646e-05,
975
+ "loss": 0.2774,
976
+ "num_input_tokens_seen": 8854904,
977
+ "step": 121
978
+ },
979
+ {
980
+ "epoch": 2.0,
981
+ "grad_norm": 0.3606414794921875,
982
+ "learning_rate": 4.87356369410476e-05,
983
+ "loss": 0.2786,
984
+ "num_input_tokens_seen": 8872656,
985
+ "step": 122
986
+ },
987
+ {
988
+ "epoch": 2.016614745586708,
989
+ "grad_norm": 0.13124766945838928,
990
+ "learning_rate": 4.8715004865637614e-05,
991
+ "loss": 0.294,
992
+ "num_input_tokens_seen": 8946480,
993
+ "step": 123
994
+ },
995
+ {
996
+ "epoch": 2.0332294911734166,
997
+ "grad_norm": 0.12415049225091934,
998
+ "learning_rate": 4.869421025023965e-05,
999
+ "loss": 0.2931,
1000
+ "num_input_tokens_seen": 9023328,
1001
+ "step": 124
1002
+ },
1003
+ {
1004
+ "epoch": 2.0498442367601246,
1005
+ "grad_norm": 0.16626115143299103,
1006
+ "learning_rate": 4.867325323737765e-05,
1007
+ "loss": 0.2887,
1008
+ "num_input_tokens_seen": 9074320,
1009
+ "step": 125
1010
+ },
1011
+ {
1012
+ "epoch": 2.0664589823468327,
1013
+ "grad_norm": 0.153628870844841,
1014
+ "learning_rate": 4.8652133970688636e-05,
1015
+ "loss": 0.2776,
1016
+ "num_input_tokens_seen": 9148784,
1017
+ "step": 126
1018
+ },
1019
+ {
1020
+ "epoch": 2.083073727933541,
1021
+ "grad_norm": 0.12231138348579407,
1022
+ "learning_rate": 4.8630852594921706e-05,
1023
+ "loss": 0.3091,
1024
+ "num_input_tokens_seen": 9246624,
1025
+ "step": 127
1026
+ },
1027
+ {
1028
+ "epoch": 2.0996884735202492,
1029
+ "grad_norm": 0.15192057192325592,
1030
+ "learning_rate": 4.860940925593703e-05,
1031
+ "loss": 0.3354,
1032
+ "num_input_tokens_seen": 9328176,
1033
+ "step": 128
1034
+ },
1035
+ {
1036
+ "epoch": 2.1163032191069573,
1037
+ "grad_norm": 0.13820070028305054,
1038
+ "learning_rate": 4.8587804100704845e-05,
1039
+ "loss": 0.282,
1040
+ "num_input_tokens_seen": 9388936,
1041
+ "step": 129
1042
+ },
1043
+ {
1044
+ "epoch": 2.132917964693666,
1045
+ "grad_norm": 0.14466816186904907,
1046
+ "learning_rate": 4.856603727730447e-05,
1047
+ "loss": 0.2801,
1048
+ "num_input_tokens_seen": 9461664,
1049
+ "step": 130
1050
+ },
1051
+ {
1052
+ "epoch": 2.149532710280374,
1053
+ "grad_norm": 0.14671838283538818,
1054
+ "learning_rate": 4.854410893492326e-05,
1055
+ "loss": 0.2927,
1056
+ "num_input_tokens_seen": 9535000,
1057
+ "step": 131
1058
+ },
1059
+ {
1060
+ "epoch": 2.166147455867082,
1061
+ "grad_norm": 0.1757712960243225,
1062
+ "learning_rate": 4.852201922385564e-05,
1063
+ "loss": 0.2807,
1064
+ "num_input_tokens_seen": 9600296,
1065
+ "step": 132
1066
+ },
1067
+ {
1068
+ "epoch": 2.1827622014537904,
1069
+ "grad_norm": 0.17755423486232758,
1070
+ "learning_rate": 4.8499768295502004e-05,
1071
+ "loss": 0.2765,
1072
+ "num_input_tokens_seen": 9686784,
1073
+ "step": 133
1074
+ },
1075
+ {
1076
+ "epoch": 2.1993769470404985,
1077
+ "grad_norm": 0.13321827352046967,
1078
+ "learning_rate": 4.847735630236773e-05,
1079
+ "loss": 0.3068,
1080
+ "num_input_tokens_seen": 9781112,
1081
+ "step": 134
1082
+ },
1083
+ {
1084
+ "epoch": 2.2159916926272065,
1085
+ "grad_norm": 0.15012745559215546,
1086
+ "learning_rate": 4.8454783398062106e-05,
1087
+ "loss": 0.2737,
1088
+ "num_input_tokens_seen": 9849528,
1089
+ "step": 135
1090
+ },
1091
+ {
1092
+ "epoch": 2.232606438213915,
1093
+ "grad_norm": 0.14000360667705536,
1094
+ "learning_rate": 4.843204973729729e-05,
1095
+ "loss": 0.2831,
1096
+ "num_input_tokens_seen": 9931080,
1097
+ "step": 136
1098
+ },
1099
+ {
1100
+ "epoch": 2.249221183800623,
1101
+ "grad_norm": 0.14742712676525116,
1102
