oodeh commited on
Commit
6f5926f
·
verified ·
1 Parent(s): a60a2a0

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 +1 -0
  2. checkpoint-1026/README.md +202 -0
  3. checkpoint-1026/adapter_config.json +34 -0
  4. checkpoint-1026/scheduler.pt +3 -0
  5. checkpoint-1026/training_args.bin +3 -0
  6. checkpoint-162/rng_state_0.pth +3 -0
  7. checkpoint-162/rng_state_1.pth +3 -0
  8. checkpoint-162/scheduler.pt +3 -0
  9. checkpoint-162/training_args.bin +3 -0
  10. checkpoint-216/rng_state_1.pth +3 -0
  11. checkpoint-270/rng_state_0.pth +3 -0
  12. checkpoint-270/scheduler.pt +3 -0
  13. checkpoint-324/merges.txt +0 -0
  14. checkpoint-324/trainer_state.json +2625 -0
  15. checkpoint-378/README.md +202 -0
  16. checkpoint-378/adapter_config.json +34 -0
  17. checkpoint-378/added_tokens.json +24 -0
  18. checkpoint-378/merges.txt +0 -0
  19. checkpoint-378/special_tokens_map.json +31 -0
  20. checkpoint-378/tokenizer_config.json +209 -0
  21. checkpoint-378/vocab.json +0 -0
  22. checkpoint-432/adapter_config.json +34 -0
  23. checkpoint-432/merges.txt +0 -0
  24. checkpoint-432/special_tokens_map.json +31 -0
  25. checkpoint-432/tokenizer_config.json +209 -0
  26. checkpoint-432/trainer_state.json +3489 -0
  27. checkpoint-432/vocab.json +0 -0
  28. checkpoint-486/README.md +202 -0
  29. checkpoint-486/adapter_config.json +34 -0
  30. checkpoint-486/added_tokens.json +24 -0
  31. checkpoint-486/merges.txt +0 -0
  32. checkpoint-486/special_tokens_map.json +31 -0
  33. checkpoint-486/tokenizer_config.json +209 -0
  34. checkpoint-486/trainer_state.json +0 -0
  35. checkpoint-486/vocab.json +0 -0
  36. checkpoint-540/README.md +202 -0
  37. checkpoint-540/adapter_config.json +34 -0
  38. checkpoint-540/added_tokens.json +24 -0
  39. checkpoint-540/merges.txt +0 -0
  40. checkpoint-540/special_tokens_map.json +31 -0
  41. checkpoint-540/tokenizer_config.json +209 -0
  42. checkpoint-540/trainer_state.json +0 -0
  43. checkpoint-540/vocab.json +0 -0
  44. checkpoint-594/README.md +202 -0
  45. checkpoint-594/adapter_config.json +34 -0
  46. checkpoint-594/added_tokens.json +24 -0
  47. checkpoint-594/merges.txt +0 -0
  48. checkpoint-594/special_tokens_map.json +31 -0
  49. checkpoint-594/tokenizer_config.json +209 -0
  50. checkpoint-594/trainer_state.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoint-1026/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-Coder-14B-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-1026/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-14B-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": 0.05,
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
+ "q_proj",
24
+ "v_proj",
25
+ "up_proj",
26
+ "gate_proj",
27
+ "o_proj",
28
+ "k_proj",
29
+ "down_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-1026/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf1ea04735033bc0224c950468a02fb1269feb4f8c9fa8854561f36195a9e832
3
+ size 1064
checkpoint-1026/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e70cdeaf6550b324dd30ee52fd6fb6259b3a65b6ec342b31522e38e2e66f88d
3
+ size 5688
checkpoint-162/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fff622f7715e6a8ed3f766771c62f005a755f047a2f49688861b07cfb708d70
3
+ size 14512
checkpoint-162/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f7afef3aa9dfeb2c7eba0ed2feddacd0a3f76d96d87a4b96377a3025f8b0e09
3
+ size 14512
checkpoint-162/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dac1c202cd7a96287d90bf25f318091a9e9fc77f4ad36899fa8e1ae6a903e81
3
+ size 1064
checkpoint-162/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e70cdeaf6550b324dd30ee52fd6fb6259b3a65b6ec342b31522e38e2e66f88d
3
+ size 5688
checkpoint-216/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da80e0d62556d8a210bb1310d9dd4c2f197962c8ed3b5a9a2d0a8efb3f81c5c4
3
+ size 14512
checkpoint-270/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff9d69a5fb63f7a32c497faaefe01d47695127e90d0f2ec59e41a3d94d941f01
3
+ size 14512
checkpoint-270/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55502e79f33694551e97d2b3fcffbea2fae603e5605d9c887f346ab3ecadf050
3
+ size 1064
checkpoint-324/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-324/trainer_state.json ADDED
@@ -0,0 +1,2625 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.89908256880734,
5
+ "eval_steps": 500,
6
+ "global_step": 324,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01834862385321101,
13
+ "grad_norm": 0.04378490149974823,
14
+ "learning_rate": 4.999989423013716e-05,
15
+ "loss": 0.6713,
16
+ "num_input_tokens_seen": 44136,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.03669724770642202,
21
+ "grad_norm": 0.040646992623806,
22
+ "learning_rate": 4.999957692144361e-05,
23
+ "loss": 0.533,
24
+ "num_input_tokens_seen": 83096,
25
+ "step": 2
26
+ },
27
+ {
28
+ "epoch": 0.05504587155963303,
29
+ "grad_norm": 0.04658753052353859,
30
+ "learning_rate": 4.999904807660428e-05,
31
+ "loss": 0.6048,
32
+ "num_input_tokens_seen": 122112,
33
+ "step": 3
34
+ },
35
+ {
36
+ "epoch": 0.07339449541284404,
37
+ "grad_norm": 0.04322144016623497,
38
+ "learning_rate": 4.999830770009406e-05,
39
+ "loss": 0.4948,
40
+ "num_input_tokens_seen": 163064,
41
+ "step": 4
42
+ },
43
+ {
44
+ "epoch": 0.09174311926605505,
45
+ "grad_norm": 0.06536195427179337,
46
+ "learning_rate": 4.999735579817769e-05,
47
+ "loss": 0.6607,
48
+ "num_input_tokens_seen": 203808,
49
+ "step": 5
50
+ },
51
+ {
52
+ "epoch": 0.11009174311926606,
53
+ "grad_norm": 0.059904925525188446,
54
+ "learning_rate": 4.9996192378909786e-05,
55
+ "loss": 0.5802,
56
+ "num_input_tokens_seen": 241824,
57
+ "step": 6
58
+ },
59
+ {
60
+ "epoch": 0.12844036697247707,
61
+ "grad_norm": 0.19818365573883057,
62
+ "learning_rate": 4.999481745213471e-05,
63
+ "loss": 0.5148,
64
+ "num_input_tokens_seen": 287608,
65
+ "step": 7
66
+ },
67
+ {
68
+ "epoch": 0.14678899082568808,
69
+ "grad_norm": 0.05985472351312637,
70
+ "learning_rate": 4.9993231029486544e-05,
71
+ "loss": 0.5714,
72
+ "num_input_tokens_seen": 325320,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.1651376146788991,
77
+ "grad_norm": 0.061375778168439865,
78
+ "learning_rate": 4.999143312438893e-05,
79
+ "loss": 0.6812,
80
+ "num_input_tokens_seen": 369848,
81
+ "step": 9
82
+ },
83
+ {
84
+ "epoch": 0.1834862385321101,
85
+ "grad_norm": 0.06196414306759834,
86
+ "learning_rate": 4.998942375205502e-05,
87
+ "loss": 0.5358,
88
+ "num_input_tokens_seen": 415104,
89
+ "step": 10
90
+ },
91
+ {
92
+ "epoch": 0.2018348623853211,
93
+ "grad_norm": 0.07861393690109253,
94
+ "learning_rate": 4.9987202929487275e-05,
95
+ "loss": 0.6527,
96
+ "num_input_tokens_seen": 467224,
97
+ "step": 11
98
+ },
99
+ {
100
+ "epoch": 0.22018348623853212,
101
+ "grad_norm": 0.05596446990966797,
102
+ "learning_rate": 4.99847706754774e-05,
103
+ "loss": 0.5354,
104
+ "num_input_tokens_seen": 502824,
105
+ "step": 12
106
+ },
107
+ {
108
+ "epoch": 0.23853211009174313,
109
+ "grad_norm": 0.05289844051003456,
110
+ "learning_rate": 4.998212701060612e-05,
111
+ "loss": 0.5263,
112
+ "num_input_tokens_seen": 544744,
113
+ "step": 13
114
+ },
115
+ {
116
+ "epoch": 0.25688073394495414,
117
+ "grad_norm": 0.04996591433882713,
118
+ "learning_rate": 4.997927195724303e-05,
119
+ "loss": 0.5536,
120
+ "num_input_tokens_seen": 591136,
121
+ "step": 14
122
+ },
123
+ {
124
+ "epoch": 0.27522935779816515,
125
+ "grad_norm": 0.05822828412055969,
126
+ "learning_rate": 4.997620553954645e-05,
127
+ "loss": 0.6106,
128
+ "num_input_tokens_seen": 629664,
129
+ "step": 15
130
+ },
131
+ {
132
+ "epoch": 0.29357798165137616,
133
+ "grad_norm": 0.06353770196437836,
134
+ "learning_rate": 4.997292778346312e-05,
135
+ "loss": 0.5129,
136
+ "num_input_tokens_seen": 663392,
137
+ "step": 16
138
+ },
139
+ {
140
+ "epoch": 0.3119266055045872,
141
+ "grad_norm": 0.07256966829299927,
142
+ "learning_rate": 4.996943871672807e-05,
143
+ "loss": 0.6377,
144
+ "num_input_tokens_seen": 698360,
145
+ "step": 17
146
+ },
147
+ {
148
+ "epoch": 0.3302752293577982,
149
+ "grad_norm": 0.055458713322877884,
150
+ "learning_rate": 4.996573836886435e-05,
151
+ "loss": 0.4083,
152
+ "num_input_tokens_seen": 737520,
153
+ "step": 18
154
+ },
155
+ {
156
+ "epoch": 0.3486238532110092,
157
+ "grad_norm": 0.07792335003614426,
158
+ "learning_rate": 4.9961826771182784e-05,
159
+ "loss": 0.6086,
160
+ "num_input_tokens_seen": 768056,
161
+ "step": 19
162
+ },
163
+ {
164
+ "epoch": 0.3669724770642202,
165
+ "grad_norm": 0.06627275049686432,
166
+ "learning_rate": 4.995770395678171e-05,
167
+ "loss": 0.4591,
168
+ "num_input_tokens_seen": 806256,
169
+ "step": 20
170
+ },
171
+ {
172
+ "epoch": 0.3853211009174312,
173
+ "grad_norm": 0.05830290913581848,
174
+ "learning_rate": 4.9953369960546676e-05,
175
+ "loss": 0.3731,
176
+ "num_input_tokens_seen": 842336,
177
+ "step": 21
178
+ },
179
+ {
180
+ "epoch": 0.4036697247706422,
181
+ "grad_norm": 0.07277437299489975,
182
+ "learning_rate": 4.9948824819150185e-05,
183
+ "loss": 0.6243,
184
+ "num_input_tokens_seen": 876672,
185
+ "step": 22
186
+ },
187
+ {
188
+ "epoch": 0.42201834862385323,
189
+ "grad_norm": 0.07477546483278275,
190
+ "learning_rate": 4.994406857105136e-05,
191
+ "loss": 0.5788,
192
+ "num_input_tokens_seen": 915192,
193
+ "step": 23
194
+ },
195
+ {
196
+ "epoch": 0.44036697247706424,
197
+ "grad_norm": 0.06912907212972641,
198
+ "learning_rate": 4.993910125649561e-05,
199
+ "loss": 0.4753,
200
+ "num_input_tokens_seen": 951904,
201
+ "step": 24
202
+ },
203
+ {
204
+ "epoch": 0.45871559633027525,
205
+ "grad_norm": 0.0655476376414299,
206
+ "learning_rate": 4.993392291751431e-05,
207
+ "loss": 0.4518,
208
+ "num_input_tokens_seen": 1001816,
209
+ "step": 25
210
+ },
211
+ {
212
+ "epoch": 0.47706422018348627,
213
+ "grad_norm": 0.06466512382030487,
214
+ "learning_rate": 4.992853359792444e-05,
215
+ "loss": 0.5638,
216
+ "num_input_tokens_seen": 1053064,
217
+ "step": 26
218
+ },
219
+ {
220
+ "epoch": 0.4954128440366973,
221
+ "grad_norm": 0.0645688995718956,
222
+ "learning_rate": 4.99229333433282e-05,
223
+ "loss": 0.4644,
224
+ "num_input_tokens_seen": 1086688,
225
+ "step": 27
226
+ },
227
+ {
228
+ "epoch": 0.5137614678899083,
229
+ "grad_norm": 0.07181251049041748,
230
+ "learning_rate": 4.9917122201112656e-05,
231
+ "loss": 0.6191,
232
+ "num_input_tokens_seen": 1134824,
233
+ "step": 28
234
+ },
235
+ {
236
+ "epoch": 0.5321100917431193,
237
+ "grad_norm": 0.07322589308023453,
238
+ "learning_rate": 4.9911100220449293e-05,
239
+ "loss": 0.6752,
240
+ "num_input_tokens_seen": 1172072,
241
+ "step": 29
242
+ },
243
+ {
244
+ "epoch": 0.5504587155963303,
245
+ "grad_norm": 0.06396070122718811,
246
+ "learning_rate": 4.990486745229364e-05,
247
+ "loss": 0.3587,
248
+ "num_input_tokens_seen": 1211096,
249
+ "step": 30
250
+ },
251
+ {
252
+ "epoch": 0.5688073394495413,
253
+ "grad_norm": 0.07803395390510559,
254
+ "learning_rate": 4.989842394938482e-05,
255
+ "loss": 0.459,
256
+ "num_input_tokens_seen": 1259456,
257
+ "step": 31
258
+ },
259
+ {
260
+ "epoch": 0.5871559633027523,
261
+ "grad_norm": 0.05974648892879486,
262
+ "learning_rate": 4.989176976624511e-05,
263
+ "loss": 0.4148,
264
+ "num_input_tokens_seen": 1306944,
265
+ "step": 32
266
+ },
267
+ {
268
+ "epoch": 0.6055045871559633,
269
+ "grad_norm": 0.09784268587827682,
270
+ "learning_rate": 4.988490495917947e-05,
271
+ "loss": 0.539,
272
+ "num_input_tokens_seen": 1353744,
273
+ "step": 33
274
+ },
275
+ {
276
+ "epoch": 0.6238532110091743,
277
+ "grad_norm": 0.09906516224145889,
278
+ "learning_rate": 4.987782958627508e-05,
279
+ "loss": 0.5453,
280
+ "num_input_tokens_seen": 1394736,
281
+ "step": 34
282
+ },
283
+ {
284
+ "epoch": 0.6422018348623854,
285
+ "grad_norm": 0.08984062820672989,
286
+ "learning_rate": 4.987054370740083e-05,
287
+ "loss": 0.468,
288
+ "num_input_tokens_seen": 1442048,
289
+ "step": 35
290
+ },
291
+ {
292
+ "epoch": 0.6605504587155964,
293
+ "grad_norm": 0.08672655373811722,
294
+ "learning_rate": 4.9863047384206835e-05,
295
+ "loss": 0.4078,
296
+ "num_input_tokens_seen": 1478440,
297
+ "step": 36
298
+ },
299
+ {
300
+ "epoch": 0.6788990825688074,
301
+ "grad_norm": 0.1327345073223114,
302
+ "learning_rate": 4.9855340680123905e-05,
303
+ "loss": 0.5299,
304
+ "num_input_tokens_seen": 1525992,
305
+ "step": 37
306
+ },
307
+ {
308
+ "epoch": 0.6972477064220184,
309
+ "grad_norm": 0.09178602695465088,
310
+ "learning_rate": 4.9847423660363e-05,
311
+ "loss": 0.439,
312
+ "num_input_tokens_seen": 1555608,
313
+ "step": 38
314
+ },
315
+ {
316
+ "epoch": 0.7155963302752294,
317
+ "grad_norm": 0.09418320655822754,
318
+ "learning_rate": 4.983929639191469e-05,
319
+ "loss": 0.5337,
320
+ "num_input_tokens_seen": 1597392,
321
+ "step": 39
322
+ },
323
+ {
324
+ "epoch": 0.7339449541284404,
325
+ "grad_norm": 0.08294719457626343,
326
+ "learning_rate": 4.983095894354858e-05,
327
+ "loss": 0.4536,
328
+ "num_input_tokens_seen": 1649656,
329
+ "step": 40
330
+ },
331
+ {
332
+ "epoch": 0.7522935779816514,
333
+ "grad_norm": 0.09774205833673477,
334
+ "learning_rate": 4.982241138581273e-05,
335
+ "loss": 0.5221,
336
+ "num_input_tokens_seen": 1695952,
337
+ "step": 41
338
+ },
339
+ {
340
+ "epoch": 0.7706422018348624,
341
+ "grad_norm": 0.09319107979536057,
342
+ "learning_rate": 4.9813653791033057e-05,
343
+ "loss": 0.4279,
344
+ "num_input_tokens_seen": 1737224,
345
+ "step": 42
346
+ },
347
+ {
348
+ "epoch": 0.7889908256880734,
349
+ "grad_norm": 0.09561405330896378,
350
+ "learning_rate": 4.980468623331273e-05,
351
+ "loss": 0.5121,
352
+ "num_input_tokens_seen": 1772320,
353
+ "step": 43
354
+ },
355
+ {
356
+ "epoch": 0.8073394495412844,
357
+ "grad_norm": 0.08274025470018387,
358
+ "learning_rate": 4.979550878853154e-05,
359
+ "loss": 0.54,
360
+ "num_input_tokens_seen": 1823888,
361
+ "step": 44
362
+ },
363
+ {
364
+ "epoch": 0.8256880733944955,
365
+ "grad_norm": 0.08728913217782974,
366
+ "learning_rate": 4.9786121534345265e-05,
367
+ "loss": 0.4488,
368
+ "num_input_tokens_seen": 1872488,
369
+ "step": 45
370
+ },
371
+ {
372
+ "epoch": 0.8440366972477065,
373
+ "grad_norm": 0.0787016749382019,
374
+ "learning_rate": 4.9776524550184965e-05,
375
+ "loss": 0.4353,
376
+ "num_input_tokens_seen": 1924744,
377
+ "step": 46
378
+ },
379
+ {
380
+ "epoch": 0.8623853211009175,
381
+ "grad_norm": 0.10952188074588776,
382
+ "learning_rate": 4.97667179172564e-05,
383
+ "loss": 0.4784,
384
+ "num_input_tokens_seen": 1959936,
385
+ "step": 47
386
+ },
387
+ {
388
+ "epoch": 0.8807339449541285,
389
+ "grad_norm": 0.08525826781988144,
390
+ "learning_rate": 4.975670171853926e-05,
391
+ "loss": 0.3586,
392
+ "num_input_tokens_seen": 2003896,
393
+ "step": 48
394
+ },
395
+ {
396
+ "epoch": 0.8990825688073395,
397
+ "grad_norm": 0.10409987717866898,
398
+ "learning_rate": 4.9746476038786496e-05,
399
+ "loss": 0.4451,
400
+ "num_input_tokens_seen": 2047632,
401
+ "step": 49
402
+ },
403
+ {
404
+ "epoch": 0.9174311926605505,
405
+ "grad_norm": 0.0782993957400322,
406
+ "learning_rate": 4.973604096452361e-05,
407
+ "loss": 0.3591,
408
+ "num_input_tokens_seen": 2096928,
409
+ "step": 50
410
+ },
411
+ {
412
+ "epoch": 0.9357798165137615,
413
+ "grad_norm": 0.09829951077699661,
414
+ "learning_rate": 4.9725396584047925e-05,
415
+ "loss": 0.3415,
416
+ "num_input_tokens_seen": 2129536,
417
+ "step": 51
418
+ },
419
+ {
420
+ "epoch": 0.9541284403669725,
421
+ "grad_norm": 0.10606162995100021,
422
+ "learning_rate": 4.971454298742779e-05,
423
+ "loss": 0.3758,
424
+ "num_input_tokens_seen": 2169144,
425
+ "step": 52
426
+ },
427
+ {
428
+ "epoch": 0.9724770642201835,
429
+ "grad_norm": 0.09280356764793396,
430
+ "learning_rate": 4.97034802665019e-05,
431
+ "loss": 0.485,
432
+ "num_input_tokens_seen": 2207720,
433
+ "step": 53
434
+ },
435
+ {
436
+ "epoch": 0.9908256880733946,
437
+ "grad_norm": 0.11888203024864197,
438
+ "learning_rate": 4.9692208514878444e-05,
439
+ "loss": 0.3469,
440
+ "num_input_tokens_seen": 2236392,
441
+ "step": 54
442
+ },
443
+ {
444
+ "epoch": 1.0,
445
+ "grad_norm": 0.13222463428974152,
446
+ "learning_rate": 4.9680727827934354e-05,
447
+ "loss": 0.4284,
448
+ "num_input_tokens_seen": 2259088,
449
+ "step": 55
450
+ },
451
+ {
452
+ "epoch": 1.018348623853211,
453
+ "grad_norm": 0.10572745651006699,
454
+ "learning_rate": 4.966903830281449e-05,
455
+ "loss": 0.4186,
456
+ "num_input_tokens_seen": 2298496,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 1.036697247706422,
461
+ "grad_norm": 0.11462350189685822,
462
+ "learning_rate": 4.965714003843079e-05,
463
+ "loss": 0.4696,
464
+ "num_input_tokens_seen": 2333016,
465
+ "step": 57
466
+ },
467
+ {
468
+ "epoch": 1.0550458715596331,
469
+ "grad_norm": 0.11215240508317947,
470
+ "learning_rate": 4.9645033135461494e-05,
471
+ "loss": 0.3905,
472
+ "num_input_tokens_seen": 2367992,
473
+ "step": 58
474
+ },
475
+ {
476
+ "epoch": 1.073394495412844,
477
+ "grad_norm": 0.0973561555147171,
478
+ "learning_rate": 4.963271769635024e-05,
479
+ "loss": 0.3588,
480
+ "num_input_tokens_seen": 2415328,
481
+ "step": 59
482
+ },
483
+ {
484
+ "epoch": 1.091743119266055,
485
+ "grad_norm": 0.10240709036588669,
486
+ "learning_rate": 4.962019382530521e-05,
487
+ "loss": 0.5532,
488
+ "num_input_tokens_seen": 2454792,
489
+ "step": 60
490
+ },
491
+ {
492
+ "epoch": 1.110091743119266,
493
+ "grad_norm": 0.0959337130188942,
494
+ "learning_rate": 4.9607461628298244e-05,
495
+ "loss": 0.331,
496
+ "num_input_tokens_seen": 2503072,
497
+ "step": 61
498
+ },
499
+ {
500
+ "epoch": 1.1284403669724772,
501
+ "grad_norm": 0.10228750854730606,
502
+ "learning_rate": 4.9594521213063974e-05,
503
+ "loss": 0.3728,
504
+ "num_input_tokens_seen": 2546960,
505
+ "step": 62
506
+ },
507
+ {
508
+ "epoch": 1.146788990825688,
509
+ "grad_norm": 0.09403488785028458,
510
+ "learning_rate": 4.958137268909887e-05,
511
+ "loss": 0.4695,
512
+ "num_input_tokens_seen": 2595432,
513
+ "step": 63
514
+ },
515
+ {
516
+ "epoch": 1.165137614678899,
517
+ "grad_norm": 0.11396344751119614,
518
+ "learning_rate": 4.9568016167660334e-05,
519
+ "loss": 0.3653,
520
+ "num_input_tokens_seen": 2633912,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 1.18348623853211,
525
+ "grad_norm": 0.09487481415271759,
526
+ "learning_rate": 4.9554451761765766e-05,
527
+ "loss": 0.3498,
528
+ "num_input_tokens_seen": 2680792,
529
+ "step": 65
530
+ },
531
+ {
532
+ "epoch": 1.2018348623853212,
533
+ "grad_norm": 0.1249895691871643,
534
+ "learning_rate": 4.9540679586191605e-05,
535
+ "loss": 0.4053,
536
+ "num_input_tokens_seen": 2716584,
537
+ "step": 66
538
+ },
539
+ {
540
+ "epoch": 1.2201834862385321,
541
+ "grad_norm": 0.12268221378326416,
542
+ "learning_rate": 4.952669975747232e-05,
543
+ "loss": 0.4189,
544
+ "num_input_tokens_seen": 2757088,
545
+ "step": 67
546
+ },
547
+ {
548
+ "epoch": 1.238532110091743,
549
+ "grad_norm": 0.12126032263040543,
550
+ "learning_rate": 4.951251239389948e-05,
551
+ "loss": 0.4994,
552
+ "num_input_tokens_seen": 2795664,
553
+ "step": 68
554
+ },
555
+ {
556
+ "epoch": 1.2568807339449541,
557
+ "grad_norm": 0.1069057360291481,
558
+ "learning_rate": 4.949811761552074e-05,
559
+ "loss": 0.3275,
560
+ "num_input_tokens_seen": 2840936,
561
+ "step": 69
562
+ },
563
+ {
564
+ "epoch": 1.2752293577981653,
565
+ "grad_norm": 0.10893313586711884,
566
+ "learning_rate": 4.948351554413879e-05,
567
+ "loss": 0.4366,
568
+ "num_input_tokens_seen": 2886768,
569
+ "step": 70
570
+ },
571
+ {
572
+ "epoch": 1.2935779816513762,
573
+ "grad_norm": 0.12898756563663483,
574
+ "learning_rate": 4.9468706303310355e-05,
575
+ "loss": 0.3916,
576
+ "num_input_tokens_seen": 2919328,
577
+ "step": 71
578
+ },
579
+ {
580
+ "epoch": 1.311926605504587,
581
+ "grad_norm": 0.12405356019735336,
582
+ "learning_rate": 4.9453690018345144e-05,
583
+ "loss": 0.3249,
584
+ "num_input_tokens_seen": 2966744,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 1.3302752293577982,
589
+ "grad_norm": 0.13137595355510712,
590
+ "learning_rate": 4.943846681630479e-05,
591
+ "loss": 0.3956,
592
+ "num_input_tokens_seen": 3007248,
593
+ "step": 73
594
+ },
595
+ {
596
+ "epoch": 1.3486238532110093,
597
+ "grad_norm": 0.13920250535011292,
598
+ "learning_rate": 4.942303682600178e-05,
599
+ "loss": 0.3956,
600
+ "num_input_tokens_seen": 3050960,
601
+ "step": 74
602
+ },
603
+ {
604
+ "epoch": 1.3669724770642202,
605
+ "grad_norm": 0.1255589872598648,
606
+ "learning_rate": 4.940740017799833e-05,
607
+ "loss": 0.3773,
608
+ "num_input_tokens_seen": 3088592,
609
+ "step": 75
610
+ },
611
+ {
612
+ "epoch": 1.385321100917431,
613
+ "grad_norm": 0.10222747176885605,
614
+ "learning_rate": 4.939155700460536e-05,
615
+ "loss": 0.4,
616
+ "num_input_tokens_seen": 3153520,
617
+ "step": 76
618
+ },
619
+ {
620
+ "epoch": 1.4036697247706422,
621
+ "grad_norm": 0.13205283880233765,
622
+ "learning_rate": 4.9375507439881266e-05,
623
+ "loss": 0.4343,
624
+ "num_input_tokens_seen": 3199272,
625
+ "step": 77
626
+ },
627
+ {
628
+ "epoch": 1.4220183486238533,
629
+ "grad_norm": 0.11005694419145584,
630
+ "learning_rate": 4.9359251619630886e-05,
631
+ "loss": 0.3881,
632
+ "num_input_tokens_seen": 3247128,
633
+ "step": 78
634
+ },
635
+ {
636
+ "epoch": 1.4403669724770642,
637
+ "grad_norm": 0.14799247682094574,
638
+ "learning_rate": 4.9342789681404275e-05,
639
+ "loss": 0.3972,
640
+ "num_input_tokens_seen": 3294192,
641
+ "step": 79
642
+ },
643
+ {
644
+ "epoch": 1.4587155963302751,
645
+ "grad_norm": 0.1279418021440506,
646
+ "learning_rate": 4.9326121764495596e-05,
647
+ "loss": 0.3438,
648
+ "num_input_tokens_seen": 3329736,
649
+ "step": 80
650
+ },
651
+ {
652
+ "epoch": 1.4770642201834863,
653
+ "grad_norm": 0.11036807298660278,
654
+ "learning_rate": 4.9309248009941914e-05,
655
+ "loss": 0.3189,
656
+ "num_input_tokens_seen": 3371376,
657
+ "step": 81
658
+ },
659
+ {
660
+ "epoch": 1.4954128440366974,
661
+ "grad_norm": 0.11855707317590714,
662
+ "learning_rate": 4.9292168560522014e-05,
663
+ "loss": 0.401,
664
+ "num_input_tokens_seen": 3412368,
665
+ "step": 82
666
+ },
667
+ {
668
+ "epoch": 1.5137614678899083,
669
+ "grad_norm": 0.13195356726646423,
670
+ "learning_rate": 4.9274883560755156e-05,
671
+ "loss": 0.4973,
672
+ "num_input_tokens_seen": 3455000,
673
+ "step": 83
674
+ },
675
+ {
