Hugging Face's logo

finalform
/
foamqwen

Text Generation
PEFT
TensorBoard
Safetensors
Transformers
lora
sft
trl
conversational
Model card Files
xet
Metrics Community
finalform commited on
Commit
25fd194
·
verified ·
1 Parent(s): 0cfbf96

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +8 -0
  2. README.md +62 -0
  3. adapter_config.json +42 -0
  4. adapter_model.safetensors +3 -0
  5. added_tokens.json +24 -0
  6. chat_template.jinja +54 -0
  7. checkpoint-1245/README.md +209 -0
  8. checkpoint-1245/adapter_config.json +42 -0
  9. checkpoint-1245/adapter_model.safetensors +3 -0
  10. checkpoint-1245/added_tokens.json +24 -0
  11. checkpoint-1245/chat_template.jinja +54 -0
  12. checkpoint-1245/merges.txt +0 -0
  13. checkpoint-1245/optimizer.pt +3 -0
  14. checkpoint-1245/rng_state.pth +3 -0
  15. checkpoint-1245/scheduler.pt +3 -0
  16. checkpoint-1245/special_tokens_map.json +25 -0
  17. checkpoint-1245/tokenizer.json +3 -0
  18. checkpoint-1245/tokenizer_config.json +207 -0
  19. checkpoint-1245/trainer_state.json +505 -0
  20. checkpoint-1245/training_args.bin +3 -0
  21. checkpoint-1245/vocab.json +0 -0
  22. checkpoint-1660/README.md +209 -0
  23. checkpoint-1660/adapter_config.json +42 -0
  24. checkpoint-1660/adapter_model.safetensors +3 -0
  25. checkpoint-1660/added_tokens.json +24 -0
  26. checkpoint-1660/chat_template.jinja +54 -0
  27. checkpoint-1660/merges.txt +0 -0
  28. checkpoint-1660/optimizer.pt +3 -0
  29. checkpoint-1660/rng_state.pth +3 -0
  30. checkpoint-1660/scheduler.pt +3 -0
  31. checkpoint-1660/special_tokens_map.json +25 -0
  32. checkpoint-1660/tokenizer.json +3 -0
  33. checkpoint-1660/tokenizer_config.json +207 -0
  34. checkpoint-1660/trainer_state.json +668 -0
  35. checkpoint-1660/training_args.bin +3 -0
  36. checkpoint-1660/vocab.json +0 -0
  37. checkpoint-2075/README.md +209 -0
  38. checkpoint-2075/adapter_config.json +42 -0
  39. checkpoint-2075/adapter_model.safetensors +3 -0
  40. checkpoint-2075/added_tokens.json +24 -0
  41. checkpoint-2075/chat_template.jinja +54 -0
  42. checkpoint-2075/merges.txt +0 -0
  43. checkpoint-2075/optimizer.pt +3 -0
  44. checkpoint-2075/rng_state.pth +3 -0
  45. checkpoint-2075/scheduler.pt +3 -0
  46. checkpoint-2075/special_tokens_map.json +25 -0
  47. checkpoint-2075/tokenizer.json +3 -0
  48. checkpoint-2075/tokenizer_config.json +207 -0
  49. checkpoint-2075/trainer_state.json +831 -0
  50. checkpoint-2075/training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,11 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-1245/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-1660/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ checkpoint-2075/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ checkpoint-2490/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
+ checkpoint-2905/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
+ checkpoint-415/tokenizer.json filter=lfs diff=lfs merge=lfs -text
42
+ checkpoint-830/tokenizer.json filter=lfs diff=lfs merge=lfs -text
43
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-7B-Instruct
3
+ library_name: peft
4
+ model_name: foamqwen
5
+ tags:
6
+ - base_model:adapter:Qwen/Qwen2.5-7B-Instruct
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ licence: license
12
+ pipeline_tag: text-generation
13
+ ---
14
+
15
+ # Model Card for foamqwen
16
+
17
+ This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct).
18
+ It has been trained using [TRL](https://github.com/huggingface/trl).
19
+
20
+ ## Quick start
21
+
22
+ ```python
23
+ from transformers import pipeline
24
+
25
+ question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
26
+ generator = pipeline("text-generation", model="None", device="cuda")
27
+ output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
28
+ print(output["generated_text"])
29
+ ```
30
+
31
+ ## Training procedure
32
+
33
+
34
+
35
+
36
+ This model was trained with SFT.
37
+
38
+ ### Framework versions
39
+
40
+ - PEFT 0.17.0
41
+ - TRL: 0.19.0
42
+ - Transformers: 4.52.3
43
+ - Pytorch: 2.7.1
44
+ - Datasets: 3.5.0
45
+ - Tokenizers: 0.21.1
46
+
47
+ ## Citations
48
+
49
+
50
+
51
+ Cite TRL as:
52
+
53
+ ```bibtex
54
+ @misc{vonwerra2022trl,
55
+ title = {{TRL: Transformer Reinforcement Learning}},
56
+ author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
57
+ year = 2020,
58
+ journal = {GitHub repository},
59
+ publisher = {GitHub},
60
+ howpublished = {\url{https://github.com/huggingface/trl}}
61
+ }
62
+ ```
adapter_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.1,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "qalora_group_size": 16,
24
+ "r": 32,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "o_proj",
29
+ "v_proj",
30
+ "up_proj",
31
+ "down_proj",
32
+ "gate_proj",
33
+ "q_proj",
34
+ "k_proj"
35
+ ],
36
+ "target_parameters": null,
37
+ "task_type": "CAUSAL_LM",
38
+ "trainable_token_indices": null,
39
+ "use_dora": false,
40
+ "use_qalora": false,
41
+ "use_rslora": false
42
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:727129a86604c24892779cc3f27c843650c7807b66178181932adfd2bfe29747
3
+ size 323014168
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
+ }
chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\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>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\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" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
checkpoint-1245/README.md ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-7B-Instruct
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:Qwen/Qwen2.5-7B-Instruct
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ ---
12
+
13
+ # Model Card for Model ID
14
+
15
+ <!-- Provide a quick summary of what the model is/does. -->
16
+
17
+
18
+
19
+ ## Model Details
20
+
21
+ ### Model Description
22
+
23
+ <!-- Provide a longer summary of what this model is. -->
24
+
25
+
26
+
27
+ - **Developed by:** [More Information Needed]
28
+ - **Funded by [optional]:** [More Information Needed]
29
+ - **Shared by [optional]:** [More Information Needed]
30
+ - **Model type:** [More Information Needed]
31
+ - **Language(s) (NLP):** [More Information Needed]
32
+ - **License:** [More Information Needed]
33
+ - **Finetuned from model [optional]:** [More Information Needed]
34
+
35
+ ### Model Sources [optional]
36
+
37
+ <!-- Provide the basic links for the model. -->
38
+
39
+ - **Repository:** [More Information Needed]
40
+ - **Paper [optional]:** [More Information Needed]
41
+ - **Demo [optional]:** [More Information Needed]
42
+
43
+ ## Uses
44
+
45
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
46
+
47
+ ### Direct Use
48
+
49
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
50
+
51
+ [More Information Needed]
52
+
53
+ ### Downstream Use [optional]
54
+
55
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
56
+
57
+ [More Information Needed]
58
+
59
+ ### Out-of-Scope Use
60
+
61
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
62
+
63
+ [More Information Needed]
64
+
65
+ ## Bias, Risks, and Limitations
66
+
67
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
68
+
69
+ [More Information Needed]
70
+
71
+ ### Recommendations
72
+
73
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
74
+
75
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
76
+
77
+ ## How to Get Started with the Model
78
+
79
+ Use the code below to get started with the model.
80
+
81
+ [More Information Needed]
82
+
83
+ ## Training Details
84
+
85
+ ### Training Data
86
+
87
+ <!-- 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. -->
88
+
89
+ [More Information Needed]
90
+
91
+ ### Training Procedure
92
+
93
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
94
+
95
+ #### Preprocessing [optional]
96
+
97
+ [More Information Needed]
98
+
99
+
100
+ #### Training Hyperparameters
101
+
102
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
103
+
104
+ #### Speeds, Sizes, Times [optional]
105
+
106
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
107
+
108
+ [More Information Needed]
109
+
110
+ ## Evaluation
111
+
112
+ <!-- This section describes the evaluation protocols and provides the results. -->
113
+
114
+ ### Testing Data, Factors & Metrics
115
+
116
+ #### Testing Data
117
+
118
+ <!-- This should link to a Dataset Card if possible. -->
119
+
120
+ [More Information Needed]
121
+
122
+ #### Factors
123
+
124
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
125
+
126
+ [More Information Needed]
127
+
128
+ #### Metrics
129
+
130
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
131
+
132
+ [More Information Needed]
133
+
134
+ ### Results
135
+
136
+ [More Information Needed]
137
+
138
+ #### Summary
139
+
140
+
141
+
142
+ ## Model Examination [optional]
143
+
144
+ <!-- Relevant interpretability work for the model goes here -->
145
+
146
+ [More Information Needed]
147
+
148
+ ## Environmental Impact
149
+
150
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
151
+
152
+ 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).
153
+
154
+ - **Hardware Type:** [More Information Needed]
155
+ - **Hours used:** [More Information Needed]
156
+ - **Cloud Provider:** [More Information Needed]
157
+ - **Compute Region:** [More Information Needed]
158
+ - **Carbon Emitted:** [More Information Needed]
159
+
160
+ ## Technical Specifications [optional]
161
+
162
+ ### Model Architecture and Objective
163
+
164
+ [More Information Needed]
165
+
166
+ ### Compute Infrastructure
167
+
168
+ [More Information Needed]
169
+
170
+ #### Hardware
171
+
172
+ [More Information Needed]
173
+
174
+ #### Software
175
+
176
+ [More Information Needed]
177
+
178
+ ## Citation [optional]
179
+
180
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
181
+
182
+ **BibTeX:**
183
+
184
+ [More Information Needed]
185
+
186
+ **APA:**
187
+
188
+ [More Information Needed]
189
+
190
+ ## Glossary [optional]
191
+
192
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
193
+
194
+ [More Information Needed]
195
+
196