+ "learning_rate": 4.840915547588725e-05,
1103
+ "loss": 0.3047,
1104
+ "num_input_tokens_seen": 10011176,
1105
+ "step": 137
1106
+ },
1107
+ {
1108
+ "epoch": 2.265835929387331,
1109
+ "grad_norm": 0.16192346811294556,
1110
+ "learning_rate": 4.838610077074669e-05,
1111
+ "loss": 0.2759,
1112
+ "num_input_tokens_seen": 10084128,
1113
+ "step": 138
1114
+ },
1115
+ {
1116
+ "epoch": 2.2824506749740396,
1117
+ "grad_norm": 0.1502583771944046,
1118
+ "learning_rate": 4.836288577988996e-05,
1119
+ "loss": 0.298,
1120
+ "num_input_tokens_seen": 10155536,
1121
+ "step": 139
1122
+ },
1123
+ {
1124
+ "epoch": 2.2990654205607477,
1125
+ "grad_norm": 0.12661044299602509,
1126
+ "learning_rate": 4.8339510662430046e-05,
1127
+ "loss": 0.255,
1128
+ "num_input_tokens_seen": 10251160,
1129
+ "step": 140
1130
+ },
1131
+ {
1132
+ "epoch": 2.3156801661474558,
1133
+ "grad_norm": 0.14002998173236847,
1134
+ "learning_rate": 4.8315975578577355e-05,
1135
+ "loss": 0.2566,
1136
+ "num_input_tokens_seen": 10345864,
1137
+ "step": 141
1138
+ },
1139
+ {
1140
+ "epoch": 2.3322949117341643,
1141
+ "grad_norm": 0.17870523035526276,
1142
+ "learning_rate": 4.8292280689638725e-05,
1143
+ "loss": 0.4367,
1144
+ "num_input_tokens_seen": 10417616,
1145
+ "step": 142
1146
+ },
1147
+ {
1148
+ "epoch": 2.3489096573208723,
1149
+ "grad_norm": 0.17209866642951965,
1150
+ "learning_rate": 4.826842615801628e-05,
1151
+ "loss": 0.2954,
1152
+ "num_input_tokens_seen": 10481816,
1153
+ "step": 143
1154
+ },
1155
+ {
1156
+ "epoch": 2.3655244029075804,
1157
+ "grad_norm": 0.1665940284729004,
1158
+ "learning_rate": 4.8244412147206284e-05,
1159
+ "loss": 0.341,
1160
+ "num_input_tokens_seen": 10562056,
1161
+ "step": 144
1162
+ },
1163
+ {
1164
+ "epoch": 2.382139148494289,
1165
+ "grad_norm": 0.18919898569583893,
1166
+ "learning_rate": 4.822023882179811e-05,
1167
+ "loss": 0.2716,
1168
+ "num_input_tokens_seen": 10612808,
1169
+ "step": 145
1170
+ },
1171
+ {
1172
+ "epoch": 2.398753894080997,
1173
+ "grad_norm": 0.1681865006685257,
1174
+ "learning_rate": 4.8195906347473e-05,
1175
+ "loss": 0.2716,
1176
+ "num_input_tokens_seen": 10682328,
1177
+ "step": 146
1178
+ },
1179
+ {
1180
+ "epoch": 2.415368639667705,
1181
+ "grad_norm": 0.13141104578971863,
1182
+ "learning_rate": 4.817141489100302e-05,
1183
+ "loss": 0.2829,
1184
+ "num_input_tokens_seen": 10771912,
1185
+ "step": 147
1186
+ },
1187
+ {
1188
+ "epoch": 2.431983385254413,
1189
+ "grad_norm": 0.16544249653816223,
1190
+ "learning_rate": 4.814676462024988e-05,
1191
+ "loss": 0.3038,
1192
+ "num_input_tokens_seen": 10842232,
1193
+ "step": 148
1194
+ },
1195
+ {
1196
+ "epoch": 2.4485981308411215,
1197
+ "grad_norm": 0.17946277558803558,
1198
+ "learning_rate": 4.8121955704163745e-05,
1199
+ "loss": 0.2792,
1200
+ "num_input_tokens_seen": 10902264,
1201
+ "step": 149
1202
+ },
1203
+ {
1204
+ "epoch": 2.4652128764278296,
1205
+ "grad_norm": 0.14012685418128967,
1206
+ "learning_rate": 4.8096988312782174e-05,
1207
+ "loss": 0.2403,
1208
+ "num_input_tokens_seen": 10992744,
1209
+ "step": 150
1210
+ },
1211
+ {
1212
+ "epoch": 2.4818276220145377,
1213
+ "grad_norm": 0.103813536465168,
1214
+ "learning_rate": 4.8071862617228855e-05,
1215
+ "loss": 0.1605,
1216
+ "num_input_tokens_seen": 11090064,
1217
+ "step": 151
1218
+ },
1219
+ {
1220
+ "epoch": 2.498442367601246,
1221
+ "grad_norm": 0.1596001833677292,
1222
+ "learning_rate": 4.8046578789712515e-05,
1223
+ "loss": 0.2547,
1224
+ "num_input_tokens_seen": 11162864,
1225
+ "step": 152
1226
+ },
1227
+ {
1228
+ "epoch": 2.515057113187954,