676
+ "epoch": 1.5321100917431192,
677
+ "grad_norm": 0.1462787538766861,
678
+ "learning_rate": 4.925739315689991e-05,
679
+ "loss": 0.3768,
680
+ "num_input_tokens_seen": 3488960,
681
+ "step": 84
682
+ },
683
+ {
684
+ "epoch": 1.5504587155963303,
685
+ "grad_norm": 0.13765974342823029,
686
+ "learning_rate": 4.92396974969529e-05,
687
+ "loss": 0.2999,
688
+ "num_input_tokens_seen": 3521320,
689
+ "step": 85
690
+ },
691
+ {
692
+ "epoch": 1.5688073394495414,
693
+ "grad_norm": 0.15276113152503967,
694
+ "learning_rate": 4.9221796730647516e-05,
695
+ "loss": 0.3638,
696
+ "num_input_tokens_seen": 3559464,
697
+ "step": 86
698
+ },
699
+ {
700
+ "epoch": 1.5871559633027523,
701
+ "grad_norm": 0.1441674381494522,
702
+ "learning_rate": 4.92036910094527e-05,
703
+ "loss": 0.3919,
704
+ "num_input_tokens_seen": 3598080,
705
+ "step": 87
706
+ },
707
+ {
708
+ "epoch": 1.6055045871559632,
709
+ "grad_norm": 0.1780252456665039,
710
+ "learning_rate": 4.9185380486571595e-05,
711
+ "loss": 0.3626,
712
+ "num_input_tokens_seen": 3630064,
713
+ "step": 88
714
+ },
715
+ {
716
+ "epoch": 1.6238532110091743,
717
+ "grad_norm": 0.16947726905345917,
718
+ "learning_rate": 4.916686531694035e-05,
719
+ "loss": 0.3439,
720
+ "num_input_tokens_seen": 3661408,
721
+ "step": 89
722
+ },
723
+ {
724
+ "epoch": 1.6422018348623855,
725
+ "grad_norm": 0.1552971601486206,
726
+ "learning_rate": 4.914814565722671e-05,
727
+ "loss": 0.3236,
728
+ "num_input_tokens_seen": 3695480,
729
+ "step": 90
730
+ },
731
+ {
732
+ "epoch": 1.6605504587155964,
733
+ "grad_norm": 0.14925938844680786,
734
+ "learning_rate": 4.912922166582874e-05,
735
+ "loss": 0.4255,
736
+ "num_input_tokens_seen": 3734560,
737
+ "step": 91
738
+ },
739
+ {
740
+ "epoch": 1.6788990825688073,
741
+ "grad_norm": 0.1332874596118927,
742
+ "learning_rate": 4.9110093502873476e-05,
743
+ "loss": 0.3061,
744
+ "num_input_tokens_seen": 3773112,
745
+ "step": 92
746
+ },
747
+ {
748
+ "epoch": 1.6972477064220184,
749
+ "grad_norm": 0.15471243858337402,
750
+ "learning_rate": 4.909076133021557e-05,
751
+ "loss": 0.3275,
752
+ "num_input_tokens_seen": 3813392,
753
+ "step": 93
754
+ },
755
+ {
756
+ "epoch": 1.7155963302752295,
757
+ "grad_norm": 0.16010524332523346,
758
+ "learning_rate": 4.907122531143594e-05,
759
+ "loss": 0.4179,
760
+ "num_input_tokens_seen": 3856416,
761
+ "step": 94
762
+ },
763
+ {
764
+ "epoch": 1.7339449541284404,
765
+ "grad_norm": 0.13423003256320953,
766
+ "learning_rate": 4.905148561184033e-05,
767
+ "loss": 0.3593,
768
+ "num_input_tokens_seen": 3899472,
769
+ "step": 95
770
+ },
771
+ {
772
+ "epoch": 1.7522935779816513,
773
+ "grad_norm": 0.14900773763656616,
774
+ "learning_rate": 4.9031542398457974e-05,
775
+ "loss": 0.5007,
776
+ "num_input_tokens_seen": 3962976,
777
+ "step": 96
778
+ },
779
+ {
780
+ "epoch": 1.7706422018348624,
781
+ "grad_norm": 0.15728624165058136,
782
+ "learning_rate": 4.9011395840040144e-05,
783
+ "loss": 0.3484,
784
+ "num_input_tokens_seen": 4000696,
785
+ "step": 97
786
+ },
787
+ {
788
+ "epoch": 1.7889908256880735,
789
+ "grad_norm": 0.11092367768287659,
790
+ "learning_rate": 4.8991046107058735e-05,
791
+ "loss": 0.2889,
792
+ "num_input_tokens_seen": 4045256,
793
+ "step": 98
794
+ },
795
+ {
796
+ "epoch": 1.8073394495412844,
797
+ "grad_norm": 0.1289113610982895,
798
+ "learning_rate": 4.8970493371704826e-05,
799
+ "loss": 0.2203,
800
+ "num_input_tokens_seen": 4076800,
801
+ "step": 99
802
+ },
803
+ {
804
+ "epoch": 1.8256880733944953,
805
+ "grad_norm": 0.18886639177799225,
806
+ "learning_rate": 4.894973780788722e-05,
807
+ "loss": 0.3966,
808
+ "num_input_tokens_seen": 4119840,
809
+ "step": 100
810
+ },
811
+ {
812
+ "epoch": 1.8440366972477065,
813
+ "grad_norm": 0.1563039869070053,
814
+ "learning_rate": 4.892877959123097e-05,
815
+ "loss": 0.4417,
816
+ "num_input_tokens_seen": 4165848,
817
+ "step": 101
818
+ },
819
+ {
820
+ "epoch": 1.8623853211009176,
821
+ "grad_norm": 0.16883380711078644,
822
+ "learning_rate": 4.890761889907589e-05,
823
+ "loss": 0.4258,
824
+ "num_input_tokens_seen": 4202824,
825
+ "step": 102
826
+ },
827
+ {
828
+ "epoch": 1.8807339449541285,
829
+ "grad_norm": 0.18241995573043823,
830
+ "learning_rate": 4.8886255910475054e-05,
831
+ "loss": 0.3952,
832
+ "num_input_tokens_seen": 4233888,
833
+ "step": 103
834
+ },
835
+ {
836
+ "epoch": 1.8990825688073394,
837
+ "grad_norm": 0.19913265109062195,
838
+ "learning_rate": 4.88646908061933e-05,
839
+ "loss": 0.3241,
840
+ "num_input_tokens_seen": 4267064,
841
+ "step": 104
842
+ },
843
+ {
844
+ "epoch": 1.9174311926605505,
845
+ "grad_norm": 0.18295545876026154,
846
+ "learning_rate": 4.884292376870567e-05,
847
+ "loss": 0.4239,
848
+ "num_input_tokens_seen": 4312536,
849
+ "step": 105
850
+ },
851
+ {
852
+ "epoch": 1.9357798165137616,
853
+ "grad_norm": 0.16657495498657227,
854
+ "learning_rate": 4.8820954982195905e-05,
855
+ "loss": 0.2579,
856
+ "num_input_tokens_seen": 4356656,
857
+ "step": 106
858
+ },
859
+ {
860
+ "epoch": 1.9541284403669725,
861
+ "grad_norm": 0.18504932522773743,
862
+ "learning_rate": 4.879878463255483e-05,
863
+ "loss": 0.44,
864
+ "num_input_tokens_seen": 4400216,
865
+ "step": 107
866
+ },
867
+ {
868
+ "epoch": 1.9724770642201834,
869
+ "grad_norm": 0.1923118382692337,
870
+ "learning_rate": 4.877641290737884e-05,
871
+ "loss": 0.2662,
872
+ "num_input_tokens_seen": 4436968,
873
+ "step": 108
874
+ },
875
+ {
876
+ "epoch": 1.9908256880733946,
877
+ "grad_norm": 0.19636788964271545,
878
+ "learning_rate": 4.875383999596828e-05,
879
+ "loss": 0.4211,
880
+ "num_input_tokens_seen": 4488232,
881
+ "step": 109
882
+ },
883
+ {
884
+ "epoch": 2.0,
885
+ "grad_norm": 0.3168099820613861,
886
+ "learning_rate": 4.873106608932585e-05,
887
+ "loss": 0.2499,
888
+ "num_input_tokens_seen": 4518176,
889
+ "step": 110
890
+ },
891
+ {
892
+ "epoch": 2.018348623853211,
893
+ "grad_norm": 0.14410308003425598,
894
+ "learning_rate": 4.8708091380154984e-05,
895
+ "loss": 0.2722,
896
+ "num_input_tokens_seen": 4570896,
897
+ "step": 111
898
+ },
899
+ {
900
+ "epoch": 2.036697247706422,
901
+ "grad_norm": 0.17840909957885742,
902
+ "learning_rate": 4.868491606285823e-05,
903
+ "loss": 0.2758,
904
+ "num_input_tokens_seen": 4613576,
905
+ "step": 112
906
+ },
907
+ {
908
+ "epoch": 2.055045871559633,
909
+ "grad_norm": 0.178523987531662,
910
+ "learning_rate": 4.866154033353561e-05,
911
+ "loss": 0.3361,
912
+ "num_input_tokens_seen": 4652896,
913
+ "step": 113
914
+ },
915
+ {
916
+ "epoch": 2.073394495412844,
917
+ "grad_norm": 0.17396725714206696,
918
+ "learning_rate": 4.8637964389982926e-05,
919
+ "loss": 0.2667,
920
+ "num_input_tokens_seen": 4694256,
921
+ "step": 114
922
+ },
923
+ {
924
+ "epoch": 2.091743119266055,
925
+ "grad_norm": 0.19471587240695953,
926
+ "learning_rate": 4.8614188431690125e-05,
927
+ "loss": 0.3628,
928
+ "num_input_tokens_seen": 4747552,
929
+ "step": 115
930
+ },
931
+ {
932
+ "epoch": 2.1100917431192663,
933
+ "grad_norm": 0.1722450852394104,
934
+ "learning_rate": 4.859021265983959e-05,
935
+ "loss": 0.3599,
936
+ "num_input_tokens_seen": 4794080,
937
+ "step": 116
938
+ },
939
+ {
940
+ "epoch": 2.128440366972477,
941
+ "grad_norm": 0.20137006044387817,
942
+ "learning_rate": 4.856603727730447e-05,
943
+ "loss": 0.4262,
944
+ "num_input_tokens_seen": 4847912,
945
+ "step": 117
946
+ },
947
+ {
948
+ "epoch": 2.146788990825688,
949
+ "grad_norm": 0.19395771622657776,
950
+ "learning_rate": 4.854166248864689e-05,
951
+ "loss": 0.3118,
952
+ "num_input_tokens_seen": 4885480,
953
+ "step": 118
954
+ },
955
+ {
956
+ "epoch": 2.165137614678899,
957
+ "grad_norm": 0.209548681974411,
958
+ "learning_rate": 4.85170885001163e-05,
959
+ "loss": 0.3725,
960
+ "num_input_tokens_seen": 4921240,
961
+ "step": 119
962
+ },
963
+ {
964
+ "epoch": 2.18348623853211,
965
+ "grad_norm": 0.18228279054164886,
966
+ "learning_rate": 4.849231551964771e-05,
967
+ "loss": 0.3816,
968
+ "num_input_tokens_seen": 4960224,
969
+ "step": 120
970
+ },
971
+ {
972
+ "epoch": 2.2018348623853212,
973
+ "grad_norm": 0.24349354207515717,
974
+ "learning_rate": 4.846734375685989e-05,
975
+ "loss": 0.3383,
976
+ "num_input_tokens_seen": 4990536,
977
+ "step": 121
978
+ },
979
+ {
980
+ "epoch": 2.220183486238532,
981
+ "grad_norm": 0.17600344121456146,
982
+ "learning_rate": 4.844217342305363e-05,
983
+ "loss": 0.3011,
984
+ "num_input_tokens_seen": 5044296,
985
+ "step": 122
986
+ },
987
+ {
988
+ "epoch": 2.238532110091743,
989
+ "grad_norm": 0.18766675889492035,
990
+ "learning_rate": 4.8416804731209945e-05,
991
+ "loss": 0.4458,
992
+ "num_input_tokens_seen": 5088368,
993
+ "step": 123
994
+ },
995
+ {
996
+ "epoch": 2.2568807339449544,
997
+ "grad_norm": 0.17657820880413055,
998
+ "learning_rate": 4.839123789598829e-05,
999
+ "loss": 0.2564,
1000
+ "num_input_tokens_seen": 5133472,
1001
+ "step": 124
1002
+ },
1003
+ {
1004
+ "epoch": 2.2752293577981653,
1005
+ "grad_norm": 0.20606014132499695,
1006
+ "learning_rate": 4.836547313372471e-05,
1007
+ "loss": 0.313,
1008
+ "num_input_tokens_seen": 5167768,
1009
+ "step": 125
1010
+ },
1011
+ {
1012
+ "epoch": 2.293577981651376,
1013
+ "grad_norm": 0.23511061072349548,
1014
+ "learning_rate": 4.8339510662430046e-05,
1015
+ "loss": 0.2963,
1016
+ "num_input_tokens_seen": 5209400,
1017
+ "step": 126
1018
+ },
1019
+ {
1020
+ "epoch": 2.311926605504587,
1021
+ "grad_norm": 0.18234293162822723,
1022
+ "learning_rate": 4.8313350701788054e-05,
1023
+ "loss": 0.2566,
1024
+ "num_input_tokens_seen": 5249360,
1025
+ "step": 127
1026
+ },
1027
+ {
1028
+ "epoch": 2.330275229357798,
1029
+ "grad_norm": 0.2223992496728897,
1030
+ "learning_rate": 4.828699347315356e-05,
1031
+ "loss": 0.2833,
1032
+ "num_input_tokens_seen": 5300808,
1033
+ "step": 128
1034
+ },
1035
+ {
1036
+ "epoch": 2.3486238532110093,
1037
+ "grad_norm": 0.23101739585399628,
1038
+ "learning_rate": 4.826043919955062e-05,
1039
+ "loss": 0.3099,
1040
+ "num_input_tokens_seen": 5332960,
1041
+ "step": 129
1042
+ },
1043
+ {
1044
+ "epoch": 2.36697247706422,
1045
+ "grad_norm": 0.26640889048576355,
1046
+ "learning_rate": 4.823368810567056e-05,
1047
+ "loss": 0.3238,
1048
+ "num_input_tokens_seen": 5365008,
1049
+ "step": 130
1050
+ },
1051
+ {
1052
+ "epoch": 2.385321100917431,
1053
+ "grad_norm": 0.2374572902917862,
1054
+ "learning_rate": 4.820674041787017e-05,
1055
+ "loss": 0.3153,
1056
+ "num_input_tokens_seen": 5400184,
1057
+ "step": 131
1058
+ },
1059
+ {
1060
+ "epoch": 2.4036697247706424,
1061
+ "grad_norm": 0.22812288999557495,
1062
+ "learning_rate": 4.817959636416969e-05,
1063
+ "loss": 0.2997,
1064
+ "num_input_tokens_seen": 5440320,
1065
+ "step": 132
1066
+ },
1067
+ {
1068
+ "epoch": 2.4220183486238533,
1069
+ "grad_norm": 0.20079149305820465,
1070
+ "learning_rate": 4.815225617425095e-05,
1071
+ "loss": 0.2373,
1072
+ "num_input_tokens_seen": 5480832,
1073
+ "step": 133
1074
+ },
1075
+ {
1076
+ "epoch": 2.4403669724770642,
1077
+ "grad_norm": 0.196709543466568,
1078
+ "learning_rate": 4.81247200794554e-05,
1079
+ "loss": 0.2456,
1080
+ "num_input_tokens_seen": 5526936,
1081
+ "step": 134
1082
+ },
1083
+ {
1084
+ "epoch": 2.458715596330275,
1085
+ "grad_norm": 0.17305873334407806,
1086
+ "learning_rate": 4.8096988312782174e-05,
1087
+ "loss": 0.2099,
1088
+ "num_input_tokens_seen": 5566384,
1089
+ "step": 135
1090
+ },
1091
+ {
1092
+ "epoch": 2.477064220183486,
1093
+ "grad_norm": 3.584635019302368,
1094
+ "learning_rate": 4.806906110888606e-05,
1095
+ "loss": 0.3485,
1096
+ "num_input_tokens_seen": 5629896,
1097
+ "step": 136
1098
+ },
1099
+ {
1100
+ "epoch": 2.4954128440366974,
1101
+ "grad_norm": 0.23481500148773193,
1102
+ "learning_rate": 4.80409387040756e-05,
1103
+ "loss": 0.2231,
1104
+ "num_input_tokens_seen": 5674504,
1105
+ "step": 137
1106
+ },
1107
+ {
1108
+ "epoch": 2.5137614678899083,
1109
+ "grad_norm": 0.27899855375289917,
1110
+ "learning_rate": 4.8012621336311016e-05,
1111
+ "loss": 0.4285,
1112
+ "num_input_tokens_seen": 5714000,
1113
+ "step": 138
1114
+ },
1115
+ {
1116
+ "epoch": 2.532110091743119,
1117
+ "grad_norm": 0.24404938519001007,
1118
+ "learning_rate": 4.798410924520223e-05,
1119
+ "loss": 0.3343,
1120
+ "num_input_tokens_seen": 5756856,
1121
+ "step": 139
1122
+ },
1123
+ {
1124
+ "epoch": 2.5504587155963305,
1125
+ "grad_norm": 0.26869162917137146,
1126
+ "learning_rate": 4.7955402672006854e-05,
1127
+ "loss": 0.2497,
1128
+ "num_input_tokens_seen": 5781192,
1129
+ "step": 140
1130
+ },
1131
+ {
1132
+ "epoch": 2.5688073394495414,
1133
+ "grad_norm": 0.2057972550392151,
1134
+ "learning_rate": 4.79265018596281e-05,
1135
+ "loss": 0.2991,
1136
+ "num_input_tokens_seen": 5824024,
1137
+ "step": 141
1138
+ },
1139
+ {
1140
+ "epoch": 2.5871559633027523,
1141
+ "grad_norm": 0.2184937596321106,
1142
+ "learning_rate": 4.789740705261278e-05,
1143
+ "loss": 0.2406,
1144
+ "num_input_tokens_seen": 5862584,
1145
+ "step": 142
1146
+ },
1147
+ {
1148
+ "epoch": 2.6055045871559632,
1149
+ "grad_norm": 0.23603741824626923,
1150
+ "learning_rate": 4.786811849714918e-05,
1151
+ "loss": 0.2722,
1152
+ "num_input_tokens_seen": 5897344,
1153
+ "step": 143
1154
+ },
1155
+ {
1156
+ "epoch": 2.623853211009174,
1157
+ "grad_norm": 0.22983981668949127,
1158
+ "learning_rate": 4.783863644106502e-05,
1159
+ "loss": 0.374,
1160
+ "num_input_tokens_seen": 5931736,
1161
+ "step": 144
1162
+ },
1163
+ {
1164
+ "epoch": 2.6422018348623855,
1165
+ "grad_norm": 0.2825419306755066,
1166
+ "learning_rate": 4.780896113382536e-05,
1167
+ "loss": 0.3386,
1168
+ "num_input_tokens_seen": 5972784,
1169
+ "step": 145
1170
+ },
1171
+ {
1172
+ "epoch": 2.6605504587155964,
1173
+ "grad_norm": 0.4502134621143341,
1174
+ "learning_rate": 4.777909282653042e-05,
1175
+ "loss": 0.2289,
1176
+ "num_input_tokens_seen": 6018968,
1177
+ "step": 146
1178
+ },
1179
+ {
1180
+ "epoch": 2.6788990825688073,
1181
+ "grad_norm": 0.2428288459777832,
1182
+ "learning_rate": 4.7749031771913584e-05,
1183
+ "loss": 0.4061,
1184
+ "num_input_tokens_seen": 6062520,
1185
+ "step": 147
1186
+ },
1187
+ {
1188
+ "epoch": 2.6972477064220186,
1189
+ "grad_norm": 0.2685629725456238,
1190
+ "learning_rate": 4.771877822433911e-05,
1191
+ "loss": 0.2198,
1192
+ "num_input_tokens_seen": 6087928,
1193
+ "step": 148
1194
+ },
1195
+ {
1196
+ "epoch": 2.7155963302752295,
1197
+ "grad_norm": 0.24021446704864502,
1198
+ "learning_rate": 4.7688332439800096e-05,
1199
+ "loss": 0.34,
1200
+ "num_input_tokens_seen": 6134792,
1201
+ "step": 149
1202
+ },
1203
+ {
1204
+ "epoch": 2.7339449541284404,
1205
+ "grad_norm": 0.2568534314632416,
1206
+ "learning_rate": 4.765769467591625e-05,
1207
+ "loss": 0.3292,
1208
+ "num_input_tokens_seen": 6183296,
1209
+ "step": 150
1210
+ },
1211
+ {
1212
+ "epoch": 2.7522935779816513,
1213
+ "grad_norm": 0.20823974907398224,
1214
+ "learning_rate": 4.762686519193175e-05,
1215
+ "loss": 0.2539,
1216
+ "num_input_tokens_seen": 6225840,
1217
+ "step": 151
1218
+ },
1219
+ {
1220
+ "epoch": 2.770642201834862,
1221
+ "grad_norm": 0.23333317041397095,
1222
+ "learning_rate": 4.759584424871302e-05,
1223
+ "loss": 0.3571,
1224
+ "num_input_tokens_seen": 6274760,
1225
+ "step": 152
1226
+ },
1227
+ {
1228
+ "epoch": 2.7889908256880735,
1229
+ "grad_norm": 0.20232398808002472,
1230
+ "learning_rate": 4.756463210874652e-05,
1231
+ "loss": 0.2783,
1232
+ "num_input_tokens_seen": 6326168,
1233
+ "step": 153
1234
+ },
1235
+ {
1236
+ "epoch": 2.8073394495412844,
1237
+ "grad_norm": 0.3479433059692383,
1238
+ "learning_rate": 4.7533229036136553e-05,
1239
+ "loss": 0.2925,
1240
+ "num_input_tokens_seen": 6360312,
1241
+ "step": 154
1242
+ },
1243
+ {
1244
+ "epoch": 2.8256880733944953,
1245
+ "grad_norm": 0.2659524083137512,
1246
+ "learning_rate": 4.750163529660303e-05,
1247
+ "loss": 0.2606,
1248
+ "num_input_tokens_seen": 6395496,
1249
+ "step": 155
1250
+ },
1251
+ {
1252
+ "epoch": 2.8440366972477067,
1253
+ "grad_norm": 0.24823158979415894,
1254
+ "learning_rate": 4.7469851157479177e-05,
1255
+ "loss": 0.3721,
1256
+ "num_input_tokens_seen": 6437064,
1257
+ "step": 156
1258
+ },
1259
+ {
1260
+ "epoch": 2.8623853211009176,
1261
+ "grad_norm": 0.32034072279930115,
1262
+ "learning_rate": 4.743787688770932e-05,
1263
+ "loss": 0.3931,
1264
+ "num_input_tokens_seen": 6477616,
1265
+ "step": 157
1266
+ },
1267
+ {
1268
+ "epoch": 2.8807339449541285,
1269
+ "grad_norm": 0.23295725882053375,
1270
+ "learning_rate": 4.740571275784659e-05,
1271
+ "loss": 0.2201,
1272
+ "num_input_tokens_seen": 6518680,
1273
+ "step": 158
1274
+ },
1275
+ {
1276
+ "epoch": 2.8990825688073394,
1277
+ "grad_norm": 0.2758423984050751,
1278
+ "learning_rate": 4.737335904005063e-05,
1279
+ "loss": 0.2579,
1280
+ "num_input_tokens_seen": 6549768,
1281
+ "step": 159
1282
+ },
1283
+ {
1284
+ "epoch": 2.9174311926605503,
1285
+ "grad_norm": 0.26690953969955444,
1286
+ "learning_rate": 4.734081600808531e-05,
1287
+ "loss": 0.2575,
1288
+ "num_input_tokens_seen": 6581000,
1289
+ "step": 160
1290
+ },
1291
+ {
1292
+ "epoch": 2.9357798165137616,
1293
+ "grad_norm": 0.26657482981681824,
1294
+ "learning_rate": 4.730808393731639e-05,
1295
+ "loss": 0.2597,
1296
+ "num_input_tokens_seen": 6612632,
1297
+ "step": 161
1298
+ },
1299
+ {
1300
+ "epoch": 2.9541284403669725,
1301
+ "grad_norm": 0.22647295892238617,
1302
+ "learning_rate": 4.72751631047092e-05,
1303
+ "loss": 0.3335,
1304
+ "num_input_tokens_seen": 6654288,
1305
+ "step": 162
1306
+ },
1307
+ {
1308
+ "epoch": 2.9724770642201834,
1309
+ "grad_norm": 0.2863366901874542,
1310
+ "learning_rate": 4.72420537888263e-05,
1311
+ "loss": 0.374,
1312
+ "num_input_tokens_seen": 6707208,
1313
+ "step": 163
1314
+ },
1315
+ {
1316
+ "epoch": 2.9908256880733948,
1317
+ "grad_norm": 0.2606408894062042,
1318
+ "learning_rate": 4.7208756269825104e-05,
1319
+ "loss": 0.3477,
1320
+ "num_input_tokens_seen": 6748448,
1321
+ "step": 164
1322
+ },
1323
+ {
1324
+ "epoch": 3.0,
1325
+ "grad_norm": 0.440924733877182,
1326
+ "learning_rate": 4.717527082945554e-05,
1327
+ "loss": 0.3214,
1328
+ "num_input_tokens_seen": 6777264,
1329
+ "step": 165
1330
+ },
1331
+ {
1332
+ "epoch": 3.018348623853211,
1333
+ "grad_norm": 0.27583903074264526,
1334
+ "learning_rate": 4.714159775105765e-05,
1335
+ "loss": 0.2681,
1336
+ "num_input_tokens_seen": 6809456,
1337
+ "step": 166
1338
+ },
1339
+ {
1340
+ "epoch": 3.036697247706422,
1341
+ "grad_norm": 0.2995987832546234,
1342
+ "learning_rate": 4.7107737319559176e-05,
1343
+ "loss": 0.2633,
1344
+ "num_input_tokens_seen": 6845768,
1345
+ "step": 167
1346
+ },
1347
+ {
1348
+ "epoch": 3.055045871559633,
1349
+ "grad_norm": 0.23999951779842377,
1350
+ "learning_rate": 4.707368982147318e-05,
1351
+ "loss": 0.1961,
1352
+ "num_input_tokens_seen": 6893056,
1353
+ "step": 168
1354
+ },
1355
+ {
1356
+ "epoch": 3.073394495412844,
1357
+ "grad_norm": 0.23356525599956512,
1358
+ "learning_rate": 4.703945554489558e-05,
1359
+ "loss": 0.2836,
1360
+ "num_input_tokens_seen": 6932480,
1361
+ "step": 169
1362
+ },
1363
+ {
1364
+ "epoch": 3.091743119266055,
1365
+ "grad_norm": 0.29919493198394775,
1366
+ "learning_rate": 4.700503477950278e-05,
1367
+ "loss": 0.2838,
1368
+ "num_input_tokens_seen": 6975992,
1369
+ "step": 170
1370
+ },
1371
+ {
1372
+ "epoch": 3.1100917431192663,
1373
+ "grad_norm": 0.3350690007209778,
1374
+ "learning_rate": 4.697042781654913e-05,
1375
+ "loss": 0.3489,
1376
+ "num_input_tokens_seen": 7021840,
1377
+ "step": 171
1378
+ },
1379
+ {
1380
+ "epoch": 3.128440366972477,
1381
+ "grad_norm": 0.2837466895580292,
1382
+ "learning_rate": 4.693563494886455e-05,
1383
+ "loss": 0.3797,
1384
+ "num_input_tokens_seen": 7065192,
1385
+ "step": 172
1386
+ },
1387
+ {
1388
+ "epoch": 3.146788990825688,
1389
+ "grad_norm": 0.24601787328720093,
1390
+ "learning_rate": 4.6900656470851964e-05,
1391
+ "loss": 0.2046,
1392
+ "num_input_tokens_seen": 7114544,
1393
+ "step": 173
1394
+ },
1395
+ {
1396
+ "epoch": 3.165137614678899,
1397
+ "grad_norm": 0.32290250062942505,
1398
+ "learning_rate": 4.6865492678484895e-05,
1399
+ "loss": 0.2596,
1400
+ "num_input_tokens_seen": 7152736,
1401
+ "step": 174
1402
+ },
1403
+ {
1404
+ "epoch": 3.18348623853211,
1405
+ "grad_norm": 0.33591920137405396,
1406
+ "learning_rate": 4.68301438693049e-05,
1407
+ "loss": 0.3045,
1408
+ "num_input_tokens_seen": 7207464,
1409
+ "step": 175
1410
+ },
1411
+ {
1412
+ "epoch": 3.2018348623853212,
1413
+ "grad_norm": 0.25471043586730957,
1414
+ "learning_rate": 4.679461034241906e-05,
1415
+ "loss": 0.2096,
1416
+ "num_input_tokens_seen": 7238640,
1417
+ "step": 176
1418
+ },
1419
+ {
1420
+ "epoch": 3.220183486238532,
1421
+ "grad_norm": 0.31238994002342224,
1422
+ "learning_rate": 4.6758892398497494e-05,
1423
+ "loss": 0.2226,
1424
+ "num_input_tokens_seen": 7279112,
1425
+ "step": 177
1426
+ },
1427
+ {
1428
+ "epoch": 3.238532110091743,
1429
+ "grad_norm": 0.35679712891578674,
1430
+ "learning_rate": 4.672299033977076e-05,
1431
+ "loss": 0.2403,
1432
+ "num_input_tokens_seen": 7311632,
1433
+ "step": 178
1434
+ },
1435
+ {
1436
+ "epoch": 3.2568807339449544,
1437
+ "grad_norm": 0.326914519071579,
1438
+ "learning_rate": 4.6686904470027316e-05,
1439
+ "loss": 0.2156,
1440
+ "num_input_tokens_seen": 7344864,
1441
+ "step": 179
1442
+ },
1443
+ {
1444
+ "epoch": 3.2752293577981653,
1445
+ "grad_norm": 0.3293381929397583,
1446
+ "learning_rate": 4.665063509461097e-05,
1447
+ "loss": 0.238,
1448
+ "num_input_tokens_seen": 7389944,
1449
+ "step": 180
1450
+ },
1451
+ {
1452
+ "epoch": 3.293577981651376,
1453
+ "grad_norm": 0.3313307762145996,
1454
+ "learning_rate": 4.661418252041827e-05,
1455
+ "loss": 0.2251,
1456
+ "num_input_tokens_seen": 7423672,
1457
+ "step": 181
1458
+ },
1459
+ {
1460
+ "epoch": 3.311926605504587,
1461
+ "grad_norm": 0.3328595459461212,
1462
+ "learning_rate": 4.657754705589591e-05,
1463
+ "loss": 0.2922,
1464
+ "num_input_tokens_seen": 7459576,
1465
+ "step": 182
1466
+ },
1467
+ {
1468
+ "epoch": 3.330275229357798,
1469
+ "grad_norm": 0.2721710801124573,
1470
+ "learning_rate": 4.6540729011038146e-05,
1471
+ "loss": 0.2698,
1472
+ "num_input_tokens_seen": 7511736,
1473
+ "step": 183
1474
+ },
1475
+ {
1476
+ "epoch": 3.3486238532110093,
1477
+ "grad_norm": 0.2488890290260315,
1478
+ "learning_rate": 4.650372869738414e-05,
1479