+ ## More Information [optional]
197
+
198
+ [More Information Needed]
199
+
200
+ ## Model Card Authors [optional]
201
+
202
+ [More Information Needed]
203
+
204
+ ## Model Card Contact
205
+
206
+ [More Information Needed]
207
+ ### Framework versions
208
+
209
+ - PEFT 0.17.0
checkpoint-1245/adapter_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.1,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "qalora_group_size": 16,
24
+ "r": 32,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "o_proj",
29
+ "v_proj",
30
+ "up_proj",
31
+ "down_proj",
32
+ "gate_proj",
33
+ "q_proj",
34
+ "k_proj"
35
+ ],
36
+ "target_parameters": null,
37
+ "task_type": "CAUSAL_LM",
38
+ "trainable_token_indices": null,
39
+ "use_dora": false,
40
+ "use_qalora": false,
41
+ "use_rslora": false
42
+ }
checkpoint-1245/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5328588a681c0859fc2c43eb1e4aac729393fa2d4e6db1a5f602207f83a7910
3
+ size 323014168
checkpoint-1245/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-1245/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\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>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\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" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
checkpoint-1245/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1245/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6af85be715aba61d98a0a2401cf6b94153d60a2a5cca37a31a285b1c48fcd11b
3
+ size 646164683
checkpoint-1245/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb72db5e472cf6e8b37ee2de9a7176ce9fff88ff5ec75957762dee0076f6e3d2
3
+ size 14645
checkpoint-1245/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0507b5178a097f1a47eb13bf2dc725ccef8bd541a0c05887db5c53c97f9a004
3
+ size 1465
checkpoint-1245/special_tokens_map.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|im_end|>"
25
+ }
checkpoint-1245/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3f9d93e80cff961819dcba7d892cf9656e086a0cf83cdbef23f10c1a493faa2
3
+ size 11422061
checkpoint-1245/tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|im_end|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
checkpoint-1245/trainer_state.json ADDED
@@ -0,0 +1,505 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1245,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.060350030175015085,
14
+ "grad_norm": 0.31135597825050354,
15
+ "learning_rate": 8.18181818181818e-05,
16
+ "loss": 1.9235,
17
+ "mean_token_accuracy": 0.6165974247455597,
18
+ "num_tokens": 157030.0,
19
+ "step": 25
20
+ },
21
+ {
22
+ "epoch": 0.12070006035003017,
23
+ "grad_norm": 0.32249024510383606,
24
+ "learning_rate": 0.00016704545454545452,
25
+ "loss": 1.0538,
26
+ "mean_token_accuracy": 0.7450298243761062,
27
+ "num_tokens": 284204.0,
28
+ "step": 50
29
+ },
30
+ {
31
+ "epoch": 0.18105009052504525,
32
+ "grad_norm": 0.3015844523906708,
33
+ "learning_rate": 0.0002522727272727273,
34
+ "loss": 0.6726,
35
+ "mean_token_accuracy": 0.8188469475507736,
36
+ "num_tokens": 441659.0,
37
+ "step": 75
38
+ },
39
+ {
40
+ "epoch": 0.24140012070006034,
41
+ "grad_norm": 0.5104885697364807,
42
+ "learning_rate": 0.0002999887132933212,
43
+ "loss": 0.5348,
44
+ "mean_token_accuracy": 0.8504667854309083,
45
+ "num_tokens": 567533.0,
46
+ "step": 100
47
+ },
48
+ {
49
+ "epoch": 0.30175015087507545,
50
+ "grad_norm": 0.278422474861145,
51
+ "learning_rate": 0.0002998791256978121,
52
+ "loss": 0.4144,
53
+ "mean_token_accuracy": 0.8816475421190262,
54
+ "num_tokens": 725296.0,
55
+ "step": 125
56
+ },
57
+ {
58
+ "epoch": 0.3621001810500905,
59
+ "grad_norm": 0.35799795389175415,
60
+ "learning_rate": 0.0002996530399366737,
61
+ "loss": 0.3693,
62
+ "mean_token_accuracy": 0.8962992638349533,
63
+ "num_tokens": 851708.0,
64
+ "step": 150
65
+ },
66
+ {
67
+ "epoch": 0.4224502112251056,
68
+ "grad_norm": 0.2955951690673828,
69
+ "learning_rate": 0.00029931063174202567,
70
+ "loss": 0.2746,
71
+ "mean_token_accuracy": 0.921732594370842,
72
+ "num_tokens": 1008739.0,
73
+ "step": 175
74
+ },
75
+ {
76
+ "epoch": 0.4828002414001207,
77
+ "grad_norm": 0.3763117790222168,
78
+ "learning_rate": 0.00029885216726118104,
79
+ "loss": 0.2386,
80
+ "mean_token_accuracy": 0.9305408012866974,
81
+ "num_tokens": 1134832.0,
82
+ "step": 200
83
+ },
84
+ {
85
+ "epoch": 0.5431502715751357,
86
+ "grad_norm": 0.3240911066532135,
87
+ "learning_rate": 0.00029827800284977474,
88
+ "loss": 0.1885,
89
+ "mean_token_accuracy": 0.9465595126152039,
90
+ "num_tokens": 1293095.0,
91
+ "step": 225
92
+ },
93
+ {
94
+ "epoch": 0.6035003017501509,
95
+ "grad_norm": 0.3682485520839691,
96
+ "learning_rate": 0.00029758858479477575,
97
+ "loss": 0.1832,
98
+ "mean_token_accuracy": 0.9486982274055481,
99
+ "num_tokens": 1419060.0,
100
+ "step": 250
101
+ },
102
+ {
103
+ "epoch": 0.663850331925166,
104
+ "grad_norm": 0.29996615648269653,
105
+ "learning_rate": 0.0002967844489675963,
106
+ "loss": 0.1501,
107
+ "mean_token_accuracy": 0.9576406496763229,
108
+ "num_tokens": 1577978.0,
109
+ "step": 275
110
+ },
111
+ {
112
+ "epoch": 0.724200362100181,
113
+ "grad_norm": 0.3568132221698761,
114
+ "learning_rate": 0.00029586622040756957,
115
+ "loss": 0.1246,
116
+ "mean_token_accuracy": 0.964940841794014,
117
+ "num_tokens": 1705052.0,
118
+ "step": 300
119
+ },
120
+ {
121
+ "epoch": 0.7845503922751962,
122
+ "grad_norm": 0.258465439081192,
123
+ "learning_rate": 0.0002948346128361186,
124
+ "loss": 0.1089,
125
+ "mean_token_accuracy": 0.970317553281784,
126
+ "num_tokens": 1861669.0,
127
+ "step": 325
128
+ },
129
+ {
130
+ "epoch": 0.8449004224502112,
131
+ "grad_norm": 0.3066297173500061,
132
+ "learning_rate": 0.00029369042810199416,
133
+ "loss": 0.1072,
134
+ "mean_token_accuracy": 0.9702006059885026,
135
+ "num_tokens": 1988735.0,
136
+ "step": 350
137
+ },
138
+ {
139
+ "epoch": 0.9052504526252263,
140
+ "grad_norm": 0.22371642291545868,
141
+ "learning_rate": 0.0002924345555580135,
142
+ "loss": 0.1117,
143
+ "mean_token_accuracy": 0.9696371680498124,
144
+ "num_tokens": 2146989.0,
145
+ "step": 375
146
+ },
147
+ {
148
+ "epoch": 0.9656004828002414,
149
+ "grad_norm": 0.4630758762359619,
150
+ "learning_rate": 0.000291067971369783,
151
+ "loss": 0.0863,
152
+ "mean_token_accuracy": 0.9765483093261719,
153
+ "num_tokens": 2274615.0,
154
+ "step": 400
155
+ },
156
+ {
157
+ "epoch": 1.0,
158
+ "eval_loss": 0.09050165861845016,
159
+ "eval_mean_token_accuracy": 0.9750120665576006,
160
+ "eval_num_tokens": 2354180.0,
161
+ "eval_runtime": 61.8103,
162
+ "eval_samples_per_second": 5.97,
163
+ "eval_steps_per_second": 2.993,
164
+ "step": 415
165
+ },
166
+ {
167
+ "epoch": 1.024140012070006,
168
+ "grad_norm": 0.17408408224582672,
169
+ "learning_rate": 0.0002895917377569438,
170
+ "loss": 0.1029,
171
+ "mean_token_accuracy": 0.9737048333453149,
172
+ "num_tokens": 2423619.0,
173
+ "step": 425
174
+ },
175
+ {
176
+ "epoch": 1.0844900422450212,
177
+ "grad_norm": 0.20633958280086517,
178
+ "learning_rate": 0.00028800700216752875,
179
+ "loss": 0.0578,
180
+ "mean_token_accuracy": 0.9834175568819046,
181
+ "num_tokens": 2566868.0,
182
+ "step": 450
183
+ },
184
+ {
185
+ "epoch": 1.1448400724200363,
186
+ "grad_norm": 0.1839175969362259,
187
+ "learning_rate": 0.00028631499638607285,
188
+ "loss": 0.0801,
189
+ "mean_token_accuracy": 0.9778328466415406,
190
+ "num_tokens": 2709054.0,
191
+ "step": 475
192
+ },
193
+ {
194
+ "epoch": 1.2051901025950513,
195
+ "grad_norm": 0.25615933537483215,
196
+ "learning_rate": 0.0002845170355761712,
197
+ "loss": 0.0614,
198
+ "mean_token_accuracy": 0.9824786186218262,
199
+ "num_tokens": 2851375.0,
200
+ "step": 500
201
+ },
202
+ {
203
+ "epoch": 1.2655401327700664,
204
+ "grad_norm": 0.16976642608642578,
205
+ "learning_rate": 0.0002826145172582274,
206
+ "loss": 0.0701,
207
+ "mean_token_accuracy": 0.9807569885253906,
208
+ "num_tokens": 2993397.0,
209
+ "step": 525
210
+ },
211
+ {
212
+ "epoch": 1.3258901629450814,
213
+ "grad_norm": 0.15633493661880493,
214
+ "learning_rate": 0.00028060892022318764,
215
+ "loss": 0.0555,
216
+ "mean_token_accuracy": 0.9843500143289566,
217
+ "num_tokens": 3136497.0,
218
+ "step": 550
219
+ },
220
+ {
221
+ "epoch": 1.3862401931200965,
222
+ "grad_norm": 0.16217610239982605,
223
+ "learning_rate": 0.0002785018033831051,
224
+ "loss": 0.0652,
225
+ "mean_token_accuracy": 0.982210916876793,
226
+ "num_tokens": 3277611.0,
227
+ "step": 575
228
+ },
229
+ {
230
+ "epoch": 1.4465902232951118,
231
+ "grad_norm": 0.10138845443725586,
232
+ "learning_rate": 0.0002762948045594276,
233
+ "loss": 0.0523,
234
+ "mean_token_accuracy": 0.985246667265892,
235
+ "num_tokens": 3420182.0,
236
+ "step": 600
237
+ },
238
+ {
239
+ "epoch": 1.5069402534701268,
240
+ "grad_norm": 0.12522730231285095,
241
+ "learning_rate": 0.0002739896392099502,
242
+ "loss": 0.063,
243
+ "mean_token_accuracy": 0.9825242179632186,
244
+ "num_tokens": 3561580.0,
245
+ "step": 625
246
+ },
247
+ {
248
+ "epoch": 1.567290283645142,
249
+ "grad_norm": 0.16772225499153137,
250
+ "learning_rate": 0.00027158809909542307,
251
+ "loss": 0.0458,
252
+ "mean_token_accuracy": 0.9863684195280075,
253
+ "num_tokens": 3703648.0,
254
+ "step": 650
255
+ },
256
+ {
257
+ "epoch": 1.627640313820157,
258
+ "grad_norm": 0.11150436848402023,
259
+ "learning_rate": 0.00026909205088685,
260
+ "loss": 0.0701,
261
+ "mean_token_accuracy": 0.9805551666021347,
262
+ "num_tokens": 3846275.0,
263
+ "step": 675
264
+ },
265
+ {
266
+ "epoch": 1.687990343995172,
267
+ "grad_norm": 0.13114990293979645,
268
+ "learning_rate": 0.0002665034347145612,
269
+ "loss": 0.047,
270
+ "mean_token_accuracy": 0.9866662234067917,
271
+ "num_tokens": 3990181.0,
272
+ "step": 700
273
+ },
274
+ {
275
+ "epoch": 1.748340374170187,
276
+ "grad_norm": 0.1373077780008316,
277
+ "learning_rate": 0.000263824262660187,
278
+ "loss": 0.0658,
279
+ "mean_token_accuracy": 0.9822418791055679,
280
+ "num_tokens": 4132061.0,
281
+ "step": 725
282
+ },
283
+ {
284
+ "epoch": 1.8086904043452021,
285
+ "grad_norm": 0.1755433827638626,