1229
+ "grad_norm": 0.17366129159927368,
1230
+ "learning_rate": 4.8021137003525664e-05,
1231
+ "loss": 0.2676,
1232
+ "num_input_tokens_seen": 11224368,
1233
+ "step": 153
1234
+ },
1235
+ {
1236
+ "epoch": 2.5316718587746623,
1237
+ "grad_norm": 0.1615227609872818,
1238
+ "learning_rate": 4.7995537433043446e-05,
1239
+ "loss": 0.2898,
1240
+ "num_input_tokens_seen": 11291056,
1241
+ "step": 154
1242
+ },
1243
+ {
1244
+ "epoch": 2.5482866043613708,
1245
+ "grad_norm": 0.1951528787612915,
1246
+ "learning_rate": 4.796978025372246e-05,
1247
+ "loss": 0.2546,
1248
+ "num_input_tokens_seen": 11345464,
1249
+ "step": 155
1250
+ },
1251
+ {
1252
+ "epoch": 2.564901349948079,
1253
+ "grad_norm": 0.15065862238407135,
1254
+ "learning_rate": 4.794386564209953e-05,
1255
+ "loss": 0.3134,
1256
+ "num_input_tokens_seen": 11418912,
1257
+ "step": 156
1258
+ },
1259
+ {
1260
+ "epoch": 2.581516095534787,
1261
+ "grad_norm": 0.17094938457012177,
1262
+ "learning_rate": 4.79177937757905e-05,
1263
+ "loss": 0.2689,
1264
+ "num_input_tokens_seen": 11491216,
1265
+ "step": 157
1266
+ },
1267
+ {
1268
+ "epoch": 2.5981308411214954,
1269
+ "grad_norm": 0.16850312054157257,
1270
+ "learning_rate": 4.7891564833489035e-05,
1271
+ "loss": 0.2359,
1272
+ "num_input_tokens_seen": 11558016,
1273
+ "step": 158
1274
+ },
1275
+ {
1276
+ "epoch": 2.6147455867082035,
1277
+ "grad_norm": 0.16789822280406952,
1278
+ "learning_rate": 4.7865178994965344e-05,
1279
+ "loss": 0.2735,
1280
+ "num_input_tokens_seen": 11630432,
1281
+ "step": 159
1282
+ },
1283
+ {
1284
+ "epoch": 2.6313603322949115,
1285
+ "grad_norm": 0.19538354873657227,
1286
+ "learning_rate": 4.783863644106502e-05,
1287
+ "loss": 0.254,
1288
+ "num_input_tokens_seen": 11684624,
1289
+ "step": 160
1290
+ },
1291
+ {
1292
+ "epoch": 2.64797507788162,
1293
+ "grad_norm": 0.1609475016593933,
1294
+ "learning_rate": 4.781193735370777e-05,
1295
+ "loss": 0.2763,
1296
+ "num_input_tokens_seen": 11770232,
1297
+ "step": 161
1298
+ },
1299
+ {
1300
+ "epoch": 2.664589823468328,
1301
+ "grad_norm": 0.1964447796344757,
1302
+ "learning_rate": 4.7785081915886134e-05,
1303
+ "loss": 0.2663,
1304
+ "num_input_tokens_seen": 11828360,
1305
+ "step": 162
1306
+ },
1307
+ {
1308
+ "epoch": 2.681204569055036,
1309
+ "grad_norm": 0.18869946897029877,
1310
+ "learning_rate": 4.775807031166428e-05,
1311
+ "loss": 0.2625,
1312
+ "num_input_tokens_seen": 11915944,
1313
+ "step": 163
1314
+ },
1315
+ {
1316
+ "epoch": 2.6978193146417446,
1317
+ "grad_norm": 0.20539921522140503,
1318
+ "learning_rate": 4.773090272617672e-05,
1319
+ "loss": 0.2615,
1320
+ "num_input_tokens_seen": 11981792,
1321
+ "step": 164
1322
+ },
1323
+ {
1324
+ "epoch": 2.7144340602284527,
1325
+ "grad_norm": 0.1616145521402359,
1326
+ "learning_rate": 4.7703579345627035e-05,
1327
+ "loss": 0.3453,
1328
+ "num_input_tokens_seen": 12044024,
1329
+ "step": 165
1330
+ },
1331
+ {
1332
+ "epoch": 2.7310488058151607,
1333
+ "grad_norm": 0.22601978480815887,
1334
+ "learning_rate": 4.7676100357286624e-05,
1335
+ "loss": 0.3036,
1336
+ "num_input_tokens_seen": 12093424,
1337
+ "step": 166
1338
+ },
1339
+ {
1340
+ "epoch": 2.7476635514018692,
1341
+ "grad_norm": 0.15262462198734283,
1342
+ "learning_rate": 4.76484659494934e-05,
1343
+ "loss": 0.2523,
1344
+ "num_input_tokens_seen": 12167792,
1345
+ "step": 167
1346
+ },
1347
+ {
1348
+ "epoch": 2.7642782969885773,
1349
+ "grad_norm": 0.17928001284599304,
1350
+ "learning_rate": 4.762067631165049e-05,
1351
+ "loss": 0.2791,
1352
+ "num_input_tokens_seen": 12233712,