+ "loss": 0.173,
1480
+ "num_input_tokens_seen": 7558552,
1481
+ "step": 184
1482
+ },
1483
+ {
1484
+ "epoch": 3.36697247706422,
1485
+ "grad_norm": 0.3800615668296814,
1486
+ "learning_rate": 4.6466546428015336e-05,
1487
+ "loss": 0.32,
1488
+ "num_input_tokens_seen": 7599040,
1489
+ "step": 185
1490
+ },
1491
+ {
1492
+ "epoch": 3.385321100917431,
1493
+ "grad_norm": 0.3377014100551605,
1494
+ "learning_rate": 4.642918251755281e-05,
1495
+ "loss": 0.3058,
1496
+ "num_input_tokens_seen": 7653264,
1497
+ "step": 186
1498
+ },
1499
+ {
1500
+ "epoch": 3.4036697247706424,
1501
+ "grad_norm": 0.25239789485931396,
1502
+ "learning_rate": 4.639163728215463e-05,
1503
+ "loss": 0.1896,
1504
+ "num_input_tokens_seen": 7694272,
1505
+ "step": 187
1506
+ },
1507
+ {
1508
+ "epoch": 3.4220183486238533,
1509
+ "grad_norm": 0.34607502818107605,
1510
+ "learning_rate": 4.6353911039513145e-05,
1511
+ "loss": 0.2933,
1512
+ "num_input_tokens_seen": 7730848,
1513
+ "step": 188
1514
+ },
1515
+ {
1516
+ "epoch": 3.4403669724770642,
1517
+ "grad_norm": 0.30653324723243713,
1518
+ "learning_rate": 4.6316004108852305e-05,
1519
+ "loss": 0.2625,
1520
+ "num_input_tokens_seen": 7781200,
1521
+ "step": 189
1522
+ },
1523
+ {
1524
+ "epoch": 3.458715596330275,
1525
+ "grad_norm": 0.2943236231803894,
1526
+ "learning_rate": 4.627791681092499e-05,
1527
+ "loss": 0.3372,
1528
+ "num_input_tokens_seen": 7825032,
1529
+ "step": 190
1530
+ },
1531
+ {
1532
+ "epoch": 3.477064220183486,
1533
+ "grad_norm": 0.30080685019493103,
1534
+ "learning_rate": 4.623964946801027e-05,
1535
+ "loss": 0.2229,
1536
+ "num_input_tokens_seen": 7855840,
1537
+ "step": 191
1538
+ },
1539
+ {
1540
+ "epoch": 3.4954128440366974,
1541
+ "grad_norm": 0.3511403799057007,
1542
+ "learning_rate": 4.620120240391065e-05,
1543
+ "loss": 0.3967,
1544
+ "num_input_tokens_seen": 7905928,
1545
+ "step": 192
1546
+ },
1547
+ {
1548
+ "epoch": 3.5137614678899083,
1549
+ "grad_norm": 0.273583322763443,
1550
+ "learning_rate": 4.61625759439494e-05,
1551
+ "loss": 0.2254,
1552
+ "num_input_tokens_seen": 7955992,
1553
+ "step": 193
1554
+ },
1555
+ {
1556
+ "epoch": 3.532110091743119,
1557
+ "grad_norm": 0.3457902669906616,
1558
+ "learning_rate": 4.612377041496776e-05,
1559
+ "loss": 0.2553,
1560
+ "num_input_tokens_seen": 7998024,
1561
+ "step": 194
1562
+ },
1563
+ {
1564
+ "epoch": 3.5504587155963305,
1565
+ "grad_norm": 0.31968954205513,
1566
+ "learning_rate": 4.608478614532215e-05,
1567
+ "loss": 0.2197,
1568
+ "num_input_tokens_seen": 8055672,
1569
+ "step": 195
1570
+ },
1571
+ {
1572
+ "epoch": 3.5688073394495414,
1573
+ "grad_norm": 0.34753403067588806,
1574
+ "learning_rate": 4.604562346488144e-05,
1575
+ "loss": 0.2507,
1576
+ "num_input_tokens_seen": 8090848,
1577
+ "step": 196
1578
+ },
1579
+ {
1580
+ "epoch": 3.5871559633027523,
1581
+ "grad_norm": 0.3808669149875641,
1582
+ "learning_rate": 4.6006282705024144e-05,
1583
+ "loss": 0.2422,
1584
+ "num_input_tokens_seen": 8136680,
1585
+ "step": 197
1586
+ },
1587
+ {
1588
+ "epoch": 3.6055045871559632,
1589
+ "grad_norm": 0.3004499673843384,
1590
+ "learning_rate": 4.5966764198635606e-05,
1591
+ "loss": 0.2107,
1592
+ "num_input_tokens_seen": 8187472,
1593
+ "step": 198
1594
+ },
1595
+ {
1596
+ "epoch": 3.623853211009174,
1597
+ "grad_norm": 0.30718186497688293,
1598
+ "learning_rate": 4.592706828010518e-05,
1599
+ "loss": 0.1854,
1600
+ "num_input_tokens_seen": 8225216,
1601
+ "step": 199
1602
+ },
1603
+ {
1604
+ "epoch": 3.6422018348623855,
1605
+ "grad_norm": 0.23112858831882477,
1606
+ "learning_rate": 4.588719528532342e-05,
1607
+ "loss": 0.1687,
1608
+ "num_input_tokens_seen": 8274456,
1609
+ "step": 200
1610
+ },
1611
+ {
1612
+ "epoch": 3.6605504587155964,
1613
+ "grad_norm": 0.25966888666152954,
1614
+ "learning_rate": 4.5847145551679206e-05,
1615
+ "loss": 0.2549,
1616
+ "num_input_tokens_seen": 8317016,
1617
+ "step": 201
1618
+ },
1619
+ {
1620
+ "epoch": 3.6788990825688073,
1621
+ "grad_norm": 0.25600987672805786,
1622
+ "learning_rate": 4.580691941805695e-05,
1623
+ "loss": 0.1602,
1624
+ "num_input_tokens_seen": 8361856,
1625
+ "step": 202
1626
+ },
1627
+ {
1628
+ "epoch": 3.6972477064220186,
1629
+ "grad_norm": 0.33986184000968933,
1630
+ "learning_rate": 4.5766517224833637e-05,
1631
+ "loss": 0.2495,
1632
+ "num_input_tokens_seen": 8410696,
1633
+ "step": 203
1634
+ },
1635
+ {
1636
+ "epoch": 3.7155963302752295,
1637
+ "grad_norm": 0.36899781227111816,
1638
+ "learning_rate": 4.572593931387604e-05,
1639
+ "loss": 0.2012,
1640
+ "num_input_tokens_seen": 8441872,
1641
+ "step": 204
1642
+ },
1643
+ {
1644
+ "epoch": 3.7339449541284404,
1645
+ "grad_norm": 0.42072632908821106,
1646
+ "learning_rate": 4.568518602853776e-05,
1647
+ "loss": 0.2373,
1648
+ "num_input_tokens_seen": 8482544,
1649
+ "step": 205
1650
+ },
1651
+ {
1652
+ "epoch": 3.7522935779816513,
1653
+ "grad_norm": 0.40593233704566956,
1654
+ "learning_rate": 4.5644257713656356e-05,
1655
+ "loss": 0.233,
1656
+ "num_input_tokens_seen": 8519856,
1657
+ "step": 206
1658
+ },
1659
+ {
1660
+ "epoch": 3.770642201834862,
1661
+ "grad_norm": 0.38003161549568176,
1662
+ "learning_rate": 4.5603154715550386e-05,
1663
+ "loss": 0.225,
1664
+ "num_input_tokens_seen": 8551392,
1665
+ "step": 207
1666
+ },
1667
+ {
1668
+ "epoch": 3.7889908256880735,
1669
+ "grad_norm": 0.2564244568347931,
1670
+ "learning_rate": 4.556187738201656e-05,
1671
+ "loss": 0.2975,
1672
+ "num_input_tokens_seen": 8599472,
1673
+ "step": 208
1674
+ },
1675
+ {
1676
+ "epoch": 3.8073394495412844,
1677
+ "grad_norm": 0.29023391008377075,
1678
+ "learning_rate": 4.552042606232668e-05,
1679
+ "loss": 0.2033,
1680
+ "num_input_tokens_seen": 8631880,
1681
+ "step": 209
1682
+ },
1683
+ {
1684
+ "epoch": 3.8256880733944953,
1685
+ "grad_norm": 0.32886001467704773,
1686
+ "learning_rate": 4.54788011072248e-05,
1687
+ "loss": 0.2024,
1688
+ "num_input_tokens_seen": 8675016,
1689
+ "step": 210
1690
+ },
1691
+ {
1692
+ "epoch": 3.8440366972477067,
1693
+ "grad_norm": 0.36749884486198425,
1694
+ "learning_rate": 4.5437002868924166e-05,
1695
+ "loss": 0.2304,
1696
+ "num_input_tokens_seen": 8713248,
1697
+ "step": 211
1698
+ },
1699
+ {
1700
+ "epoch": 3.8623853211009176,
1701
+ "grad_norm": 0.3055097758769989,
1702
+ "learning_rate": 4.539503170110431e-05,
1703
+ "loss": 0.2928,
1704
+ "num_input_tokens_seen": 8748800,
1705
+ "step": 212
1706
+ },
1707
+ {
1708
+ "epoch": 3.8807339449541285,
1709
+ "grad_norm": 0.38436686992645264,
1710
+ "learning_rate": 4.535288795890798e-05,
1711
+ "loss": 0.2214,
1712
+ "num_input_tokens_seen": 8787832,
1713
+ "step": 213
1714
+ },
1715
+ {
1716
+ "epoch": 3.8990825688073394,
1717
+ "grad_norm": 0.44330883026123047,
1718
+ "learning_rate": 4.531057199893824e-05,
1719
+ "loss": 0.2168,
1720
+ "num_input_tokens_seen": 8819616,
1721
+ "step": 214
1722
+ },
1723
+ {
1724
+ "epoch": 3.9174311926605503,
1725
+ "grad_norm": 0.28318527340888977,
1726
+ "learning_rate": 4.526808417925531e-05,
1727
+ "loss": 0.279,
1728
+ "num_input_tokens_seen": 8860744,
1729
+ "step": 215
1730
+ },
1731
+ {
1732
+ "epoch": 3.9357798165137616,
1733
+ "grad_norm": 0.3287319839000702,
1734
+ "learning_rate": 4.522542485937369e-05,
1735
+ "loss": 0.2597,
1736
+ "num_input_tokens_seen": 8906432,
1737
+ "step": 216
1738
+ },
1739
+ {
1740
+ "epoch": 3.9541284403669725,
1741
+ "grad_norm": 0.35815751552581787,
1742
+ "learning_rate": 4.5182594400259e-05,
1743
+ "loss": 0.241,
1744
+ "num_input_tokens_seen": 8955104,
1745
+ "step": 217
1746
+ },
1747
+ {
1748
+ "epoch": 3.9724770642201834,
1749
+ "grad_norm": 0.3299608528614044,
1750
+ "learning_rate": 4.5139593164324986e-05,
1751
+ "loss": 0.2157,
1752
+ "num_input_tokens_seen": 8990200,
1753
+ "step": 218
1754
+ },
1755
+ {
1756
+ "epoch": 3.9908256880733948,
1757
+ "grad_norm": 0.2916093170642853,
1758
+ "learning_rate": 4.509642151543043e-05,
1759
+ "loss": 0.2046,
1760
+ "num_input_tokens_seen": 9020760,
1761
+ "step": 219
1762
+ },
1763
+ {
1764
+ "epoch": 4.0,
1765
+ "grad_norm": 0.40076637268066406,
1766
+ "learning_rate": 4.50530798188761e-05,
1767
+ "loss": 0.1714,
1768
+ "num_input_tokens_seen": 9036352,
1769
+ "step": 220
1770
+ },
1771
+ {
1772
+ "epoch": 4.018348623853211,
1773
+ "grad_norm": 0.40515249967575073,
1774
+ "learning_rate": 4.50095684414016e-05,
1775
+ "loss": 0.1811,
1776
+ "num_input_tokens_seen": 9091776,
1777
+ "step": 221
1778
+ },
1779
+ {
1780
+ "epoch": 4.036697247706422,
1781
+ "grad_norm": 0.32984718680381775,
1782
+ "learning_rate": 4.496588775118232e-05,
1783
+ "loss": 0.2101,
1784
+ "num_input_tokens_seen": 9134080,
1785
+ "step": 222
1786
+ },
1787
+ {
1788
+ "epoch": 4.055045871559633,
1789
+ "grad_norm": 0.27288541197776794,
1790
+ "learning_rate": 4.4922038117826334e-05,
1791
+ "loss": 0.1444,
1792
+ "num_input_tokens_seen": 9172720,
1793
+ "step": 223
1794
+ },
1795
+ {
1796
+ "epoch": 4.073394495412844,
1797
+ "grad_norm": 0.5168021321296692,
1798
+ "learning_rate": 4.48780199123712e-05,
1799
+ "loss": 0.2342,
1800
+ "num_input_tokens_seen": 9213664,
1801
+ "step": 224
1802
+ },
1803
+ {
1804
+ "epoch": 4.091743119266055,
1805
+ "grad_norm": 0.3986498713493347,
1806
+ "learning_rate": 4.4833833507280884e-05,
1807
+ "loss": 0.1676,
1808
+ "num_input_tokens_seen": 9261768,
1809
+ "step": 225
1810
+ },
1811
+ {
1812
+ "epoch": 4.110091743119266,
1813
+ "grad_norm": 0.4472793936729431,
1814
+ "learning_rate": 4.478947927644258e-05,
1815
+ "loss": 0.295,
1816
+ "num_input_tokens_seen": 9300928,
1817
+ "step": 226
1818
+ },
1819
+ {
1820
+ "epoch": 4.128440366972477,
1821
+ "grad_norm": 0.39240705966949463,
1822
+ "learning_rate": 4.474495759516358e-05,
1823
+ "loss": 0.17,
1824
+ "num_input_tokens_seen": 9329472,
1825
+ "step": 227
1826
+ },
1827
+ {
1828
+ "epoch": 4.146788990825688,
1829
+ "grad_norm": 0.354526549577713,
1830
+ "learning_rate": 4.4700268840168045e-05,
1831
+ "loss": 0.1759,
1832
+ "num_input_tokens_seen": 9365640,
1833
+ "step": 228
1834
+ },
1835
+ {
1836
+ "epoch": 4.165137614678899,
1837
+ "grad_norm": 0.3216766119003296,
1838
+ "learning_rate": 4.4655413389593856e-05,
1839
+ "loss": 0.1878,
1840
+ "num_input_tokens_seen": 9410552,
1841
+ "step": 229
1842
+ },
1843
+ {
1844
+ "epoch": 4.18348623853211,
1845
+ "grad_norm": 0.30976617336273193,
1846
+ "learning_rate": 4.4610391622989396e-05,
1847
+ "loss": 0.1637,
1848
+ "num_input_tokens_seen": 9452416,
1849
+ "step": 230
1850
+ },
1851
+ {
1852
+ "epoch": 4.201834862385321,
1853
+ "grad_norm": 0.385437935590744,
1854
+ "learning_rate": 4.456520392131035e-05,
1855
+ "loss": 0.2748,
1856
+ "num_input_tokens_seen": 9503528,
1857
+ "step": 231
1858
+ },
1859
+ {
1860
+ "epoch": 4.220183486238533,
1861
+ "grad_norm": 0.37948480248451233,
1862
+ "learning_rate": 4.4519850666916484e-05,
1863
+ "loss": 0.2635,
1864
+ "num_input_tokens_seen": 9541592,
1865
+ "step": 232
1866
+ },
1867
+ {
1868
+ "epoch": 4.238532110091743,
1869
+ "grad_norm": 0.36141568422317505,
1870
+ "learning_rate": 4.447433224356839e-05,
1871
+ "loss": 0.2027,
1872
+ "num_input_tokens_seen": 9586064,
1873
+ "step": 233
1874
+ },
1875
+ {
1876
+ "epoch": 4.256880733944954,
1877
+ "grad_norm": 0.4549350440502167,
1878
+ "learning_rate": 4.442864903642428e-05,
1879
+ "loss": 0.2107,
1880
+ "num_input_tokens_seen": 9641688,
1881
+ "step": 234
1882
+ },
1883
+ {
1884
+ "epoch": 4.275229357798165,
1885
+ "grad_norm": 0.3979765474796295,
1886
+ "learning_rate": 4.438280143203665e-05,
1887
+ "loss": 0.2879,
1888
+ "num_input_tokens_seen": 9686240,
1889
+ "step": 235
1890
+ },
1891
+ {
1892
+ "epoch": 4.293577981651376,
1893
+ "grad_norm": 0.35011065006256104,
1894
+ "learning_rate": 4.43367898183491e-05,
1895
+ "loss": 0.2594,
1896
+ "num_input_tokens_seen": 9735632,
1897
+ "step": 236
1898
+ },
1899
+ {
1900
+ "epoch": 4.3119266055045875,
1901
+ "grad_norm": 0.3999224007129669,
1902
+ "learning_rate": 4.4290614584693004e-05,
1903
+ "loss": 0.1907,
1904
+ "num_input_tokens_seen": 9766536,
1905
+ "step": 237
1906
+ },
1907
+ {
1908
+ "epoch": 4.330275229357798,
1909
+ "grad_norm": 0.39629611372947693,
1910
+ "learning_rate": 4.4244276121784195e-05,
1911
+ "loss": 0.1805,
1912
+ "num_input_tokens_seen": 9796400,
1913
+ "step": 238
1914
+ },
1915
+ {
1916
+ "epoch": 4.348623853211009,
1917
+ "grad_norm": 0.36784592270851135,
1918
+ "learning_rate": 4.4197774821719714e-05,
1919
+ "loss": 0.1824,
1920
+ "num_input_tokens_seen": 9831992,
1921
+ "step": 239
1922
+ },
1923
+ {
1924
+ "epoch": 4.36697247706422,
1925
+ "grad_norm": 0.3408430516719818,
1926
+ "learning_rate": 4.415111107797445e-05,
1927
+ "loss": 0.1721,
1928
+ "num_input_tokens_seen": 9875640,
1929
+ "step": 240
1930
+ },
1931
+ {
1932
+ "epoch": 4.385321100917431,
1933
+ "grad_norm": 0.3232553005218506,
1934
+ "learning_rate": 4.410428528539783e-05,
1935
+ "loss": 0.275,
1936
+ "num_input_tokens_seen": 9916816,
1937
+ "step": 241
1938
+ },
1939
+ {
1940
+ "epoch": 4.4036697247706424,
1941
+ "grad_norm": 0.38150206208229065,
1942
+ "learning_rate": 4.405729784021046e-05,
1943
+ "loss": 0.1963,
1944
+ "num_input_tokens_seen": 9962928,
1945
+ "step": 242
1946
+ },
1947
+ {
1948
+ "epoch": 4.422018348623853,
1949
+ "grad_norm": 0.4176963269710541,
1950
+ "learning_rate": 4.401014914000078e-05,
1951
+ "loss": 0.1626,
1952
+ "num_input_tokens_seen": 9997224,
1953
+ "step": 243
1954
+ },
1955
+ {
1956
+ "epoch": 4.440366972477064,
1957
+ "grad_norm": 0.38855600357055664,
1958
+ "learning_rate": 4.396283958372173e-05,
1959
+ "loss": 0.1733,
1960
+ "num_input_tokens_seen": 10036248,
1961
+ "step": 244
1962
+ },
1963
+ {
1964
+ "epoch": 4.458715596330276,
1965
+ "grad_norm": 0.3860638737678528,
1966
+ "learning_rate": 4.391536957168733e-05,
1967
+ "loss": 0.1936,
1968
+ "num_input_tokens_seen": 10070312,
1969
+ "step": 245
1970
+ },
1971
+ {
1972
+ "epoch": 4.477064220183486,
1973
+ "grad_norm": 0.31510865688323975,
1974
+ "learning_rate": 4.386773950556931e-05,
1975
+ "loss": 0.1847,
1976
+ "num_input_tokens_seen": 10114568,
1977
+ "step": 246
1978
+ },
1979
+ {
1980
+ "epoch": 4.495412844036697,
1981
+ "grad_norm": 0.3280925154685974,
1982
+ "learning_rate": 4.381994978839371e-05,
1983
+ "loss": 0.1981,
1984
+ "num_input_tokens_seen": 10150280,
1985
+ "step": 247
1986
+ },
1987
+ {
1988
+ "epoch": 4.513761467889909,
1989
+ "grad_norm": 0.33136090636253357,
1990
+ "learning_rate": 4.377200082453749e-05,
1991
+ "loss": 0.1681,
1992
+ "num_input_tokens_seen": 10194000,
1993
+ "step": 248
1994
+ },
1995
+ {
1996
+ "epoch": 4.532110091743119,
1997
+ "grad_norm": 0.43955501914024353,
1998
+ "learning_rate": 4.372389301972506e-05,
1999
+ "loss": 0.2111,
2000
+ "num_input_tokens_seen": 10232264,
2001
+ "step": 249
2002
+ },
2003
+ {
2004
+ "epoch": 4.5504587155963305,
2005
+ "grad_norm": 0.28938886523246765,
2006
+ "learning_rate": 4.36756267810249e-05,
2007
+ "loss": 0.2307,
2008
+ "num_input_tokens_seen": 10271880,
2009
+ "step": 250
2010
+ },
2011
+ {
2012
+ "epoch": 4.568807339449541,
2013
+ "grad_norm": 0.37232765555381775,
2014
+ "learning_rate": 4.36272025168461e-05,
2015
+ "loss": 0.1609,
2016
+ "num_input_tokens_seen": 10317720,
2017
+ "step": 251
2018
+ },
2019
+ {
2020
+ "epoch": 4.587155963302752,
2021
+ "grad_norm": 0.6248548030853271,
2022
+ "learning_rate": 4.357862063693486e-05,
2023
+ "loss": 0.2456,
2024
+ "num_input_tokens_seen": 10362168,
2025
+ "step": 252
2026
+ },
2027
+ {
2028
+ "epoch": 4.605504587155964,
2029
+ "grad_norm": 0.32828131318092346,
2030
+ "learning_rate": 4.3529881552371096e-05,
2031
+ "loss": 0.3159,
2032
+ "num_input_tokens_seen": 10414312,
2033
+ "step": 253
2034
+ },
2035
+ {
2036
+ "epoch": 4.623853211009174,
2037
+ "grad_norm": 0.4158332049846649,
2038
+ "learning_rate": 4.34809856755649e-05,
2039
+ "loss": 0.2194,
2040
+ "num_input_tokens_seen": 10451800,
2041
+ "step": 254
2042
+ },
2043
+ {
2044
+ "epoch": 4.6422018348623855,
2045
+ "grad_norm": 0.3648194670677185,
2046
+ "learning_rate": 4.34319334202531e-05,
2047
+ "loss": 0.1846,
2048
+ "num_input_tokens_seen": 10496224,
2049
+ "step": 255
2050
+ },
2051
+ {
2052
+ "epoch": 4.660550458715596,
2053
+ "grad_norm": 0.36835575103759766,
2054
+ "learning_rate": 4.3382725201495723e-05,
2055
+ "loss": 0.1906,
2056
+ "num_input_tokens_seen": 10536392,
2057
+ "step": 256
2058
+ },
2059
+ {
2060
+ "epoch": 4.678899082568807,
2061
+ "grad_norm": 0.3501613140106201,
2062
+ "learning_rate": 4.333336143567247e-05,
2063
+ "loss": 0.1793,
2064
+ "num_input_tokens_seen": 10577640,
2065
+ "step": 257
2066
+ },
2067
+ {
2068
+ "epoch": 4.697247706422019,
2069
+ "grad_norm": 0.3431616425514221,
2070
+ "learning_rate": 4.3283842540479264e-05,
2071
+ "loss": 0.1576,
2072
+ "num_input_tokens_seen": 10613376,
2073
+ "step": 258
2074
+ },
2075
+ {
2076
+ "epoch": 4.715596330275229,
2077
+ "grad_norm": 0.3290237784385681,
2078
+ "learning_rate": 4.3234168934924636e-05,
2079
+ "loss": 0.1447,
2080
+ "num_input_tokens_seen": 10647232,
2081
+ "step": 259
2082
+ },
2083
+ {
2084
+ "epoch": 4.73394495412844,
2085
+ "grad_norm": 0.40264153480529785,
2086
+ "learning_rate": 4.318434103932622e-05,
2087
+ "loss": 0.1488,
2088
+ "num_input_tokens_seen": 10696024,
2089
+ "step": 260
2090
+ },
2091
+ {
2092
+ "epoch": 4.752293577981652,
2093
+ "grad_norm": 0.3453703820705414,
2094
+ "learning_rate": 4.313435927530719e-05,
2095
+ "loss": 0.1597,
2096
+ "num_input_tokens_seen": 10730408,
2097
+ "step": 261
2098
+ },
2099
+ {
2100
+ "epoch": 4.770642201834862,
2101
+ "grad_norm": 0.3993653655052185,
2102
+ "learning_rate": 4.30842240657927e-05,
2103
+ "loss": 0.2266,
2104
+ "num_input_tokens_seen": 10764776,
2105
+ "step": 262
2106
+ },
2107
+ {
2108
+ "epoch": 4.7889908256880735,
2109
+ "grad_norm": 0.4080798923969269,
2110
+ "learning_rate": 4.303393583500628e-05,
2111
+ "loss": 0.1562,
2112
+ "num_input_tokens_seen": 10792272,
2113
+ "step": 263
2114
+ },
2115
+ {
2116
+ "epoch": 4.807339449541285,
2117
+ "grad_norm": 0.3028413951396942,
2118
+ "learning_rate": 4.2983495008466276e-05,
2119
+ "loss": 0.1504,
2120
+ "num_input_tokens_seen": 10825240,
2121
+ "step": 264
2122
+ },
2123
+ {
2124
+ "epoch": 4.825688073394495,
2125
+ "grad_norm": 0.3980019688606262,
2126
+ "learning_rate": 4.293290201298223e-05,
2127
+ "loss": 0.1648,
2128
+ "num_input_tokens_seen": 10883592,
2129
+ "step": 265
2130
+ },
2131
+ {
2132
+ "epoch": 4.844036697247707,
2133
+ "grad_norm": 0.42035797238349915,
2134
+ "learning_rate": 4.288215727665129e-05,
2135
+ "loss": 0.1652,
2136
+ "num_input_tokens_seen": 10922640,
2137
+ "step": 266
2138
+ },
2139
+ {
2140
+ "epoch": 4.862385321100917,
2141
+ "grad_norm": 0.37766003608703613,
2142
+ "learning_rate": 4.2831261228854544e-05,
2143
+ "loss": 0.1817,
2144
+ "num_input_tokens_seen": 10967288,
2145
+ "step": 267
2146
+ },
2147
+ {
2148
+ "epoch": 4.8807339449541285,
2149
+ "grad_norm": 0.3495088815689087,
2150
+ "learning_rate": 4.278021430025343e-05,
2151
+ "loss": 0.2066,
2152
+ "num_input_tokens_seen": 11011152,
2153
+ "step": 268
2154
+ },
2155
+ {
2156
+ "epoch": 4.89908256880734,
2157
+ "grad_norm": 0.34071093797683716,
2158
+ "learning_rate": 4.272901692278609e-05,
2159
+ "loss": 0.1522,
2160
+ "num_input_tokens_seen": 11055608,
2161
+ "step": 269
2162
+ },
2163
+ {
2164
+ "epoch": 4.91743119266055,
2165
+ "grad_norm": 0.33437398076057434,
2166
+ "learning_rate": 4.267766952966369e-05,
2167
+ "loss": 0.2201,
2168
+ "num_input_tokens_seen": 11101992,
2169
+ "step": 270
2170
+ },
2171
+ {
2172
+ "epoch": 4.935779816513762,
2173
+ "grad_norm": 0.3340584337711334,
2174
+ "learning_rate": 4.262617255536676e-05,
2175
+ "loss": 0.2777,
2176
+ "num_input_tokens_seen": 11141408,
2177
+ "step": 271
2178
+ },
2179
+ {
2180
+ "epoch": 4.954128440366972,
2181
+ "grad_norm": 0.348679780960083,
2182
+ "learning_rate": 4.257452643564155e-05,
2183
+ "loss": 0.1857,
2184
+ "num_input_tokens_seen": 11185344,
2185
+ "step": 272
2186
+ },
2187
+ {
2188
+ "epoch": 4.972477064220183,
2189
+ "grad_norm": 0.3691309094429016,
2190
+ "learning_rate": 4.2522731607496275e-05,
2191
+ "loss": 0.1653,
2192
+ "num_input_tokens_seen": 11216160,
2193
+ "step": 273
2194
+ },
2195
+ {
2196
+ "epoch": 4.990825688073395,
2197
+ "grad_norm": 0.4692390561103821,
2198
+ "learning_rate": 4.24707885091975e-05,
2199
+ "loss": 0.1761,
2200
+ "num_input_tokens_seen": 11276200,
2201
+ "step": 274
2202
+ },
2203
+ {
2204
+ "epoch": 5.0,
2205
+ "grad_norm": 0.4963766932487488,
2206
+ "learning_rate": 4.241869758026638e-05,
2207
+ "loss": 0.1582,
2208
+ "num_input_tokens_seen": 11295440,
2209
+ "step": 275
2210
+ },
2211
+ {
2212
+ "epoch": 5.018348623853211,
2213
+ "grad_norm": 0.37284544110298157,
2214
+ "learning_rate": 4.2366459261474933e-05,
2215
+ "loss": 0.1538,
2216
+ "num_input_tokens_seen": 11336400,
2217
+ "step": 276
2218
+ },
2219
+ {
2220
+ "epoch": 5.036697247706422,
2221
+ "grad_norm": 0.2949577867984772,
2222
+ "learning_rate": 4.231407399484236e-05,
2223
+ "loss": 0.1319,
2224
+ "num_input_tokens_seen": 11374056,
2225
+ "step": 277
2226
+ },
2227
+ {
2228
+ "epoch": 5.055045871559633,
2229
+ "grad_norm": 0.32850027084350586,
2230
+ "learning_rate": 4.226154222363124e-05,
2231
+ "loss": 0.174,
2232
+ "num_input_tokens_seen": 11414776,
2233
+ "step": 278
2234
+ },
2235
+ {
2236
+ "epoch": 5.073394495412844,
2237
+ "grad_norm": 0.3812579810619354,
2238
+ "learning_rate": 4.220886439234385e-05,
2239
+ "loss": 0.1831,
2240
+ "num_input_tokens_seen": 11465456,
2241
+ "step": 279
2242
+ },
2243
+ {
2244
+ "epoch": 5.091743119266055,
2245
+ "grad_norm": 0.3396337032318115,
2246
+ "learning_rate": 4.215604094671835e-05,
2247
+ "loss": 0.1515,
2248
+ "num_input_tokens_seen": 11500184,
2249
+ "step": 280
2250
+ },
2251
+ {
2252
+ "epoch": 5.110091743119266,
2253
+ "grad_norm": 0.35079169273376465,
2254
+ "learning_rate": 4.2103072333725e-05,
2255
+ "loss": 0.1295,
2256
+ "num_input_tokens_seen": 11537112,
2257
+ "step": 281
2258
+ },
2259
+ {
2260
+ "epoch": 5.128440366972477,
2261
+ "grad_norm": 0.3811327815055847,
2262
+ "learning_rate": 4.2049959001562464e-05,
2263
+ "loss": 0.1339,
2264
+ "num_input_tokens_seen": 11579440,
2265
+ "step": 282
2266
+ },
2267
+ {
2268
+ "epoch": 5.146788990825688,
2269
+ "grad_norm": 0.3935602009296417,
2270
+ "learning_rate": 4.199670139965393e-05,
2271
+ "loss": 0.1909,
2272
+ "num_input_tokens_seen": 11643272,