286
+ "learning_rate": 0.0002610566171927056,
287
+ "loss": 0.0393,
288
+ "mean_token_accuracy": 0.9886017143726349,
289
+ "num_tokens": 4273899.0,
290
+ "step": 750
291
+ },
292
+ {
293
+ "epoch": 1.8690404345202172,
294
+ "grad_norm": 0.12637771666049957,
295
+ "learning_rate": 0.00025820264954977976,
296
+ "loss": 0.0632,
297
+ "mean_token_accuracy": 0.9825896525382996,
298
+ "num_tokens": 4414846.0,
299
+ "step": 775
300
+ },
301
+ {
302
+ "epoch": 1.9293904646952322,
303
+ "grad_norm": 0.0651940405368805,
304
+ "learning_rate": 0.00025526457806564136,
305
+ "loss": 0.0419,
306
+ "mean_token_accuracy": 0.9879031604528428,
307
+ "num_tokens": 4557169.0,
308
+ "step": 800
309
+ },
310
+ {
311
+ "epoch": 1.9897404948702473,
312
+ "grad_norm": 0.12048754841089249,
313
+ "learning_rate": 0.00025224468644682245,
314
+ "loss": 0.0498,
315
+ "mean_token_accuracy": 0.9858449596166611,
316
+ "num_tokens": 4688618.0,
317
+ "step": 825
318
+ },
319
+ {
320
+ "epoch": 2.0,
321
+ "eval_loss": 0.054688576608896255,
322
+ "eval_mean_token_accuracy": 0.9851620287508578,
323
+ "eval_num_tokens": 4708360.0,
324
+ "eval_runtime": 61.7668,
325
+ "eval_samples_per_second": 5.974,
326
+ "eval_steps_per_second": 2.995,
327
+ "step": 830
328
+ },
329
+ {
330
+ "epoch": 2.048280024140012,
331
+ "grad_norm": 0.10747923702001572,
332
+ "learning_rate": 0.00024914532199707444,
333
+ "loss": 0.0491,
334
+ "mean_token_accuracy": 0.9856173869260808,
335
+ "num_tokens": 4837968.0,
336
+ "step": 850
337
+ },
338
+ {
339
+ "epoch": 2.1086300543150274,
340
+ "grad_norm": 0.13443028926849365,
341
+ "learning_rate": 0.00024596889379285353,
342
+ "loss": 0.0316,
343
+ "mean_token_accuracy": 0.9905168610811234,
344
+ "num_tokens": 4971141.0,
345
+ "step": 875
346
+ },
347
+ {
348
+ "epoch": 2.1689800844900424,
349
+ "grad_norm": 0.1226191446185112,
350
+ "learning_rate": 0.00024271787081079228,
351
+ "loss": 0.0527,
352
+ "mean_token_accuracy": 0.9845808875560761,
353
+ "num_tokens": 5124003.0,
354
+ "step": 900
355
+ },
356
+ {
357
+ "epoch": 2.2293301146650575,
358
+ "grad_norm": 0.13954219222068787,
359
+ "learning_rate": 0.00023939478000861117,
360
+ "loss": 0.03,
361
+ "mean_token_accuracy": 0.991157540678978,
362
+ "num_tokens": 5256623.0,
363
+ "step": 925
364
+ },
365
+ {
366
+ "epoch": 2.2896801448400725,
367
+ "grad_norm": 0.07871092110872269,
368
+ "learning_rate": 0.00023600220436096318,
369
+ "loss": 0.0401,
370
+ "mean_token_accuracy": 0.9883328771591187,
371
+ "num_tokens": 5405783.0,
372
+ "step": 950
373
+ },
374
+ {
375
+ "epoch": 2.3500301750150876,
376
+ "grad_norm": 0.07625500857830048,
377
+ "learning_rate": 0.00023254278085173684,
378
+ "loss": 0.0329,
379
+ "mean_token_accuracy": 0.9900754565000534,
380
+ "num_tokens": 5538983.0,
381
+ "step": 975
382
+ },
383
+ {
384
+ "epoch": 2.4103802051901027,
385
+ "grad_norm": 0.08441416919231415,
386
+ "learning_rate": 0.00022901919842437972,
387
+ "loss": 0.045,
388
+ "mean_token_accuracy": 0.9868701863288879,
389
+ "num_tokens": 5689941.0,
390
+ "step": 1000
391
+ },
392
+ {
393
+ "epoch": 2.4707302353651177,
394
+ "grad_norm": 0.10544892400503159,
395
+ "learning_rate": 0.00022543419589183397,
396
+ "loss": 0.0282,
397
+ "mean_token_accuracy": 0.991428604722023,
398
+ "num_tokens": 5823463.0,
399
+ "step": 1025
400
+ },
401
+ {
402
+ "epoch": 2.5310802655401328,
403
+ "grad_norm": 0.08695073425769806,
404
+ "learning_rate": 0.00022179055980770993,
405
+ "loss": 0.0461,
406
+ "mean_token_accuracy": 0.9864470016956329,
407
+ "num_tokens": 5974358.0,
408
+ "step": 1050
409
+ },
410
+ {
411
+ "epoch": 2.591430295715148,
412
+ "grad_norm": 0.09350312501192093,
413
+ "learning_rate": 0.0002180911223003513,
414
+ "loss": 0.0327,
415
+ "mean_token_accuracy": 0.990239828824997,
416
+ "num_tokens": 6106913.0,
417
+ "step": 1075
418
+ },
419
+ {
420
+ "epoch": 2.651780325890163,
421
+ "grad_norm": 0.06971506774425507,
422
+ "learning_rate": 0.00021433875887147627,
423
+ "loss": 0.0496,
424
+ "mean_token_accuracy": 0.9856115758419037,
425
+ "num_tokens": 6260849.0,
426
+ "step": 1100
427
+ },
428
+ {
429
+ "epoch": 2.712130356065178,
430
+ "grad_norm": 0.07409551739692688,
431
+ "learning_rate": 0.00021053638616110525,
432
+ "loss": 0.031,
433
+ "mean_token_accuracy": 0.9906682467460632,
434
+ "num_tokens": 6393788.0,
435
+ "step": 1125
436
+ },
437
+ {
438
+ "epoch": 2.772480386240193,
439
+ "grad_norm": 0.08459241688251495,
440
+ "learning_rate": 0.00020668695968051274,
441
+ "loss": 0.0417,
442
+ "mean_token_accuracy": 0.9878255265951157,
443
+ "num_tokens": 6545295.0,
444
+ "step": 1150
445
+ },
446
+ {
447
+ "epoch": 2.832830416415208,
448
+ "grad_norm": 0.06320163607597351,
449
+ "learning_rate": 0.00020279347151496482,
450
+ "loss": 0.0305,
451
+ "mean_token_accuracy": 0.9911946403980255,
452
+ "num_tokens": 6677075.0,
453
+ "step": 1175
454
+ },
455
+ {
456
+ "epoch": 2.8931804465902236,
457
+ "grad_norm": 0.08129168301820755,
458
+ "learning_rate": 0.00019885894799802922,
459
+ "loss": 0.0465,
460
+ "mean_token_accuracy": 0.9863498049974442,
461
+ "num_tokens": 6828145.0,
462
+ "step": 1200
463
+ },
464
+ {
465
+ "epoch": 2.9535304767652386,
466
+ "grad_norm": 0.054761067032814026,
467
+ "learning_rate": 0.00019488644735926396,
468
+ "loss": 0.0298,
469
+ "mean_token_accuracy": 0.9909803092479705,
470
+ "num_tokens": 6960911.0,
471
+ "step": 1225
472
+ },
473
+ {
474
+ "epoch": 3.0,
475
+ "eval_loss": 0.04527445137500763,
476
+ "eval_mean_token_accuracy": 0.9875696955500423,
477
+ "eval_num_tokens": 7062540.0,
478
+ "eval_runtime": 61.7191,
479
+ "eval_samples_per_second": 5.979,
480
+ "eval_steps_per_second": 2.997,
481
+ "step": 1245
482
+ }
483
+ ],
484
+ "logging_steps": 25,
485
+ "max_steps": 2905,
486
+ "num_input_tokens_seen": 0,
487
+ "num_train_epochs": 7,
488
+ "save_steps": 500,
489
+ "stateful_callbacks": {
490
+ "TrainerControl": {
491
+ "args": {
492
+ "should_epoch_stop": false,
493
+ "should_evaluate": false,
494
+ "should_log": false,
495
+ "should_save": true,
496
+ "should_training_stop": false
497
+ },
498
+ "attributes": {}
499
+ }
500
+ },
501
+ "total_flos": 3.03401775495297e+17,
502
+ "train_batch_size": 2,
503
+ "trial_name": null,
504
+ "trial_params": null
505
+ }
checkpoint-1245/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd12954384614c3a1cf14ace2441d4d0f84fee8508c198a9b8f1387a477c18df
3
+ size 6097
checkpoint-1245/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1660/README.md ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-7B-Instruct
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:Qwen/Qwen2.5-7B-Instruct
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ ---
12
+
13
+ # Model Card for Model ID
14
+
15
+ <!-- Provide a quick summary of what the model is/does. -->
16
+
17
+
18
+
19
+ ## Model Details
20
+
21
+ ### Model Description
22
+
23
+ <!-- Provide a longer summary of what this model is. -->
24
+
25
+
26
+
27
+ - **Developed by:** [More Information Needed]
28
+ - **Funded by [optional]:** [More Information Needed]
29
+ - **Shared by [optional]:** [More Information Needed]
30
+ - **Model type:** [More Information Needed]
31
+ - **Language(s) (NLP):** [More Information Needed]
32
+ - **License:** [More Information Needed]
33
+ - **Finetuned from model [optional]:** [More Information Needed]
34
+
35
+ ### Model Sources [optional]
36
+
37
+ <!-- Provide the basic links for the model. -->
38
+
39
+ - **Repository:** [More Information Needed]
40
+ - **Paper [optional]:** [More Information Needed]
41
+ - **Demo [optional]:** [More Information Needed]
42
+
43
+ ## Uses
44
+
45
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
46
+
47
+ ### Direct Use
48
+
49
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
50
+
51
+ [More Information Needed]
52
+
53
+ ### Downstream Use [optional]
54
+
55
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
56
+
57
+ [More Information Needed]
58
+
59
+ ### Out-of-Scope Use
60
+
61
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
62
+
63
+ [More Information Needed]
64
+
65
+ ## Bias, Risks, and Limitations
66
+
67
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
68
+
69
+ [More Information Needed]
70
+
71
+ ### Recommendations
72
+
73
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
74
+
75
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
76
+
77
+ ## How to Get Started with the Model
78
+
79
+ Use the code below to get started with the model.
80
+
81
+ [More Information Needed]
82
+
83
+ ## Training Details
84
+
85
+ ### Training Data
86
+
87
+ <!-- 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. -->
88
+
89
+ [More Information Needed]
90
+
91
+ ### Training Procedure
92
+
93
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
94
+
95
+ #### Preprocessing [optional]
96
+
97
+ [More Information Needed]
98
+
99
+
100
+ #### Training Hyperparameters
101
+
102
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
103
+
104
+ #### Speeds, Sizes, Times [optional]
105
+
106
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
107
+
108
+ [More Information Needed]
109
+
110
+ ## Evaluation
111
+
112
+ <!-- This section describes the evaluation protocols and provides the results. -->
113
+
114
+ ### Testing Data, Factors & Metrics
115
+
116
+ #### Testing Data
117
+
118
+ <!-- This should link to a Dataset Card if possible. -->
119
+
120
+ [More Information Needed]
121
+
122
+ #### Factors
123
+
124
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
125
+
126
+ [More Information Needed]
127
+
128
+ #### Metrics
129
+
130
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
131
+
132
+ [More Information Needed]
133
+
134
+ ### Results
135
+
136
+ [More Information Needed]
137
+
138
+ #### Summary
139
+
140
+
141
+
142
+ ## Model Examination [optional]
143
+
144
+ <!-- Relevant interpretability work for the model goes here -->
145
+
146
+ [More Information Needed]
147
+
148
+ ## Environmental Impact
149
+
150
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
151
+
152
+ 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).