1353
+ "step": 168
1354
+ },
1355
+ {
1356
+ "epoch": 2.7808930425752854,
1357
+ "grad_norm": 0.15228766202926636,
1358
+ "learning_rate": 4.7592731634224966e-05,
1359
+ "loss": 0.2291,
1360
+ "num_input_tokens_seen": 12310544,
1361
+ "step": 169
1362
+ },
1363
+ {
1364
+ "epoch": 2.797507788161994,
1365
+ "grad_norm": 0.18862110376358032,
1366
+ "learning_rate": 4.756463210874652e-05,
1367
+ "loss": 0.2628,
1368
+ "num_input_tokens_seen": 12400160,
1369
+ "step": 170
1370
+ },
1371
+ {
1372
+ "epoch": 2.814122533748702,
1373
+ "grad_norm": 0.16640189290046692,
1374
+ "learning_rate": 4.753637792780614e-05,
1375
+ "loss": 0.2824,
1376
+ "num_input_tokens_seen": 12480432,
1377
+ "step": 171
1378
+ },
1379
+ {
1380
+ "epoch": 2.83073727933541,
1381
+ "grad_norm": 0.151117205619812,
1382
+ "learning_rate": 4.7507969285054845e-05,
1383
+ "loss": 0.2663,
1384
+ "num_input_tokens_seen": 12568064,
1385
+ "step": 172
1386
+ },
1387
+ {
1388
+ "epoch": 2.8473520249221185,
1389
+ "grad_norm": 0.26551589369773865,
1390
+ "learning_rate": 4.7479406375202264e-05,
1391
+ "loss": 0.28,
1392
+ "num_input_tokens_seen": 12647400,
1393
+ "step": 173
1394
+ },
1395
+ {
1396
+ "epoch": 2.8639667705088265,
1397
+ "grad_norm": 0.22416891157627106,
1398
+ "learning_rate": 4.745068939401539e-05,
1399
+ "loss": 0.2424,
1400
+ "num_input_tokens_seen": 12698208,
1401
+ "step": 174
1402
+ },
1403
+ {
1404
+ "epoch": 2.8805815160955346,
1405
+ "grad_norm": 0.2024654597043991,
1406
+ "learning_rate": 4.742181853831721e-05,
1407
+ "loss": 0.2518,
1408
+ "num_input_tokens_seen": 12758528,
1409
+ "step": 175
1410
+ },
1411
+ {
1412
+ "epoch": 2.897196261682243,
1413
+ "grad_norm": 0.18288369476795197,
1414
+ "learning_rate": 4.7392794005985326e-05,
1415
+ "loss": 0.259,
1416
+ "num_input_tokens_seen": 12837264,
1417
+ "step": 176
1418
+ },
1419
+ {
1420
+ "epoch": 2.913811007268951,
1421
+ "grad_norm": 0.18088208138942719,
1422
+ "learning_rate": 4.7363615995950626e-05,
1423
+ "loss": 0.247,
1424
+ "num_input_tokens_seen": 12902368,
1425
+ "step": 177
1426
+ },
1427
+ {
1428
+ "epoch": 2.930425752855659,
1429
+ "grad_norm": 0.16595424711704254,
1430
+ "learning_rate": 4.733428470819594e-05,
1431
+ "loss": 0.2438,
1432
+ "num_input_tokens_seen": 12974296,
1433
+ "step": 178
1434
+ },
1435
+ {
1436
+ "epoch": 2.9470404984423677,
1437
+ "grad_norm": 0.17989091575145721,
1438
+ "learning_rate": 4.730480034375462e-05,
1439
+ "loss": 0.2708,
1440
+ "num_input_tokens_seen": 13057280,
1441
+ "step": 179
1442
+ },
1443
+ {
1444
+ "epoch": 2.9636552440290758,
1445
+ "grad_norm": 0.16136637330055237,
1446
+ "learning_rate": 4.72751631047092e-05,
1447
+ "loss": 0.3171,
1448
+ "num_input_tokens_seen": 13158232,
1449
+ "step": 180
1450
+ },
1451
+ {
1452
+ "epoch": 2.980269989615784,
1453
+ "grad_norm": 0.1870911419391632,
1454
+ "learning_rate": 4.7245373194189994e-05,
1455
+ "loss": 0.24,
1456
+ "num_input_tokens_seen": 13229840,
1457
+ "step": 181
1458
+ },
1459
+ {
1460
+ "epoch": 2.9968847352024923,
1461
+ "grad_norm": 0.1857272833585739,
1462
+ "learning_rate": 4.7215430816373726e-05,
1463
+ "loss": 0.2674,
1464
+ "num_input_tokens_seen": 13296520,
1465
+ "step": 182
1466
+ },
1467
+ {
1468
+ "epoch": 3.0,
1469
+ "grad_norm": 0.31230616569519043,
1470
+ "learning_rate": 4.718533617648209e-05,
1471
+ "loss": 0.1677,
1472
+ "num_input_tokens_seen": 13309672,
1473
+ "step": 183
1474
+ },
1475
+ {
1476
+ "epoch": 3.016614745586708,
1477
+ "grad_norm": 0.20352481305599213,
1478
+ "learning_rate": 4.715508948078037e-05,