2273
+ "step": 283
2274
+ },
2275
+ {
2276
+ "epoch": 5.165137614678899,
2277
+ "grad_norm": 0.3952607810497284,
2278
+ "learning_rate": 4.194329997864331e-05,
2279
+ "loss": 0.2334,
2280
+ "num_input_tokens_seen": 11677528,
2281
+ "step": 284
2282
+ },
2283
+ {
2284
+ "epoch": 5.18348623853211,
2285
+ "grad_norm": 0.3687472939491272,
2286
+ "learning_rate": 4.188975519039151e-05,
2287
+ "loss": 0.1406,
2288
+ "num_input_tokens_seen": 11727944,
2289
+ "step": 285
2290
+ },
2291
+ {
2292
+ "epoch": 5.201834862385321,
2293
+ "grad_norm": 0.3518407344818115,
2294
+ "learning_rate": 4.183606748797251e-05,
2295
+ "loss": 0.138,
2296
+ "num_input_tokens_seen": 11779568,
2297
+ "step": 286
2298
+ },
2299
+ {
2300
+ "epoch": 5.220183486238533,
2301
+ "grad_norm": 0.4072832763195038,
2302
+ "learning_rate": 4.1782237325669595e-05,
2303
+ "loss": 0.159,
2304
+ "num_input_tokens_seen": 11824600,
2305
+ "step": 287
2306
+ },
2307
+ {
2308
+ "epoch": 5.238532110091743,
2309
+ "grad_norm": 0.386280357837677,
2310
+ "learning_rate": 4.172826515897146e-05,
2311
+ "loss": 0.2517,
2312
+ "num_input_tokens_seen": 11873736,
2313
+ "step": 288
2314
+ },
2315
+ {
2316
+ "epoch": 5.256880733944954,
2317
+ "grad_norm": 0.3576860725879669,
2318
+ "learning_rate": 4.167415144456841e-05,
2319
+ "loss": 0.1349,
2320
+ "num_input_tokens_seen": 11909608,
2321
+ "step": 289
2322
+ },
2323
+ {
2324
+ "epoch": 5.275229357798165,
2325
+ "grad_norm": 0.3952435851097107,
2326
+ "learning_rate": 4.1619896640348445e-05,
2327
+ "loss": 0.1348,
2328
+ "num_input_tokens_seen": 11945440,
2329
+ "step": 290
2330
+ },
2331
+ {
2332
+ "epoch": 5.293577981651376,
2333
+ "grad_norm": 0.3565181493759155,
2334
+ "learning_rate": 4.1565501205393445e-05,
2335
+ "loss": 0.1331,
2336
+ "num_input_tokens_seen": 11985568,
2337
+ "step": 291
2338
+ },
2339
+ {
2340
+ "epoch": 5.3119266055045875,
2341
+ "grad_norm": 0.40558820962905884,
2342
+ "learning_rate": 4.1510965599975196e-05,
2343
+ "loss": 0.2337,
2344
+ "num_input_tokens_seen": 12034320,
2345
+ "step": 292
2346
+ },
2347
+ {
2348
+ "epoch": 5.330275229357798,
2349
+ "grad_norm": 0.36426106095314026,
2350
+ "learning_rate": 4.1456290285551596e-05,
2351
+ "loss": 0.1299,
2352
+ "num_input_tokens_seen": 12070184,
2353
+ "step": 293
2354
+ },
2355
+ {
2356
+ "epoch": 5.348623853211009,
2357
+ "grad_norm": 0.33881404995918274,
2358
+ "learning_rate": 4.140147572476268e-05,
2359
+ "loss": 0.1239,
2360
+ "num_input_tokens_seen": 12111512,
2361
+ "step": 294
2362
+ },
2363
+ {
2364
+ "epoch": 5.36697247706422,
2365
+ "grad_norm": 0.38019630312919617,
2366
+ "learning_rate": 4.1346522381426744e-05,
2367
+ "loss": 0.133,
2368
+ "num_input_tokens_seen": 12156792,
2369
+ "step": 295
2370
+ },
2371
+ {
2372
+ "epoch": 5.385321100917431,
2373
+ "grad_norm": 0.38179296255111694,
2374
+ "learning_rate": 4.129143072053638e-05,
2375
+ "loss": 0.1301,
2376
+ "num_input_tokens_seen": 12185168,
2377
+ "step": 296
2378
+ },
2379
+ {
2380
+ "epoch": 5.4036697247706424,
2381
+ "grad_norm": 0.35054150223731995,
2382
+ "learning_rate": 4.123620120825459e-05,
2383
+ "loss": 0.1298,
2384
+ "num_input_tokens_seen": 12222256,
2385
+ "step": 297
2386
+ },
2387
+ {
2388
+ "epoch": 5.422018348623853,
2389
+ "grad_norm": 0.3463946580886841,
2390
+ "learning_rate": 4.118083431191081e-05,
2391
+ "loss": 0.2088,
2392
+ "num_input_tokens_seen": 12257536,
2393
+ "step": 298
2394
+ },
2395
+ {
2396
+ "epoch": 5.440366972477064,
2397
+ "grad_norm": 0.42584434151649475,
2398
+ "learning_rate": 4.112533049999696e-05,
2399
+ "loss": 0.1062,
2400
+ "num_input_tokens_seen": 12290576,
2401
+ "step": 299
2402
+ },
2403
+ {
2404
+ "epoch": 5.458715596330276,
2405
+ "grad_norm": 0.4341515600681305,
2406
+ "learning_rate": 4.1069690242163484e-05,
2407
+ "loss": 0.1989,
2408
+ "num_input_tokens_seen": 12323416,
2409
+ "step": 300
2410
+ },
2411
+ {
2412
+ "epoch": 5.477064220183486,
2413
+ "grad_norm": 0.4299938380718231,
2414
+ "learning_rate": 4.101391400921538e-05,
2415
+ "loss": 0.1243,
2416
+ "num_input_tokens_seen": 12370264,
2417
+ "step": 301
2418
+ },
2419
+ {
2420
+ "epoch": 5.495412844036697,
2421
+ "grad_norm": 0.4070415198802948,
2422
+ "learning_rate": 4.095800227310821e-05,
2423
+ "loss": 0.2281,
2424
+ "num_input_tokens_seen": 12410568,
2425
+ "step": 302
2426
+ },
2427
+ {
2428
+ "epoch": 5.513761467889909,
2429
+ "grad_norm": 0.4446506202220917,
2430
+ "learning_rate": 4.09019555069441e-05,
2431
+ "loss": 0.1462,
2432
+ "num_input_tokens_seen": 12442880,
2433
+ "step": 303
2434
+ },
2435
+ {
2436
+ "epoch": 5.532110091743119,
2437
+ "grad_norm": 0.36110538244247437,
2438
+ "learning_rate": 4.0845774184967754e-05,
2439
+ "loss": 0.1497,
2440
+ "num_input_tokens_seen": 12487016,
2441
+ "step": 304
2442
+ },
2443
+ {
2444
+ "epoch": 5.5504587155963305,
2445
+ "grad_norm": 0.42756903171539307,
2446
+ "learning_rate": 4.078945878256244e-05,
2447
+ "loss": 0.2082,
2448
+ "num_input_tokens_seen": 12525072,
2449
+ "step": 305
2450
+ },
2451
+ {
2452
+ "epoch": 5.568807339449541,
2453
+ "grad_norm": 0.360649049282074,
2454
+ "learning_rate": 4.073300977624594e-05,
2455
+ "loss": 0.1214,
2456
+ "num_input_tokens_seen": 12555792,
2457
+ "step": 306
2458
+ },
2459
+ {
2460
+ "epoch": 5.587155963302752,
2461
+ "grad_norm": 0.3768391013145447,
2462
+ "learning_rate": 4.067642764366654e-05,
2463
+ "loss": 0.1278,
2464
+ "num_input_tokens_seen": 12601616,
2465
+ "step": 307
2466
+ },
2467
+ {
2468
+ "epoch": 5.605504587155964,
2469
+ "grad_norm": 0.3882285952568054,
2470
+ "learning_rate": 4.0619712863599e-05,
2471
+ "loss": 0.1485,
2472
+ "num_input_tokens_seen": 12634360,
2473
+ "step": 308
2474
+ },
2475
+ {
2476
+ "epoch": 5.623853211009174,
2477
+ "grad_norm": 0.38816162943840027,
2478
+ "learning_rate": 4.0562865915940496e-05,
2479
+ "loss": 0.1221,
2480
+ "num_input_tokens_seen": 12674808,
2481
+ "step": 309
2482
+ },
2483
+ {
2484
+ "epoch": 5.6422018348623855,
2485
+ "grad_norm": 0.41803887486457825,
2486
+ "learning_rate": 4.05058872817065e-05,
2487
+ "loss": 0.1388,
2488
+ "num_input_tokens_seen": 12710864,
2489
+ "step": 310
2490
+ },
2491
+ {
2492
+ "epoch": 5.660550458715596,
2493
+ "grad_norm": 0.3802741467952728,
2494
+ "learning_rate": 4.044877744302683e-05,
2495
+ "loss": 0.1349,
2496
+ "num_input_tokens_seen": 12750920,
2497
+ "step": 311
2498
+ },
2499
+ {
2500
+ "epoch": 5.678899082568807,
2501
+ "grad_norm": 0.48202404379844666,
2502
+ "learning_rate": 4.039153688314145e-05,
2503
+ "loss": 0.1555,
2504
+ "num_input_tokens_seen": 12789488,
2505
+ "step": 312
2506
+ },
2507
+ {
2508
+ "epoch": 5.697247706422019,
2509
+ "grad_norm": 0.3168826103210449,
2510
+ "learning_rate": 4.0334166086396484e-05,
2511
+ "loss": 0.1063,
2512
+ "num_input_tokens_seen": 12831408,
2513
+ "step": 313
2514
+ },
2515
+ {
2516
+ "epoch": 5.715596330275229,
2517
+ "grad_norm": 0.43414828181266785,
2518
+ "learning_rate": 4.0276665538239996e-05,
2519
+ "loss": 0.127,
2520
+ "num_input_tokens_seen": 12872584,
2521
+ "step": 314
2522
+ },
2523
+ {
2524
+ "epoch": 5.73394495412844,
2525
+ "grad_norm": 0.47761547565460205,
2526
+ "learning_rate": 4.021903572521802e-05,
2527
+ "loss": 0.1428,
2528
+ "num_input_tokens_seen": 12910528,
2529
+ "step": 315
2530
+ },
2531
+ {
2532
+ "epoch": 5.752293577981652,
2533
+ "grad_norm": 0.3542017936706543,
2534
+ "learning_rate": 4.0161277134970345e-05,
2535
+ "loss": 0.1279,
2536
+ "num_input_tokens_seen": 12942800,
2537
+ "step": 316
2538
+ },
2539
+ {
2540
+ "epoch": 5.770642201834862,
2541
+ "grad_norm": 0.31866851449012756,
2542
+ "learning_rate": 4.010339025622641e-05,
2543
+ "loss": 0.1459,
2544
+ "num_input_tokens_seen": 12989136,
2545
+ "step": 317
2546
+ },
2547
+ {
2548
+ "epoch": 5.7889908256880735,
2549
+ "grad_norm": 0.44918256998062134,
2550
+ "learning_rate": 4.0045375578801214e-05,
2551
+ "loss": 0.1429,
2552
+ "num_input_tokens_seen": 13035472,
2553
+ "step": 318
2554
+ },
2555
+ {
2556
+ "epoch": 5.807339449541285,
2557
+ "grad_norm": 0.32426726818084717,
2558
+ "learning_rate": 3.99872335935911e-05,
2559
+ "loss": 0.1257,
2560
+ "num_input_tokens_seen": 13074952,
2561
+ "step": 319
2562
+ },
2563
+ {
2564
+ "epoch": 5.825688073394495,
2565
+ "grad_norm": 0.6903991103172302,
2566
+ "learning_rate": 3.9928964792569655e-05,
2567
+ "loss": 0.1807,
2568
+ "num_input_tokens_seen": 13124624,
2569
+ "step": 320
2570
+ },
2571
+ {
2572
+ "epoch": 5.844036697247707,
2573
+ "grad_norm": 0.3665274679660797,
2574
+ "learning_rate": 3.9870569668783536e-05,
2575
+ "loss": 0.1853,
2576
+ "num_input_tokens_seen": 13171464,
2577
+ "step": 321
2578
+ },
2579
+ {
2580
+ "epoch": 5.862385321100917,
2581
+ "grad_norm": 0.41457998752593994,
2582
+ "learning_rate": 3.981204871634827e-05,
2583
+ "loss": 0.214,
2584
+ "num_input_tokens_seen": 13225240,
2585
+ "step": 322
2586
+ },
2587
+ {
2588
+ "epoch": 5.8807339449541285,
2589
+ "grad_norm": 0.4047159254550934,
2590
+ "learning_rate": 3.9753402430444116e-05,
2591
+ "loss": 0.1907,
2592
+ "num_input_tokens_seen": 13275848,
2593
+ "step": 323
2594
+ },
2595
+ {
2596
+ "epoch": 5.89908256880734,
2597
+ "grad_norm": 0.4578211307525635,
2598
+ "learning_rate": 3.969463130731183e-05,
2599
+ "loss": 0.27,
2600
+ "num_input_tokens_seen": 13311096,
2601
+ "step": 324
2602
+ }
2603
+ ],
2604
+ "logging_steps": 1.0,
2605
+ "max_steps": 1080,
2606
+ "num_input_tokens_seen": 13311096,
2607
+ "num_train_epochs": 20,
2608
+ "save_steps": 54,
2609
+ "stateful_callbacks": {
2610
+ "TrainerControl": {
2611
+ "args": {
2612
+ "should_epoch_stop": false,
2613
+ "should_evaluate": false,
2614
+ "should_log": false,
2615
+ "should_save": true,
2616
+ "should_training_stop": false
2617
+ },
2618
+ "attributes": {}
2619
+ }
2620
+ },
2621
+ "total_flos": 1.1229463256131174e+18,
2622
+ "train_batch_size": 1,
2623
+ "trial_name": null,
2624
+ "trial_params": null
2625
+ }
checkpoint-378/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-Coder-14B-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-378/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-14B-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": 0.05,
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
+ "q_proj",
24
+ "v_proj",
25
+ "up_proj",
26
+ "gate_proj",
27
+ "o_proj",
28
+ "k_proj",
29
+ "down_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-378/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-378/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-378/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-378/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": 15000,
204
+ "pad_token": "<|endoftext|>",
205
+ "padding_side": "right",
206
+ "split_special_tokens": false,
207
+ "tokenizer_class": "Qwen2Tokenizer",
208
+ "unk_token": null
209
+ }
checkpoint-378/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-432/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-14B-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": 0.05,
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
+ "q_proj",
24
+ "v_proj",
25
+ "up_proj",
26
+ "gate_proj",
27
+ "o_proj",
28
+ "k_proj",
29
+ "down_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-432/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-432/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-432/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": 15000,
204
+ "pad_token": "<|endoftext|>",
205
+ "padding_side": "right",
206
+ "split_special_tokens": false,
207
+ "tokenizer_class": "Qwen2Tokenizer",
208
+ "unk_token": null
209
+ }
checkpoint-432/trainer_state.json ADDED
@@ -0,0 +1,3489 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 7.862385321100917,
5
+ "eval_steps": 500,
6
+ "global_step": 432,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01834862385321101,
13
+ "grad_norm": 0.04378490149974823,
14
+ "learning_rate": 4.999989423013716e-05,
15
+ "loss": 0.6713,
16
+ "num_input_tokens_seen": 44136,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.03669724770642202,
21
+ "grad_norm": 0.040646992623806,
22
+ "learning_rate": 4.999957692144361e-05,
23
+ "loss": 0.533,
24
+ "num_input_tokens_seen": 83096,
25
+ "step": 2
26
+ },
27
+ {
28
+ "epoch": 0.05504587155963303,
29
+ "grad_norm": 0.04658753052353859,
30
+ "learning_rate": 4.999904807660428e-05,
31
+ "loss": 0.6048,
32
+ "num_input_tokens_seen": 122112,
33
+ "step": 3
34
+ },
35
+ {
36
+ "epoch": 0.07339449541284404,
37
+ "grad_norm": 0.04322144016623497,
38
+ "learning_rate": 4.999830770009406e-05,
39
+ "loss": 0.4948,
40
+ "num_input_tokens_seen": 163064,
41
+ "step": 4
42
+ },
43
+ {
44
+ "epoch": 0.09174311926605505,
45
+ "grad_norm": 0.06536195427179337,
46
+ "learning_rate": 4.999735579817769e-05,
47
+ "loss": 0.6607,
48
+ "num_input_tokens_seen": 203808,
49
+ "step": 5
50
+ },
51
+ {
52
+ "epoch": 0.11009174311926606,
53
+ "grad_norm": 0.059904925525188446,
54
+ "learning_rate": 4.9996192378909786e-05,
55
+ "loss": 0.5802,
56
+ "num_input_tokens_seen": 241824,
57
+ "step": 6
58
+ },
59
+ {
60
+ "epoch": 0.12844036697247707,
61
+ "grad_norm": 0.19818365573883057,
62
+ "learning_rate": 4.999481745213471e-05,
63
+ "loss": 0.5148,
64
+ "num_input_tokens_seen": 287608,
65
+ "step": 7
66
+ },
67
+ {
68
+ "epoch": 0.14678899082568808,
69
+ "grad_norm": 0.05985472351312637,
70
+ "learning_rate": 4.9993231029486544e-05,
71
+ "loss": 0.5714,
72
+ "num_input_tokens_seen": 325320,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.1651376146788991,
77
+ "grad_norm": 0.061375778168439865,
78
+ "learning_rate": 4.999143312438893e-05,
79
+ "loss": 0.6812,
80
+ "num_input_tokens_seen": 369848,
81
+ "step": 9
82
+ },
83
+ {
84
+ "epoch": 0.1834862385321101,
85
+ "grad_norm": 0.06196414306759834,
86
+ "learning_rate": 4.998942375205502e-05,
87
+ "loss": 0.5358,
88
+ "num_input_tokens_seen": 415104,
89
+ "step": 10
90
+ },
91
+ {
92
+ "epoch": 0.2018348623853211,
93
+ "grad_norm": 0.07861393690109253,
94
+ "learning_rate": 4.9987202929487275e-05,
95
+ "loss": 0.6527,
96
+ "num_input_tokens_seen": 467224,
97
+ "step": 11
98
+ },
99
+ {
100
+ "epoch": 0.22018348623853212,
101
+ "grad_norm": 0.05596446990966797,
102
+ "learning_rate": 4.99847706754774e-05,
103
+ "loss": 0.5354,
104
+ "num_input_tokens_seen": 502824,
105
+ "step": 12
106
+ },
107
+ {
108
+ "epoch": 0.23853211009174313,
109
+ "grad_norm": 0.05289844051003456,
110
+ "learning_rate": 4.998212701060612e-05,
111
+ "loss": 0.5263,
112
+ "num_input_tokens_seen": 544744,
113
+ "step": 13
114
+ },
115
+ {
116
+ "epoch": 0.25688073394495414,
117
+ "grad_norm": 0.04996591433882713,
118
+ "learning_rate": 4.997927195724303e-05,
119
+ "loss": 0.5536,
120
+ "num_input_tokens_seen": 591136,
121
+ "step": 14
122
+ },
123
+ {
124
+ "epoch": 0.27522935779816515,
125
+ "grad_norm": 0.05822828412055969,
126
+ "learning_rate": 4.997620553954645e-05,
127
+ "loss": 0.6106,
128
+ "num_input_tokens_seen": 629664,
129
+ "step": 15
130
+ },
131
+ {
132
+ "epoch": 0.29357798165137616,
133
+ "grad_norm": 0.06353770196437836,
134
+ "learning_rate": 4.997292778346312e-05,
135
+ "loss": 0.5129,
136
+ "num_input_tokens_seen": 663392,
137
+ "step": 16
138
+ },
139
+ {
140
+ "epoch": 0.3119266055045872,
141
+ "grad_norm": 0.07256966829299927,
142
+ "learning_rate": 4.996943871672807e-05,
143
+ "loss": 0.6377,
144
+ "num_input_tokens_seen": 698360,
145
+ "step": 17
146
+ },
147
+ {
148
+ "epoch": 0.3302752293577982,
149
+ "grad_norm": 0.055458713322877884,
150
+ "learning_rate": 4.996573836886435e-05,
151
+ "loss": 0.4083,
152
+ "num_input_tokens_seen": 737520,
153
+ "step": 18
154
+ },
155
+ {
156
+ "epoch": 0.3486238532110092,
157
+ "grad_norm": 0.07792335003614426,
158
+ "learning_rate": 4.9961826771182784e-05,
159
+ "loss": 0.6086,
160
+ "num_input_tokens_seen": 768056,
161
+ "step": 19
162
+ },
163
+ {
164
+ "epoch": 0.3669724770642202,
165
+ "grad_norm": 0.06627275049686432,
166
+ "learning_rate": 4.995770395678171e-05,
167
+ "loss": 0.4591,
168
+ "num_input_tokens_seen": 806256,
169
+ "step": 20
170
+ },
171
+ {
172
+ "epoch": 0.3853211009174312,
173
+ "grad_norm": 0.05830290913581848,
174
+ "learning_rate": 4.9953369960546676e-05,
175
+ "loss": 0.3731,
176
+ "num_input_tokens_seen": 842336,
177
+ "step": 21
178
+ },
179
+ {
180
+ "epoch": 0.4036697247706422,
181
+ "grad_norm": 0.07277437299489975,
182
+ "learning_rate": 4.9948824819150185e-05,
183
+ "loss": 0.6243,
184
+ "num_input_tokens_seen": 876672,
185
+ "step": 22
186
+ },
187
+ {
188
+ "epoch": 0.42201834862385323,
189
+ "grad_norm": 0.07477546483278275,
190
+ "learning_rate": 4.994406857105136e-05,
191
+ "loss": 0.5788,
192
+ "num_input_tokens_seen": 915192,
193
+ "step": 23
194
+ },
195
+ {
196
+ "epoch": 0.44036697247706424,
197
+ "grad_norm": 0.06912907212972641,
198
+ "learning_rate": 4.993910125649561e-05,
199
+ "loss": 0.4753,
200
+ "num_input_tokens_seen": 951904,
201
+ "step": 24
202
+ },
203
+ {
204
+ "epoch": 0.45871559633027525,
205
+ "grad_norm": 0.0655476376414299,
206
+ "learning_rate": 4.993392291751431e-05,
207
+ "loss": 0.4518,
208
+ "num_input_tokens_seen": 1001816,
209
+ "step": 25
210
+ },
211
+ {
212
+ "epoch": 0.47706422018348627,
213
+ "grad_norm": 0.06466512382030487,
214
+ "learning_rate": 4.992853359792444e-05,
215
+ "loss": 0.5638,
216
+ "num_input_tokens_seen": 1053064,
217
+ "step": 26
218
+ },
219
+ {
220
+ "epoch": 0.4954128440366973,
221
+ "grad_norm": 0.0645688995718956,
222
+ "learning_rate": 4.99229333433282e-05,
223
+ "loss": 0.4644,
224
+ "num_input_tokens_seen": 1086688,
225
+ "step": 27
226
+ },
227
+ {
228
+ "epoch": 0.5137614678899083,
229
+ "grad_norm": 0.07181251049041748,
230
+ "learning_rate": 4.9917122201112656e-05,
231
+ "loss": 0.6191,
232
+ "num_input_tokens_seen": 1134824,
233
+ "step": 28
234
+ },
235
+ {
236
+ "epoch": 0.5321100917431193,
237
+ "grad_norm": 0.07322589308023453,
238
+ "learning_rate": 4.9911100220449293e-05,
239
+ "loss": 0.6752,
240
+ "num_input_tokens_seen": 1172072,
241
+ "step": 29
242
+ },
243
+ {
244
+ "epoch": 0.5504587155963303,
245
+ "grad_norm": 0.06396070122718811,
246
+ "learning_rate": 4.990486745229364e-05,
247
+ "loss": 0.3587,
248
+ "num_input_tokens_seen": 1211096,
249
+ "step": 30
250
+ },
251
+ {
252
+ "epoch": 0.5688073394495413,
253
+ "grad_norm": 0.07803395390510559,
254
+ "learning_rate": 4.989842394938482e-05,
255
+ "loss": 0.459,
256
+ "num_input_tokens_seen": 1259456,
257
+ "step": 31
258
+ },
259
+ {
260
+ "epoch": 0.5871559633027523,
261
+ "grad_norm": 0.05974648892879486,
262
+ "learning_rate": 4.989176976624511e-05,
263
+ "loss": 0.4148,
264
+ "num_input_tokens_seen": 1306944,
265
+ "step": 32
266
+ },
267
+ {
268
+ "epoch": 0.6055045871559633,
269
+ "grad_norm": 0.09784268587827682,
270
+ "learning_rate": 4.988490495917947e-05,
271
+ "loss": 0.539,
272
+ "num_input_tokens_seen": 1353744,
273
+ "step": 33
274
+ },
275
+ {
276
+ "epoch": 0.6238532110091743,
277
+ "grad_norm": 0.09906516224145889,
278
+ "learning_rate": 4.987782958627508e-05,
279
+ "loss": 0.5453,
280
+ "num_input_tokens_seen": 1394736,
281
+ "step": 34
282
+ },
283
+ {
284
+ "epoch": 0.6422018348623854,
285
+ "grad_norm": 0.08984062820672989,
286
+ "learning_rate": 4.987054370740083e-05,
287
+ "loss": 0.468,
288
+ "num_input_tokens_seen": 1442048,
289
+ "step": 35
290
+ },
291
+ {
292
+ "epoch": 0.6605504587155964,
293
+ "grad_norm": 0.08672655373811722,
294
+ "learning_rate": 4.9863047384206835e-05,
295
+ "loss": 0.4078,
296
+ "num_input_tokens_seen": 1478440,
297
+ "step": 36
298
+ },
299
+ {
300
+ "epoch": 0.6788990825688074,
301
+ "grad_norm": 0.1327345073223114,
302
+ "learning_rate": 4.9855340680123905e-05,
303
+ "loss": 0.5299,
304
+ "num_input_tokens_seen": 1525992,
305
+ "step": 37
306
+ },
307
+ {
308
+ "epoch": 0.6972477064220184,
309
+ "grad_norm": 0.09178602695465088,
310
+ "learning_rate": 4.9847423660363e-05,
311
+ "loss": 0.439,
312
+ "num_input_tokens_seen": 1555608,
313
+ "step": 38
314
+ },
315
+ {
316
+ "epoch": 0.7155963302752294,
317
+ "grad_norm": 0.09418320655822754,
318
+ "learning_rate": 4.983929639191469e-05,
319
+ "loss": 0.5337,
320
+ "num_input_tokens_seen": 1597392,
321
+ "step": 39
322
+ },
323
+ {
324
+ "epoch": 0.7339449541284404,
325
+ "grad_norm": 0.08294719457626343,
326
+ "learning_rate": 4.983095894354858e-05,
327
+ "loss": 0.4536,
328
+ "num_input_tokens_seen": 1649656,
329
+ "step": 40
330
+ },
331
+ {
332
+ "epoch": 0.7522935779816514,
333
+ "grad_norm": 0.09774205833673477,
334
+ "learning_rate": 4.982241138581273e-05,
335
+ "loss": 0.5221,
336
+ "num_input_tokens_seen": 1695952,
337
+ "step": 41
338
+ },
339
+ {
340
+ "epoch": 0.7706422018348624,
341
+ "grad_norm": 0.09319107979536057,
342
+ "learning_rate": 4.9813653791033057e-05,
343
+ "loss": 0.4279,
344
+ "num_input_tokens_seen": 1737224,
345
+ "step": 42
346
+ },
347
+ {
348
+ "epoch": 0.7889908256880734,
349
+ "grad_norm": 0.09561405330896378,
350
+ "learning_rate": 4.980468623331273e-05,
351
+ "loss": 0.5121,
352
+ "num_input_tokens_seen": 1772320,
353
+ "step": 43
354
+ },
355
+ {
356
+ "epoch": 0.8073394495412844,
357
+ "grad_norm": 0.08274025470018387,
358
+ "learning_rate": 4.979550878853154e-05,
359
+ "loss": 0.54,
360
+ "num_input_tokens_seen": 1823888,
361
+ "step": 44
362
+ },
363
+ {
364
+ "epoch": 0.8256880733944955,
365
+ "grad_norm": 0.08728913217782974,
366
+ "learning_rate": 4.9786121534345265e-05,
367
+ "loss": 0.4488,
368
+ "num_input_tokens_seen": 1872488,
369
+ "step": 45
370
+ },
371
+ {
372
+ "epoch": 0.8440366972477065,
373
+ "grad_norm": 0.0787016749382019,
374
+ "learning_rate": 4.9776524550184965e-05,
375
+ "loss": 0.4353,
376
+ "num_input_tokens_seen": 1924744,
377
+ "step": 46
378
+ },
379
+ {
380
+ "epoch": 0.8623853211009175,
381
+ "grad_norm": 0.10952188074588776,
382
+ "learning_rate": 4.97667179172564e-05,
383
+ "loss": 0.4784,
384
+ "num_input_tokens_seen": 1959936,
385
+ "step": 47
386
+ },
387
+ {
388
+ "epoch": 0.8807339449541285,
389
+ "grad_norm": 0.08525826781988144,
390
+ "learning_rate": 4.975670171853926e-05,
391
+ "loss": 0.3586,
392
+ "num_input_tokens_seen": 2003896,
393
+ "step": 48
394
+ },
395
+ {
396
+ "epoch": 0.8990825688073395,
397
+ "grad_norm": 0.10409987717866898,
398
+ "learning_rate": 4.9746476038786496e-05,
399
+ "loss": 0.4451,
400
+ "num_input_tokens_seen": 2047632,
401
+ "step": 49
402
+ },
403
+ {
404