153
+
154
+ - **Hardware Type:** [More Information Needed]
155
+ - **Hours used:** [More Information Needed]
156
+ - **Cloud Provider:** [More Information Needed]
157
+ - **Compute Region:** [More Information Needed]
158
+ - **Carbon Emitted:** [More Information Needed]
159
+
160
+ ## Technical Specifications [optional]
161
+
162
+ ### Model Architecture and Objective
163
+
164
+ [More Information Needed]
165
+
166
+ ### Compute Infrastructure
167
+
168
+ [More Information Needed]
169
+
170
+ #### Hardware
171
+
172
+ [More Information Needed]
173
+
174
+ #### Software
175
+
176
+ [More Information Needed]
177
+
178
+ ## Citation [optional]
179
+
180
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
181
+
182
+ **BibTeX:**
183
+
184
+ [More Information Needed]
185
+
186
+ **APA:**
187
+
188
+ [More Information Needed]
189
+
190
+ ## Glossary [optional]
191
+
192
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
193
+
194
+ [More Information Needed]
195
+
196
+ ## More Information [optional]
197
+
198
+ [More Information Needed]
199
+
200
+ ## Model Card Authors [optional]
201
+
202
+ [More Information Needed]
203
+
204
+ ## Model Card Contact
205
+
206
+ [More Information Needed]
207
+ ### Framework versions
208
+
209
+ - PEFT 0.17.0
checkpoint-1660/adapter_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.1,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "qalora_group_size": 16,
24
+ "r": 32,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "o_proj",
29
+ "v_proj",
30
+ "up_proj",
31
+ "down_proj",
32
+ "gate_proj",
33
+ "q_proj",
34
+ "k_proj"
35
+ ],
36
+ "target_parameters": null,
37
+ "task_type": "CAUSAL_LM",
38
+ "trainable_token_indices": null,
39
+ "use_dora": false,
40
+ "use_qalora": false,
41
+ "use_rslora": false
42
+ }
checkpoint-1660/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2045604f624af42405708ed57dc3d98484fe5ed7bbfde1e46cd7f15c5ce1f74
3
+ size 323014168
checkpoint-1660/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-1660/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\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>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\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" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
checkpoint-1660/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1660/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf2e210cdfe39bd1fb0afbab8236d4d9a696e0b2ac4e150c8e8cac021cf96225
3
+ size 646164683
checkpoint-1660/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bcd496779708e74b46e432e01d8de48ced678d9e4a0bb1e814a60ca6e71d60b
3
+ size 14645
checkpoint-1660/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:400af09f812b537d738744947529a57cd588f5dd92eadb329b9f329acf39c801
3
+ size 1465
checkpoint-1660/special_tokens_map.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|im_end|>"
25
+ }
checkpoint-1660/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3f9d93e80cff961819dcba7d892cf9656e086a0cf83cdbef23f10c1a493faa2
3
+ size 11422061
checkpoint-1660/tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|im_end|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
checkpoint-1660/trainer_state.json ADDED
@@ -0,0 +1,668 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 4.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1660,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.060350030175015085,
14
+ "grad_norm": 0.31135597825050354,
15
+ "learning_rate": 8.18181818181818e-05,
16
+ "loss": 1.9235,
17
+ "mean_token_accuracy": 0.6165974247455597,
18
+ "num_tokens": 157030.0,
19
+ "step": 25
20
+ },
21
+ {
22
+ "epoch": 0.12070006035003017,
23
+ "grad_norm": 0.32249024510383606,
24
+ "learning_rate": 0.00016704545454545452,
25
+ "loss": 1.0538,
26
+ "mean_token_accuracy": 0.7450298243761062,
27
+ "num_tokens": 284204.0,
28
+ "step": 50
29
+ },
30
+ {
31
+ "epoch": 0.18105009052504525,
32
+ "grad_norm": 0.3015844523906708,
33
+ "learning_rate": 0.0002522727272727273,
34
+ "loss": 0.6726,
35
+ "mean_token_accuracy": 0.8188469475507736,
36
+ "num_tokens": 441659.0,
37
+ "step": 75
38
+ },
39
+ {
40
+ "epoch": 0.24140012070006034,
41
+ "grad_norm": 0.5104885697364807,
42
+ "learning_rate": 0.0002999887132933212,
43
+ "loss": 0.5348,
44
+ "mean_token_accuracy": 0.8504667854309083,
45
+ "num_tokens": 567533.0,
46
+ "step": 100
47
+ },
48
+ {
49
+ "epoch": 0.30175015087507545,
50
+ "grad_norm": 0.278422474861145,
51
+ "learning_rate": 0.0002998791256978121,
52
+ "loss": 0.4144,
53
+ "mean_token_accuracy": 0.8816475421190262,
54
+ "num_tokens": 725296.0,
55
+ "step": 125
56
+ },
57
+ {
58
+ "epoch": 0.3621001810500905,
59
+ "grad_norm": 0.35799795389175415,
60
+ "learning_rate": 0.0002996530399366737,
61
+ "loss": 0.3693,
62
+ "mean_token_accuracy": 0.8962992638349533,
63
+ "num_tokens": 851708.0,
64
+ "step": 150
65
+ },
66
+ {
67
+ "epoch": 0.4224502112251056,
68
+ "grad_norm": 0.2955951690673828,
69
+ "learning_rate": 0.00029931063174202567,
70
+ "loss": 0.2746,
71
+ "mean_token_accuracy": 0.921732594370842,
72
+ "num_tokens": 1008739.0,
73
+ "step": 175
74
+ },
75
+ {
76
+ "epoch": 0.4828002414001207,
77
+ "grad_norm": 0.3763117790222168,
78
+ "learning_rate": 0.00029885216726118104,
79
+ "loss": 0.2386,
80
+ "mean_token_accuracy": 0.9305408012866974,
81
+ "num_tokens": 1134832.0,
82
+ "step": 200
83
+ },
84
+ {
85
+ "epoch": 0.5431502715751357,
86
+ "grad_norm": 0.3240911066532135,
87
+ "learning_rate": 0.00029827800284977474,
88
+ "loss": 0.1885,
89
+ "mean_token_accuracy": 0.9465595126152039,
90
+ "num_tokens": 1293095.0,
91
+ "step": 225
92
+ },
93
+ {
94
+ "epoch": 0.6035003017501509,
95
+ "grad_norm": 0.3682485520839691,
96
+ "learning_rate": 0.00029758858479477575,
97
+ "loss": 0.1832,
98
+ "mean_token_accuracy": 0.9486982274055481,
99
+ "num_tokens": 1419060.0,
100
+ "step": 250
101
+ },
102
+ {
103
+ "epoch": 0.663850331925166,
104
+ "grad_norm": 0.29996615648269653,
105
+ "learning_rate": 0.0002967844489675963,
106
+ "loss": 0.1501,
107
+ "mean_token_accuracy": 0.9576406496763229,
108
+ "num_tokens": 1577978.0,
109
+ "step": 275
110
+ },
111
+ {
112
+ "epoch": 0.724200362100181,
113
+ "grad_norm": 0.3568132221698761,
114
+ "learning_rate": 0.00029586622040756957,
115
+ "loss": 0.1246,
116
+ "mean_token_accuracy": 0.964940841794014,
117
+ "num_tokens": 1705052.0,
118
+ "step": 300
119
+ },
120
+ {
121
+ "epoch": 0.7845503922751962,
122
+ "grad_norm": 0.258465439081192,
123
+ "learning_rate": 0.0002948346128361186,
124
+ "loss": 0.1089,
125
+ "mean_token_accuracy": 0.970317553281784,
126
+ "num_tokens": 1861669.0,
127
+ "step": 325
128
+ },
129
+ {
130
+ "epoch": 0.8449004224502112,
131
+ "grad_norm": 0.3066297173500061,
132
+ "learning_rate": 0.00029369042810199416,
133
+ "loss": 0.1072,
134
+ "mean_token_accuracy": 0.9702006059885026,
135
+ "num_tokens": 1988735.0,
136
+ "step": 350
137
+ },
138
+ {
139
+ "epoch": 0.9052504526252263,
140
+ "grad_norm": 0.22371642291545868,
141
+ "learning_rate": 0.0002924345555580135,
142
+ "loss": 0.1117,
143
+ "mean_token_accuracy": 0.9696371680498124,
144
+ "num_tokens": 2146989.0,
145
+ "step": 375
146
+ },
147
+ {
148
+ "epoch": 0.9656004828002414,
149
+ "grad_norm": 0.4630758762359619,
150
+ "learning_rate": 0.000291067971369783,
151
+ "loss": 0.0863,
152
+ "mean_token_accuracy": 0.9765483093261719,
153
+ "num_tokens": 2274615.0,
154
+ "step": 400
155
+ },
156
+ {
157
+ "epoch": 1.0,
158
+ "eval_loss": 0.09050165861845016,
159
+ "eval_mean_token_accuracy": 0.9750120665576006,
160
+ "eval_num_tokens": 2354180.0,
161
+ "eval_runtime": 61.8103,
162
+ "eval_samples_per_second": 5.97,
163
+ "eval_steps_per_second": 2.993,
164
+ "step": 415
165
+ },
166
+ {
167
+ "epoch": 1.024140012070006,
168
+ "grad_norm": 0.17408408224582672,
169
+ "learning_rate": 0.0002895917377569438,
170
+ "loss": 0.1029,
171
+ "mean_token_accuracy": 0.9737048333453149,
172
+ "num_tokens": 2423619.0,
173
+ "step": 425
174
+ },
175
+ {
176
+ "epoch": 1.0844900422450212,
177
+ "grad_norm": 0.20633958280086517,
178
+ "learning_rate": 0.00028800700216752875,
179
+ "loss": 0.0578,
180
+ "mean_token_accuracy": 0.9834175568819046,
181
+ "num_tokens": 2566868.0,
182
+ "step": 450
183
+ },
184
+ {
185
+ "epoch": 1.1448400724200363,
186
+ "grad_norm": 0.1839175969362259,
187
+ "learning_rate": 0.00028631499638607285,
188
+ "loss": 0.0801,
189
+ "mean_token_accuracy": 0.9778328466415406,
190
+ "num_tokens": 2709054.0,
191
+ "step": 475
192
+ },
193
+ {
194
+ "epoch": 1.2051901025950513,
195
+ "grad_norm": 0.25615933537483215,
196
+ "learning_rate": 0.0002845170355761712,
197
+ "loss": 0.0614,
198
+ "mean_token_accuracy": 0.9824786186218262,
199
+ "num_tokens": 2851375.0,
200
+ "step": 500
201
+ },
202
+ {
203
+ "epoch": 1.2655401327700664,
204
+ "grad_norm": 0.16976642608642578,
205
+ "learning_rate": 0.0002826145172582274,
206
+ "loss": 0.0701,
207
+ "mean_token_accuracy": 0.9807569885253906,
208
+ "num_tokens": 2993397.0,
209
+ "step": 525
210
+ },
211
+ {
212
+ "epoch": 1.3258901629450814,
213
+ "grad_norm": 0.15633493661880493,
214
+ "learning_rate": 0.00028060892022318764,
215
+ "loss": 0.0555,
216
+ "mean_token_accuracy": 0.9843500143289566,
217
+ "num_tokens": 3136497.0,
218
+ "step": 550
219
+ },
220
+ {
221
+ "epoch": 1.3862401931200965,
222
+ "grad_norm": 0.16217610239982605,
223
+ "learning_rate": 0.0002785018033831051,
224
+ "loss": 0.0652,
225
+ "mean_token_accuracy": 0.982210916876793,
226
+ "num_tokens": 3277611.0,
227
+ "step": 575
228
+ },
229
+ {
230
+ "epoch": 1.4465902232951118,
231
+ "grad_norm": 0.10138845443725586,
232
+ "learning_rate": 0.0002762948045594276,
233
+ "loss": 0.0523,
234
+ "mean_token_accuracy": 0.985246667265892,
235
+ "num_tokens": 3420182.0,
236
+ "step": 600
237
+ },
238
+ {
239
+ "epoch": 1.5069402534701268,
240
+ "grad_norm": 0.12522730231285095,
241
+ "learning_rate": 0.0002739896392099502,
242
+ "loss": 0.063,
243
+ "mean_token_accuracy": 0.9825242179632186,
244
+ "num_tokens": 3561580.0,
245
+ "step": 625
246
+ },
247
+ {
248
+ "epoch": 1.567290283645142,
249
+ "grad_norm": 0.16772225499153137,
250
+ "learning_rate": 0.00027158809909542307,
251
+ "loss": 0.0458,
252
+ "mean_token_accuracy": 0.9863684195280075,
253
+ "num_tokens": 3703648.0,
254
+ "step": 650
255
+ },
256
+ {
257
+ "epoch": 1.627640313820157,
258
+ "grad_norm": 0.11150436848402023,
259
+ "learning_rate": 0.00026909205088685,
260
+ "loss": 0.0701,
261
+ "mean_token_accuracy": 0.9805551666021347,
262
+ "num_tokens": 3846275.0,
263
+ "step": 675
264
+ },
265
+ {
266
+ "epoch": 1.687990343995172,
267
+ "grad_norm": 0.13114990293979645,
268
+ "learning_rate": 0.0002665034347145612,
269
+ "loss": 0.047,
270
+ "mean_token_accuracy": 0.9866662234067917,
271
+ "num_tokens": 3990181.0,
272
+ "step": 700
273
+ },
274
+ {
275
+ "epoch": 1.748340374170187,
276
+ "grad_norm": 0.1373077780008316,
277
+ "learning_rate": 0.000263824262660187,
278
+ "loss": 0.0658,
279
+ "mean_token_accuracy": 0.9822418791055679,
280
+ "num_tokens": 4132061.0,
281
+ "step": 725
282
+ },
283
+ {
284
+ "epoch": 1.8086904043452021,
285
+ "grad_norm": 0.1755433827638626,
286
+ "learning_rate": 0.0002610566171927056,
287
+ "loss": 0.0393,
288
+ "mean_token_accuracy": 0.9886017143726349,
289
+ "num_tokens": 4273899.0,
290
+ "step": 750
291
+ },
292
+ {
293
+ "epoch": 1.8690404345202172,
294
+ "grad_norm": 0.12637771666049957,
295
+ "learning_rate": 0.00025820264954977976,
296
+ "loss": 0.0632,
297
+ "mean_token_accuracy": 0.9825896525382996,
298
+ "num_tokens": 4414846.0,
299
+ "step": 775
300
+ },
301
+ {
302
+ "epoch": 1.9293904646952322,
303
+ "grad_norm": 0.0651940405368805,
304
+ "learning_rate": 0.00025526457806564136,
305
+ "loss": 0.0419,
306
+ "mean_token_accuracy": 0.9879031604528428,
307
+ "num_tokens": 4557169.0,
308
+ "step": 800
309
+ },
310
+ {
311
+ "epoch": 1.9897404948702473,
312
+ "grad_norm": 0.12048754841089249,
313
+ "learning_rate": 0.00025224468644682245,
314
+ "loss": 0.0498,
315
+ "mean_token_accuracy": 0.9858449596166611,
316
+ "num_tokens": 4688618.0,
317
+ "step": 825
318
+ },
319
+ {
320
+ "epoch": 2.0,
321
+ "eval_loss": 0.054688576608896255,