1479
+ "loss": 0.2272,
1480
+ "num_input_tokens_seen": 13371544,
1481
+ "step": 184
1482
+ },
1483
+ {
1484
+ "epoch": 3.0332294911734166,
1485
+ "grad_norm": 0.20679159462451935,
1486
+ "learning_rate": 4.712469093657605e-05,
1487
+ "loss": 0.2133,
1488
+ "num_input_tokens_seen": 13432984,
1489
+ "step": 185
1490
+ },
1491
+ {
1492
+ "epoch": 3.0498442367601246,
1493
+ "grad_norm": 0.18731139600276947,
1494
+ "learning_rate": 4.709414075221734e-05,
1495
+ "loss": 0.2695,
1496
+ "num_input_tokens_seen": 13500016,
1497
+ "step": 186
1498
+ },
1499
+ {
1500
+ "epoch": 3.0664589823468327,
1501
+ "grad_norm": 0.21216924488544464,
1502
+ "learning_rate": 4.706343913709178e-05,
1503
+ "loss": 0.2524,
1504
+ "num_input_tokens_seen": 13579672,
1505
+ "step": 187
1506
+ },
1507
+ {
1508
+ "epoch": 3.083073727933541,
1509
+ "grad_norm": 0.2222682386636734,
1510
+ "learning_rate": 4.70325863016248e-05,
1511
+ "loss": 0.2396,
1512
+ "num_input_tokens_seen": 13630704,
1513
+ "step": 188
1514
+ },
1515
+ {
1516
+ "epoch": 3.0996884735202492,
1517
+ "grad_norm": 0.21611332893371582,
1518
+ "learning_rate": 4.7001582457278304e-05,
1519
+ "loss": 0.3057,
1520
+ "num_input_tokens_seen": 13695472,
1521
+ "step": 189
1522
+ },
1523
+ {
1524
+ "epoch": 3.1163032191069573,
1525
+ "grad_norm": 0.23094947636127472,
1526
+ "learning_rate": 4.697042781654913e-05,
1527
+ "loss": 0.2436,
1528
+ "num_input_tokens_seen": 13767792,
1529
+ "step": 190
1530
+ },
1531
+ {
1532
+ "epoch": 3.132917964693666,
1533
+ "grad_norm": 0.19241105020046234,
1534
+ "learning_rate": 4.693912259296773e-05,
1535
+ "loss": 0.2974,
1536
+ "num_input_tokens_seen": 13857352,
1537
+ "step": 191
1538
+ },
1539
+ {
1540
+ "epoch": 3.149532710280374,
1541
+ "grad_norm": 0.19635124504566193,
1542
+ "learning_rate": 4.690766700109659e-05,
1543
+ "loss": 0.2457,
1544
+ "num_input_tokens_seen": 13939928,
1545
+ "step": 192
1546
+ },
1547
+ {
1548
+ "epoch": 3.166147455867082,
1549
+ "grad_norm": 0.1822366714477539,
1550
+ "learning_rate": 4.687606125652882e-05,
1551
+ "loss": 0.2205,
1552
+ "num_input_tokens_seen": 14017936,
1553
+ "step": 193
1554
+ },
1555
+ {
1556
+ "epoch": 3.1827622014537904,
1557
+ "grad_norm": 0.22182051837444305,
1558
+ "learning_rate": 4.684430557588664e-05,
1559
+ "loss": 0.2116,
1560
+ "num_input_tokens_seen": 14074176,
1561
+ "step": 194
1562
+ },
1563
+ {
1564
+ "epoch": 3.1993769470404985,
1565
+ "grad_norm": 0.19278937578201294,
1566
+ "learning_rate": 4.681240017681993e-05,
1567
+ "loss": 0.2839,
1568
+ "num_input_tokens_seen": 14167656,
1569
+ "step": 195
1570
+ },
1571
+ {
1572
+ "epoch": 3.2159916926272065,
1573
+ "grad_norm": 0.181584894657135,
1574
+ "learning_rate": 4.678034527800474e-05,
1575
+ "loss": 0.2115,
1576
+ "num_input_tokens_seen": 14235800,
1577
+ "step": 196
1578
+ },
1579
+ {
1580
+ "epoch": 3.232606438213915,
1581
+ "grad_norm": 0.19878999888896942,
1582
+ "learning_rate": 4.674814109914174e-05,
1583
+ "loss": 0.1982,
1584
+ "num_input_tokens_seen": 14301272,
1585
+ "step": 197
1586
+ },
1587
+ {
1588
+ "epoch": 3.249221183800623,
1589
+ "grad_norm": 0.23485153913497925,
1590
+ "learning_rate": 4.671578786095478e-05,
1591
+ "loss": 0.2494,
1592
+ "num_input_tokens_seen": 14347352,
1593
+ "step": 198
1594
+ },
1595
+ {
1596
+ "epoch": 3.265835929387331,
1597
+ "grad_norm": 0.20542015135288239,
1598
+ "learning_rate": 4.668328578518933e-05,
1599
+ "loss": 0.3186,
1600
+ "num_input_tokens_seen": 14434600,
1601
+ "step": 199
1602
+ },
1603
+ {
1604
+ "epoch": 3.2824506749740396,
1605