+ "epoch": 0.9174311926605505,
405
+ "grad_norm": 0.0782993957400322,
406
+ "learning_rate": 4.973604096452361e-05,
407
+ "loss": 0.3591,
408
+ "num_input_tokens_seen": 2096928,
409
+ "step": 50
410
+ },
411
+ {
412
+ "epoch": 0.9357798165137615,
413
+ "grad_norm": 0.09829951077699661,
414
+ "learning_rate": 4.9725396584047925e-05,
415
+ "loss": 0.3415,
416
+ "num_input_tokens_seen": 2129536,
417
+ "step": 51
418
+ },
419
+ {
420
+ "epoch": 0.9541284403669725,
421
+ "grad_norm": 0.10606162995100021,
422
+ "learning_rate": 4.971454298742779e-05,
423
+ "loss": 0.3758,
424
+ "num_input_tokens_seen": 2169144,
425
+ "step": 52
426
+ },
427
+ {
428
+ "epoch": 0.9724770642201835,
429
+ "grad_norm": 0.09280356764793396,
430
+ "learning_rate": 4.97034802665019e-05,
431
+ "loss": 0.485,
432
+ "num_input_tokens_seen": 2207720,
433
+ "step": 53
434
+ },
435
+ {
436
+ "epoch": 0.9908256880733946,
437
+ "grad_norm": 0.11888203024864197,
438
+ "learning_rate": 4.9692208514878444e-05,
439
+ "loss": 0.3469,
440
+ "num_input_tokens_seen": 2236392,
441
+ "step": 54
442
+ },
443
+ {
444
+ "epoch": 1.0,
445
+ "grad_norm": 0.13222463428974152,
446
+ "learning_rate": 4.9680727827934354e-05,
447
+ "loss": 0.4284,
448
+ "num_input_tokens_seen": 2259088,
449
+ "step": 55
450
+ },
451
+ {
452
+ "epoch": 1.018348623853211,
453
+ "grad_norm": 0.10572745651006699,
454
+ "learning_rate": 4.966903830281449e-05,
455
+ "loss": 0.4186,
456
+ "num_input_tokens_seen": 2298496,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 1.036697247706422,
461
+ "grad_norm": 0.11462350189685822,
462
+ "learning_rate": 4.965714003843079e-05,
463
+ "loss": 0.4696,
464
+ "num_input_tokens_seen": 2333016,
465
+ "step": 57
466
+ },
467
+ {
468
+ "epoch": 1.0550458715596331,
469
+ "grad_norm": 0.11215240508317947,
470
+ "learning_rate": 4.9645033135461494e-05,
471
+ "loss": 0.3905,
472
+ "num_input_tokens_seen": 2367992,
473
+ "step": 58
474
+ },
475
+ {
476
+ "epoch": 1.073394495412844,
477
+ "grad_norm": 0.0973561555147171,
478
+ "learning_rate": 4.963271769635024e-05,
479
+ "loss": 0.3588,
480
+ "num_input_tokens_seen": 2415328,
481
+ "step": 59
482
+ },
483
+ {
484
+ "epoch": 1.091743119266055,
485
+ "grad_norm": 0.10240709036588669,
486
+ "learning_rate": 4.962019382530521e-05,
487
+ "loss": 0.5532,
488
+ "num_input_tokens_seen": 2454792,
489
+ "step": 60
490
+ },
491
+ {
492
+ "epoch": 1.110091743119266,
493
+ "grad_norm": 0.0959337130188942,
494
+ "learning_rate": 4.9607461628298244e-05,
495
+ "loss": 0.331,
496
+ "num_input_tokens_seen": 2503072,
497
+ "step": 61
498
+ },
499
+ {
500
+ "epoch": 1.1284403669724772,
501
+ "grad_norm": 0.10228750854730606,
502
+ "learning_rate": 4.9594521213063974e-05,
503
+ "loss": 0.3728,
504
+ "num_input_tokens_seen": 2546960,
505
+ "step": 62
506
+ },
507
+ {
508
+ "epoch": 1.146788990825688,
509
+ "grad_norm": 0.09403488785028458,
510
+ "learning_rate": 4.958137268909887e-05,
511
+ "loss": 0.4695,
512
+ "num_input_tokens_seen": 2595432,
513
+ "step": 63
514
+ },
515
+ {
516
+ "epoch": 1.165137614678899,
517
+ "grad_norm": 0.11396344751119614,
518
+ "learning_rate": 4.9568016167660334e-05,
519
+ "loss": 0.3653,
520
+ "num_input_tokens_seen": 2633912,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 1.18348623853211,
525
+ "grad_norm": 0.09487481415271759,
526
+ "learning_rate": 4.9554451761765766e-05,
527
+ "loss": 0.3498,
528
+ "num_input_tokens_seen": 2680792,
529
+ "step": 65
530
+ },
531
+ {
532
+ "epoch": 1.2018348623853212,
533
+ "grad_norm": 0.1249895691871643,
534
+ "learning_rate": 4.9540679586191605e-05,
535
+ "loss": 0.4053,
536
+ "num_input_tokens_seen": 2716584,
537
+ "step": 66
538
+ },
539
+ {
540
+ "epoch": 1.2201834862385321,
541
+ "grad_norm": 0.12268221378326416,
542
+ "learning_rate": 4.952669975747232e-05,
543
+ "loss": 0.4189,
544
+ "num_input_tokens_seen": 2757088,
545
+ "step": 67
546
+ },
547
+ {
548
+ "epoch": 1.238532110091743,
549
+ "grad_norm": 0.12126032263040543,
550
+ "learning_rate": 4.951251239389948e-05,
551
+ "loss": 0.4994,
552
+ "num_input_tokens_seen": 2795664,
553
+ "step": 68
554
+ },
555
+ {
556
+ "epoch": 1.2568807339449541,
557
+ "grad_norm": 0.1069057360291481,
558
+ "learning_rate": 4.949811761552074e-05,
559
+ "loss": 0.3275,
560
+ "num_input_tokens_seen": 2840936,
561
+ "step": 69
562
+ },
563
+ {
564
+ "epoch": 1.2752293577981653,
565
+ "grad_norm": 0.10893313586711884,
566
+ "learning_rate": 4.948351554413879e-05,
567
+ "loss": 0.4366,
568
+ "num_input_tokens_seen": 2886768,
569
+ "step": 70
570
+ },
571
+ {
572
+ "epoch": 1.2935779816513762,
573
+ "grad_norm": 0.12898756563663483,
574
+ "learning_rate": 4.9468706303310355e-05,
575
+ "loss": 0.3916,
576
+ "num_input_tokens_seen": 2919328,
577
+ "step": 71
578
+ },
579
+ {
580
+ "epoch": 1.311926605504587,
581
+ "grad_norm": 0.12405356019735336,
582
+ "learning_rate": 4.9453690018345144e-05,
583
+ "loss": 0.3249,
584
+ "num_input_tokens_seen": 2966744,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 1.3302752293577982,
589
+ "grad_norm": 0.13137595355510712,
590
+ "learning_rate": 4.943846681630479e-05,
591
+ "loss": 0.3956,
592
+ "num_input_tokens_seen": 3007248,
593
+ "step": 73
594
+ },
595
+ {
596
+ "epoch": 1.3486238532110093,
597
+ "grad_norm": 0.13920250535011292,
598
+ "learning_rate": 4.942303682600178e-05,
599
+ "loss": 0.3956,
600
+ "num_input_tokens_seen": 3050960,
601
+ "step": 74
602
+ },
603
+ {
604
+ "epoch": 1.3669724770642202,
605
+ "grad_norm": 0.1255589872598648,
606
+ "learning_rate": 4.940740017799833e-05,
607
+ "loss": 0.3773,
608
+ "num_input_tokens_seen": 3088592,
609
+ "step": 75
610
+ },
611
+ {
612
+ "epoch": 1.385321100917431,
613
+ "grad_norm": 0.10222747176885605,
614
+ "learning_rate": 4.939155700460536e-05,
615
+ "loss": 0.4,
616
+ "num_input_tokens_seen": 3153520,
617
+ "step": 76
618
+ },
619
+ {
620
+ "epoch": 1.4036697247706422,
621
+ "grad_norm": 0.13205283880233765,
622
+ "learning_rate": 4.9375507439881266e-05,
623
+ "loss": 0.4343,
624
+ "num_input_tokens_seen": 3199272,
625
+ "step": 77
626
+ },
627
+ {
628
+ "epoch": 1.4220183486238533,
629
+ "grad_norm": 0.11005694419145584,
630
+ "learning_rate": 4.9359251619630886e-05,
631
+ "loss": 0.3881,
632
+ "num_input_tokens_seen": 3247128,
633
+ "step": 78
634
+ },
635
+ {
636
+ "epoch": 1.4403669724770642,
637
+ "grad_norm": 0.14799247682094574,
638
+ "learning_rate": 4.9342789681404275e-05,
639
+ "loss": 0.3972,
640
+ "num_input_tokens_seen": 3294192,
641
+ "step": 79
642
+ },
643
+ {
644
+ "epoch": 1.4587155963302751,
645
+ "grad_norm": 0.1279418021440506,
646
+ "learning_rate": 4.9326121764495596e-05,
647
+ "loss": 0.3438,
648
+ "num_input_tokens_seen": 3329736,
649
+ "step": 80
650
+ },
651
+ {
652
+ "epoch": 1.4770642201834863,
653
+ "grad_norm": 0.11036807298660278,
654
+ "learning_rate": 4.9309248009941914e-05,
655
+ "loss": 0.3189,
656
+ "num_input_tokens_seen": 3371376,
657
+ "step": 81
658
+ },
659
+ {
660
+ "epoch": 1.4954128440366974,
661
+ "grad_norm": 0.11855707317590714,
662
+ "learning_rate": 4.9292168560522014e-05,
663
+ "loss": 0.401,
664
+ "num_input_tokens_seen": 3412368,
665
+ "step": 82
666
+ },
667
+ {
668
+ "epoch": 1.5137614678899083,
669
+ "grad_norm": 0.13195356726646423,
670
+ "learning_rate": 4.9274883560755156e-05,
671
+ "loss": 0.4973,
672
+ "num_input_tokens_seen": 3455000,
673
+ "step": 83
674
+ },
675
+ {
676
+ "epoch": 1.5321100917431192,
677
+ "grad_norm": 0.1462787538766861,
678
+ "learning_rate": 4.925739315689991e-05,
679
+ "loss": 0.3768,
680
+ "num_input_tokens_seen": 3488960,
681
+ "step": 84
682
+ },
683
+ {
684
+ "epoch": 1.5504587155963303,
685
+ "grad_norm": 0.13765974342823029,
686
+ "learning_rate": 4.92396974969529e-05,
687
+ "loss": 0.2999,
688
+ "num_input_tokens_seen": 3521320,
689
+ "step": 85
690
+ },
691
+ {
692
+ "epoch": 1.5688073394495414,
693
+ "grad_norm": 0.15276113152503967,
694
+ "learning_rate": 4.9221796730647516e-05,
695
+ "loss": 0.3638,
696
+ "num_input_tokens_seen": 3559464,
697
+ "step": 86
698
+ },
699
+ {
700
+ "epoch": 1.5871559633027523,
701
+ "grad_norm": 0.1441674381494522,
702
+ "learning_rate": 4.92036910094527e-05,
703
+ "loss": 0.3919,
704
+ "num_input_tokens_seen": 3598080,
705
+ "step": 87
706
+ },
707
+ {
708
+ "epoch": 1.6055045871559632,
709
+ "grad_norm": 0.1780252456665039,
710
+ "learning_rate": 4.9185380486571595e-05,
711
+ "loss": 0.3626,
712
+ "num_input_tokens_seen": 3630064,
713
+ "step": 88
714
+ },
715
+ {
716
+ "epoch": 1.6238532110091743,
717
+ "grad_norm": 0.16947726905345917,
718
+ "learning_rate": 4.916686531694035e-05,
719
+ "loss": 0.3439,
720
+ "num_input_tokens_seen": 3661408,
721
+ "step": 89
722
+ },
723
+ {
724
+ "epoch": 1.6422018348623855,
725
+ "grad_norm": 0.1552971601486206,
726
+ "learning_rate": 4.914814565722671e-05,
727
+ "loss": 0.3236,
728
+ "num_input_tokens_seen": 3695480,
729
+ "step": 90
730
+ },
731
+ {
732
+ "epoch": 1.6605504587155964,
733
+ "grad_norm": 0.14925938844680786,
734
+ "learning_rate": 4.912922166582874e-05,
735
+ "loss": 0.4255,
736
+ "num_input_tokens_seen": 3734560,
737
+ "step": 91
738
+ },
739
+ {
740
+ "epoch": 1.6788990825688073,
741
+ "grad_norm": 0.1332874596118927,
742
+ "learning_rate": 4.9110093502873476e-05,
743
+ "loss": 0.3061,
744
+ "num_input_tokens_seen": 3773112,
745
+ "step": 92
746
+ },
747
+ {
748
+ "epoch": 1.6972477064220184,
749
+ "grad_norm": 0.15471243858337402,
750
+ "learning_rate": 4.909076133021557e-05,
751
+ "loss": 0.3275,
752
+ "num_input_tokens_seen": 3813392,
753
+ "step": 93
754
+ },
755
+ {
756
+ "epoch": 1.7155963302752295,
757
+ "grad_norm": 0.16010524332523346,
758
+ "learning_rate": 4.907122531143594e-05,
759
+ "loss": 0.4179,
760
+ "num_input_tokens_seen": 3856416,
761
+ "step": 94
762
+ },
763
+ {
764
+ "epoch": 1.7339449541284404,
765
+ "grad_norm": 0.13423003256320953,
766
+ "learning_rate": 4.905148561184033e-05,
767
+ "loss": 0.3593,
768
+ "num_input_tokens_seen": 3899472,
769
+ "step": 95
770
+ },
771
+ {
772
+ "epoch": 1.7522935779816513,
773
+ "grad_norm": 0.14900773763656616,
774
+ "learning_rate": 4.9031542398457974e-05,
775
+ "loss": 0.5007,
776
+ "num_input_tokens_seen": 3962976,
777
+ "step": 96
778
+ },
779
+ {
780
+ "epoch": 1.7706422018348624,
781
+ "grad_norm": 0.15728624165058136,
782
+ "learning_rate": 4.9011395840040144e-05,
783
+ "loss": 0.3484,
784
+ "num_input_tokens_seen": 4000696,
785
+ "step": 97
786
+ },
787
+ {
788
+ "epoch": 1.7889908256880735,
789
+ "grad_norm": 0.11092367768287659,
790
+ "learning_rate": 4.8991046107058735e-05,
791
+ "loss": 0.2889,
792
+ "num_input_tokens_seen": 4045256,
793
+ "step": 98
794
+ },
795
+ {
796
+ "epoch": 1.8073394495412844,
797
+ "grad_norm": 0.1289113610982895,
798
+ "learning_rate": 4.8970493371704826e-05,
799
+ "loss": 0.2203,
800
+ "num_input_tokens_seen": 4076800,
801
+ "step": 99
802
+ },
803
+ {
804
+ "epoch": 1.8256880733944953,
805
+ "grad_norm": 0.18886639177799225,
806
+ "learning_rate": 4.894973780788722e-05,
807
+ "loss": 0.3966,
808
+ "num_input_tokens_seen": 4119840,
809
+ "step": 100
810
+ },
811
+ {
812
+ "epoch": 1.8440366972477065,
813
+ "grad_norm": 0.1563039869070053,
814
+ "learning_rate": 4.892877959123097e-05,
815
+ "loss": 0.4417,
816
+ "num_input_tokens_seen": 4165848,
817
+ "step": 101
818
+ },
819
+ {
820
+ "epoch": 1.8623853211009176,
821
+ "grad_norm": 0.16883380711078644,
822
+ "learning_rate": 4.890761889907589e-05,
823
+ "loss": 0.4258,
824
+ "num_input_tokens_seen": 4202824,
825
+ "step": 102
826
+ },
827
+ {
828
+ "epoch": 1.8807339449541285,
829
+ "grad_norm": 0.18241995573043823,
830
+ "learning_rate": 4.8886255910475054e-05,
831
+ "loss": 0.3952,
832
+ "num_input_tokens_seen": 4233888,
833
+ "step": 103
834
+ },
835
+ {
836
+ "epoch": 1.8990825688073394,
837
+ "grad_norm": 0.19913265109062195,
838
+ "learning_rate": 4.88646908061933e-05,
839
+ "loss": 0.3241,
840
+ "num_input_tokens_seen": 4267064,
841
+ "step": 104
842
+ },
843
+ {
844
+ "epoch": 1.9174311926605505,
845
+ "grad_norm": 0.18295545876026154,
846
+ "learning_rate": 4.884292376870567e-05,
847
+ "loss": 0.4239,
848
+ "num_input_tokens_seen": 4312536,
849
+ "step": 105
850
+ },
851
+ {
852
+ "epoch": 1.9357798165137616,
853
+ "grad_norm": 0.16657495498657227,
854
+ "learning_rate": 4.8820954982195905e-05,
855
+ "loss": 0.2579,
856
+ "num_input_tokens_seen": 4356656,
857
+ "step": 106
858
+ },
859
+ {
860
+ "epoch": 1.9541284403669725,
861
+ "grad_norm": 0.18504932522773743,
862
+ "learning_rate": 4.879878463255483e-05,
863
+ "loss": 0.44,
864
+ "num_input_tokens_seen": 4400216,
865
+ "step": 107
866
+ },
867
+ {
868
+ "epoch": 1.9724770642201834,
869
+ "grad_norm": 0.1923118382692337,
870
+ "learning_rate": 4.877641290737884e-05,
871
+ "loss": 0.2662,
872
+ "num_input_tokens_seen": 4436968,
873
+ "step": 108
874
+ },
875
+ {
876
+ "epoch": 1.9908256880733946,
877
+ "grad_norm": 0.19636788964271545,
878
+ "learning_rate": 4.875383999596828e-05,
879
+ "loss": 0.4211,
880
+ "num_input_tokens_seen": 4488232,
881
+ "step": 109
882
+ },
883
+ {
884
+ "epoch": 2.0,
885
+ "grad_norm": 0.3168099820613861,
886
+ "learning_rate": 4.873106608932585e-05,
887
+ "loss": 0.2499,
888
+ "num_input_tokens_seen": 4518176,
889
+ "step": 110
890
+ },
891
+ {
892
+ "epoch": 2.018348623853211,
893
+ "grad_norm": 0.14410308003425598,
894
+ "learning_rate": 4.8708091380154984e-05,
895
+ "loss": 0.2722,
896
+ "num_input_tokens_seen": 4570896,
897
+ "step": 111
898
+ },
899
+ {
900
+ "epoch": 2.036697247706422,
901
+ "grad_norm": 0.17840909957885742,
902
+ "learning_rate": 4.868491606285823e-05,
903
+ "loss": 0.2758,
904
+ "num_input_tokens_seen": 4613576,
905
+ "step": 112
906
+ },
907
+ {
908
+ "epoch": 2.055045871559633,
909
+ "grad_norm": 0.178523987531662,
910
+ "learning_rate": 4.866154033353561e-05,
911
+ "loss": 0.3361,
912
+ "num_input_tokens_seen": 4652896,
913
+ "step": 113
914
+ },
915
+ {
916
+ "epoch": 2.073394495412844,
917
+ "grad_norm": 0.17396725714206696,
918
+ "learning_rate": 4.8637964389982926e-05,
919
+ "loss": 0.2667,
920
+ "num_input_tokens_seen": 4694256,
921
+ "step": 114
922
+ },
923
+ {
924
+ "epoch": 2.091743119266055,
925
+ "grad_norm": 0.19471587240695953,
926
+ "learning_rate": 4.8614188431690125e-05,
927
+ "loss": 0.3628,
928
+ "num_input_tokens_seen": 4747552,
929
+ "step": 115
930
+ },
931
+ {
932
+ "epoch": 2.1100917431192663,
933
+ "grad_norm": 0.1722450852394104,
934
+ "learning_rate": 4.859021265983959e-05,
935
+ "loss": 0.3599,
936
+ "num_input_tokens_seen": 4794080,
937
+ "step": 116
938
+ },
939
+ {
940
+ "epoch": 2.128440366972477,
941
+ "grad_norm": 0.20137006044387817,
942
+ "learning_rate": 4.856603727730447e-05,
943
+ "loss": 0.4262,
944
+ "num_input_tokens_seen": 4847912,
945
+ "step": 117
946
+ },
947
+ {
948
+ "epoch": 2.146788990825688,
949
+ "grad_norm": 0.19395771622657776,
950
+ "learning_rate": 4.854166248864689e-05,
951
+ "loss": 0.3118,
952
+ "num_input_tokens_seen": 4885480,
953
+ "step": 118
954
+ },
955
+ {
956
+ "epoch": 2.165137614678899,
957
+ "grad_norm": 0.209548681974411,
958
+ "learning_rate": 4.85170885001163e-05,
959
+ "loss": 0.3725,
960
+ "num_input_tokens_seen": 4921240,
961
+ "step": 119
962
+ },
963
+ {
964
+ "epoch": 2.18348623853211,
965
+ "grad_norm": 0.18228279054164886,
966
+ "learning_rate": 4.849231551964771e-05,
967
+ "loss": 0.3816,
968
+ "num_input_tokens_seen": 4960224,
969
+ "step": 120
970
+ },
971
+ {
972
+ "epoch": 2.2018348623853212,
973
+ "grad_norm": 0.24349354207515717,
974
+ "learning_rate": 4.846734375685989e-05,
975
+ "loss": 0.3383,
976
+ "num_input_tokens_seen": 4990536,
977
+ "step": 121
978
+ },
979
+ {
980
+ "epoch": 2.220183486238532,
981
+ "grad_norm": 0.17600344121456146,
982
+ "learning_rate": 4.844217342305363e-05,
983
+ "loss": 0.3011,
984
+ "num_input_tokens_seen": 5044296,
985
+ "step": 122
986
+ },
987
+ {
988
+ "epoch": 2.238532110091743,
989
+ "grad_norm": 0.18766675889492035,
990
+ "learning_rate": 4.8416804731209945e-05,
991
+ "loss": 0.4458,
992
+ "num_input_tokens_seen": 5088368,
993
+ "step": 123
994
+ },
995
+ {
996
+ "epoch": 2.2568807339449544,
997
+ "grad_norm": 0.17657820880413055,
998
+ "learning_rate": 4.839123789598829e-05,
999
+ "loss": 0.2564,
1000
+ "num_input_tokens_seen": 5133472,
1001
+ "step": 124
1002
+ },
1003
+ {
1004
+ "epoch": 2.2752293577981653,
1005
+ "grad_norm": 0.20606014132499695,
1006
+ "learning_rate": 4.836547313372471e-05,
1007
+ "loss": 0.313,
1008
+ "num_input_tokens_seen": 5167768,
1009
+ "step": 125
1010
+ },
1011
+ {
1012
+ "epoch": 2.293577981651376,
1013
+ "grad_norm": 0.23511061072349548,
1014
+ "learning_rate": 4.8339510662430046e-05,
1015
+ "loss": 0.2963,
1016
+ "num_input_tokens_seen": 5209400,
1017
+ "step": 126
1018
+ },
1019
+ {
1020
+ "epoch": 2.311926605504587,
1021
+ "grad_norm": 0.18234293162822723,
1022
+ "learning_rate": 4.8313350701788054e-05,
1023
+ "loss": 0.2566,
1024
+ "num_input_tokens_seen": 5249360,
1025
+ "step": 127
1026
+ },
1027
+ {
1028
+ "epoch": 2.330275229357798,
1029
+ "grad_norm": 0.2223992496728897,
1030
+ "learning_rate": 4.828699347315356e-05,
1031
+ "loss": 0.2833,
1032
+ "num_input_tokens_seen": 5300808,
1033
+ "step": 128
1034
+ },
1035
+ {
1036
+ "epoch": 2.3486238532110093,
1037
+ "grad_norm": 0.23101739585399628,
1038
+ "learning_rate": 4.826043919955062e-05,
1039
+ "loss": 0.3099,
1040
+ "num_input_tokens_seen": 5332960,
1041
+ "step": 129
1042
+ },
1043
+ {
1044
+ "epoch": 2.36697247706422,
1045
+ "grad_norm": 0.26640889048576355,
1046
+ "learning_rate": 4.823368810567056e-05,
1047
+ "loss": 0.3238,
1048
+ "num_input_tokens_seen": 5365008,
1049
+ "step": 130
1050
+ },
1051
+ {
1052
+ "epoch": 2.385321100917431,
1053
+ "grad_norm": 0.2374572902917862,
1054
+ "learning_rate": 4.820674041787017e-05,
1055
+ "loss": 0.3153,
1056
+ "num_input_tokens_seen": 5400184,
1057
+ "step": 131
1058
+ },
1059
+ {
1060
+ "epoch": 2.4036697247706424,
1061
+ "grad_norm": 0.22812288999557495,
1062
+ "learning_rate": 4.817959636416969e-05,
1063
+ "loss": 0.2997,
1064
+ "num_input_tokens_seen": 5440320,
1065
+ "step": 132
1066
+ },
1067
+ {
1068
+ "epoch": 2.4220183486238533,
1069
+ "grad_norm": 0.20079149305820465,
1070
+ "learning_rate": 4.815225617425095e-05,
1071
+ "loss": 0.2373,
1072
+ "num_input_tokens_seen": 5480832,
1073
+ "step": 133
1074
+ },
1075
+ {
1076
+ "epoch": 2.4403669724770642,
1077
+ "grad_norm": 0.196709543466568,
1078
+ "learning_rate": 4.81247200794554e-05,
1079
+ "loss": 0.2456,
1080
+ "num_input_tokens_seen": 5526936,
1081
+ "step": 134
1082
+ },
1083
+ {
1084
+ "epoch": 2.458715596330275,
1085
+ "grad_norm": 0.17305873334407806,
1086
+ "learning_rate": 4.8096988312782174e-05,
1087
+ "loss": 0.2099,
1088
+ "num_input_tokens_seen": 5566384,
1089
+ "step": 135
1090
+ },
1091
+ {
1092
+ "epoch": 2.477064220183486,
1093
+ "grad_norm": 3.584635019302368,
1094
+ "learning_rate": 4.806906110888606e-05,
1095
+ "loss": 0.3485,
1096
+ "num_input_tokens_seen": 5629896,
1097
+ "step": 136
1098
+ },
1099
+ {
1100
+ "epoch": 2.4954128440366974,
1101
+ "grad_norm": 0.23481500148773193,
1102
+ "learning_rate": 4.80409387040756e-05,
1103
+ "loss": 0.2231,
1104
+ "num_input_tokens_seen": 5674504,
1105
+ "step": 137
1106
+ },
1107
+ {
1108
+ "epoch": 2.5137614678899083,
1109
+ "grad_norm": 0.27899855375289917,
1110
+ "learning_rate": 4.8012621336311016e-05,
1111
+ "loss": 0.4285,
1112
+ "num_input_tokens_seen": 5714000,
1113
+ "step": 138
1114
+ },
1115
+ {
1116
+ "epoch": 2.532110091743119,
1117
+ "grad_norm": 0.24404938519001007,
1118
+ "learning_rate": 4.798410924520223e-05,
1119
+ "loss": 0.3343,
1120
+ "num_input_tokens_seen": 5756856,
1121
+ "step": 139
1122
+ },
1123
+ {
1124
+ "epoch": 2.5504587155963305,
1125
+ "grad_norm": 0.26869162917137146,
1126
+ "learning_rate": 4.7955402672006854e-05,
1127
+ "loss": 0.2497,
1128
+ "num_input_tokens_seen": 5781192,
1129
+ "step": 140
1130
+ },
1131
+ {
1132
+ "epoch": 2.5688073394495414,
1133
+ "grad_norm": 0.2057972550392151,
1134
+ "learning_rate": 4.79265018596281e-05,
1135
+ "loss": 0.2991,
1136
+ "num_input_tokens_seen": 5824024,
1137
+ "step": 141
1138
+ },
1139
+ {
1140
+ "epoch": 2.5871559633027523,
1141
+ "grad_norm": 0.2184937596321106,
1142
+ "learning_rate": 4.789740705261278e-05,
1143
+ "loss": 0.2406,
1144
+ "num_input_tokens_seen": 5862584,
1145
+ "step": 142
1146
+ },
1147
+ {
1148
+ "epoch": 2.6055045871559632,
1149
+ "grad_norm": 0.23603741824626923,
1150
+ "learning_rate": 4.786811849714918e-05,
1151
+ "loss": 0.2722,
1152
+ "num_input_tokens_seen": 5897344,
1153
+ "step": 143
1154
+ },
1155
+ {
1156
+ "epoch": 2.623853211009174,
1157
+ "grad_norm": 0.22983981668949127,
1158
+ "learning_rate": 4.783863644106502e-05,
1159
+ "loss": 0.374,
1160
+ "num_input_tokens_seen": 5931736,
1161
+ "step": 144
1162
+ },
1163
+ {
1164
+ "epoch": 2.6422018348623855,
1165
+ "grad_norm": 0.2825419306755066,
1166
+ "learning_rate": 4.780896113382536e-05,
1167
+ "loss": 0.3386,
1168
+ "num_input_tokens_seen": 5972784,
1169
+ "step": 145
1170
+ },
1171
+ {
1172
+ "epoch": 2.6605504587155964,
1173
+ "grad_norm": 0.4502134621143341,
1174
+ "learning_rate": 4.777909282653042e-05,
1175
+ "loss": 0.2289,
1176
+ "num_input_tokens_seen": 6018968,
1177
+ "step": 146
1178
+ },
1179
+ {
1180
+ "epoch": 2.6788990825688073,
1181
+ "grad_norm": 0.2428288459777832,
1182
+ "learning_rate": 4.7749031771913584e-05,
1183
+ "loss": 0.4061,
1184
+ "num_input_tokens_seen": 6062520,
1185
+ "step": 147
1186
+ },
1187
+ {
1188
+ "epoch": 2.6972477064220186,
1189
+ "grad_norm": 0.2685629725456238,
1190
+ "learning_rate": 4.771877822433911e-05,
1191
+ "loss": 0.2198,
1192
+ "num_input_tokens_seen": 6087928,
1193
+ "step": 148
1194
+ },
1195
+ {
1196
+ "epoch": 2.7155963302752295,
1197
+ "grad_norm": 0.24021446704864502,
1198
+ "learning_rate": 4.7688332439800096e-05,
1199
+ "loss": 0.34,
1200
+ "num_input_tokens_seen": 6134792,
1201
+ "step": 149
1202
+ },
1203
+ {
1204
+ "epoch": 2.7339449541284404,
1205
+ "grad_norm": 0.2568534314632416,
1206
+ "learning_rate": 4.765769467591625e-05,
1207
+ "loss": 0.3292,
1208
+ "num_input_tokens_seen": 6183296,
1209
+ "step": 150
1210
+ },
1211
+ {
1212
+ "epoch": 2.7522935779816513,
1213
+ "grad_norm": 0.20823974907398224,
1214
+ "learning_rate": 4.762686519193175e-05,
1215
+ "loss": 0.2539,
1216
+ "num_input_tokens_seen": 6225840,
1217