322
+ "eval_mean_token_accuracy": 0.9851620287508578,
323
+ "eval_num_tokens": 4708360.0,
324
+ "eval_runtime": 61.7668,
325
+ "eval_samples_per_second": 5.974,
326
+ "eval_steps_per_second": 2.995,
327
+ "step": 830
328
+ },
329
+ {
330
+ "epoch": 2.048280024140012,
331
+ "grad_norm": 0.10747923702001572,
332
+ "learning_rate": 0.00024914532199707444,
333
+ "loss": 0.0491,
334
+ "mean_token_accuracy": 0.9856173869260808,
335
+ "num_tokens": 4837968.0,
336
+ "step": 850
337
+ },
338
+ {
339
+ "epoch": 2.1086300543150274,
340
+ "grad_norm": 0.13443028926849365,
341
+ "learning_rate": 0.00024596889379285353,
342
+ "loss": 0.0316,
343
+ "mean_token_accuracy": 0.9905168610811234,
344
+ "num_tokens": 4971141.0,
345
+ "step": 875
346
+ },
347
+ {
348
+ "epoch": 2.1689800844900424,
349
+ "grad_norm": 0.1226191446185112,
350
+ "learning_rate": 0.00024271787081079228,
351
+ "loss": 0.0527,
352
+ "mean_token_accuracy": 0.9845808875560761,
353
+ "num_tokens": 5124003.0,
354
+ "step": 900
355
+ },
356
+ {
357
+ "epoch": 2.2293301146650575,
358
+ "grad_norm": 0.13954219222068787,
359
+ "learning_rate": 0.00023939478000861117,
360
+ "loss": 0.03,
361
+ "mean_token_accuracy": 0.991157540678978,
362
+ "num_tokens": 5256623.0,
363
+ "step": 925
364
+ },
365
+ {
366
+ "epoch": 2.2896801448400725,
367
+ "grad_norm": 0.07871092110872269,
368
+ "learning_rate": 0.00023600220436096318,
369
+ "loss": 0.0401,
370
+ "mean_token_accuracy": 0.9883328771591187,
371
+ "num_tokens": 5405783.0,
372
+ "step": 950
373
+ },
374
+ {
375
+ "epoch": 2.3500301750150876,
376
+ "grad_norm": 0.07625500857830048,
377
+ "learning_rate": 0.00023254278085173684,
378
+ "loss": 0.0329,
379
+ "mean_token_accuracy": 0.9900754565000534,
380
+ "num_tokens": 5538983.0,
381
+ "step": 975
382
+ },
383
+ {
384
+ "epoch": 2.4103802051901027,
385
+ "grad_norm": 0.08441416919231415,
386
+ "learning_rate": 0.00022901919842437972,
387
+ "loss": 0.045,
388
+ "mean_token_accuracy": 0.9868701863288879,
389
+ "num_tokens": 5689941.0,
390
+ "step": 1000
391
+ },
392
+ {
393
+ "epoch": 2.4707302353651177,
394
+ "grad_norm": 0.10544892400503159,
395
+ "learning_rate": 0.00022543419589183397,
396
+ "loss": 0.0282,
397
+ "mean_token_accuracy": 0.991428604722023,
398
+ "num_tokens": 5823463.0,
399
+ "step": 1025
400
+ },
401
+ {
402
+ "epoch": 2.5310802655401328,
403
+ "grad_norm": 0.08695073425769806,
404
+ "learning_rate": 0.00022179055980770993,
405
+ "loss": 0.0461,
406
+ "mean_token_accuracy": 0.9864470016956329,
407
+ "num_tokens": 5974358.0,
408
+ "step": 1050
409
+ },
410
+ {
411
+ "epoch": 2.591430295715148,
412
+ "grad_norm": 0.09350312501192093,
413
+ "learning_rate": 0.0002180911223003513,
414
+ "loss": 0.0327,
415
+ "mean_token_accuracy": 0.990239828824997,
416
+ "num_tokens": 6106913.0,
417
+ "step": 1075
418
+ },
419
+ {
420
+ "epoch": 2.651780325890163,
421
+ "grad_norm": 0.06971506774425507,
422
+ "learning_rate": 0.00021433875887147627,
423
+ "loss": 0.0496,
424
+ "mean_token_accuracy": 0.9856115758419037,
425
+ "num_tokens": 6260849.0,
426
+ "step": 1100
427
+ },
428
+ {
429
+ "epoch": 2.712130356065178,
430
+ "grad_norm": 0.07409551739692688,
431
+ "learning_rate": 0.00021053638616110525,
432
+ "loss": 0.031,
433
+ "mean_token_accuracy": 0.9906682467460632,
434
+ "num_tokens": 6393788.0,
435
+ "step": 1125
436
+ },
437
+ {
438
+ "epoch": 2.772480386240193,
439
+ "grad_norm": 0.08459241688251495,
440
+ "learning_rate": 0.00020668695968051274,
441
+ "loss": 0.0417,
442
+ "mean_token_accuracy": 0.9878255265951157,
443
+ "num_tokens": 6545295.0,
444
+ "step": 1150
445
+ },
446
+ {
447
+ "epoch": 2.832830416415208,
448
+ "grad_norm": 0.06320163607597351,
449
+ "learning_rate": 0.00020279347151496482,
450
+ "loss": 0.0305,
451
+ "mean_token_accuracy": 0.9911946403980255,
452
+ "num_tokens": 6677075.0,
453
+ "step": 1175
454
+ },
455
+ {
456
+ "epoch": 2.8931804465902236,
457
+ "grad_norm": 0.08129168301820755,
458
+ "learning_rate": 0.00019885894799802922,
459
+ "loss": 0.0465,
460
+ "mean_token_accuracy": 0.9863498049974442,
461
+ "num_tokens": 6828145.0,
462
+ "step": 1200
463
+ },
464
+ {
465
+ "epoch": 2.9535304767652386,
466
+ "grad_norm": 0.054761067032814026,
467
+ "learning_rate": 0.00019488644735926396,
468
+ "loss": 0.0298,
469
+ "mean_token_accuracy": 0.9909803092479705,
470
+ "num_tokens": 6960911.0,
471
+ "step": 1225
472
+ },
473
+ {
474
+ "epoch": 3.0,
475
+ "eval_loss": 0.04527445137500763,
476
+ "eval_mean_token_accuracy": 0.9875696955500423,
477
+ "eval_num_tokens": 7062540.0,
478
+ "eval_runtime": 61.7191,
479
+ "eval_samples_per_second": 5.979,
480
+ "eval_steps_per_second": 2.997,
481
+ "step": 1245
482
+ },
483
+ {
484
+ "epoch": 3.012070006035003,
485
+ "grad_norm": 0.061567842960357666,
486
+ "learning_rate": 0.00019087905734711452,
487
+ "loss": 0.0384,
488
+ "mean_token_accuracy": 0.9884870881886826,
489
+ "num_tokens": 7098246.0,
490
+ "step": 1250
491
+ },
492
+ {
493
+ "epoch": 3.0724200362100182,
494
+ "grad_norm": 0.07762719690799713,
495
+ "learning_rate": 0.00018683989282886613,
496
+ "loss": 0.0252,
497
+ "mean_token_accuracy": 0.9920413041114807,
498
+ "num_tokens": 7246634.0,
499
+ "step": 1275
500
+ },
501
+ {
502
+ "epoch": 3.1327700663850333,
503
+ "grad_norm": 0.07748158276081085,
504
+ "learning_rate": 0.0001827720933695173,
505
+ "loss": 0.0313,
506
+ "mean_token_accuracy": 0.9904079920053482,
507
+ "num_tokens": 7381014.0,
508
+ "step": 1300
509
+ },
510
+ {
511
+ "epoch": 3.1931200965600484,
512
+ "grad_norm": 0.06404800713062286,
513
+ "learning_rate": 0.00017867882079145627,
514
+ "loss": 0.0276,
515
+ "mean_token_accuracy": 0.9916363900899887,
516
+ "num_tokens": 7528065.0,
517
+ "step": 1325
518
+ },
519
+ {
520
+ "epoch": 3.2534701267350634,
521
+ "grad_norm": 0.09366205334663391,
522
+ "learning_rate": 0.00017456325671683724,
523
+ "loss": 0.0288,
524
+ "mean_token_accuracy": 0.9909596383571625,
525
+ "num_tokens": 7664596.0,
526
+ "step": 1350
527
+ },
528
+ {
529
+ "epoch": 3.3138201569100785,
530
+ "grad_norm": 0.06945887953042984,
531
+ "learning_rate": 0.00017042860009456638,
532
+ "loss": 0.029,
533
+ "mean_token_accuracy": 0.9913074505329132,
534
+ "num_tokens": 7814551.0,
535
+ "step": 1375
536
+ },
537
+ {
538
+ "epoch": 3.3741701870850935,
539
+ "grad_norm": 0.07191596925258636,
540
+ "learning_rate": 0.00016627806471382066,
541
+ "loss": 0.0311,
542
+ "mean_token_accuracy": 0.9902618253231048,
543
+ "num_tokens": 7952304.0,
544
+ "step": 1400
545
+ },
546
+ {
547
+ "epoch": 3.4345202172601086,
548
+ "grad_norm": 0.07108636200428009,
549
+ "learning_rate": 0.00016211487670603078,
550
+ "loss": 0.0263,
551
+ "mean_token_accuracy": 0.9916422361135483,
552
+ "num_tokens": 8102624.0,
553
+ "step": 1425
554
+ },
555
+ {
556
+ "epoch": 3.4948702474351236,
557
+ "grad_norm": 0.1367121785879135,
558
+ "learning_rate": 0.0001579422720372715,
559
+ "loss": 0.0286,
560
+ "mean_token_accuracy": 0.9912952971458435,
561
+ "num_tokens": 8239465.0,
562
+ "step": 1450
563
+ },
564
+ {
565
+ "epoch": 3.5552202776101387,
566
+ "grad_norm": 0.064446821808815,
567
+ "learning_rate": 0.00015376349399300745,
568
+ "loss": 0.0246,
569
+ "mean_token_accuracy": 0.9919304746389389,
570
+ "num_tokens": 8387292.0,
571
+ "step": 1475
572
+ },
573
+ {
574
+ "epoch": 3.6155703077851538,
575
+ "grad_norm": 0.1252497136592865,
576
+ "learning_rate": 0.0001495817906571492,
577
+ "loss": 0.031,
578
+ "mean_token_accuracy": 0.990118277668953,
579
+ "num_tokens": 8523620.0,
580
+ "step": 1500
581
+ },
582
+ {
583
+ "epoch": 3.675920337960169,
584
+ "grad_norm": 0.04818420112133026,
585
+ "learning_rate": 0.00014540041238738055,
586
+ "loss": 0.0262,
587
+ "mean_token_accuracy": 0.9917533618211746,
588
+ "num_tokens": 8673400.0,
589
+ "step": 1525
590
+ },
591
+ {
592
+ "epoch": 3.736270368135184,
593
+ "grad_norm": 0.08937755227088928,
594
+ "learning_rate": 0.00014122260928871734,
595
+ "loss": 0.0307,
596
+ "mean_token_accuracy": 0.9904319751262665,
597
+ "num_tokens": 8810209.0,
598
+ "step": 1550
599
+ },
600
+ {
601
+ "epoch": 3.796620398310199,
602
+ "grad_norm": 0.0582498162984848,
603
+ "learning_rate": 0.00013705162868726396,
604
+ "loss": 0.0264,
605
+ "mean_token_accuracy": 0.9915424859523774,
606
+ "num_tokens": 8958149.0,
607
+ "step": 1575
608
+ },
609
+ {
610
+ "epoch": 3.856970428485214,
611
+ "grad_norm": 0.08708362281322479,
612
+ "learning_rate": 0.00013289071260612855,
613
+ "loss": 0.0267,
614
+ "mean_token_accuracy": 0.9918914479017258,
615
+ "num_tokens": 9093310.0,
616
+ "step": 1600
617
+ },
618
+ {
619
+ "epoch": 3.9173204586602295,
620
+ "grad_norm": 0.08365115523338318,
621
+ "learning_rate": 0.00012874309524546083,
622
+ "loss": 0.0263,
623
+ "mean_token_accuracy": 0.9918374270200729,
624
+ "num_tokens": 9238911.0,
625
+ "step": 1625
626
+ },
627
+ {
628
+ "epoch": 3.9776704888352445,
629
+ "grad_norm": 0.08191365003585815,
630
+ "learning_rate": 0.00012461200046857084,
631
+ "loss": 0.0256,
632
+ "mean_token_accuracy": 0.9919486922025681,
633
+ "num_tokens": 9369805.0,
634
+ "step": 1650
635
+ },
636
+ {
637
+ "epoch": 4.0,
638
+ "eval_loss": 0.04307638853788376,
639
+ "eval_mean_token_accuracy": 0.9885664443711977,
640
+ "eval_num_tokens": 9416720.0,
641
+ "eval_runtime": 61.7987,
642
+ "eval_samples_per_second": 5.971,
643
+ "eval_steps_per_second": 2.994,
644
+ "step": 1660
645
+ }
646
+ ],
647
+ "logging_steps": 25,
648
+ "max_steps": 2905,
649
+ "num_input_tokens_seen": 0,
650
+ "num_train_epochs": 7,
651
+ "save_steps": 500,
652
+ "stateful_callbacks": {
653
+ "TrainerControl": {
654
+ "args": {
655
+ "should_epoch_stop": false,
656
+ "should_evaluate": false,
657
+ "should_log": false,
658
+ "should_save": true,
659
+ "should_training_stop": false
660
+ },
661
+ "attributes": {}
662
+ }
663
+ },
664
+ "total_flos": 4.045378031600855e+17,
665
+ "train_batch_size": 2,
666
+ "trial_name": null,
667
+ "trial_params": null
668
+ }
checkpoint-1660/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd12954384614c3a1cf14ace2441d4d0f84fee8508c198a9b8f1387a477c18df
3
+ size 6097
checkpoint-1660/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2075/README.md ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-7B-Instruct
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:Qwen/Qwen2.5-7B-Instruct
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ ---
12
+
13
+ # Model Card for Model ID
14
+
15
+ <!-- Provide a quick summary of what the model is/does. -->
16
+
17
+
18
+
19
+ ## Model Details
20
+
21
+ ### Model Description
22
+
23
+ <!-- Provide a longer summary of what this model is. -->
24
+
25
+
26
+
27
+ - **Developed by:** [More Information Needed]
28
+ - **Funded by [optional]:** [More Information Needed]
29
+ - **Shared by [optional]:** [More Information Needed]
30
+ - **Model type:** [More Information Needed]
31
+ - **Language(s) (NLP):** [More Information Needed]
32
+ - **License:** [More Information Needed]
33
+ - **Finetuned from model [optional]:** [More Information Needed]
34
+
35
+ ### Model Sources [optional]
36
+
37
+ <!-- Provide the basic links for the model. -->
38
+
39
+ - **Repository:** [More Information Needed]
40
+ - **Paper [optional]:** [More Information Needed]
41
+ - **Demo [optional]:** [More Information Needed]
42
+
43
+ ## Uses
44
+
45
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
46
+
47
+ ### Direct Use
48
+
49
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
50
+
51
+ [More Information Needed]
52
+
53
+ ### Downstream Use [optional]
54
+
55
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
56
+
57
+ [More Information Needed]
58
+
59
+ ### Out-of-Scope Use
60
+
61
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
62
+
63
+ [More Information Needed]
64
+
65
+ ## Bias, Risks, and Limitations
66
+
67
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
68
+
69
+ [More Information Needed]
70
+
71
+ ### Recommendations
72
+
73
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
74
+
75
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
76
+
77
+ ## How to Get Started with the Model
78
+
79
+ Use the code below to get started with the model.