+ "grad_norm": 0.27169138193130493,
1606
+ "learning_rate": 4.665063509461097e-05,
1607
+ "loss": 0.2361,
1608
+ "num_input_tokens_seen": 14484104,
1609
+ "step": 200
1610
+ },
1611
+ {
1612
+ "epoch": 3.2990654205607477,
1613
+ "grad_norm": 0.18548518419265747,
1614
+ "learning_rate": 4.661783601300388e-05,
1615
+ "loss": 0.2457,
1616
+ "num_input_tokens_seen": 14567152,
1617
+ "step": 201
1618
+ },
1619
+ {
1620
+ "epoch": 3.3156801661474558,
1621
+ "grad_norm": 0.2257690727710724,
1622
+ "learning_rate": 4.6584888765169296e-05,
1623
+ "loss": 0.2885,
1624
+ "num_input_tokens_seen": 14647040,
1625
+ "step": 202
1626
+ },
1627
+ {
1628
+ "epoch": 3.3322949117341643,
1629
+ "grad_norm": 0.1882171332836151,
1630
+ "learning_rate": 4.6551793576923964e-05,
1631
+ "loss": 0.259,
1632
+ "num_input_tokens_seen": 14738216,
1633
+ "step": 203
1634
+ },
1635
+ {
1636
+ "epoch": 3.3489096573208723,
1637
+ "grad_norm": 0.1976601928472519,
1638
+ "learning_rate": 4.65185506750986e-05,
1639
+ "loss": 0.2102,
1640
+ "num_input_tokens_seen": 14811216,
1641
+ "step": 204
1642
+ },
1643
+ {
1644
+ "epoch": 3.3655244029075804,
1645
+ "grad_norm": 0.20320351421833038,
1646
+ "learning_rate": 4.648516028753632e-05,
1647
+ "loss": 0.1858,
1648
+ "num_input_tokens_seen": 14885992,
1649
+ "step": 205
1650
+ },
1651
+ {
1652
+ "epoch": 3.382139148494289,
1653
+ "grad_norm": 0.20090511441230774,
1654
+ "learning_rate": 4.645162264309112e-05,
1655
+ "loss": 0.272,
1656
+ "num_input_tokens_seen": 14961984,
1657
+ "step": 206
1658
+ },
1659
+ {
1660
+ "epoch": 3.398753894080997,
1661
+ "grad_norm": 0.21391013264656067,
1662
+ "learning_rate": 4.6417937971626245e-05,
1663
+ "loss": 0.2036,
1664
+ "num_input_tokens_seen": 15021240,
1665
+ "step": 207
1666
+ },
1667
+ {
1668
+ "epoch": 3.415368639667705,
1669
+ "grad_norm": 0.23000560700893402,
1670
+ "learning_rate": 4.638410650401267e-05,
1671
+ "loss": 0.2011,
1672
+ "num_input_tokens_seen": 15092016,
1673
+ "step": 208
1674
+ },
1675
+ {
1676
+ "epoch": 3.431983385254413,
1677
+ "grad_norm": 0.17034712433815002,
1678
+ "learning_rate": 4.635012847212748e-05,
1679
+ "loss": 0.2007,
1680
+ "num_input_tokens_seen": 15198192,
1681
+ "step": 209
1682
+ },
1683
+ {
1684
+ "epoch": 3.4485981308411215,
1685
+ "grad_norm": 0.23642270267009735,
1686
+ "learning_rate": 4.6316004108852305e-05,
1687
+ "loss": 0.2139,
1688
+ "num_input_tokens_seen": 15258432,
1689
+ "step": 210
1690
+ },
1691
+ {
1692
+ "epoch": 3.4652128764278296,
1693
+ "grad_norm": 0.22289924323558807,
1694
+ "learning_rate": 4.628173364807171e-05,
1695
+ "loss": 0.2441,
1696
+ "num_input_tokens_seen": 15329600,
1697
+ "step": 211
1698
+ },
1699
+ {
1700
+ "epoch": 3.4818276220145377,
1701
+ "grad_norm": 0.19895371794700623,
1702
+ "learning_rate": 4.6247317324671605e-05,
1703
+ "loss": 0.2368,
1704
+ "num_input_tokens_seen": 15407920,
1705
+ "step": 212
1706
+ },
1707
+ {
1708
+ "epoch": 3.498442367601246,
1709
+ "grad_norm": 0.19507868587970734,
1710
+ "learning_rate": 4.6212755374537596e-05,
1711
+ "loss": 0.231,
1712
+ "num_input_tokens_seen": 15479640,
1713
+ "step": 213
1714
+ },
1715
+ {
1716
+ "epoch": 3.515057113187954,
1717
+ "grad_norm": 0.23565508425235748,
1718
+ "learning_rate": 4.617804803455344e-05,
1719
+ "loss": 0.2336,
1720
+ "num_input_tokens_seen": 15561960,
1721
+ "step": 214
1722
+ },
1723
+ {
1724
+ "epoch": 3.5316718587746623,
1725
+ "grad_norm": 0.21157748997211456,
1726
+ "learning_rate": 4.614319554259934e-05,
1727
+ "loss": 0.2638,
1728
+ "num_input_tokens_seen": 15641440,
1729
+ "step": 215