+ "step": 151
1218
+ },
1219
+ {
1220
+ "epoch": 2.770642201834862,
1221
+ "grad_norm": 0.23333317041397095,
1222
+ "learning_rate": 4.759584424871302e-05,
1223
+ "loss": 0.3571,
1224
+ "num_input_tokens_seen": 6274760,
1225
+ "step": 152
1226
+ },
1227
+ {
1228
+ "epoch": 2.7889908256880735,
1229
+ "grad_norm": 0.20232398808002472,
1230
+ "learning_rate": 4.756463210874652e-05,
1231
+ "loss": 0.2783,
1232
+ "num_input_tokens_seen": 6326168,
1233
+ "step": 153
1234
+ },
1235
+ {
1236
+ "epoch": 2.8073394495412844,
1237
+ "grad_norm": 0.3479433059692383,
1238
+ "learning_rate": 4.7533229036136553e-05,
1239
+ "loss": 0.2925,
1240
+ "num_input_tokens_seen": 6360312,
1241
+ "step": 154
1242
+ },
1243
+ {
1244
+ "epoch": 2.8256880733944953,
1245
+ "grad_norm": 0.2659524083137512,
1246
+ "learning_rate": 4.750163529660303e-05,
1247
+ "loss": 0.2606,
1248
+ "num_input_tokens_seen": 6395496,
1249
+ "step": 155
1250
+ },
1251
+ {
1252
+ "epoch": 2.8440366972477067,
1253
+ "grad_norm": 0.24823158979415894,
1254
+ "learning_rate": 4.7469851157479177e-05,
1255
+ "loss": 0.3721,
1256
+ "num_input_tokens_seen": 6437064,
1257
+ "step": 156
1258
+ },
1259
+ {
1260
+ "epoch": 2.8623853211009176,
1261
+ "grad_norm": 0.32034072279930115,
1262
+ "learning_rate": 4.743787688770932e-05,
1263
+ "loss": 0.3931,
1264
+ "num_input_tokens_seen": 6477616,
1265
+ "step": 157
1266
+ },
1267
+ {
1268
+ "epoch": 2.8807339449541285,
1269
+ "grad_norm": 0.23295725882053375,
1270
+ "learning_rate": 4.740571275784659e-05,
1271
+ "loss": 0.2201,
1272
+ "num_input_tokens_seen": 6518680,
1273
+ "step": 158
1274
+ },
1275
+ {
1276
+ "epoch": 2.8990825688073394,
1277
+ "grad_norm": 0.2758423984050751,
1278
+ "learning_rate": 4.737335904005063e-05,
1279
+ "loss": 0.2579,
1280
+ "num_input_tokens_seen": 6549768,
1281
+ "step": 159
1282
+ },
1283
+ {
1284
+ "epoch": 2.9174311926605503,
1285
+ "grad_norm": 0.26690953969955444,
1286
+ "learning_rate": 4.734081600808531e-05,
1287
+ "loss": 0.2575,
1288
+ "num_input_tokens_seen": 6581000,
1289
+ "step": 160
1290
+ },
1291
+ {
1292
+ "epoch": 2.9357798165137616,
1293
+ "grad_norm": 0.26657482981681824,
1294
+ "learning_rate": 4.730808393731639e-05,
1295
+ "loss": 0.2597,
1296
+ "num_input_tokens_seen": 6612632,
1297
+ "step": 161
1298
+ },
1299
+ {
1300
+ "epoch": 2.9541284403669725,
1301
+ "grad_norm": 0.22647295892238617,
1302
+ "learning_rate": 4.72751631047092e-05,
1303
+ "loss": 0.3335,
1304
+ "num_input_tokens_seen": 6654288,
1305
+ "step": 162
1306
+ },
1307
+ {
1308
+ "epoch": 2.9724770642201834,
1309
+ "grad_norm": 0.2863366901874542,
1310
+ "learning_rate": 4.72420537888263e-05,
1311
+ "loss": 0.374,
1312
+ "num_input_tokens_seen": 6707208,
1313
+ "step": 163
1314
+ },
1315
+ {
1316
+ "epoch": 2.9908256880733948,
1317
+ "grad_norm": 0.2606408894062042,
1318
+ "learning_rate": 4.7208756269825104e-05,
1319
+ "loss": 0.3477,
1320
+ "num_input_tokens_seen": 6748448,
1321
+ "step": 164
1322
+ },
1323
+ {
1324
+ "epoch": 3.0,
1325
+ "grad_norm": 0.440924733877182,
1326
+ "learning_rate": 4.717527082945554e-05,
1327
+ "loss": 0.3214,
1328
+ "num_input_tokens_seen": 6777264,
1329
+ "step": 165
1330
+ },
1331
+ {
1332
+ "epoch": 3.018348623853211,
1333
+ "grad_norm": 0.27583903074264526,
1334
+ "learning_rate": 4.714159775105765e-05,
1335
+ "loss": 0.2681,
1336
+ "num_input_tokens_seen": 6809456,
1337
+ "step": 166
1338
+ },
1339
+ {
1340
+ "epoch": 3.036697247706422,
1341
+ "grad_norm": 0.2995987832546234,
1342
+ "learning_rate": 4.7107737319559176e-05,
1343
+ "loss": 0.2633,
1344
+ "num_input_tokens_seen": 6845768,
1345
+ "step": 167
1346
+ },
1347
+ {
1348
+ "epoch": 3.055045871559633,
1349
+ "grad_norm": 0.23999951779842377,
1350
+ "learning_rate": 4.707368982147318e-05,
1351
+ "loss": 0.1961,
1352
+ "num_input_tokens_seen": 6893056,
1353
+ "step": 168
1354
+ },
1355
+ {
1356
+ "epoch": 3.073394495412844,
1357
+ "grad_norm": 0.23356525599956512,
1358
+ "learning_rate": 4.703945554489558e-05,
1359
+ "loss": 0.2836,
1360
+ "num_input_tokens_seen": 6932480,
1361
+ "step": 169
1362
+ },
1363
+ {
1364
+ "epoch": 3.091743119266055,
1365
+ "grad_norm": 0.29919493198394775,
1366
+ "learning_rate": 4.700503477950278e-05,
1367
+ "loss": 0.2838,
1368
+ "num_input_tokens_seen": 6975992,
1369
+ "step": 170
1370
+ },
1371
+ {
1372
+ "epoch": 3.1100917431192663,
1373
+ "grad_norm": 0.3350690007209778,
1374
+ "learning_rate": 4.697042781654913e-05,
1375
+ "loss": 0.3489,
1376
+ "num_input_tokens_seen": 7021840,
1377
+ "step": 171
1378
+ },
1379
+ {
1380
+ "epoch": 3.128440366972477,
1381
+ "grad_norm": 0.2837466895580292,
1382
+ "learning_rate": 4.693563494886455e-05,
1383
+ "loss": 0.3797,
1384
+ "num_input_tokens_seen": 7065192,
1385
+ "step": 172
1386
+ },
1387
+ {
1388
+ "epoch": 3.146788990825688,
1389
+ "grad_norm": 0.24601787328720093,
1390
+ "learning_rate": 4.6900656470851964e-05,
1391
+ "loss": 0.2046,
1392
+ "num_input_tokens_seen": 7114544,
1393
+ "step": 173
1394
+ },
1395
+ {
1396
+ "epoch": 3.165137614678899,
1397
+ "grad_norm": 0.32290250062942505,
1398
+ "learning_rate": 4.6865492678484895e-05,
1399
+ "loss": 0.2596,
1400
+ "num_input_tokens_seen": 7152736,
1401
+ "step": 174
1402
+ },
1403
+ {
1404
+ "epoch": 3.18348623853211,
1405
+ "grad_norm": 0.33591920137405396,
1406
+ "learning_rate": 4.68301438693049e-05,
1407
+ "loss": 0.3045,
1408
+ "num_input_tokens_seen": 7207464,
1409
+ "step": 175
1410
+ },
1411
+ {
1412
+ "epoch": 3.2018348623853212,
1413
+ "grad_norm": 0.25471043586730957,
1414
+ "learning_rate": 4.679461034241906e-05,
1415
+ "loss": 0.2096,
1416
+ "num_input_tokens_seen": 7238640,
1417
+ "step": 176
1418
+ },
1419
+ {
1420
+ "epoch": 3.220183486238532,
1421
+ "grad_norm": 0.31238994002342224,
1422
+ "learning_rate": 4.6758892398497494e-05,
1423
+ "loss": 0.2226,
1424
+ "num_input_tokens_seen": 7279112,
1425
+ "step": 177
1426
+ },
1427
+ {
1428
+ "epoch": 3.238532110091743,
1429
+ "grad_norm": 0.35679712891578674,
1430
+ "learning_rate": 4.672299033977076e-05,
1431
+ "loss": 0.2403,
1432
+ "num_input_tokens_seen": 7311632,
1433
+ "step": 178
1434
+ },
1435
+ {
1436
+ "epoch": 3.2568807339449544,
1437
+ "grad_norm": 0.326914519071579,
1438
+ "learning_rate": 4.6686904470027316e-05,
1439
+ "loss": 0.2156,
1440
+ "num_input_tokens_seen": 7344864,
1441
+ "step": 179
1442
+ },
1443
+ {
1444
+ "epoch": 3.2752293577981653,
1445
+ "grad_norm": 0.3293381929397583,
1446
+ "learning_rate": 4.665063509461097e-05,
1447
+ "loss": 0.238,
1448
+ "num_input_tokens_seen": 7389944,
1449
+ "step": 180
1450
+ },
1451
+ {
1452
+ "epoch": 3.293577981651376,
1453
+ "grad_norm": 0.3313307762145996,
1454
+ "learning_rate": 4.661418252041827e-05,
1455
+ "loss": 0.2251,
1456
+ "num_input_tokens_seen": 7423672,
1457
+ "step": 181
1458
+ },
1459
+ {
1460
+ "epoch": 3.311926605504587,
1461
+ "grad_norm": 0.3328595459461212,
1462
+ "learning_rate": 4.657754705589591e-05,
1463
+ "loss": 0.2922,
1464
+ "num_input_tokens_seen": 7459576,
1465
+ "step": 182
1466
+ },
1467
+ {
1468
+ "epoch": 3.330275229357798,
1469
+ "grad_norm": 0.2721710801124573,
1470
+ "learning_rate": 4.6540729011038146e-05,
1471
+ "loss": 0.2698,
1472
+ "num_input_tokens_seen": 7511736,
1473
+ "step": 183
1474
+ },
1475
+ {
1476
+ "epoch": 3.3486238532110093,
1477
+ "grad_norm": 0.2488890290260315,
1478
+ "learning_rate": 4.650372869738414e-05,
1479
+ "loss": 0.173,
1480
+ "num_input_tokens_seen": 7558552,
1481
+ "step": 184
1482
+ },
1483
+ {
1484
+ "epoch": 3.36697247706422,
1485
+ "grad_norm": 0.3800615668296814,
1486
+ "learning_rate": 4.6466546428015336e-05,
1487
+ "loss": 0.32,
1488
+ "num_input_tokens_seen": 7599040,
1489
+ "step": 185
1490
+ },
1491
+ {
1492
+ "epoch": 3.385321100917431,
1493
+ "grad_norm": 0.3377014100551605,
1494
+ "learning_rate": 4.642918251755281e-05,
1495
+ "loss": 0.3058,
1496
+ "num_input_tokens_seen": 7653264,
1497
+ "step": 186
1498
+ },
1499
+ {
1500
+ "epoch": 3.4036697247706424,
1501
+ "grad_norm": 0.25239789485931396,
1502
+ "learning_rate": 4.639163728215463e-05,
1503
+ "loss": 0.1896,
1504
+ "num_input_tokens_seen": 7694272,
1505
+ "step": 187
1506
+ },
1507
+ {
1508
+ "epoch": 3.4220183486238533,
1509
+ "grad_norm": 0.34607502818107605,
1510
+ "learning_rate": 4.6353911039513145e-05,
1511
+ "loss": 0.2933,
1512
+ "num_input_tokens_seen": 7730848,
1513
+ "step": 188
1514
+ },
1515
+ {
1516
+ "epoch": 3.4403669724770642,
1517
+ "grad_norm": 0.30653324723243713,
1518
+ "learning_rate": 4.6316004108852305e-05,
1519
+ "loss": 0.2625,
1520
+ "num_input_tokens_seen": 7781200,
1521
+ "step": 189
1522
+ },
1523
+ {
1524
+ "epoch": 3.458715596330275,
1525
+ "grad_norm": 0.2943236231803894,
1526
+ "learning_rate": 4.627791681092499e-05,
1527
+ "loss": 0.3372,
1528
+ "num_input_tokens_seen": 7825032,
1529
+ "step": 190
1530
+ },
1531
+ {
1532
+ "epoch": 3.477064220183486,
1533
+ "grad_norm": 0.30080685019493103,
1534
+ "learning_rate": 4.623964946801027e-05,
1535
+ "loss": 0.2229,
1536
+ "num_input_tokens_seen": 7855840,
1537
+ "step": 191
1538
+ },
1539
+ {
1540
+ "epoch": 3.4954128440366974,
1541
+ "grad_norm": 0.3511403799057007,
1542
+ "learning_rate": 4.620120240391065e-05,
1543
+ "loss": 0.3967,
1544
+ "num_input_tokens_seen": 7905928,
1545
+ "step": 192
1546
+ },
1547
+ {
1548
+ "epoch": 3.5137614678899083,
1549
+ "grad_norm": 0.273583322763443,
1550
+ "learning_rate": 4.61625759439494e-05,
1551
+ "loss": 0.2254,
1552
+ "num_input_tokens_seen": 7955992,
1553
+ "step": 193
1554
+ },
1555
+ {
1556
+ "epoch": 3.532110091743119,
1557
+ "grad_norm": 0.3457902669906616,
1558
+ "learning_rate": 4.612377041496776e-05,
1559
+ "loss": 0.2553,
1560
+ "num_input_tokens_seen": 7998024,
1561
+ "step": 194
1562
+ },
1563
+ {
1564
+ "epoch": 3.5504587155963305,
1565
+ "grad_norm": 0.31968954205513,
1566
+ "learning_rate": 4.608478614532215e-05,
1567
+ "loss": 0.2197,
1568
+ "num_input_tokens_seen": 8055672,
1569
+ "step": 195
1570
+ },
1571
+ {
1572
+ "epoch": 3.5688073394495414,
1573
+ "grad_norm": 0.34753403067588806,
1574
+ "learning_rate": 4.604562346488144e-05,
1575
+ "loss": 0.2507,
1576
+ "num_input_tokens_seen": 8090848,
1577
+ "step": 196
1578
+ },
1579
+ {
1580
+ "epoch": 3.5871559633027523,
1581
+ "grad_norm": 0.3808669149875641,
1582
+ "learning_rate": 4.6006282705024144e-05,
1583
+ "loss": 0.2422,
1584
+ "num_input_tokens_seen": 8136680,
1585
+ "step": 197
1586
+ },
1587
+ {
1588
+ "epoch": 3.6055045871559632,
1589
+ "grad_norm": 0.3004499673843384,
1590
+ "learning_rate": 4.5966764198635606e-05,
1591
+ "loss": 0.2107,
1592
+ "num_input_tokens_seen": 8187472,
1593
+ "step": 198
1594
+ },
1595
+ {
1596
+ "epoch": 3.623853211009174,
1597
+ "grad_norm": 0.30718186497688293,
1598
+ "learning_rate": 4.592706828010518e-05,
1599
+ "loss": 0.1854,
1600
+ "num_input_tokens_seen": 8225216,
1601
+ "step": 199
1602
+ },
1603
+ {
1604
+ "epoch": 3.6422018348623855,
1605
+ "grad_norm": 0.23112858831882477,
1606
+ "learning_rate": 4.588719528532342e-05,
1607
+ "loss": 0.1687,
1608
+ "num_input_tokens_seen": 8274456,
1609
+ "step": 200
1610
+ },
1611
+ {
1612
+ "epoch": 3.6605504587155964,
1613
+ "grad_norm": 0.25966888666152954,
1614
+ "learning_rate": 4.5847145551679206e-05,
1615
+ "loss": 0.2549,
1616
+ "num_input_tokens_seen": 8317016,
1617
+ "step": 201
1618
+ },
1619
+ {
1620
+ "epoch": 3.6788990825688073,
1621
+ "grad_norm": 0.25600987672805786,
1622
+ "learning_rate": 4.580691941805695e-05,
1623
+ "loss": 0.1602,
1624
+ "num_input_tokens_seen": 8361856,
1625
+ "step": 202
1626
+ },
1627
+ {
1628
+ "epoch": 3.6972477064220186,
1629
+ "grad_norm": 0.33986184000968933,
1630
+ "learning_rate": 4.5766517224833637e-05,
1631
+ "loss": 0.2495,
1632
+ "num_input_tokens_seen": 8410696,
1633
+ "step": 203
1634
+ },
1635
+ {
1636
+ "epoch": 3.7155963302752295,
1637
+ "grad_norm": 0.36899781227111816,
1638
+ "learning_rate": 4.572593931387604e-05,
1639
+ "loss": 0.2012,
1640
+ "num_input_tokens_seen": 8441872,
1641
+ "step": 204
1642
+ },
1643
+ {
1644
+ "epoch": 3.7339449541284404,
1645
+ "grad_norm": 0.42072632908821106,
1646
+ "learning_rate": 4.568518602853776e-05,
1647
+ "loss": 0.2373,
1648
+ "num_input_tokens_seen": 8482544,
1649
+ "step": 205
1650
+ },
1651
+ {
1652
+ "epoch": 3.7522935779816513,
1653
+ "grad_norm": 0.40593233704566956,
1654
+ "learning_rate": 4.5644257713656356e-05,
1655
+ "loss": 0.233,
1656
+ "num_input_tokens_seen": 8519856,
1657
+ "step": 206
1658
+ },
1659
+ {
1660
+ "epoch": 3.770642201834862,
1661
+ "grad_norm": 0.38003161549568176,
1662
+ "learning_rate": 4.5603154715550386e-05,
1663
+ "loss": 0.225,
1664
+ "num_input_tokens_seen": 8551392,
1665
+ "step": 207
1666
+ },
1667
+ {
1668
+ "epoch": 3.7889908256880735,
1669
+ "grad_norm": 0.2564244568347931,
1670
+ "learning_rate": 4.556187738201656e-05,
1671
+ "loss": 0.2975,
1672
+ "num_input_tokens_seen": 8599472,
1673
+ "step": 208
1674
+ },
1675
+ {
1676
+ "epoch": 3.8073394495412844,
1677
+ "grad_norm": 0.29023391008377075,
1678
+ "learning_rate": 4.552042606232668e-05,
1679
+ "loss": 0.2033,
1680
+ "num_input_tokens_seen": 8631880,
1681
+ "step": 209
1682
+ },
1683
+ {
1684
+ "epoch": 3.8256880733944953,
1685
+ "grad_norm": 0.32886001467704773,
1686
+ "learning_rate": 4.54788011072248e-05,
1687
+ "loss": 0.2024,
1688
+ "num_input_tokens_seen": 8675016,
1689
+ "step": 210
1690
+ },
1691
+ {
1692
+ "epoch": 3.8440366972477067,
1693
+ "grad_norm": 0.36749884486198425,
1694
+ "learning_rate": 4.5437002868924166e-05,
1695
+ "loss": 0.2304,
1696
+ "num_input_tokens_seen": 8713248,
1697
+ "step": 211
1698
+ },
1699
+ {
1700
+ "epoch": 3.8623853211009176,
1701
+ "grad_norm": 0.3055097758769989,
1702
+ "learning_rate": 4.539503170110431e-05,
1703
+ "loss": 0.2928,
1704
+ "num_input_tokens_seen": 8748800,
1705
+ "step": 212
1706
+ },
1707
+ {
1708
+ "epoch": 3.8807339449541285,
1709
+ "grad_norm": 0.38436686992645264,
1710
+ "learning_rate": 4.535288795890798e-05,
1711
+ "loss": 0.2214,
1712
+ "num_input_tokens_seen": 8787832,
1713
+ "step": 213
1714
+ },
1715
+ {
1716
+ "epoch": 3.8990825688073394,
1717
+ "grad_norm": 0.44330883026123047,
1718
+ "learning_rate": 4.531057199893824e-05,
1719
+ "loss": 0.2168,
1720
+ "num_input_tokens_seen": 8819616,
1721
+ "step": 214
1722
+ },
1723
+ {
1724
+ "epoch": 3.9174311926605503,
1725
+ "grad_norm": 0.28318527340888977,
1726
+ "learning_rate": 4.526808417925531e-05,
1727
+ "loss": 0.279,
1728
+ "num_input_tokens_seen": 8860744,
1729
+ "step": 215
1730
+ },
1731
+ {
1732
+ "epoch": 3.9357798165137616,
1733
+ "grad_norm": 0.3287319839000702,
1734
+ "learning_rate": 4.522542485937369e-05,
1735
+ "loss": 0.2597,
1736
+ "num_input_tokens_seen": 8906432,
1737
+ "step": 216
1738
+ },
1739
+ {
1740
+ "epoch": 3.9541284403669725,
1741
+ "grad_norm": 0.35815751552581787,
1742
+ "learning_rate": 4.5182594400259e-05,
1743
+ "loss": 0.241,
1744
+ "num_input_tokens_seen": 8955104,
1745
+ "step": 217
1746
+ },
1747
+ {
1748
+ "epoch": 3.9724770642201834,
1749
+ "grad_norm": 0.3299608528614044,
1750
+ "learning_rate": 4.5139593164324986e-05,
1751
+ "loss": 0.2157,
1752
+ "num_input_tokens_seen": 8990200,
1753
+ "step": 218
1754
+ },
1755
+ {
1756
+ "epoch": 3.9908256880733948,
1757
+ "grad_norm": 0.2916093170642853,
1758
+ "learning_rate": 4.509642151543043e-05,
1759
+ "loss": 0.2046,
1760
+ "num_input_tokens_seen": 9020760,
1761
+ "step": 219
1762
+ },
1763
+ {
1764
+ "epoch": 4.0,
1765
+ "grad_norm": 0.40076637268066406,
1766
+ "learning_rate": 4.50530798188761e-05,
1767
+ "loss": 0.1714,
1768
+ "num_input_tokens_seen": 9036352,
1769
+ "step": 220
1770
+ },
1771
+ {
1772
+ "epoch": 4.018348623853211,
1773
+ "grad_norm": 0.40515249967575073,
1774
+ "learning_rate": 4.50095684414016e-05,
1775
+ "loss": 0.1811,
1776
+ "num_input_tokens_seen": 9091776,
1777
+ "step": 221
1778
+ },
1779
+ {
1780
+ "epoch": 4.036697247706422,
1781
+ "grad_norm": 0.32984718680381775,
1782
+ "learning_rate": 4.496588775118232e-05,
1783
+ "loss": 0.2101,
1784
+ "num_input_tokens_seen": 9134080,
1785
+ "step": 222
1786
+ },
1787
+ {
1788
+ "epoch": 4.055045871559633,
1789
+ "grad_norm": 0.27288541197776794,
1790
+ "learning_rate": 4.4922038117826334e-05,
1791
+ "loss": 0.1444,
1792
+ "num_input_tokens_seen": 9172720,
1793
+ "step": 223
1794
+ },
1795
+ {
1796
+ "epoch": 4.073394495412844,
1797
+ "grad_norm": 0.5168021321296692,
1798
+ "learning_rate": 4.48780199123712e-05,
1799
+ "loss": 0.2342,
1800
+ "num_input_tokens_seen": 9213664,
1801
+ "step": 224
1802
+ },
1803
+ {
1804
+ "epoch": 4.091743119266055,
1805
+ "grad_norm": 0.3986498713493347,
1806
+ "learning_rate": 4.4833833507280884e-05,
1807
+ "loss": 0.1676,
1808
+ "num_input_tokens_seen": 9261768,
1809
+ "step": 225
1810
+ },
1811
+ {
1812
+ "epoch": 4.110091743119266,
1813
+ "grad_norm": 0.4472793936729431,
1814
+ "learning_rate": 4.478947927644258e-05,
1815
+ "loss": 0.295,
1816
+ "num_input_tokens_seen": 9300928,
1817
+ "step": 226
1818
+ },
1819
+ {
1820
+ "epoch": 4.128440366972477,
1821
+ "grad_norm": 0.39240705966949463,
1822
+ "learning_rate": 4.474495759516358e-05,
1823
+ "loss": 0.17,
1824
+ "num_input_tokens_seen": 9329472,
1825
+ "step": 227
1826
+ },
1827
+ {
1828
+ "epoch": 4.146788990825688,
1829
+ "grad_norm": 0.354526549577713,
1830
+ "learning_rate": 4.4700268840168045e-05,
1831
+ "loss": 0.1759,
1832
+ "num_input_tokens_seen": 9365640,
1833
+ "step": 228
1834
+ },
1835
+ {
1836
+ "epoch": 4.165137614678899,
1837
+ "grad_norm": 0.3216766119003296,
1838
+ "learning_rate": 4.4655413389593856e-05,
1839
+ "loss": 0.1878,
1840
+ "num_input_tokens_seen": 9410552,
1841
+ "step": 229
1842
+ },
1843
+ {
1844
+ "epoch": 4.18348623853211,
1845
+ "grad_norm": 0.30976617336273193,
1846
+ "learning_rate": 4.4610391622989396e-05,
1847
+ "loss": 0.1637,
1848
+ "num_input_tokens_seen": 9452416,
1849
+ "step": 230
1850
+ },
1851
+ {
1852
+ "epoch": 4.201834862385321,
1853
+ "grad_norm": 0.385437935590744,
1854
+ "learning_rate": 4.456520392131035e-05,
1855
+ "loss": 0.2748,
1856
+ "num_input_tokens_seen": 9503528,
1857
+ "step": 231
1858
+ },
1859
+ {
1860
+ "epoch": 4.220183486238533,
1861
+ "grad_norm": 0.37948480248451233,
1862
+ "learning_rate": 4.4519850666916484e-05,
1863
+ "loss": 0.2635,
1864
+ "num_input_tokens_seen": 9541592,
1865
+ "step": 232
1866
+ },
1867
+ {
1868
+ "epoch": 4.238532110091743,
1869
+ "grad_norm": 0.36141568422317505,
1870
+ "learning_rate": 4.447433224356839e-05,
1871
+ "loss": 0.2027,
1872
+ "num_input_tokens_seen": 9586064,
1873
+ "step": 233
1874
+ },
1875
+ {
1876
+ "epoch": 4.256880733944954,
1877
+ "grad_norm": 0.4549350440502167,
1878
+ "learning_rate": 4.442864903642428e-05,
1879
+ "loss": 0.2107,
1880
+ "num_input_tokens_seen": 9641688,
1881
+ "step": 234
1882
+ },
1883
+ {
1884
+ "epoch": 4.275229357798165,
1885
+ "grad_norm": 0.3979765474796295,
1886
+ "learning_rate": 4.438280143203665e-05,
1887
+ "loss": 0.2879,
1888
+ "num_input_tokens_seen": 9686240,
1889
+ "step": 235
1890
+ },
1891
+ {
1892
+ "epoch": 4.293577981651376,
1893
+ "grad_norm": 0.35011065006256104,
1894
+ "learning_rate": 4.43367898183491e-05,
1895
+ "loss": 0.2594,
1896
+ "num_input_tokens_seen": 9735632,
1897
+ "step": 236
1898
+ },
1899
+ {
1900
+ "epoch": 4.3119266055045875,
1901
+ "grad_norm": 0.3999224007129669,
1902
+ "learning_rate": 4.4290614584693004e-05,
1903
+ "loss": 0.1907,
1904
+ "num_input_tokens_seen": 9766536,
1905
+ "step": 237
1906
+ },
1907
+ {
1908
+ "epoch": 4.330275229357798,
1909
+ "grad_norm": 0.39629611372947693,
1910
+ "learning_rate": 4.4244276121784195e-05,
1911
+ "loss": 0.1805,
1912
+ "num_input_tokens_seen": 9796400,
1913
+ "step": 238
1914
+ },
1915
+ {
1916
+ "epoch": 4.348623853211009,
1917
+ "grad_norm": 0.36784592270851135,
1918
+ "learning_rate": 4.4197774821719714e-05,
1919
+ "loss": 0.1824,
1920
+ "num_input_tokens_seen": 9831992,
1921
+ "step": 239
1922
+ },
1923
+ {
1924
+ "epoch": 4.36697247706422,
1925
+ "grad_norm": 0.3408430516719818,
1926
+ "learning_rate": 4.415111107797445e-05,
1927
+ "loss": 0.1721,
1928
+ "num_input_tokens_seen": 9875640,
1929
+ "step": 240
1930
+ },
1931
+ {
1932
+ "epoch": 4.385321100917431,
1933
+ "grad_norm": 0.3232553005218506,
1934
+ "learning_rate": 4.410428528539783e-05,
1935
+ "loss": 0.275,
1936
+ "num_input_tokens_seen": 9916816,
1937
+ "step": 241
1938
+ },
1939
+ {
1940
+ "epoch": 4.4036697247706424,
1941
+ "grad_norm": 0.38150206208229065,
1942
+ "learning_rate": 4.405729784021046e-05,
1943
+ "loss": 0.1963,
1944
+ "num_input_tokens_seen": 9962928,
1945
+ "step": 242
1946
+ },
1947
+ {
1948
+ "epoch": 4.422018348623853,
1949
+ "grad_norm": 0.4176963269710541,
1950
+ "learning_rate": 4.401014914000078e-05,
1951
+ "loss": 0.1626,
1952
+ "num_input_tokens_seen": 9997224,
1953
+ "step": 243
1954
+ },
1955
+ {
1956
+ "epoch": 4.440366972477064,
1957
+ "grad_norm": 0.38855600357055664,
1958
+ "learning_rate": 4.396283958372173e-05,
1959
+ "loss": 0.1733,
1960
+ "num_input_tokens_seen": 10036248,
1961
+ "step": 244
1962
+ },
1963
+ {
1964
+ "epoch": 4.458715596330276,
1965
+ "grad_norm": 0.3860638737678528,
1966
+ "learning_rate": 4.391536957168733e-05,
1967
+ "loss": 0.1936,
1968
+ "num_input_tokens_seen": 10070312,
1969
+ "step": 245
1970
+ },
1971
+ {
1972
+ "epoch": 4.477064220183486,
1973
+ "grad_norm": 0.31510865688323975,
1974
+ "learning_rate": 4.386773950556931e-05,
1975
+ "loss": 0.1847,
1976
+ "num_input_tokens_seen": 10114568,
1977
+ "step": 246
1978
+ },
1979
+ {
1980
+ "epoch": 4.495412844036697,
1981
+ "grad_norm": 0.3280925154685974,
1982
+ "learning_rate": 4.381994978839371e-05,
1983
+ "loss": 0.1981,
1984
+ "num_input_tokens_seen": 10150280,
1985
+ "step": 247
1986
+ },
1987
+ {
1988
+ "epoch": 4.513761467889909,
1989
+ "grad_norm": 0.33136090636253357,
1990
+ "learning_rate": 4.377200082453749e-05,
1991
+ "loss": 0.1681,
1992
+ "num_input_tokens_seen": 10194000,
1993
+ "step": 248
1994
+ },
1995
+ {
1996
+ "epoch": 4.532110091743119,
1997
+ "grad_norm": 0.43955501914024353,
1998
+ "learning_rate": 4.372389301972506e-05,
1999
+ "loss": 0.2111,
2000
+ "num_input_tokens_seen": 10232264,
2001
+ "step": 249
2002
+ },
2003
+ {
2004
+ "epoch": 4.5504587155963305,
2005
+ "grad_norm": 0.28938886523246765,
2006
+ "learning_rate": 4.36756267810249e-05,
2007
+ "loss": 0.2307,
2008
+ "num_input_tokens_seen": 10271880,
2009
+ "step": 250
2010
+ },
2011
+ {
2012