80
+
81
+ [More Information Needed]
82
+
83
+ ## Training Details
84
+
85
+ ### Training Data
86
+
87
+ <!-- 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. -->
88
+
89
+ [More Information Needed]
90
+
91
+ ### Training Procedure
92
+
93
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
94
+
95
+ #### Preprocessing [optional]
96
+
97
+ [More Information Needed]
98
+
99
+
100
+ #### Training Hyperparameters
101
+
102
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
103
+
104
+ #### Speeds, Sizes, Times [optional]
105
+
106
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
107
+
108
+ [More Information Needed]
109
+
110
+ ## Evaluation
111
+
112
+ <!-- This section describes the evaluation protocols and provides the results. -->
113
+
114
+ ### Testing Data, Factors & Metrics
115
+
116
+ #### Testing Data
117
+
118
+ <!-- This should link to a Dataset Card if possible. -->
119
+
120
+ [More Information Needed]
121
+
122
+ #### Factors
123
+
124
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
125
+
126
+ [More Information Needed]
127
+
128
+ #### Metrics
129
+
130
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
131
+
132
+ [More Information Needed]
133
+
134
+ ### Results
135
+
136
+ [More Information Needed]
137
+
138
+ #### Summary
139
+
140
+
141
+
142
+ ## Model Examination [optional]
143
+
144
+ <!-- Relevant interpretability work for the model goes here -->
145
+
146
+ [More Information Needed]
147
+
148
+ ## Environmental Impact
149
+
150
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
151
+
152
+ 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).
153
+
154
+ - **Hardware Type:** [More Information Needed]
155
+ - **Hours used:** [More Information Needed]
156
+ - **Cloud Provider:** [More Information Needed]
157
+ - **Compute Region:** [More Information Needed]
158
+ - **Carbon Emitted:** [More Information Needed]
159
+
160
+ ## Technical Specifications [optional]
161
+
162
+ ### Model Architecture and Objective
163
+
164
+ [More Information Needed]
165
+
166
+ ### Compute Infrastructure
167
+
168
+ [More Information Needed]
169
+
170
+ #### Hardware
171
+
172
+ [More Information Needed]
173
+
174
+ #### Software
175
+
176
+ [More Information Needed]
177
+
178
+ ## Citation [optional]
179
+
180
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
181
+
182
+ **BibTeX:**
183
+
184
+ [More Information Needed]
185
+
186
+ **APA:**
187
+
188
+ [More Information Needed]
189
+
190
+ ## Glossary [optional]
191
+
192
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
193
+
194
+ [More Information Needed]
195
+
196
+ ## More Information [optional]
197
+
198
+ [More Information Needed]
199
+
200
+ ## Model Card Authors [optional]
201
+
202
+ [More Information Needed]
203
+
204
+ ## Model Card Contact
205
+
206
+ [More Information Needed]
207
+ ### Framework versions
208
+
209
+ - PEFT 0.17.0
checkpoint-2075/adapter_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.1,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "qalora_group_size": 16,
24
+ "r": 32,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "o_proj",
29
+ "v_proj",
30
+ "up_proj",
31
+ "down_proj",
32
+ "gate_proj",
33
+ "q_proj",
34
+ "k_proj"
35
+ ],
36
+ "target_parameters": null,
37
+ "task_type": "CAUSAL_LM",
38
+ "trainable_token_indices": null,
39
+ "use_dora": false,
40
+ "use_qalora": false,
41
+ "use_rslora": false
42
+ }
checkpoint-2075/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d4652735447470cb854f5b764e7ae4c3ac8dc6f7db5ff90e6257734c21e9181
3
+ size 323014168
checkpoint-2075/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-2075/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\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>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\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" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
checkpoint-2075/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2075/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b47c6c85ef0e0df6b6810ba4936319432478a4165f519e9e82aa5fe5570c6de3
3
+ size 646164683
checkpoint-2075/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bdc2b661c24ba4410331d04a8b143cebe73b7edc1929b8354ebcf0dbb4d9094
3
+ size 14645
checkpoint-2075/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdeac6d1a7910e1e533a39a2d59ab67f6fb22254f41224ded16d311412dbc0b1
3
+ size 1465
checkpoint-2075/special_tokens_map.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|im_end|>"
25
+ }
checkpoint-2075/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3f9d93e80cff961819dcba7d892cf9656e086a0cf83cdbef23f10c1a493faa2
3
+ size 11422061
checkpoint-2075/tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|im_end|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
checkpoint-2075/trainer_state.json ADDED
@@ -0,0 +1,831 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 5.0,
6
+ "eval_steps": 500,
7
+ "global_step": 2075,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.060350030175015085,
14
+ "grad_norm": 0.31135597825050354,
15
+ "learning_rate": 8.18181818181818e-05,
16
+ "loss": 1.9235,
17
+ "mean_token_accuracy": 0.6165974247455597,
18
+ "num_tokens": 157030.0,
19
+ "step": 25
20
+ },
21
+ {
22
+ "epoch": 0.12070006035003017,
23
+ "grad_norm": 0.32249024510383606,
24
+ "learning_rate": 0.00016704545454545452,
25
+ "loss": 1.0538,
26
+ "mean_token_accuracy": 0.7450298243761062,
27
+ "num_tokens": 284204.0,
28
+ "step": 50
29
+ },
30
+ {
31
+ "epoch": 0.18105009052504525,
32
+ "grad_norm": 0.3015844523906708,
33
+ "learning_rate": 0.0002522727272727273,
34
+ "loss": 0.6726,
35
+ "mean_token_accuracy": 0.8188469475507736,
36
+ "num_tokens": 441659.0,
37
+ "step": 75
38
+ },
39
+ {
40
+ "epoch": 0.24140012070006034,
41
+ "grad_norm": 0.5104885697364807,
42
+ "learning_rate": 0.0002999887132933212,
43
+ "loss": 0.5348,
44
+ "mean_token_accuracy": 0.8504667854309083,
45
+ "num_tokens": 567533.0,
46
+ "step": 100
47
+ },
48
+ {
49
+ "epoch": 0.30175015087507545,
50
+ "grad_norm": 0.278422474861145,
51
+ "learning_rate": 0.0002998791256978121,
52
+ "loss": 0.4144,
53
+ "mean_token_accuracy": 0.8816475421190262,
54
+ "num_tokens": 725296.0,
55
+ "step": 125
56
+ },
57
+ {
58
+ "epoch": 0.3621001810500905,
59
+ "grad_norm": 0.35799795389175415,
60
+ "learning_rate": 0.0002996530399366737,
61
+ "loss": 0.3693,
62
+ "mean_token_accuracy": 0.8962992638349533,
63
+ "num_tokens": 851708.0,
64
+ "step": 150
65
+ },
66
+ {
67
+ "epoch": 0.4224502112251056,
68
+ "grad_norm": 0.2955951690673828,
69
+ "learning_rate": 0.00029931063174202567,
70
+ "loss": 0.2746,
71
+ "mean_token_accuracy": 0.921732594370842,
72
+ "num_tokens": 1008739.0,
73
+ "step": 175
74
+ },
75
+ {
76
+ "epoch": 0.4828002414001207,
77
+ "grad_norm": 0.3763117790222168,
78
+ "learning_rate": 0.00029885216726118104,
79
+ "loss": 0.2386,
80
+ "mean_token_accuracy": 0.9305408012866974,
81
+ "num_tokens": 1134832.0,
82
+ "step": 200
83
+ },
84
+ {
85
+ "epoch": 0.5431502715751357,
86
+ "grad_norm": 0.3240911066532135,
87
+ "learning_rate": 0.00029827800284977474,
88
+ "loss": 0.1885,
89
+ "mean_token_accuracy": 0.9465595126152039,
90
+ "num_tokens": 1293095.0,
91
+ "step": 225
92
+ },
93
+ {
94
+ "epoch": 0.6035003017501509,
95
+ "grad_norm": 0.3682485520839691,
96
+ "learning_rate": 0.00029758858479477575,
97
+ "loss": 0.1832,
98
+ "mean_token_accuracy": 0.9486982274055481,
99
+ "num_tokens": 1419060.0,
100
+ "step": 250
101
+ },
102
+ {
103
+ "epoch": 0.663850331925166,
104
+ "grad_norm": 0.29996615648269653,
105
+ "learning_rate": 0.0002967844489675963,
106
+ "loss": 0.1501,
107
+ "mean_token_accuracy": 0.9576406496763229,
108
+ "num_tokens": 1577978.0,
109
+ "step": 275
110
+ },
111
+ {
112
+ "epoch": 0.724200362100181,
113
+ "grad_norm": 0.3568132221698761,
114
+ "learning_rate": 0.00029586622040756957,
115
+ "loss": 0.1246,
116
+ "mean_token_accuracy": 0.964940841794014,
117
+ "num_tokens": 1705052.0,
118
+ "step": 300
119
+ },
120
+ {
121
+ "epoch": 0.7845503922751962,
122
+ "grad_norm": 0.258465439081192,
123
+ "learning_rate": 0.0002948346128361186,
124
+ "loss": 0.1089,
125
+ "mean_token_accuracy": 0.970317553281784,
126
+ "num_tokens": 1861669.0,
127
+ "step": 325
128
+ },
129
+ {
130
+ "epoch": 0.8449004224502112,
131
+ "grad_norm": 0.3066297173500061,
132
+ "learning_rate": 0.00029369042810199416,
133
+ "loss": 0.1072,
134
+ "mean_token_accuracy": 0.9702006059885026,
135
+ "num_tokens": 1988735.0,
136
+ "step": 350
137
+ },
138
+ {
139
+ "epoch": 0.9052504526252263,
140
+ "grad_norm": 0.22371642291545868,
141
+ "learning_rate": 0.0002924345555580135,
142
+ "loss": 0.1117,
143
+ "mean_token_accuracy": 0.9696371680498124,
144
+ "num_tokens": 2146989.0,
145
+ "step": 375
146
+ },
147
+ {
148
+ "epoch": 0.9656004828002414,
149
+ "grad_norm": 0.4630758762359619,
150
+ "learning_rate": 0.000291067971369783,
151
+ "loss": 0.0863,
152
+ "mean_token_accuracy": 0.9765483093261719,
153
+ "num_tokens": 2274615.0,
154
+ "step": 400
155
+ },
156
+ {
157
+ "epoch": 1.0,
158
+ "eval_loss": 0.09050165861845016,
159
+ "eval_mean_token_accuracy": 0.9750120665576006,
160
+ "eval_num_tokens": 2354180.0,
161
+ "eval_runtime": 61.8103,
162
+ "eval_samples_per_second": 5.97,
163
+ "eval_steps_per_second": 2.993,
164
+ "step": 415
165
+ },
166
+ {
167
+ "epoch": 1.024140012070006,
168
+ "grad_norm": 0.17408408224582672,
169
+ "learning_rate": 0.0002895917377569438,
170
+ "loss": 0.1029,
171
+ "mean_token_accuracy": 0.9737048333453149,