1730
+ },
1731
+ {
1732
+ "epoch": 3.5482866043613708,
1733
+ "grad_norm": 0.2260795533657074,
1734
+ "learning_rate": 4.610819813755038e-05,
1735
+ "loss": 0.2646,
1736
+ "num_input_tokens_seen": 15728872,
1737
+ "step": 216
1738
+ },
1739
+ {
1740
+ "epoch": 3.564901349948079,
1741
+ "grad_norm": 0.20947663486003876,
1742
+ "learning_rate": 4.607305605927487e-05,
1743
+ "loss": 0.2211,
1744
+ "num_input_tokens_seen": 15798112,
1745
+ "step": 217
1746
+ },
1747
+ {
1748
+ "epoch": 3.581516095534787,
1749
+ "grad_norm": 0.22466345131397247,
1750
+ "learning_rate": 4.6037769548632656e-05,
1751
+ "loss": 0.2901,
1752
+ "num_input_tokens_seen": 15865936,
1753
+ "step": 218
1754
+ },
1755
+ {
1756
+ "epoch": 3.5981308411214954,
1757
+ "grad_norm": 0.2176472693681717,
1758
+ "learning_rate": 4.600233884747355e-05,
1759
+ "loss": 0.2713,
1760
+ "num_input_tokens_seen": 15941368,
1761
+ "step": 219
1762
+ },
1763
+ {
1764
+ "epoch": 3.6147455867082035,
1765
+ "grad_norm": 0.20593321323394775,
1766
+ "learning_rate": 4.5966764198635606e-05,
1767
+ "loss": 0.2047,
1768
+ "num_input_tokens_seen": 16028208,
1769
+ "step": 220
1770
+ },
1771
+ {
1772
+ "epoch": 3.6313603322949115,
1773
+ "grad_norm": 0.21239908039569855,
1774
+ "learning_rate": 4.5931045845943474e-05,
1775
+ "loss": 0.1872,
1776
+ "num_input_tokens_seen": 16104408,
1777
+ "step": 221
1778
+ },
1779
+ {
1780
+ "epoch": 3.64797507788162,
1781
+ "grad_norm": 0.22399188578128815,
1782
+ "learning_rate": 4.5895184034206765e-05,
1783
+ "loss": 0.3526,
1784
+ "num_input_tokens_seen": 16156800,
1785
+ "step": 222
1786
+ },
1787
+ {
1788
+ "epoch": 3.664589823468328,
1789
+ "grad_norm": 0.18427705764770508,
1790
+ "learning_rate": 4.585917900921829e-05,
1791
+ "loss": 0.2905,
1792
+ "num_input_tokens_seen": 16256712,
1793
+ "step": 223
1794
+ },
1795
+ {
1796
+ "epoch": 3.681204569055036,
1797
+ "grad_norm": 0.22559204697608948,
1798
+ "learning_rate": 4.5823031017752485e-05,
1799
+ "loss": 0.2014,
1800
+ "num_input_tokens_seen": 16330344,
1801
+ "step": 224
1802
+ },
1803
+ {
1804
+ "epoch": 3.6978193146417446,
1805
+ "grad_norm": 0.22590497136116028,
1806
+ "learning_rate": 4.5786740307563636e-05,
1807
+ "loss": 0.2178,
1808
+ "num_input_tokens_seen": 16399792,
1809
+ "step": 225
1810
+ },
1811
+ {
1812
+ "epoch": 3.7144340602284527,
1813
+ "grad_norm": 0.20590999722480774,
1814
+ "learning_rate": 4.575030712738419e-05,
1815
+ "loss": 0.2149,
1816
+ "num_input_tokens_seen": 16466368,
1817
+ "step": 226
1818
+ },
1819
+ {
1820
+ "epoch": 3.7310488058151607,
1821
+ "grad_norm": 0.23313546180725098,
1822
+ "learning_rate": 4.571373172692309e-05,
1823
+ "loss": 0.2164,
1824
+ "num_input_tokens_seen": 16530976,
1825
+ "step": 227
1826
+ },
1827
+ {
1828
+ "epoch": 3.7476635514018692,
1829
+ "grad_norm": 0.2081821709871292,
1830
+ "learning_rate": 4.567701435686404e-05,
1831
+ "loss": 0.2197,
1832
+ "num_input_tokens_seen": 16600216,
1833
+ "step": 228
1834
+ },
1835
+ {
1836
+ "epoch": 3.7642782969885773,
1837
+ "grad_norm": 0.22633281350135803,
1838
+ "learning_rate": 4.5640155268863796e-05,
1839
+ "loss": 0.2527,
1840
+ "num_input_tokens_seen": 16673192,
1841
+ "step": 229
1842
+ },
1843
+ {
1844
+ "epoch": 3.7808930425752854,
1845
+ "grad_norm": 0.2317536324262619,
1846
+ "learning_rate": 4.5603154715550386e-05,
1847
+ "loss": 0.1974,
1848
+ "num_input_tokens_seen": 16739912,
1849
+ "step": 230
1850
+ },
1851
+ {
1852
+ "epoch": 3.797507788161994,
1853
+ "grad_norm": 0.18925197422504425,
1854
+ "learning_rate": 4.55660129505215e-05,
1855
+ "loss": 0.2098,
1856
+ "num_input_tokens_seen": 16834632,
1857
+ "step": 231
1858
+ },
1859
+ {
1860
+ "epoch": 3.814122533748702,
1861
+ "grad_norm": 0.1934100240468979,
1862
+ "learning_rate": 4.5528730228342605e-05,
1863
+ "loss": 0.2109,
1864
+ "num_input_tokens_seen": 16914728,
1865
+ "step": 232
1866
+ },
1867
+ {
1868
+ "epoch": 3.83073727933541,
1869
+ "grad_norm": 0.1923092156648636,
1870
+ "learning_rate": 4.549130680454532e-05,
1871
+ "loss": 0.2492,
1872
+ "num_input_tokens_seen": 17014304,
1873
+ "step": 233
1874
+ },
1875
+ {
1876
+ "epoch": 3.8473520249221185,
1877
+ "grad_norm": 0.2139277458190918,
1878
+ "learning_rate": 4.545374293562559e-05,
1879
+ "loss": 0.2415,
1880
+ "num_input_tokens_seen": 17106664,
1881
+ "step": 234
1882
+ },
1883
+ {
1884
+ "epoch": 3.8639667705088265,
1885
+ "grad_norm": 0.2056339681148529,
1886
+ "learning_rate": 4.541603887904198e-05,
1887
+ "loss": 0.2311,
1888
+ "num_input_tokens_seen": 17193744,
1889
+ "step": 235
1890
+ },
1891
+ {
1892
+ "epoch": 3.8805815160955346,
1893
+ "grad_norm": 0.2485012263059616,
1894
+ "learning_rate": 4.537819489321386e-05,
1895
+ "loss": 0.2309,
1896
+ "num_input_tokens_seen": 17254656,
1897
+ "step": 236
1898
+ },
1899
+ {
1900
+ "epoch": 3.897196261682243,
1901
+ "grad_norm": 0.21751578152179718,
1902
+ "learning_rate": 4.534021123751968e-05,
1903
+ "loss": 0.2334,
1904
+ "num_input_tokens_seen": 17325896,
1905
+ "step": 237
1906
+ },
1907
+ {
1908
+ "epoch": 3.913811007268951,
1909
+ "grad_norm": 0.27809038758277893,
1910
+ "learning_rate": 4.5302088172295156e-05,
1911
+ "loss": 0.2598,
1912
+ "num_input_tokens_seen": 17394424,
1913
+ "step": 238
1914
+ },
1915
+ {
1916
+ "epoch": 3.930425752855659,
1917
+ "grad_norm": 0.23579885065555573,
1918
+ "learning_rate": 4.526382595883152e-05,
1919
+ "loss": 0.2132,
1920
+ "num_input_tokens_seen": 17456352,
1921
+ "step": 239
1922
+ },
1923
+ {
1924
+ "epoch": 3.9470404984423677,
1925
+ "grad_norm": 0.2328771948814392,
1926
+ "learning_rate": 4.522542485937369e-05,
1927
+ "loss": 0.2139,
1928
+ "num_input_tokens_seen": 17519168,
1929
+ "step": 240
1930
+ }
1931
+ ],
1932
+ "logging_steps": 1.0,
1933
+ "max_steps": 1200,
1934
+ "num_input_tokens_seen": 17519168,
1935
+ "num_train_epochs": 20,
1936
+ "save_steps": 60,
1937
+ "stateful_callbacks": {
1938
+ "TrainerControl": {
1939
+ "args": {
1940
+ "should_epoch_stop": false,
1941
+ "should_evaluate": false,
1942
+ "should_log": false,
1943
+ "should_save": true,
1944
+ "should_training_stop": false
1945
+ },
1946
+ "attributes": {}
1947
+ }
1948
+ },
1949
+ "total_flos": 7.47471699057836e+17,
1950
+ "train_batch_size": 1,
1951
+ "trial_name": null,
1952
+ "trial_params": null
1953
+ }
checkpoint-240/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9746167dc82a516aeee83c5731c4b250770d2cfb0fb68a7cd590dc02bd3eb0d6
3
+ size 5688
checkpoint-240/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-300/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-Coder-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 0.12.0
checkpoint-300/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-Coder-7B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "down_proj",
24
+ "k_proj",
25
+ "v_proj",
26
+ "q_proj",
27
+ "o_proj",
28
+ "gate_proj",
29
+ "up_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-300/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a879eebee8194f633986cafcb81b465ac89ecad3d0d48fd23ab0e96f7ddd182
3
+ size 161533192
checkpoint-300/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
+ }