+ "epoch": 4.568807339449541,
2013
+ "grad_norm": 0.37232765555381775,
2014
+ "learning_rate": 4.36272025168461e-05,
2015
+ "loss": 0.1609,
2016
+ "num_input_tokens_seen": 10317720,
2017
+ "step": 251
2018
+ },
2019
+ {
2020
+ "epoch": 4.587155963302752,
2021
+ "grad_norm": 0.6248548030853271,
2022
+ "learning_rate": 4.357862063693486e-05,
2023
+ "loss": 0.2456,
2024
+ "num_input_tokens_seen": 10362168,
2025
+ "step": 252
2026
+ },
2027
+ {
2028
+ "epoch": 4.605504587155964,
2029
+ "grad_norm": 0.32828131318092346,
2030
+ "learning_rate": 4.3529881552371096e-05,
2031
+ "loss": 0.3159,
2032
+ "num_input_tokens_seen": 10414312,
2033
+ "step": 253
2034
+ },
2035
+ {
2036
+ "epoch": 4.623853211009174,
2037
+ "grad_norm": 0.4158332049846649,
2038
+ "learning_rate": 4.34809856755649e-05,
2039
+ "loss": 0.2194,
2040
+ "num_input_tokens_seen": 10451800,
2041
+ "step": 254
2042
+ },
2043
+ {
2044
+ "epoch": 4.6422018348623855,
2045
+ "grad_norm": 0.3648194670677185,
2046
+ "learning_rate": 4.34319334202531e-05,
2047
+ "loss": 0.1846,
2048
+ "num_input_tokens_seen": 10496224,
2049
+ "step": 255
2050
+ },
2051
+ {
2052
+ "epoch": 4.660550458715596,
2053
+ "grad_norm": 0.36835575103759766,
2054
+ "learning_rate": 4.3382725201495723e-05,
2055
+ "loss": 0.1906,
2056
+ "num_input_tokens_seen": 10536392,
2057
+ "step": 256
2058
+ },
2059
+ {
2060
+ "epoch": 4.678899082568807,
2061
+ "grad_norm": 0.3501613140106201,
2062
+ "learning_rate": 4.333336143567247e-05,
2063
+ "loss": 0.1793,
2064
+ "num_input_tokens_seen": 10577640,
2065
+ "step": 257
2066
+ },
2067
+ {
2068
+ "epoch": 4.697247706422019,
2069
+ "grad_norm": 0.3431616425514221,
2070
+ "learning_rate": 4.3283842540479264e-05,
2071
+ "loss": 0.1576,
2072
+ "num_input_tokens_seen": 10613376,
2073
+ "step": 258
2074
+ },
2075
+ {
2076
+ "epoch": 4.715596330275229,
2077
+ "grad_norm": 0.3290237784385681,
2078
+ "learning_rate": 4.3234168934924636e-05,
2079
+ "loss": 0.1447,
2080
+ "num_input_tokens_seen": 10647232,
2081
+ "step": 259
2082
+ },
2083
+ {
2084
+ "epoch": 4.73394495412844,
2085
+ "grad_norm": 0.40264153480529785,
2086
+ "learning_rate": 4.318434103932622e-05,
2087
+ "loss": 0.1488,
2088
+ "num_input_tokens_seen": 10696024,
2089
+ "step": 260
2090
+ },
2091
+ {
2092
+ "epoch": 4.752293577981652,
2093
+ "grad_norm": 0.3453703820705414,
2094
+ "learning_rate": 4.313435927530719e-05,
2095
+ "loss": 0.1597,
2096
+ "num_input_tokens_seen": 10730408,
2097
+ "step": 261
2098
+ },
2099
+ {
2100
+ "epoch": 4.770642201834862,
2101
+ "grad_norm": 0.3993653655052185,
2102
+ "learning_rate": 4.30842240657927e-05,
2103
+ "loss": 0.2266,
2104
+ "num_input_tokens_seen": 10764776,
2105
+ "step": 262
2106
+ },
2107
+ {
2108
+ "epoch": 4.7889908256880735,
2109
+ "grad_norm": 0.4080798923969269,
2110
+ "learning_rate": 4.303393583500628e-05,
2111
+ "loss": 0.1562,
2112
+ "num_input_tokens_seen": 10792272,
2113
+ "step": 263
2114
+ },
2115
+ {
2116
+ "epoch": 4.807339449541285,
2117
+ "grad_norm": 0.3028413951396942,
2118
+ "learning_rate": 4.2983495008466276e-05,
2119
+ "loss": 0.1504,
2120
+ "num_input_tokens_seen": 10825240,
2121
+ "step": 264
2122
+ },
2123
+ {
2124
+ "epoch": 4.825688073394495,
2125
+ "grad_norm": 0.3980019688606262,
2126
+ "learning_rate": 4.293290201298223e-05,
2127
+ "loss": 0.1648,
2128
+ "num_input_tokens_seen": 10883592,
2129
+ "step": 265
2130
+ },
2131
+ {
2132
+ "epoch": 4.844036697247707,
2133
+ "grad_norm": 0.42035797238349915,
2134
+ "learning_rate": 4.288215727665129e-05,
2135
+ "loss": 0.1652,
2136
+ "num_input_tokens_seen": 10922640,
2137
+ "step": 266
2138
+ },
2139
+ {
2140
+ "epoch": 4.862385321100917,
2141
+ "grad_norm": 0.37766003608703613,
2142
+ "learning_rate": 4.2831261228854544e-05,
2143
+ "loss": 0.1817,
2144
+ "num_input_tokens_seen": 10967288,
2145
+ "step": 267
2146
+ },
2147
+ {
2148
+ "epoch": 4.8807339449541285,
2149
+ "grad_norm": 0.3495088815689087,
2150
+ "learning_rate": 4.278021430025343e-05,
2151
+ "loss": 0.2066,
2152
+ "num_input_tokens_seen": 11011152,
2153
+ "step": 268
2154
+ },
2155
+ {
2156
+ "epoch": 4.89908256880734,
2157
+ "grad_norm": 0.34071093797683716,
2158
+ "learning_rate": 4.272901692278609e-05,
2159
+ "loss": 0.1522,
2160
+ "num_input_tokens_seen": 11055608,
2161
+ "step": 269
2162
+ },
2163
+ {
2164
+ "epoch": 4.91743119266055,
2165
+ "grad_norm": 0.33437398076057434,
2166
+ "learning_rate": 4.267766952966369e-05,
2167
+ "loss": 0.2201,
2168
+ "num_input_tokens_seen": 11101992,
2169
+ "step": 270
2170
+ },
2171
+ {
2172
+ "epoch": 4.935779816513762,
2173
+ "grad_norm": 0.3340584337711334,
2174
+ "learning_rate": 4.262617255536676e-05,
2175
+ "loss": 0.2777,
2176
+ "num_input_tokens_seen": 11141408,
2177
+ "step": 271
2178
+ },
2179
+ {
2180
+ "epoch": 4.954128440366972,
2181
+ "grad_norm": 0.348679780960083,
2182
+ "learning_rate": 4.257452643564155e-05,
2183
+ "loss": 0.1857,
2184
+ "num_input_tokens_seen": 11185344,
2185
+ "step": 272
2186
+ },
2187
+ {
2188
+ "epoch": 4.972477064220183,
2189
+ "grad_norm": 0.3691309094429016,
2190
+ "learning_rate": 4.2522731607496275e-05,
2191
+ "loss": 0.1653,
2192
+ "num_input_tokens_seen": 11216160,
2193
+ "step": 273
2194
+ },
2195
+ {
2196
+ "epoch": 4.990825688073395,
2197
+ "grad_norm": 0.4692390561103821,
2198
+ "learning_rate": 4.24707885091975e-05,
2199
+ "loss": 0.1761,
2200
+ "num_input_tokens_seen": 11276200,
2201
+ "step": 274
2202
+ },
2203
+ {
2204
+ "epoch": 5.0,
2205
+ "grad_norm": 0.4963766932487488,
2206
+ "learning_rate": 4.241869758026638e-05,
2207
+ "loss": 0.1582,
2208
+ "num_input_tokens_seen": 11295440,
2209
+ "step": 275
2210
+ },
2211
+ {
2212
+ "epoch": 5.018348623853211,
2213
+ "grad_norm": 0.37284544110298157,
2214
+ "learning_rate": 4.2366459261474933e-05,
2215
+ "loss": 0.1538,
2216
+ "num_input_tokens_seen": 11336400,
2217
+ "step": 276
2218
+ },
2219
+ {
2220
+ "epoch": 5.036697247706422,
2221
+ "grad_norm": 0.2949577867984772,
2222
+ "learning_rate": 4.231407399484236e-05,
2223
+ "loss": 0.1319,
2224
+ "num_input_tokens_seen": 11374056,
2225
+ "step": 277
2226
+ },
2227
+ {
2228
+ "epoch": 5.055045871559633,
2229
+ "grad_norm": 0.32850027084350586,
2230
+ "learning_rate": 4.226154222363124e-05,
2231
+ "loss": 0.174,
2232
+ "num_input_tokens_seen": 11414776,
2233
+ "step": 278
2234
+ },
2235
+ {
2236
+ "epoch": 5.073394495412844,
2237
+ "grad_norm": 0.3812579810619354,
2238
+ "learning_rate": 4.220886439234385e-05,
2239
+ "loss": 0.1831,
2240
+ "num_input_tokens_seen": 11465456,
2241
+ "step": 279
2242
+ },
2243
+ {
2244
+ "epoch": 5.091743119266055,
2245
+ "grad_norm": 0.3396337032318115,
2246
+ "learning_rate": 4.215604094671835e-05,
2247
+ "loss": 0.1515,
2248
+ "num_input_tokens_seen": 11500184,
2249
+ "step": 280
2250
+ },
2251
+ {
2252
+ "epoch": 5.110091743119266,
2253
+ "grad_norm": 0.35079169273376465,
2254
+ "learning_rate": 4.2103072333725e-05,
2255
+ "loss": 0.1295,
2256
+ "num_input_tokens_seen": 11537112,
2257
+ "step": 281
2258
+ },
2259
+ {
2260
+ "epoch": 5.128440366972477,
2261
+ "grad_norm": 0.3811327815055847,
2262
+ "learning_rate": 4.2049959001562464e-05,
2263
+ "loss": 0.1339,
2264
+ "num_input_tokens_seen": 11579440,
2265
+ "step": 282
2266
+ },
2267
+ {
2268
+ "epoch": 5.146788990825688,
2269
+ "grad_norm": 0.3935602009296417,
2270
+ "learning_rate": 4.199670139965393e-05,
2271
+ "loss": 0.1909,
2272
+ "num_input_tokens_seen": 11643272,
2273
+ "step": 283
2274
+ },
2275
+ {
2276
+ "epoch": 5.165137614678899,
2277
+ "grad_norm": 0.3952607810497284,
2278
+ "learning_rate": 4.194329997864331e-05,
2279
+ "loss": 0.2334,
2280
+ "num_input_tokens_seen": 11677528,
2281
+ "step": 284
2282
+ },
2283
+ {
2284
+ "epoch": 5.18348623853211,
2285
+ "grad_norm": 0.3687472939491272,
2286
+ "learning_rate": 4.188975519039151e-05,
2287
+ "loss": 0.1406,
2288
+ "num_input_tokens_seen": 11727944,
2289
+ "step": 285
2290
+ },
2291
+ {
2292
+ "epoch": 5.201834862385321,
2293
+ "grad_norm": 0.3518407344818115,
2294
+ "learning_rate": 4.183606748797251e-05,
2295
+ "loss": 0.138,
2296
+ "num_input_tokens_seen": 11779568,
2297
+ "step": 286
2298
+ },
2299
+ {
2300
+ "epoch": 5.220183486238533,
2301
+ "grad_norm": 0.4072832763195038,
2302
+ "learning_rate": 4.1782237325669595e-05,
2303
+ "loss": 0.159,
2304
+ "num_input_tokens_seen": 11824600,
2305
+ "step": 287
2306
+ },
2307
+ {
2308
+ "epoch": 5.238532110091743,
2309
+ "grad_norm": 0.386280357837677,
2310
+ "learning_rate": 4.172826515897146e-05,
2311
+ "loss": 0.2517,
2312
+ "num_input_tokens_seen": 11873736,
2313
+ "step": 288
2314
+ },
2315
+ {
2316
+ "epoch": 5.256880733944954,
2317
+ "grad_norm": 0.3576860725879669,
2318
+ "learning_rate": 4.167415144456841e-05,
2319
+ "loss": 0.1349,
2320
+ "num_input_tokens_seen": 11909608,
2321
+ "step": 289
2322
+ },
2323
+ {
2324
+ "epoch": 5.275229357798165,
2325
+ "grad_norm": 0.3952435851097107,
2326
+ "learning_rate": 4.1619896640348445e-05,
2327
+ "loss": 0.1348,
2328
+ "num_input_tokens_seen": 11945440,
2329
+ "step": 290
2330
+ },
2331
+ {
2332
+ "epoch": 5.293577981651376,
2333
+ "grad_norm": 0.3565181493759155,
2334
+ "learning_rate": 4.1565501205393445e-05,
2335
+ "loss": 0.1331,
2336
+ "num_input_tokens_seen": 11985568,
2337
+ "step": 291
2338
+ },
2339
+ {
2340
+ "epoch": 5.3119266055045875,
2341
+ "grad_norm": 0.40558820962905884,
2342
+ "learning_rate": 4.1510965599975196e-05,
2343
+ "loss": 0.2337,
2344
+ "num_input_tokens_seen": 12034320,
2345
+ "step": 292
2346
+ },
2347
+ {
2348
+ "epoch": 5.330275229357798,
2349
+ "grad_norm": 0.36426106095314026,
2350
+ "learning_rate": 4.1456290285551596e-05,
2351
+ "loss": 0.1299,
2352
+ "num_input_tokens_seen": 12070184,
2353
+ "step": 293
2354
+ },
2355
+ {
2356
+ "epoch": 5.348623853211009,
2357
+ "grad_norm": 0.33881404995918274,
2358
+ "learning_rate": 4.140147572476268e-05,
2359
+ "loss": 0.1239,
2360
+ "num_input_tokens_seen": 12111512,
2361
+ "step": 294
2362
+ },
2363
+ {
2364
+ "epoch": 5.36697247706422,
2365
+ "grad_norm": 0.38019630312919617,
2366
+ "learning_rate": 4.1346522381426744e-05,
2367
+ "loss": 0.133,
2368
+ "num_input_tokens_seen": 12156792,
2369
+ "step": 295
2370
+ },
2371
+ {
2372
+ "epoch": 5.385321100917431,
2373
+ "grad_norm": 0.38179296255111694,
2374
+ "learning_rate": 4.129143072053638e-05,
2375
+ "loss": 0.1301,
2376
+ "num_input_tokens_seen": 12185168,
2377
+ "step": 296
2378
+ },
2379
+ {
2380
+ "epoch": 5.4036697247706424,
2381
+ "grad_norm": 0.35054150223731995,
2382
+ "learning_rate": 4.123620120825459e-05,
2383
+ "loss": 0.1298,
2384
+ "num_input_tokens_seen": 12222256,
2385
+ "step": 297
2386
+ },
2387
+ {
2388
+ "epoch": 5.422018348623853,
2389
+ "grad_norm": 0.3463946580886841,
2390
+ "learning_rate": 4.118083431191081e-05,
2391
+ "loss": 0.2088,
2392
+ "num_input_tokens_seen": 12257536,
2393
+ "step": 298
2394
+ },
2395
+ {
2396
+ "epoch": 5.440366972477064,
2397
+ "grad_norm": 0.42584434151649475,
2398
+ "learning_rate": 4.112533049999696e-05,
2399
+ "loss": 0.1062,
2400
+ "num_input_tokens_seen": 12290576,
2401
+ "step": 299
2402
+ },
2403
+ {
2404
+ "epoch": 5.458715596330276,
2405
+ "grad_norm": 0.4341515600681305,
2406
+ "learning_rate": 4.1069690242163484e-05,
2407
+ "loss": 0.1989,
2408
+ "num_input_tokens_seen": 12323416,
2409
+ "step": 300
2410
+ },
2411
+ {
2412
+ "epoch": 5.477064220183486,
2413
+ "grad_norm": 0.4299938380718231,
2414
+ "learning_rate": 4.101391400921538e-05,
2415
+ "loss": 0.1243,
2416
+ "num_input_tokens_seen": 12370264,
2417
+ "step": 301
2418
+ },
2419
+ {
2420
+ "epoch": 5.495412844036697,
2421
+ "grad_norm": 0.4070415198802948,
2422
+ "learning_rate": 4.095800227310821e-05,
2423
+ "loss": 0.2281,
2424
+ "num_input_tokens_seen": 12410568,
2425
+ "step": 302
2426
+ },
2427
+ {
2428
+ "epoch": 5.513761467889909,
2429
+ "grad_norm": 0.4446506202220917,
2430
+ "learning_rate": 4.09019555069441e-05,
2431
+ "loss": 0.1462,
2432
+ "num_input_tokens_seen": 12442880,
2433
+ "step": 303
2434
+ },
2435
+ {
2436
+ "epoch": 5.532110091743119,
2437
+ "grad_norm": 0.36110538244247437,
2438
+ "learning_rate": 4.0845774184967754e-05,
2439
+ "loss": 0.1497,
2440
+ "num_input_tokens_seen": 12487016,
2441
+ "step": 304
2442
+ },
2443
+ {
2444
+ "epoch": 5.5504587155963305,
2445
+ "grad_norm": 0.42756903171539307,
2446
+ "learning_rate": 4.078945878256244e-05,
2447
+ "loss": 0.2082,
2448
+ "num_input_tokens_seen": 12525072,
2449
+ "step": 305
2450
+ },
2451
+ {
2452
+ "epoch": 5.568807339449541,
2453
+ "grad_norm": 0.360649049282074,
2454
+ "learning_rate": 4.073300977624594e-05,
2455
+ "loss": 0.1214,
2456
+ "num_input_tokens_seen": 12555792,
2457
+ "step": 306
2458
+ },
2459
+ {
2460
+ "epoch": 5.587155963302752,
2461
+ "grad_norm": 0.3768391013145447,
2462
+ "learning_rate": 4.067642764366654e-05,
2463
+ "loss": 0.1278,
2464
+ "num_input_tokens_seen": 12601616,
2465
+ "step": 307
2466
+ },
2467
+ {
2468
+ "epoch": 5.605504587155964,
2469
+ "grad_norm": 0.3882285952568054,
2470
+ "learning_rate": 4.0619712863599e-05,
2471
+ "loss": 0.1485,
2472
+ "num_input_tokens_seen": 12634360,
2473
+ "step": 308
2474
+ },
2475
+ {
2476
+ "epoch": 5.623853211009174,
2477
+ "grad_norm": 0.38816162943840027,
2478
+ "learning_rate": 4.0562865915940496e-05,
2479
+ "loss": 0.1221,
2480
+ "num_input_tokens_seen": 12674808,
2481
+ "step": 309
2482
+ },
2483
+ {
2484
+ "epoch": 5.6422018348623855,
2485
+ "grad_norm": 0.41803887486457825,
2486
+ "learning_rate": 4.05058872817065e-05,
2487
+ "loss": 0.1388,
2488
+ "num_input_tokens_seen": 12710864,
2489
+ "step": 310
2490
+ },
2491
+ {
2492
+ "epoch": 5.660550458715596,
2493
+ "grad_norm": 0.3802741467952728,
2494
+ "learning_rate": 4.044877744302683e-05,
2495
+ "loss": 0.1349,
2496
+ "num_input_tokens_seen": 12750920,
2497
+ "step": 311
2498
+ },
2499
+ {
2500
+ "epoch": 5.678899082568807,
2501
+ "grad_norm": 0.48202404379844666,
2502
+ "learning_rate": 4.039153688314145e-05,
2503
+ "loss": 0.1555,
2504
+ "num_input_tokens_seen": 12789488,
2505
+ "step": 312
2506
+ },
2507
+ {
2508
+ "epoch": 5.697247706422019,
2509
+ "grad_norm": 0.3168826103210449,
2510
+ "learning_rate": 4.0334166086396484e-05,
2511
+ "loss": 0.1063,
2512
+ "num_input_tokens_seen": 12831408,
2513
+ "step": 313
2514
+ },
2515
+ {
2516
+ "epoch": 5.715596330275229,
2517
+ "grad_norm": 0.43414828181266785,
2518
+ "learning_rate": 4.0276665538239996e-05,
2519
+ "loss": 0.127,
2520
+ "num_input_tokens_seen": 12872584,
2521
+ "step": 314
2522
+ },
2523
+ {
2524
+ "epoch": 5.73394495412844,
2525
+ "grad_norm": 0.47761547565460205,
2526
+ "learning_rate": 4.021903572521802e-05,
2527
+ "loss": 0.1428,
2528
+ "num_input_tokens_seen": 12910528,
2529
+ "step": 315
2530
+ },
2531
+ {
2532
+ "epoch": 5.752293577981652,
2533
+ "grad_norm": 0.3542017936706543,
2534
+ "learning_rate": 4.0161277134970345e-05,
2535
+ "loss": 0.1279,
2536
+ "num_input_tokens_seen": 12942800,
2537
+ "step": 316
2538
+ },
2539
+ {
2540
+ "epoch": 5.770642201834862,
2541
+ "grad_norm": 0.31866851449012756,
2542
+ "learning_rate": 4.010339025622641e-05,
2543
+ "loss": 0.1459,
2544
+ "num_input_tokens_seen": 12989136,
2545
+ "step": 317
2546
+ },
2547
+ {
2548
+ "epoch": 5.7889908256880735,
2549
+ "grad_norm": 0.44918256998062134,
2550
+ "learning_rate": 4.0045375578801214e-05,
2551
+ "loss": 0.1429,
2552
+ "num_input_tokens_seen": 13035472,
2553
+ "step": 318
2554
+ },
2555
+ {
2556
+ "epoch": 5.807339449541285,
2557
+ "grad_norm": 0.32426726818084717,
2558
+ "learning_rate": 3.99872335935911e-05,
2559
+ "loss": 0.1257,
2560
+ "num_input_tokens_seen": 13074952,
2561
+ "step": 319
2562
+ },
2563
+ {
2564
+ "epoch": 5.825688073394495,
2565
+ "grad_norm": 0.6903991103172302,
2566
+ "learning_rate": 3.9928964792569655e-05,
2567
+ "loss": 0.1807,
2568
+ "num_input_tokens_seen": 13124624,
2569
+ "step": 320
2570
+ },
2571
+ {
2572
+ "epoch": 5.844036697247707,
2573
+ "grad_norm": 0.3665274679660797,
2574
+ "learning_rate": 3.9870569668783536e-05,
2575
+ "loss": 0.1853,
2576
+ "num_input_tokens_seen": 13171464,
2577
+ "step": 321
2578
+ },
2579
+ {
2580
+ "epoch": 5.862385321100917,
2581
+ "grad_norm": 0.41457998752593994,
2582
+ "learning_rate": 3.981204871634827e-05,
2583
+ "loss": 0.214,
2584
+ "num_input_tokens_seen": 13225240,
2585
+ "step": 322
2586
+ },
2587
+ {
2588
+ "epoch": 5.8807339449541285,
2589
+ "grad_norm": 0.4047159254550934,
2590
+ "learning_rate": 3.9753402430444116e-05,
2591
+ "loss": 0.1907,
2592
+ "num_input_tokens_seen": 13275848,
2593
+ "step": 323
2594
+ },
2595
+ {
2596
+ "epoch": 5.89908256880734,
2597
+ "grad_norm": 0.4578211307525635,
2598
+ "learning_rate": 3.969463130731183e-05,
2599
+ "loss": 0.27,
2600
+ "num_input_tokens_seen": 13311096,
2601
+ "step": 324
2602
+ },
2603
+ {
2604
+ "epoch": 5.91743119266055,
2605
+ "grad_norm": 0.42030438780784607,
2606
+ "learning_rate": 3.963573584424852e-05,
2607
+ "loss": 0.1775,
2608
+ "num_input_tokens_seen": 13375064,
2609
+ "step": 325
2610
+ },
2611
+ {
2612
+ "epoch": 5.935779816513762,
2613
+ "grad_norm": 0.3531726598739624,
2614
+ "learning_rate": 3.957671653960337e-05,
2615
+ "loss": 0.1206,
2616
+ "num_input_tokens_seen": 13427072,
2617
+ "step": 326
2618
+ },
2619
+ {
2620
+ "epoch": 5.954128440366972,
2621
+ "grad_norm": 0.41528916358947754,
2622
+ "learning_rate": 3.9517573892773494e-05,
2623
+ "loss": 0.1232,
2624
+ "num_input_tokens_seen": 13454088,
2625
+ "step": 327
2626
+ },
2627
+ {
2628
+ "epoch": 5.972477064220183,
2629
+ "grad_norm": 0.5357607007026672,
2630
+ "learning_rate": 3.945830840419966e-05,
2631
+ "loss": 0.1696,
2632
+ "num_input_tokens_seen": 13486504,
2633
+ "step": 328
2634
+ },
2635
+ {
2636
+ "epoch": 5.990825688073395,
2637
+ "grad_norm": 0.32135313749313354,
2638
+ "learning_rate": 3.9398920575362086e-05,
2639
+ "loss": 0.1055,
2640
+ "num_input_tokens_seen": 13523736,
2641
+ "step": 329
2642
+ },
2643
+ {
2644
+ "epoch": 6.0,
2645
+ "grad_norm": 0.5267924666404724,
2646
+ "learning_rate": 3.933941090877615e-05,
2647
+ "loss": 0.2192,
2648
+ "num_input_tokens_seen": 13554528,
2649
+ "step": 330
2650
+ },
2651
+ {
2652
+ "epoch": 6.018348623853211,
2653
+ "grad_norm": 0.38375183939933777,
2654
+ "learning_rate": 3.9279779907988215e-05,
2655
+ "loss": 0.1318,
2656
+ "num_input_tokens_seen": 13587424,
2657
+ "step": 331
2658
+ },
2659
+ {
2660
+ "epoch": 6.036697247706422,
2661
+ "grad_norm": 0.38274672627449036,
2662
+ "learning_rate": 3.9220028077571295e-05,
2663
+ "loss": 0.1136,
2664
+ "num_input_tokens_seen": 13624376,
2665
+ "step": 332
2666
+ },
2667
+ {
2668
+ "epoch": 6.055045871559633,
2669
+ "grad_norm": 0.3571849465370178,
2670
+ "learning_rate": 3.916015592312082e-05,
2671
+ "loss": 0.0891,
2672
+ "num_input_tokens_seen": 13652848,
2673
+ "step": 333
2674
+ },
2675
+ {
2676
+ "epoch": 6.073394495412844,
2677
+ "grad_norm": 0.3958500921726227,
2678
+ "learning_rate": 3.910016395125037e-05,
2679
+ "loss": 0.1477,
2680
+ "num_input_tokens_seen": 13719880,
2681
+ "step": 334
2682
+ },
2683
+ {
2684
+ "epoch": 6.091743119266055,
2685
+ "grad_norm": 0.3360799551010132,
2686
+ "learning_rate": 3.9040052669587325e-05,
2687
+ "loss": 0.0943,
2688
+ "num_input_tokens_seen": 13764864,
2689
+ "step": 335
2690
+ },
2691
+ {
2692
+ "epoch": 6.110091743119266,
2693
+ "grad_norm": 0.4332111179828644,
2694
+ "learning_rate": 3.897982258676867e-05,
2695
+ "loss": 0.1039,
2696
+ "num_input_tokens_seen": 13795048,
2697
+ "step": 336
2698
+ },
2699
+ {
2700
+ "epoch": 6.128440366972477,
2701
+ "grad_norm": 0.4539923071861267,
2702
+ "learning_rate": 3.891947421243661e-05,
2703
+ "loss": 0.1294,
2704
+ "num_input_tokens_seen": 13830064,
2705
+ "step": 337
2706
+ },
2707
+ {
2708
+ "epoch": 6.146788990825688,
2709
+ "grad_norm": 0.43116849660873413,
2710
+ "learning_rate": 3.885900805723429e-05,
2711
+ "loss": 0.1233,
2712
+ "num_input_tokens_seen": 13870392,
2713
+ "step": 338
2714
+ },
2715
+ {
2716
+ "epoch": 6.165137614678899,
2717
+ "grad_norm": 0.40204253792762756,
2718
+ "learning_rate": 3.879842463280145e-05,
2719
+ "loss": 0.1252,
2720
+ "num_input_tokens_seen": 13913144,
2721
+ "step": 339
2722
+ },
2723
+ {
2724
+ "epoch": 6.18348623853211,
2725
+ "grad_norm": 0.4300351142883301,
2726
+ "learning_rate": 3.873772445177015e-05,
2727
+ "loss": 0.1191,
2728
+ "num_input_tokens_seen": 13950384,
2729
+ "step": 340
2730
+ },
2731
+ {
2732
+ "epoch": 6.201834862385321,
2733
+ "grad_norm": 0.3162730038166046,
2734
+ "learning_rate": 3.8676908027760364e-05,
2735
+ "loss": 0.1028,
2736
+ "num_input_tokens_seen": 13990464,
2737
+ "step": 341
2738
+ },
2739
+ {
2740
+ "epoch": 6.220183486238533,
2741
+ "grad_norm": 0.4316507875919342,
2742
+ "learning_rate": 3.861597587537568e-05,
2743
+ "loss": 0.0996,
2744
+ "num_input_tokens_seen": 14029080,
2745
+ "step": 342
2746
+ },
2747
+ {
2748
+ "epoch": 6.238532110091743,
2749
+ "grad_norm": 0.34346097707748413,
2750
+ "learning_rate": 3.855492851019893e-05,
2751
+ "loss": 0.172,
2752
+ "num_input_tokens_seen": 14069824,
2753
+ "step": 343
2754
+ },
2755
+ {
2756
+ "epoch": 6.256880733944954,
2757
+ "grad_norm": 0.41037800908088684,
2758
+ "learning_rate": 3.8493766448787825e-05,
2759
+ "loss": 0.1244,
2760
+ "num_input_tokens_seen": 14107616,
2761
+ "step": 344
2762
+ },
2763
+ {
2764
+ "epoch": 6.275229357798165,
2765
+ "grad_norm": 0.5019925236701965,
2766
+ "learning_rate": 3.84324902086706e-05,
2767
+ "loss": 0.1584,
2768
+ "num_input_tokens_seen": 14146224,
2769
+ "step": 345
2770
+ },
2771
+ {
2772
+ "epoch": 6.293577981651376,
2773
+ "grad_norm": 0.40119829773902893,
2774
+ "learning_rate": 3.837110030834161e-05,
2775
+ "loss": 0.1154,
2776
+ "num_input_tokens_seen": 14183880,
2777
+ "step": 346
2778
+ },
2779
+ {
2780
+ "epoch": 6.3119266055045875,
2781
+ "grad_norm": 0.37845325469970703,
2782
+ "learning_rate": 3.830959726725697e-05,
2783
+ "loss": 0.098,
2784
+ "num_input_tokens_seen": 14214632,
2785
+ "step": 347
2786
+ },
2787
+ {
2788
+ "epoch": 6.330275229357798,
2789
+ "grad_norm": 0.338489294052124,
2790
+ "learning_rate": 3.824798160583012e-05,
2791
+ "loss": 0.2212,
2792
+ "num_input_tokens_seen": 14263168,
2793
+ "step": 348
2794
+ },
2795
+ {
2796
+ "epoch": 6.348623853211009,
2797
+ "grad_norm": 0.4595409631729126,
2798
+ "learning_rate": 3.81862538454275e-05,
2799
+ "loss": 0.1423,
2800
+ "num_input_tokens_seen": 14303680,
2801
+ "step": 349
2802
+ },
2803
+ {
2804