172
+ "num_tokens": 2423619.0,
173
+ "step": 425
174
+ },
175
+ {
176
+ "epoch": 1.0844900422450212,
177
+ "grad_norm": 0.20633958280086517,
178
+ "learning_rate": 0.00028800700216752875,
179
+ "loss": 0.0578,
180
+ "mean_token_accuracy": 0.9834175568819046,
181
+ "num_tokens": 2566868.0,
182
+ "step": 450
183
+ },
184
+ {
185
+ "epoch": 1.1448400724200363,
186
+ "grad_norm": 0.1839175969362259,
187
+ "learning_rate": 0.00028631499638607285,
188
+ "loss": 0.0801,
189
+ "mean_token_accuracy": 0.9778328466415406,
190
+ "num_tokens": 2709054.0,
191
+ "step": 475
192
+ },
193
+ {
194
+ "epoch": 1.2051901025950513,
195
+ "grad_norm": 0.25615933537483215,
196
+ "learning_rate": 0.0002845170355761712,
197
+ "loss": 0.0614,
198
+ "mean_token_accuracy": 0.9824786186218262,
199
+ "num_tokens": 2851375.0,
200
+ "step": 500
201
+ },
202
+ {
203
+ "epoch": 1.2655401327700664,
204
+ "grad_norm": 0.16976642608642578,
205
+ "learning_rate": 0.0002826145172582274,
206
+ "loss": 0.0701,
207
+ "mean_token_accuracy": 0.9807569885253906,
208
+ "num_tokens": 2993397.0,
209
+ "step": 525
210
+ },
211
+ {
212
+ "epoch": 1.3258901629450814,
213
+ "grad_norm": 0.15633493661880493,
214
+ "learning_rate": 0.00028060892022318764,
215
+ "loss": 0.0555,
216
+ "mean_token_accuracy": 0.9843500143289566,
217
+ "num_tokens": 3136497.0,
218
+ "step": 550
219
+ },
220
+ {
221
+ "epoch": 1.3862401931200965,
222
+ "grad_norm": 0.16217610239982605,
223
+ "learning_rate": 0.0002785018033831051,
224
+ "loss": 0.0652,
225
+ "mean_token_accuracy": 0.982210916876793,
226
+ "num_tokens": 3277611.0,
227
+ "step": 575
228
+ },
229
+ {
230
+ "epoch": 1.4465902232951118,
231
+ "grad_norm": 0.10138845443725586,
232
+ "learning_rate": 0.0002762948045594276,
233
+ "loss": 0.0523,
234
+ "mean_token_accuracy": 0.985246667265892,
235
+ "num_tokens": 3420182.0,
236
+ "step": 600
237
+ },
238
+ {
239
+ "epoch": 1.5069402534701268,
240
+ "grad_norm": 0.12522730231285095,
241
+ "learning_rate": 0.0002739896392099502,
242
+ "loss": 0.063,
243
+ "mean_token_accuracy": 0.9825242179632186,
244
+ "num_tokens": 3561580.0,
245
+ "step": 625
246
+ },
247
+ {
248
+ "epoch": 1.567290283645142,
249
+ "grad_norm": 0.16772225499153137,
250
+ "learning_rate": 0.00027158809909542307,
251
+ "loss": 0.0458,
252
+ "mean_token_accuracy": 0.9863684195280075,
253
+ "num_tokens": 3703648.0,
254
+ "step": 650
255
+ },
256
+ {
257
+ "epoch": 1.627640313820157,
258
+ "grad_norm": 0.11150436848402023,
259
+ "learning_rate": 0.00026909205088685,
260
+ "loss": 0.0701,
261
+ "mean_token_accuracy": 0.9805551666021347,
262
+ "num_tokens": 3846275.0,
263
+ "step": 675
264
+ },
265
+ {
266
+ "epoch": 1.687990343995172,
267
+ "grad_norm": 0.13114990293979645,
268
+ "learning_rate": 0.0002665034347145612,
269
+ "loss": 0.047,
270
+ "mean_token_accuracy": 0.9866662234067917,
271
+ "num_tokens": 3990181.0,
272
+ "step": 700
273
+ },
274
+ {
275
+ "epoch": 1.748340374170187,
276
+ "grad_norm": 0.1373077780008316,
277
+ "learning_rate": 0.000263824262660187,
278
+ "loss": 0.0658,
279
+ "mean_token_accuracy": 0.9822418791055679,
280
+ "num_tokens": 4132061.0,
281
+ "step": 725
282
+ },
283
+ {
284
+ "epoch": 1.8086904043452021,
285
+ "grad_norm": 0.1755433827638626,
286
+ "learning_rate": 0.0002610566171927056,
287
+ "loss": 0.0393,
288
+ "mean_token_accuracy": 0.9886017143726349,
289
+ "num_tokens": 4273899.0,
290
+ "step": 750
291
+ },
292
+ {
293
+ "epoch": 1.8690404345202172,
294
+ "grad_norm": 0.12637771666049957,
295
+ "learning_rate": 0.00025820264954977976,
296
+ "loss": 0.0632,
297
+ "mean_token_accuracy": 0.9825896525382996,
298
+ "num_tokens": 4414846.0,
299
+ "step": 775
300
+ },
301
+ {
302
+ "epoch": 1.9293904646952322,
303
+ "grad_norm": 0.0651940405368805,
304
+ "learning_rate": 0.00025526457806564136,
305
+ "loss": 0.0419,
306
+ "mean_token_accuracy": 0.9879031604528428,
307
+ "num_tokens": 4557169.0,
308
+ "step": 800
309
+ },
310
+ {
311
+ "epoch": 1.9897404948702473,
312
+ "grad_norm": 0.12048754841089249,
313
+ "learning_rate": 0.00025224468644682245,
314
+ "loss": 0.0498,
315
+ "mean_token_accuracy": 0.9858449596166611,
316
+ "num_tokens": 4688618.0,
317
+ "step": 825
318
+ },
319
+ {
320
+ "epoch": 2.0,
321
+ "eval_loss": 0.054688576608896255,
322
+ "eval_mean_token_accuracy": 0.9851620287508578,
323
+ "eval_num_tokens": 4708360.0,
324
+ "eval_runtime": 61.7668,
325
+ "eval_samples_per_second": 5.974,
326
+ "eval_steps_per_second": 2.995,
327
+ "step": 830
328
+ },
329
+ {
330
+ "epoch": 2.048280024140012,
331
+ "grad_norm": 0.10747923702001572,
332
+ "learning_rate": 0.00024914532199707444,
333
+ "loss": 0.0491,
334
+ "mean_token_accuracy": 0.9856173869260808,
335
+ "num_tokens": 4837968.0,
336
+ "step": 850
337
+ },
338
+ {
339
+ "epoch": 2.1086300543150274,
340
+ "grad_norm": 0.13443028926849365,
341
+ "learning_rate": 0.00024596889379285353,
342
+ "loss": 0.0316,
343
+ "mean_token_accuracy": 0.9905168610811234,
344
+ "num_tokens": 4971141.0,
345
+ "step": 875
346
+ },
347
+ {
348
+ "epoch": 2.1689800844900424,
349
+ "grad_norm": 0.1226191446185112,
350
+ "learning_rate": 0.00024271787081079228,
351
+ "loss": 0.0527,
352
+ "mean_token_accuracy": 0.9845808875560761,
353
+ "num_tokens": 5124003.0,
354
+ "step": 900
355
+ },
356
+ {
357
+ "epoch": 2.2293301146650575,
358
+ "grad_norm": 0.13954219222068787,
359
+ "learning_rate": 0.00023939478000861117,
360
+ "loss": 0.03,
361
+ "mean_token_accuracy": 0.991157540678978,
362
+ "num_tokens": 5256623.0,
363
+ "step": 925
364
+ },
365
+ {
366
+ "epoch": 2.2896801448400725,
367
+ "grad_norm": 0.07871092110872269,
368
+ "learning_rate": 0.00023600220436096318,
369
+ "loss": 0.0401,
370
+ "mean_token_accuracy": 0.9883328771591187,
371
+ "num_tokens": 5405783.0,
372
+ "step": 950
373
+ },
374
+ {
375
+ "epoch": 2.3500301750150876,
376
+ "grad_norm": 0.07625500857830048,
377
+ "learning_rate": 0.00023254278085173684,
378
+ "loss": 0.0329,
379
+ "mean_token_accuracy": 0.9900754565000534,
380
+ "num_tokens": 5538983.0,
381
+ "step": 975
382
+ },
383
+ {
384
+ "epoch": 2.4103802051901027,
385
+ "grad_norm": 0.08441416919231415,
386
+ "learning_rate": 0.00022901919842437972,
387
+ "loss": 0.045,
388
+ "mean_token_accuracy": 0.9868701863288879,
389
+ "num_tokens": 5689941.0,
390
+ "step": 1000
391
+ },
392
+ {
393
+ "epoch": 2.4707302353651177,
394
+ "grad_norm": 0.10544892400503159,
395
+ "learning_rate": 0.00022543419589183397,
396
+ "loss": 0.0282,
397
+ "mean_token_accuracy": 0.991428604722023,
398
+ "num_tokens": 5823463.0,
399
+ "step": 1025
400
+ },
401
+ {
402
+ "epoch": 2.5310802655401328,
403
+ "grad_norm": 0.08695073425769806,
404
+ "learning_rate": 0.00022179055980770993,
405
+ "loss": 0.0461,
406
+ "mean_token_accuracy": 0.9864470016956329,
407
+ "num_tokens": 5974358.0,
408
+ "step": 1050
409
+ },
410
+ {
411
+ "epoch": 2.591430295715148,
412
+ "grad_norm": 0.09350312501192093,
413
+ "learning_rate": 0.0002180911223003513,
414
+ "loss": 0.0327,
415
+ "mean_token_accuracy": 0.990239828824997,
416
+ "num_tokens": 6106913.0,
417
+ "step": 1075
418
+ },
419
+ {
420
+ "epoch": 2.651780325890163,
421
+ "grad_norm": 0.06971506774425507,
422
+ "learning_rate": 0.00021433875887147627,
423
+ "loss": 0.0496,
424
+ "mean_token_accuracy": 0.9856115758419037,
425
+ "num_tokens": 6260849.0,
426
+ "step": 1100
427
+ },
428
+ {
429
+ "epoch": 2.712130356065178,
430
+ "grad_norm": 0.07409551739692688,
431
+ "learning_rate": 0.00021053638616110525,
432
+ "loss": 0.031,
433
+ "mean_token_accuracy": 0.9906682467460632,
434
+ "num_tokens": 6393788.0,
435
+ "step": 1125
436
+ },
437
+ {
438
+ "epoch": 2.772480386240193,
439
+ "grad_norm": 0.08459241688251495,
440
+ "learning_rate": 0.00020668695968051274,
441
+ "loss": 0.0417,
442
+ "mean_token_accuracy": 0.9878255265951157,
443
+ "num_tokens": 6545295.0,
444
+ "step": 1150
445
+ },
446
+ {
447
+ "epoch": 2.832830416415208,
448
+ "grad_norm": 0.06320163607597351,
449
+ "learning_rate": 0.00020279347151496482,
450
+ "loss": 0.0305,
451
+ "mean_token_accuracy": 0.9911946403980255,
452
+ "num_tokens": 6677075.0,
453
+ "step": 1175
454
+ },
455
+ {
456
+ "epoch": 2.8931804465902236,
457
+ "grad_norm": 0.08129168301820755,
458
+ "learning_rate": 0.00019885894799802922,
459
+ "loss": 0.0465,
460
+ "mean_token_accuracy": 0.9863498049974442,
461
+ "num_tokens": 6828145.0,
462
+ "step": 1200
463
+ },
464
+ {
465
+ "epoch": 2.9535304767652386,
466
+ "grad_norm": 0.054761067032814026,
467
+ "learning_rate": 0.00019488644735926396,
468
+ "loss": 0.0298,
469
+ "mean_token_accuracy": 0.9909803092479705,
470
+ "num_tokens": 6960911.0,
471
+ "step": 1225
472
+ },
473
+ {
474
+ "epoch": 3.0,
475
+ "eval_loss": 0.04527445137500763,
476
+ "eval_mean_token_accuracy": 0.9875696955500423,
477
+ "eval_num_tokens": 7062540.0,
478
+ "eval_runtime": 61.7191,
479
+ "eval_samples_per_second": 5.979,
480
+ "eval_steps_per_second": 2.997,
481
+ "step": 1245
482
+ },
483
+ {
484
+ "epoch": 3.012070006035003,
485
+ "grad_norm": 0.061567842960357666,
486
+ "learning_rate": 0.00019087905734711452,
487
+ "loss": 0.0384,
488
+ "mean_token_accuracy": 0.9884870881886826,
489
+ "num_tokens": 7098246.0,
490
+ "step": 1250
491
+ },
492
+ {
493
+ "epoch": 3.0724200362100182,
494
+ "grad_norm": 0.07762719690799713,
495
+ "learning_rate": 0.00018683989282886613,
496
+ "loss": 0.0252,
497
+ "mean_token_accuracy": 0.9920413041114807,
498
+ "num_tokens": 7246634.0,
499
+ "step": 1275
500
+ },
501
+ {
502
+ "epoch": 3.1327700663850333,
503
+ "grad_norm": 0.07748158276081085,
504
+ "learning_rate": 0.0001827720933695173,
505
+ "loss": 0.0313,
506
+ "mean_token_accuracy": 0.9904079920053482,
507
+ "num_tokens": 7381014.0,
508
+ "step": 1300
509
+ },
510
+ {
511
+ "epoch": 3.1931200965600484,
512
+ "grad_norm": 0.06404800713062286,
513
+ "learning_rate": 0.00017867882079145627,
514
+ "loss": 0.0276,
515
+ "mean_token_accuracy": 0.9916363900899887,
516
+ "num_tokens": 7528065.0,
517
+ "step": 1325
518
+ },
519
+ {
520
+ "epoch": 3.2534701267350634,
521
+ "grad_norm": 0.09366205334663391,
522
+ "learning_rate": 0.00017456325671683724,
523
+ "loss": 0.0288,
524
+ "mean_token_accuracy": 0.9909596383571625,
525
+ "num_tokens": 7664596.0,
526
+ "step": 1350
527
+ },
528
+ {
529
+ "epoch": 3.3138201569100785,
530
+ "grad_norm": 0.06945887953042984,
531
+ "learning_rate": 0.00017042860009456638,
532
+ "loss": 0.029,
533
+ "mean_token_accuracy": 0.9913074505329132,
534
+ "num_tokens": 7814551.0,
535
+ "step": 1375
536
+ },
537
+ {
538
+ "epoch": 3.3741701870850935,
539
+ "grad_norm": 0.07191596925258636,
540
+ "learning_rate": 0.00016627806471382066,
541
+ "loss": 0.0311,
542
+ "mean_token_accuracy": 0.9902618253231048,
543
+ "num_tokens": 7952304.0,
544
+ "step": 1400
545
+ },
546
+ {
547
+ "epoch": 3.4345202172601086,
548
+ "grad_norm": 0.07108636200428009,
549
+ "learning_rate": 0.00016211487670603078,
550
+ "loss": 0.0263,
551
+ "mean_token_accuracy": 0.9916422361135483,
552
+ "num_tokens": 8102624.0,
553
+ "step": 1425
554
+ },
555
+ {
556
+ "epoch": 3.4948702474351236,
557
+ "grad_norm": 0.1367121785879135,
558
+ "learning_rate": 0.0001579422720372715,
559
+ "loss": 0.0286,
560
+ "mean_token_accuracy": 0.9912952971458435,
561
+ "num_tokens": 8239465.0,
562
+ "step": 1450
563
+ },
564
+ {
565
+ "epoch": 3.5552202776101387,
566
+ "grad_norm": 0.064446821808815,
567
+ "learning_rate": 0.00015376349399300745,
568
+ "loss": 0.0246,
569
+ "mean_token_accuracy": 0.9919304746389389,
570
+ "num_tokens": 8387292.0,
571
+ "step": 1475
572
+ },
573
+ {
574
+ "epoch": 3.6155703077851538,
575
+ "grad_norm": 0.1252497136592865,
576
+ "learning_rate": 0.0001495817906571492,
577
+ "loss": 0.031,
578
+ "mean_token_accuracy": 0.990118277668953,
579
+ "num_tokens": 8523620.0,
580
+ "step": 1500
581
+ },
582
+ {
583
+ "epoch": 3.675920337960169,
584
+ "grad_norm": 0.04818420112133026,
585
+ "learning_rate": 0.00014540041238738055,
586
+ "loss": 0.0262,
587
+ "mean_token_accuracy": 0.9917533618211746,
588
+ "num_tokens": 8673400.0,
589
+ "step": 1525
590
+ },
591
+ {
592
+ "epoch": 3.736270368135184,
593
+ "grad_norm": 0.08937755227088928,
594
+ "learning_rate": 0.00014122260928871734,
595
+ "loss": 0.0307,
596
+ "mean_token_accuracy": 0.9904319751262665,
597
+ "num_tokens": 8810209.0,
598
+ "step": 1550
599
+ },
600
+ {
601
+ "epoch": 3.796620398310199,
602
+ "grad_norm": 0.0582498162984848,
603
+ "learning_rate": 0.00013705162868726396,
604
+ "loss": 0.0264,
605
+ "mean_token_accuracy": 0.9915424859523774,
606
+ "num_tokens": 8958149.0,
607
+ "step": 1575
608
+ },
609
+ {
610
+ "epoch": 3.856970428485214,
611
+ "grad_norm": 0.08708362281322479,
612
+ "learning_rate": 0.00013289071260612855,
613
+ "loss": 0.0267,
614
+ "mean_token_accuracy": 0.9918914479017258,
615
+ "num_tokens": 9093310.0,
616
+ "step": 1600
617
+ },
618
+ {
619
+ "epoch": 3.9173204586602295,
620
+ "grad_norm": 0.08365115523338318,
621
+ "learning_rate": 0.00012874309524546083,
622
+ "loss": 0.0263,
623
+ "mean_token_accuracy": 0.9918374270200729,
624
+ "num_tokens": 9238911.0,
625
+ "step": 1625
626
+ },
627
+ {
628
+ "epoch": 3.9776704888352445,
629
+ "grad_norm": 0.08191365003585815,
630
+ "learning_rate": 0.00012461200046857084,
631
+ "loss": 0.0256,
632
+ "mean_token_accuracy": 0.9919486922025681,
633
+ "num_tokens": 9369805.0,
634
+ "step": 1650
635
+ },
636
+ {
637
+ "epoch": 4.0,
638
+ "eval_loss": 0.04307638853788376,
639
+ "eval_mean_token_accuracy": 0.9885664443711977,
640
+ "eval_num_tokens": 9416720.0,
641
+ "eval_runtime": 61.7987,
642
+ "eval_samples_per_second": 5.971,
643
+ "eval_steps_per_second": 2.994,
644
+ "step": 1660
645
+ },
646
+ {
647
+ "epoch": 4.036210018105009,
648
+ "grad_norm": 0.04609857127070427,
649
+ "learning_rate": 0.00012050063929608123,
650
+ "loss": 0.0261,
651
+ "mean_token_accuracy": 0.9915816790049838,
652
+ "num_tokens": 9518620.0,
653
+ "step": 1675
654
+ },
655
+ {
656
+ "epoch": 4.096560048280024,
657
+ "grad_norm": 0.0421195812523365,
658
+ "learning_rate": 0.0001164122074100633,
659
+ "loss": 0.0197,
660
+ "mean_token_accuracy": 0.9934104865789414,
661
+ "num_tokens": 9656880.0,
662
+ "step": 1700
663
+ },
664
+ {
665
+ "epoch": 4.15691007845504,
666
+ "grad_norm": 0.06511716544628143,
667
+ "learning_rate": 0.00011234988267009415,
668
+ "loss": 0.0238,
669
+ "mean_token_accuracy": 0.9923344779014588,
670
+ "num_tokens": 9803496.0,
671
+ "step": 1725
672
+ },
673
+ {
674
+ "epoch": 4.217260108630055,
675
+ "grad_norm": 0.04106709733605385,
676
+ "learning_rate": 0.00010831682264316787,
677
+ "loss": 0.0196,
678
+ "mean_token_accuracy": 0.9936438763141632,
679
+ "num_tokens": 9942120.0,
680
+ "step": 1750
681
+ },
682
+ {
683
+ "epoch": 4.27761013880507,
684
+ "grad_norm": 0.035884249955415726,
685
+ "learning_rate": 0.00010431616214937911,
686
+ "loss": 0.0238,
687
+ "mean_token_accuracy": 0.992466544508934,
688
+ "num_tokens": 10088250.0,
689
+ "step": 1775
690
+ },
691
+ {
692
+ "epoch": 4.337960168980085,
693
+ "grad_norm": 0.08095250278711319,
694
+ "learning_rate": 0.00010035101082528777,
695
+ "loss": 0.0194,
696
+ "mean_token_accuracy": 0.993693078160286,
697
+ "num_tokens": 10225040.0,
698
+ "step": 1800
699
+ },
700
+ {
701
+ "epoch": 4.3983101991551,
702
+ "grad_norm": 0.05341358855366707,
703
+ "learning_rate": 9.642445070685809e-05,
704
+ "loss": 0.0266,
705
+ "mean_token_accuracy": 0.9913520681858062,
706
+ "num_tokens": 10370929.0,
707
+ "step": 1825
708
+ },
709
+ {
710
+ "epoch": 4.458660229330115,
711
+ "grad_norm": 0.07090672850608826,
712
+ "learning_rate": 9.253953383385157e-05,
713
+ "loss": 0.0196,
714
+ "mean_token_accuracy": 0.9933394527435303,
715
+ "num_tokens": 10508749.0,
716
+ "step": 1850
717
+ },
718
+ {
719
+ "epoch": 4.51901025950513,
720
+ "grad_norm": 0.05845542252063751,
721
+ "learning_rate": 8.869927987753459e-05,
722
+ "loss": 0.0238,
723
+ "mean_token_accuracy": 0.992053787112236,
724
+ "num_tokens": 10655521.0,
725
+ "step": 1875
726
+ },
727
+ {
728
+ "epoch": 4.579360289680145,
729
+ "grad_norm": 0.04508192464709282,
730
+ "learning_rate": 8.490667379354661e-05,
731
+ "loss": 0.0186,
732
+ "mean_token_accuracy": 0.9938723063468933,
733
+ "num_tokens": 10792437.0,
734
+ "step": 1900
735
+ },
736
+ {
737
+ "epoch": 4.63971031985516,
738
+ "grad_norm": 0.0697343647480011,
739
+ "learning_rate": 8.116466350175079e-05,
740
+ "loss": 0.0235,
741
+ "mean_token_accuracy": 0.9926882380247116,
742
+ "num_tokens": 10938497.0,
743
+ "step": 1925
744
+ },
745
+ {
746
+ "epoch": 4.700060350030175,
747
+ "grad_norm": 0.038746606558561325,
748
+ "learning_rate": 7.747615759487304e-05,
749
+ "loss": 0.0188,
750
+ "mean_token_accuracy": 0.9936485493183136,
751
+ "num_tokens": 11076307.0,
752
+ "step": 1950
753
+ },
754
+ {
755
+ "epoch": 4.76041038020519,
756
+ "grad_norm": 0.059882089495658875,
757
+ "learning_rate": 7.38440230777085e-05,
758
+ "loss": 0.0225,
759
+ "mean_token_accuracy": 0.9926686590909958,
760
+ "num_tokens": 11222212.0,
761
+ "step": 1975
762
+ },
763
+ {
764
+ "epoch": 4.820760410380205,
765
+ "grad_norm": 0.058393221348524094,
766
+ "learning_rate": 7.027108313865378e-05,
767
+ "loss": 0.0189,
768
+ "mean_token_accuracy": 0.9937667572498321,
769
+ "num_tokens": 11359271.0,
770
+ "step": 2000
771
+ },
772
+ {
773
+ "epoch": 4.88111044055522,
774
+ "grad_norm": 0.06429804116487503,
775
+ "learning_rate": 6.676011495529687e-05,
776
+ "loss": 0.024,
777
+ "mean_token_accuracy": 0.9916912001371384,
778
+ "num_tokens": 11506584.0,
779
+ "step": 2025
780
+ },
781
+ {
782
+ "epoch": 4.941460470730235,
783
+ "grad_norm": 0.061373207718133926,
784
+ "learning_rate": 6.331384753577056e-05,
785
+ "loss": 0.0189,
786
+ "mean_token_accuracy": 0.9937462341785431,
787
+ "num_tokens": 11643764.0,
788
+ "step": 2050
789
+ },
790
+ {
791
+ "epoch": 5.0,
792
+ "grad_norm": 0.17021211981773376,
793
+ "learning_rate": 5.993495959754631e-05,
794
+ "loss": 0.0211,
795
+ "mean_token_accuracy": 0.99315461301312,
796
+ "num_tokens": 11770900.0,
797
+ "step": 2075
798
+ },
799
+ {
800
+ "epoch": 5.0,
801
+ "eval_loss": 0.04168040677905083,
802
+ "eval_mean_token_accuracy": 0.9894425063519865,
803
+ "eval_num_tokens": 11770900.0,
804
+ "eval_runtime": 61.7626,
805
+ "eval_samples_per_second": 5.974,
806
+ "eval_steps_per_second": 2.995,
807
+ "step": 2075
808
+ }
809
+ ],
810
+ "logging_steps": 25,
811
+ "max_steps": 2905,
812
+ "num_input_tokens_seen": 0,
813
+ "num_train_epochs": 7,
814
+ "save_steps": 500,
815
+ "stateful_callbacks": {
816
+ "TrainerControl": {
817
+ "args": {
818
+ "should_epoch_stop": false,
819
+ "should_evaluate": false,
820
+ "should_log": false,
821
+ "should_save": true,
822
+ "should_training_stop": false
823
+ },
824
+ "attributes": {}
825
+ }
826
+ },
827
+ "total_flos": 5.056790656200192e+17,
828
+ "train_batch_size": 2,
829
+ "trial_name": null,
830
+ "trial_params": null
831
+ }
checkpoint-2075/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd12954384614c3a1cf14ace2441d4d0f84fee8508c198a9b8f1387a477c18df
3
+ size 6097