+ "epoch": 6.36697247706422,
2805
+ "grad_norm": 0.38874781131744385,
2806
+ "learning_rate": 3.8124414508364e-05,
2807
+ "loss": 0.1119,
2808
+ "num_input_tokens_seen": 14347672,
2809
+ "step": 350
2810
+ },
2811
+ {
2812
+ "epoch": 6.385321100917431,
2813
+ "grad_norm": 0.3326081931591034,
2814
+ "learning_rate": 3.8062464117898724e-05,
2815
+ "loss": 0.1068,
2816
+ "num_input_tokens_seen": 14394848,
2817
+ "step": 351
2818
+ },
2819
+ {
2820
+ "epoch": 6.4036697247706424,
2821
+ "grad_norm": 0.40956059098243713,
2822
+ "learning_rate": 3.8000403198230387e-05,
2823
+ "loss": 0.1051,
2824
+ "num_input_tokens_seen": 14438856,
2825
+ "step": 352
2826
+ },
2827
+ {
2828
+ "epoch": 6.422018348623853,
2829
+ "grad_norm": 0.353677362203598,
2830
+ "learning_rate": 3.7938232274493e-05,
2831
+ "loss": 0.2208,
2832
+ "num_input_tokens_seen": 14498032,
2833
+ "step": 353
2834
+ },
2835
+ {
2836
+ "epoch": 6.440366972477064,
2837
+ "grad_norm": 0.45626017451286316,
2838
+ "learning_rate": 3.787595187275136e-05,
2839
+ "loss": 0.1131,
2840
+ "num_input_tokens_seen": 14534256,
2841
+ "step": 354
2842
+ },
2843
+ {
2844
+ "epoch": 6.458715596330276,
2845
+ "grad_norm": 0.4512569308280945,
2846
+ "learning_rate": 3.781356251999663e-05,
2847
+ "loss": 0.1207,
2848
+ "num_input_tokens_seen": 14575016,
2849
+ "step": 355
2850
+ },
2851
+ {
2852
+ "epoch": 6.477064220183486,
2853
+ "grad_norm": 0.3183128237724304,
2854
+ "learning_rate": 3.775106474414188e-05,
2855
+ "loss": 0.0887,
2856
+ "num_input_tokens_seen": 14627272,
2857
+ "step": 356
2858
+ },
2859
+ {
2860
+ "epoch": 6.495412844036697,
2861
+ "grad_norm": 0.36176785826683044,
2862
+ "learning_rate": 3.7688459074017606e-05,
2863
+ "loss": 0.1022,
2864
+ "num_input_tokens_seen": 14658696,
2865
+ "step": 357
2866
+ },
2867
+ {
2868
+ "epoch": 6.513761467889909,
2869
+ "grad_norm": 0.362131804227829,
2870
+ "learning_rate": 3.762574603936725e-05,
2871
+ "loss": 0.1582,
2872
+ "num_input_tokens_seen": 14702208,
2873
+ "step": 358
2874
+ },
2875
+ {
2876
+ "epoch": 6.532110091743119,
2877
+ "grad_norm": 0.27560174465179443,
2878
+ "learning_rate": 3.756292617084275e-05,
2879
+ "loss": 0.0855,
2880
+ "num_input_tokens_seen": 14757376,
2881
+ "step": 359
2882
+ },
2883
+ {
2884
+ "epoch": 6.5504587155963305,
2885
+ "grad_norm": 0.4014551043510437,
2886
+ "learning_rate": 3.7500000000000003e-05,
2887
+ "loss": 0.1923,
2888
+ "num_input_tokens_seen": 14796592,
2889
+ "step": 360
2890
+ },
2891
+ {
2892
+ "epoch": 6.568807339449541,
2893
+ "grad_norm": 0.38982701301574707,
2894
+ "learning_rate": 3.7436968059294414e-05,
2895
+ "loss": 0.1125,
2896
+ "num_input_tokens_seen": 14834656,
2897
+ "step": 361
2898
+ },
2899
+ {
2900
+ "epoch": 6.587155963302752,
2901
+ "grad_norm": 0.3973703384399414,
2902
+ "learning_rate": 3.7373830882076354e-05,
2903
+ "loss": 0.1947,
2904
+ "num_input_tokens_seen": 14869528,
2905
+ "step": 362
2906
+ },
2907
+ {
2908
+ "epoch": 6.605504587155964,
2909
+ "grad_norm": 0.43253588676452637,
2910
+ "learning_rate": 3.731058900258668e-05,
2911
+ "loss": 0.1173,
2912
+ "num_input_tokens_seen": 14909720,
2913
+ "step": 363
2914
+ },
2915
+ {
2916
+ "epoch": 6.623853211009174,
2917
+ "grad_norm": 0.4936161935329437,
2918
+ "learning_rate": 3.7247242955952175e-05,
2919
+ "loss": 0.1523,
2920
+ "num_input_tokens_seen": 14952704,
2921
+ "step": 364
2922
+ },
2923
+ {
2924
+ "epoch": 6.6422018348623855,
2925
+ "grad_norm": 0.43221941590309143,
2926
+ "learning_rate": 3.718379327818106e-05,
2927
+ "loss": 0.1313,
2928
+ "num_input_tokens_seen": 14989640,
2929
+ "step": 365
2930
+ },
2931
+ {
2932
+ "epoch": 6.660550458715596,
2933
+ "grad_norm": 0.3976401686668396,
2934
+ "learning_rate": 3.712024050615843e-05,
2935
+ "loss": 0.0985,
2936
+ "num_input_tokens_seen": 15028200,
2937
+ "step": 366
2938
+ },
2939
+ {
2940
+ "epoch": 6.678899082568807,
2941
+ "grad_norm": 0.3843483030796051,
2942
+ "learning_rate": 3.705658517764172e-05,
2943
+ "loss": 0.1905,
2944
+ "num_input_tokens_seen": 15075960,
2945
+ "step": 367
2946
+ },
2947
+ {
2948
+ "epoch": 6.697247706422019,
2949
+ "grad_norm": 0.45637550950050354,
2950
+ "learning_rate": 3.699282783125616e-05,
2951
+ "loss": 0.1166,
2952
+ "num_input_tokens_seen": 15113096,
2953
+ "step": 368
2954
+ },
2955
+ {
2956
+ "epoch": 6.715596330275229,
2957
+ "grad_norm": 0.3767227232456207,
2958
+ "learning_rate": 3.692896900649021e-05,
2959
+ "loss": 0.138,
2960
+ "num_input_tokens_seen": 15162432,
2961
+ "step": 369
2962
+ },
2963
+ {
2964
+ "epoch": 6.73394495412844,
2965
+ "grad_norm": 0.3972814977169037,
2966
+ "learning_rate": 3.686500924369101e-05,
2967
+ "loss": 0.1612,
2968
+ "num_input_tokens_seen": 15203656,
2969
+ "step": 370
2970
+ },
2971
+ {
2972
+ "epoch": 6.752293577981652,
2973
+ "grad_norm": 0.39401331543922424,
2974
+ "learning_rate": 3.680094908405978e-05,
2975
+ "loss": 0.1131,
2976
+ "num_input_tokens_seen": 15251056,
2977
+ "step": 371
2978
+ },
2979
+ {
2980
+ "epoch": 6.770642201834862,
2981
+ "grad_norm": 0.5119125247001648,
2982
+ "learning_rate": 3.673678906964727e-05,
2983
+ "loss": 0.1264,
2984
+ "num_input_tokens_seen": 15283552,
2985
+ "step": 372
2986
+ },
2987
+ {
2988
+ "epoch": 6.7889908256880735,
2989
+ "grad_norm": 0.38780996203422546,
2990
+ "learning_rate": 3.6672529743349146e-05,
2991
+ "loss": 0.1167,
2992
+ "num_input_tokens_seen": 15338944,
2993
+ "step": 373
2994
+ },
2995
+ {
2996
+ "epoch": 6.807339449541285,
2997
+ "grad_norm": 0.45605945587158203,
2998
+ "learning_rate": 3.660817164890143e-05,
2999
+ "loss": 0.131,
3000
+ "num_input_tokens_seen": 15369936,
3001
+ "step": 374
3002
+ },
3003
+ {
3004
+ "epoch": 6.825688073394495,
3005
+ "grad_norm": 0.4043484926223755,
3006
+ "learning_rate": 3.654371533087586e-05,
3007
+ "loss": 0.095,
3008
+ "num_input_tokens_seen": 15411576,
3009
+ "step": 375
3010
+ },
3011
+ {
3012
+ "epoch": 6.844036697247707,
3013
+ "grad_norm": 0.38716065883636475,
3014
+ "learning_rate": 3.6479161334675296e-05,
3015
+ "loss": 0.0937,
3016
+ "num_input_tokens_seen": 15457520,
3017
+ "step": 376
3018
+ },
3019
+ {
3020
+ "epoch": 6.862385321100917,
3021
+ "grad_norm": 0.38785362243652344,
3022
+ "learning_rate": 3.641451020652914e-05,
3023
+ "loss": 0.1017,
3024
+ "num_input_tokens_seen": 15485536,
3025
+ "step": 377
3026
+ },
3027
+ {
3028
+ "epoch": 6.8807339449541285,
3029
+ "grad_norm": 0.3736408054828644,
3030
+ "learning_rate": 3.634976249348867e-05,
3031
+ "loss": 0.1075,
3032
+ "num_input_tokens_seen": 15526704,
3033
+ "step": 378
3034
+ },
3035
+ {
3036
+ "epoch": 6.89908256880734,
3037
+ "grad_norm": 0.5013216733932495,
3038
+ "learning_rate": 3.6284918743422425e-05,
3039
+ "loss": 0.132,
3040
+ "num_input_tokens_seen": 15567344,
3041
+ "step": 379
3042
+ },
3043
+ {
3044
+ "epoch": 6.91743119266055,
3045
+ "grad_norm": 0.5258253216743469,
3046
+ "learning_rate": 3.621997950501156e-05,
3047
+ "loss": 0.1435,
3048
+ "num_input_tokens_seen": 15608408,
3049
+ "step": 380
3050
+ },
3051
+ {
3052
+ "epoch": 6.935779816513762,
3053
+ "grad_norm": 0.3486093282699585,
3054
+ "learning_rate": 3.615494532774522e-05,
3055
+ "loss": 0.0958,
3056
+ "num_input_tokens_seen": 15667496,
3057
+ "step": 381
3058
+ },
3059
+ {
3060
+ "epoch": 6.954128440366972,
3061
+ "grad_norm": 0.39199239015579224,
3062
+ "learning_rate": 3.6089816761915906e-05,
3063
+ "loss": 0.1465,
3064
+ "num_input_tokens_seen": 15715496,
3065
+ "step": 382
3066
+ },
3067
+ {
3068
+ "epoch": 6.972477064220183,
3069
+ "grad_norm": 0.3722994923591614,
3070
+ "learning_rate": 3.602459435861475e-05,
3071
+ "loss": 0.1111,
3072
+ "num_input_tokens_seen": 15755688,
3073
+ "step": 383
3074
+ },
3075
+ {
3076
+ "epoch": 6.990825688073395,
3077
+ "grad_norm": 0.41041186451911926,
3078
+ "learning_rate": 3.5959278669726935e-05,
3079
+ "loss": 0.1084,
3080
+ "num_input_tokens_seen": 15798304,
3081
+ "step": 384
3082
+ },
3083
+ {
3084
+ "epoch": 7.0,
3085
+ "grad_norm": 0.6807722449302673,
3086
+ "learning_rate": 3.589387024792699e-05,
3087
+ "loss": 0.1234,
3088
+ "num_input_tokens_seen": 15813616,
3089
+ "step": 385
3090
+ },
3091
+ {
3092
+ "epoch": 7.018348623853211,
3093
+ "grad_norm": 0.3617340922355652,
3094
+ "learning_rate": 3.582836964667408e-05,
3095
+ "loss": 0.1167,
3096
+ "num_input_tokens_seen": 15855256,
3097
+ "step": 386
3098
+ },
3099
+ {
3100
+ "epoch": 7.036697247706422,
3101
+ "grad_norm": 0.36471137404441833,
3102
+ "learning_rate": 3.576277742020738e-05,
3103
+ "loss": 0.0829,
3104
+ "num_input_tokens_seen": 15887512,
3105
+ "step": 387
3106
+ },
3107
+ {
3108
+ "epoch": 7.055045871559633,
3109
+ "grad_norm": 0.8828345537185669,
3110
+ "learning_rate": 3.569709412354136e-05,
3111
+ "loss": 0.1213,
3112
+ "num_input_tokens_seen": 15934400,
3113
+ "step": 388
3114
+ },
3115
+ {
3116
+ "epoch": 7.073394495412844,
3117
+ "grad_norm": 0.4129248261451721,
3118
+ "learning_rate": 3.563132031246108e-05,
3119
+ "loss": 0.0914,
3120
+ "num_input_tokens_seen": 15969904,
3121
+ "step": 389
3122
+ },
3123
+ {
3124
+ "epoch": 7.091743119266055,
3125
+ "grad_norm": 0.38659873604774475,
3126
+ "learning_rate": 3.556545654351749e-05,
3127
+ "loss": 0.09,
3128
+ "num_input_tokens_seen": 16010760,
3129
+ "step": 390
3130
+ },
3131
+ {
3132
+ "epoch": 7.110091743119266,
3133
+ "grad_norm": 0.46532171964645386,
3134
+ "learning_rate": 3.549950337402274e-05,
3135
+ "loss": 0.0832,
3136
+ "num_input_tokens_seen": 16059680,
3137
+ "step": 391
3138
+ },
3139
+ {
3140
+ "epoch": 7.128440366972477,
3141
+ "grad_norm": 0.3775540888309479,
3142
+ "learning_rate": 3.543346136204545e-05,
3143
+ "loss": 0.079,
3144
+ "num_input_tokens_seen": 16095992,
3145
+ "step": 392
3146
+ },
3147
+ {
3148
+ "epoch": 7.146788990825688,
3149
+ "grad_norm": 0.5437320470809937,
3150
+ "learning_rate": 3.536733106640598e-05,
3151
+ "loss": 0.1,
3152
+ "num_input_tokens_seen": 16135568,
3153
+ "step": 393
3154
+ },
3155
+ {
3156
+ "epoch": 7.165137614678899,
3157
+ "grad_norm": 0.3908531963825226,
3158
+ "learning_rate": 3.5301113046671714e-05,
3159
+ "loss": 0.0962,
3160
+ "num_input_tokens_seen": 16165016,
3161
+ "step": 394
3162
+ },
3163
+ {
3164
+ "epoch": 7.18348623853211,
3165
+ "grad_norm": 0.40789636969566345,
3166
+ "learning_rate": 3.523480786315231e-05,
3167
+ "loss": 0.0923,
3168
+ "num_input_tokens_seen": 16208344,
3169
+ "step": 395
3170
+ },
3171
+ {
3172
+ "epoch": 7.201834862385321,
3173
+ "grad_norm": 0.4682011902332306,
3174
+ "learning_rate": 3.516841607689501e-05,
3175
+ "loss": 0.101,
3176
+ "num_input_tokens_seen": 16244312,
3177
+ "step": 396
3178
+ },
3179
+ {
3180
+ "epoch": 7.220183486238533,
3181
+ "grad_norm": 0.5206179618835449,
3182
+ "learning_rate": 3.5101938249679794e-05,
3183
+ "loss": 0.1124,
3184
+ "num_input_tokens_seen": 16283848,
3185
+ "step": 397
3186
+ },
3187
+ {
3188
+ "epoch": 7.238532110091743,
3189
+ "grad_norm": 0.5803564786911011,
3190
+ "learning_rate": 3.503537494401473e-05,
3191
+ "loss": 0.1054,
3192
+ "num_input_tokens_seen": 16336288,
3193
+ "step": 398
3194
+ },
3195
+ {
3196
+ "epoch": 7.256880733944954,
3197
+ "grad_norm": 0.44892576336860657,
3198
+ "learning_rate": 3.496872672313116e-05,
3199
+ "loss": 0.1781,
3200
+ "num_input_tokens_seen": 16375448,
3201
+ "step": 399
3202
+ },
3203
+ {
3204
+ "epoch": 7.275229357798165,
3205
+ "grad_norm": 0.42554035782814026,
3206
+ "learning_rate": 3.490199415097892e-05,
3207
+ "loss": 0.0935,
3208
+ "num_input_tokens_seen": 16412608,
3209
+ "step": 400
3210
+ },
3211
+ {
3212
+ "epoch": 7.293577981651376,
3213
+ "grad_norm": 0.3525730073451996,
3214
+ "learning_rate": 3.483517779222163e-05,
3215
+ "loss": 0.0944,
3216
+ "num_input_tokens_seen": 16455904,
3217
+ "step": 401
3218
+ },
3219
+ {
3220
+ "epoch": 7.3119266055045875,
3221
+ "grad_norm": 0.3382134735584259,
3222
+ "learning_rate": 3.476827821223184e-05,
3223
+ "loss": 0.0878,
3224
+ "num_input_tokens_seen": 16496824,
3225
+ "step": 402
3226
+ },
3227
+ {
3228
+ "epoch": 7.330275229357798,
3229
+ "grad_norm": 0.38020089268684387,
3230
+ "learning_rate": 3.4701295977086324e-05,
3231
+ "loss": 0.0911,
3232
+ "num_input_tokens_seen": 16529344,
3233
+ "step": 403
3234
+ },
3235
+ {
3236
+ "epoch": 7.348623853211009,
3237
+ "grad_norm": 0.44909772276878357,
3238
+ "learning_rate": 3.463423165356121e-05,
3239
+ "loss": 0.1047,
3240
+ "num_input_tokens_seen": 16563664,
3241
+ "step": 404
3242
+ },
3243
+ {
3244
+ "epoch": 7.36697247706422,
3245
+ "grad_norm": 0.3612752854824066,
3246
+ "learning_rate": 3.456708580912725e-05,
3247
+ "loss": 0.1228,
3248
+ "num_input_tokens_seen": 16607272,
3249
+ "step": 405
3250
+ },
3251
+ {
3252
+ "epoch": 7.385321100917431,
3253
+ "grad_norm": 0.5135468244552612,
3254
+ "learning_rate": 3.449985901194498e-05,
3255
+ "loss": 0.1801,
3256
+ "num_input_tokens_seen": 16646040,
3257
+ "step": 406
3258
+ },
3259
+ {
3260
+ "epoch": 7.4036697247706424,
3261
+ "grad_norm": 0.33949241042137146,
3262
+ "learning_rate": 3.443255183085993e-05,
3263
+ "loss": 0.0883,
3264
+ "num_input_tokens_seen": 16693544,
3265
+ "step": 407
3266
+ },
3267
+ {
3268
+ "epoch": 7.422018348623853,
3269
+ "grad_norm": 0.3560762405395508,
3270
+ "learning_rate": 3.436516483539781e-05,
3271
+ "loss": 0.083,
3272
+ "num_input_tokens_seen": 16742128,
3273
+ "step": 408
3274
+ },
3275
+ {
3276
+ "epoch": 7.440366972477064,
3277
+ "grad_norm": 0.32824087142944336,
3278
+ "learning_rate": 3.4297698595759664e-05,
3279
+ "loss": 0.1247,
3280
+ "num_input_tokens_seen": 16792000,
3281
+ "step": 409
3282
+ },
3283
+ {
3284
+ "epoch": 7.458715596330276,
3285
+ "grad_norm": 0.44831863045692444,
3286
+ "learning_rate": 3.423015368281711e-05,
3287
+ "loss": 0.0948,
3288
+ "num_input_tokens_seen": 16824312,
3289
+ "step": 410
3290
+ },
3291
+ {
3292
+ "epoch": 7.477064220183486,
3293
+ "grad_norm": 0.4942893981933594,
3294
+ "learning_rate": 3.4162530668107434e-05,
3295
+ "loss": 0.0993,
3296
+ "num_input_tokens_seen": 16856344,
3297
+ "step": 411
3298
+ },
3299
+ {
3300
+ "epoch": 7.495412844036697,
3301
+ "grad_norm": 0.3783268332481384,
3302
+ "learning_rate": 3.409483012382879e-05,
3303
+ "loss": 0.1273,
3304
+ "num_input_tokens_seen": 16898256,
3305
+ "step": 412
3306
+ },
3307
+ {
3308
+ "epoch": 7.513761467889909,
3309
+ "grad_norm": 0.5532792210578918,
3310
+ "learning_rate": 3.402705262283537e-05,
3311
+ "loss": 0.1171,
3312
+ "num_input_tokens_seen": 16939304,
3313
+ "step": 413
3314
+ },
3315
+ {
3316
+ "epoch": 7.532110091743119,
3317
+ "grad_norm": 0.3667624592781067,
3318
+ "learning_rate": 3.39591987386325e-05,
3319
+ "loss": 0.1753,
3320
+ "num_input_tokens_seen": 16978632,
3321
+ "step": 414
3322
+ },
3323
+ {
3324
+ "epoch": 7.5504587155963305,
3325
+ "grad_norm": 0.42965346574783325,
3326
+ "learning_rate": 3.389126904537192e-05,
3327
+ "loss": 0.1567,
3328
+ "num_input_tokens_seen": 17016552,
3329
+ "step": 415
3330
+ },
3331
+ {
3332
+ "epoch": 7.568807339449541,
3333
+ "grad_norm": 0.41699931025505066,
3334
+ "learning_rate": 3.382326411784672e-05,
3335
+ "loss": 0.0941,
3336
+ "num_input_tokens_seen": 17067688,
3337
+ "step": 416
3338
+ },
3339
+ {
3340
+ "epoch": 7.587155963302752,
3341
+ "grad_norm": 0.3647185266017914,
3342
+ "learning_rate": 3.375518453148669e-05,
3343
+ "loss": 0.0961,
3344
+ "num_input_tokens_seen": 17126008,
3345
+ "step": 417
3346
+ },
3347
+ {
3348
+ "epoch": 7.605504587155964,
3349
+ "grad_norm": 0.5344395041465759,
3350
+ "learning_rate": 3.3687030862353286e-05,
3351
+ "loss": 0.1974,
3352
+ "num_input_tokens_seen": 17165800,
3353
+ "step": 418
3354
+ },
3355
+ {
3356
+ "epoch": 7.623853211009174,
3357
+ "grad_norm": 0.38556504249572754,
3358
+ "learning_rate": 3.361880368713486e-05,
3359
+ "loss": 0.094,
3360
+ "num_input_tokens_seen": 17199832,
3361
+ "step": 419
3362
+ },
3363
+ {
3364
+ "epoch": 7.6422018348623855,
3365
+ "grad_norm": 0.3512709438800812,
3366
+ "learning_rate": 3.355050358314172e-05,
3367
+ "loss": 0.0717,
3368
+ "num_input_tokens_seen": 17237952,
3369
+ "step": 420
3370
+ },
3371
+ {
3372
+ "epoch": 7.660550458715596,
3373
+ "grad_norm": 0.35488539934158325,
3374
+ "learning_rate": 3.348213112830128e-05,
3375
+ "loss": 0.0943,
3376
+ "num_input_tokens_seen": 17278384,
3377
+ "step": 421
3378
+ },
3379
+ {
3380
+ "epoch": 7.678899082568807,
3381
+ "grad_norm": 0.4220011234283447,
3382
+ "learning_rate": 3.3413686901153165e-05,
3383
+ "loss": 0.0814,
3384
+ "num_input_tokens_seen": 17309544,
3385
+ "step": 422
3386
+ },
3387
+ {
3388
+ "epoch": 7.697247706422019,
3389
+ "grad_norm": 0.42773446440696716,
3390
+ "learning_rate": 3.3345171480844275e-05,
3391
+ "loss": 0.1192,
3392
+ "num_input_tokens_seen": 17344896,
3393
+ "step": 423
3394
+ },
3395
+ {
3396
+ "epoch": 7.715596330275229,
3397
+ "grad_norm": 0.30265432596206665,
3398
+ "learning_rate": 3.327658544712395e-05,
3399
+ "loss": 0.104,
3400
+ "num_input_tokens_seen": 17413176,
3401
+ "step": 424
3402
+ },
3403
+ {
3404
+ "epoch": 7.73394495412844,
3405
+ "grad_norm": 0.38354116678237915,
3406
+ "learning_rate": 3.3207929380339034e-05,
3407
+ "loss": 0.0965,
3408
+ "num_input_tokens_seen": 17450416,
3409
+ "step": 425
3410
+ },
3411
+ {
3412
+ "epoch": 7.752293577981652,
3413
+ "grad_norm": 0.33634060621261597,
3414
+ "learning_rate": 3.313920386142892e-05,
3415
+ "loss": 0.0775,
3416
+ "num_input_tokens_seen": 17491256,
3417
+ "step": 426
3418
+ },
3419
+ {
3420
+ "epoch": 7.770642201834862,
3421
+ "grad_norm": 0.4931448698043823,
3422
+ "learning_rate": 3.3070409471920726e-05,
3423
+ "loss": 0.1651,
3424
+ "num_input_tokens_seen": 17521600,
3425
+ "step": 427
3426
+ },
3427
+ {
3428
+ "epoch": 7.7889908256880735,
3429
+ "grad_norm": 0.4020994007587433,
3430
+ "learning_rate": 3.3001546793924285e-05,
3431
+ "loss": 0.1071,
3432
+ "num_input_tokens_seen": 17564288,
3433
+ "step": 428
3434
+ },
3435
+ {
3436
+ "epoch": 7.807339449541285,
3437
+ "grad_norm": 0.47053155303001404,
3438
+ "learning_rate": 3.293261641012731e-05,
3439
+ "loss": 0.0987,
3440
+ "num_input_tokens_seen": 17604304,
3441
+ "step": 429
3442
+ },
3443
+ {
3444
+ "epoch": 7.825688073394495,
3445
+ "grad_norm": 0.6638731956481934,
3446
+ "learning_rate": 3.2863618903790346e-05,
3447
+ "loss": 0.1743,
3448
+ "num_input_tokens_seen": 17641384,
3449
+ "step": 430
3450
+ },
3451
+ {
3452
+ "epoch": 7.844036697247707,
3453
+ "grad_norm": 0.4213615357875824,
3454
+ "learning_rate": 3.279455485874195e-05,
3455
+ "loss": 0.0854,
3456
+ "num_input_tokens_seen": 17680560,
3457
+ "step": 431
3458
+ },
3459
+ {
3460
+ "epoch": 7.862385321100917,
3461
+ "grad_norm": 0.47264209389686584,
3462
+ "learning_rate": 3.272542485937369e-05,
3463
+ "loss": 0.0949,
3464
+ "num_input_tokens_seen": 17715312,
3465
+ "step": 432
3466
+ }
3467
+ ],
3468
+ "logging_steps": 1.0,
3469
+ "max_steps": 1080,
3470
+ "num_input_tokens_seen": 17715312,
3471
+ "num_train_epochs": 20,
3472
+ "save_steps": 54,
3473
+ "stateful_callbacks": {
3474
+ "TrainerControl": {
3475
+ "args": {
3476
+ "should_epoch_stop": false,
3477
+ "should_evaluate": false,
3478
+ "should_log": false,
3479
+ "should_save": true,
3480
+ "should_training_stop": false
3481
+ },
3482
+ "attributes": {}
3483
+ }
3484
+ },
3485
+ "total_flos": 1.4944933548665078e+18,
3486
+ "train_batch_size": 1,
3487
+ "trial_name": null,
3488
+ "trial_params": null
3489
+ }
checkpoint-432/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-486/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-Coder-14B-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-486/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-14B-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": 0.05,
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
+ "q_proj",
24
+ "v_proj",
25
+ "up_proj",
26
+ "gate_proj",
27
+ "o_proj",
28
+ "k_proj",
29
+ "down_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-486/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-486/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-486/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-486/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": 15000,
204
+ "pad_token": "<|endoftext|>",
205
+ "padding_side": "right",
206
+ "split_special_tokens": false,
207
+ "tokenizer_class": "Qwen2Tokenizer",
208
+ "unk_token": null
209
+ }
checkpoint-486/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-486/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-540/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-Coder-14B-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-540/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-14B-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": 0.05,
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
+ "q_proj",
24
+ "v_proj",
25
+ "up_proj",
26
+ "gate_proj",
27
+ "o_proj",
28
+ "k_proj",
29
+ "down_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-540/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-540/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-540/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-540/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": 15000,
204
+ "pad_token": "<|endoftext|>",
205
+ "padding_side": "right",
206
+ "split_special_tokens": false,
207
+ "tokenizer_class": "Qwen2Tokenizer",
208
+ "unk_token": null
209
+ }
checkpoint-540/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-540/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-594/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-Coder-14B-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-594/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-14B-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": 0.05,
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
+ "q_proj",
24
+ "v_proj",
25
+ "up_proj",
26
+ "gate_proj",
27
+ "o_proj",
28
+ "k_proj",
29
+ "down_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-594/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-594/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-594/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-594/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": 15000,
204
+ "pad_token": "<|endoftext|>",
205
+ "padding_side": "right",
206
+ "split_special_tokens": false,
207
+ "tokenizer_class": "Qwen2Tokenizer",
208
+ "unk_token": null
209
+ }
checkpoint-594/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff