Hugging Face's logo

PanzerBread
/
PromptCoT

Text Generation
PEFT
Safetensors
Transformers
lora
promptcot
chain-of-thought
mathematical-reasoning
unsloth
Model card Files
xet
Community
PanzerBread commited on
Commit
4da84c3
·
verified ·
1 Parent(s): fec4649

Upload folder using huggingface_hub

Browse files
Files changed (32) hide show
  1. .gitattributes +3 -0
  2. math-0.3/p/cold-start/README.md +63 -0
  3. math-0.3/p/cold-start/adapter_config.json +50 -0
  4. math-0.3/p/cold-start/adapter_model.safetensors +3 -0
  5. math-0.3/p/cold-start/chat_template.jinja +1 -0
  6. math-0.3/p/cold-start/checkpoint-500/README.md +210 -0
  7. math-0.3/p/cold-start/checkpoint-500/adapter_config.json +50 -0
  8. math-0.3/p/cold-start/checkpoint-500/adapter_model.safetensors +3 -0
  9. math-0.3/p/cold-start/checkpoint-500/chat_template.jinja +1 -0
  10. math-0.3/p/cold-start/checkpoint-500/optimizer.pt +3 -0
  11. math-0.3/p/cold-start/checkpoint-500/rng_state.pth +3 -0
  12. math-0.3/p/cold-start/checkpoint-500/scheduler.pt +3 -0
  13. math-0.3/p/cold-start/checkpoint-500/special_tokens_map.json +23 -0
  14. math-0.3/p/cold-start/checkpoint-500/tokenizer.json +3 -0
  15. math-0.3/p/cold-start/checkpoint-500/tokenizer_config.json +195 -0
  16. math-0.3/p/cold-start/checkpoint-500/trainer_state.json +741 -0
  17. math-0.3/p/cold-start/checkpoint-500/training_args.bin +3 -0
  18. math-0.3/p/cold-start/checkpoint-552/README.md +210 -0
  19. math-0.3/p/cold-start/checkpoint-552/adapter_config.json +50 -0
  20. math-0.3/p/cold-start/checkpoint-552/adapter_model.safetensors +3 -0
  21. math-0.3/p/cold-start/checkpoint-552/chat_template.jinja +1 -0
  22. math-0.3/p/cold-start/checkpoint-552/optimizer.pt +3 -0
  23. math-0.3/p/cold-start/checkpoint-552/rng_state.pth +3 -0
  24. math-0.3/p/cold-start/checkpoint-552/scheduler.pt +3 -0
  25. math-0.3/p/cold-start/checkpoint-552/special_tokens_map.json +23 -0
  26. math-0.3/p/cold-start/checkpoint-552/tokenizer.json +3 -0
  27. math-0.3/p/cold-start/checkpoint-552/tokenizer_config.json +195 -0
  28. math-0.3/p/cold-start/checkpoint-552/trainer_state.json +811 -0
  29. math-0.3/p/cold-start/checkpoint-552/training_args.bin +3 -0
  30. math-0.3/p/cold-start/special_tokens_map.json +23 -0
  31. math-0.3/p/cold-start/tokenizer.json +3 -0
  32. math-0.3/p/cold-start/tokenizer_config.json +195 -0
.gitattributes CHANGED
@@ -78,3 +78,6 @@ coding-0.2/p/latest/checkpoint-9/tokenizer.json filter=lfs diff=lfs merge=lfs -t
78
  math-0.3/q/cold-start/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
79
  math-0.3/q/cold-start/checkpoint-552/tokenizer.json filter=lfs diff=lfs merge=lfs -text
80
  math-0.3/q/cold-start/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
78
  math-0.3/q/cold-start/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
79
  math-0.3/q/cold-start/checkpoint-552/tokenizer.json filter=lfs diff=lfs merge=lfs -text
80
  math-0.3/q/cold-start/tokenizer.json filter=lfs diff=lfs merge=lfs -text
81
+ math-0.3/p/cold-start/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
82
+ math-0.3/p/cold-start/checkpoint-552/tokenizer.json filter=lfs diff=lfs merge=lfs -text
83
+ math-0.3/p/cold-start/tokenizer.json filter=lfs diff=lfs merge=lfs -text
math-0.3/p/cold-start/README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit
3
+ library_name: peft
4
+ model_name: cold-start
5
+ tags:
6
+ - base_model:adapter:unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ - unsloth
12
+ licence: license
13
+ pipeline_tag: text-generation
14
+ ---
15
+
16
+ # Model Card for cold-start
17
+
18
+ This model is a fine-tuned version of [unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit](https://huggingface.co/unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit).
19
+ It has been trained using [TRL](https://github.com/huggingface/trl).
20
+
21
+ ## Quick start
22
+
23
+ ```python
24
+ from transformers import pipeline
25
+
26
+ 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?"
27
+ generator = pipeline("text-generation", model="None", device="cuda")
28
+ output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
29
+ print(output["generated_text"])
30
+ ```
31
+
32
+ ## Training procedure
33
+
34
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/kstaron-/huggingface/runs/t3tzkuab)
35
+
36
+
37
+ This model was trained with SFT.
38
+
39
+ ### Framework versions
40
+
41
+ - PEFT 0.18.0
42
+ - TRL: 0.23.0
43
+ - Transformers: 4.57.1
44
+ - Pytorch: 2.9.0
45
+ - Datasets: 4.3.0
46
+ - Tokenizers: 0.22.1
47
+
48
+ ## Citations
49
+
50
+
51
+
52
+ Cite TRL as:
53
+
54
+ ```bibtex
55
+ @misc{vonwerra2022trl,
56
+ title = {{TRL: Transformer Reinforcement Learning}},
57
+ 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},
58
+ year = 2020,
59
+ journal = {GitHub repository},
60
+ publisher = {GitHub},
61
+ howpublished = {\url{https://github.com/huggingface/trl}}
62
+ }
63
+ ```
math-0.3/p/cold-start/adapter_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "Qwen2ForCausalLM",
7
+ "parent_library": "transformers.models.qwen2.modeling_qwen2",
8
+ "unsloth_fixed": true
9
+ },
10
+ "base_model_name_or_path": "unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit",
11
+ "bias": "none",
12
+ "corda_config": null,
13
+ "ensure_weight_tying": false,
14
+ "eva_config": null,
15
+ "exclude_modules": null,
16
+ "fan_in_fan_out": false,
17
+ "inference_mode": true,
18
+ "init_lora_weights": true,
19
+ "layer_replication": null,
20
+ "layers_pattern": null,
21
+ "layers_to_transform": null,
22
+ "loftq_config": {},
23
+ "lora_alpha": 64,
24
+ "lora_bias": false,
25
+ "lora_dropout": 0,
26
+ "megatron_config": null,
27
+ "megatron_core": "megatron.core",
28
+ "modules_to_save": null,
29
+ "peft_type": "LORA",
30
+ "peft_version": "0.18.0",
31
+ "qalora_group_size": 16,
32
+ "r": 64,
33
+ "rank_pattern": {},
34
+ "revision": null,
35
+ "target_modules": [
36
+ "k_proj",
37
+ "q_proj",
38
+ "v_proj",
39
+ "o_proj",
40
+ "gate_proj",
41
+ "down_proj",
42
+ "up_proj"
43
+ ],
44
+ "target_parameters": null,
45
+ "task_type": "CAUSAL_LM",
46
+ "trainable_token_indices": null,
47
+ "use_dora": false,
48
+ "use_qalora": false,
49
+ "use_rslora": false
50
+ }
math-0.3/p/cold-start/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:775c6ecbb7ebc662ccea7350111655c011bcec604486562fa684dfbe9e5e7ac9
3
+ size 645975704
math-0.3/p/cold-start/chat_template.jinja ADDED
@@ -0,0 +1 @@
 
 
1
+ {% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\n'}}{% endif %}
math-0.3/p/cold-start/checkpoint-500/README.md ADDED
@@ -0,0 +1,210 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ - unsloth
12
+ ---
13
+
14
+ # Model Card for Model ID
15
+
16
+ <!-- Provide a quick summary of what the model is/does. -->
17
+
18
+
19
+
20
+ ## Model Details
21
+
22
+ ### Model Description
23
+
24
+ <!-- Provide a longer summary of what this model is. -->
25
+
26
+
27
+
28
+ - **Developed by:** [More Information Needed]
29
+ - **Funded by [optional]:** [More Information Needed]
30
+ - **Shared by [optional]:** [More Information Needed]
31
+ - **Model type:** [More Information Needed]
32
+ - **Language(s) (NLP):** [More Information Needed]
33
+ - **License:** [More Information Needed]
34
+ - **Finetuned from model [optional]:** [More Information Needed]
35
+
36
+ ### Model Sources [optional]
37
+
38
+ <!-- Provide the basic links for the model. -->
39
+
40
+ - **Repository:** [More Information Needed]
41
+ - **Paper [optional]:** [More Information Needed]
42
+ - **Demo [optional]:** [More Information Needed]
43
+
44
+ ## Uses
45
+
46
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
47
+
48
+ ### Direct Use
49
+
50
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
51
+
52
+ [More Information Needed]
53
+
54
+ ### Downstream Use [optional]
55
+
56
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
57
+
58
+ [More Information Needed]
59
+
60
+ ### Out-of-Scope Use
61
+
62
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
63
+
64
+ [More Information Needed]
65
+
66
+ ## Bias, Risks, and Limitations
67
+
68
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
69
+
70
+ [More Information Needed]
71
+
72
+ ### Recommendations
73
+
74
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
75
+
76
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
77
+
78
+ ## How to Get Started with the Model
79
+
80
+ Use the code below to get started with the model.
81
+
82
+ [More Information Needed]
83
+
84
+ ## Training Details
85
+
86
+ ### Training Data
87
+
88
+ <!-- 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. -->
89
+
90
+ [More Information Needed]
91
+
92
+ ### Training Procedure
93
+
94
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
95
+
96
+ #### Preprocessing [optional]
97
+
98
+ [More Information Needed]
99
+
100
+
101
+ #### Training Hyperparameters
102
+
103
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
104
+
105
+ #### Speeds, Sizes, Times [optional]
106
+
107
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
108
+
109
+ [More Information Needed]
110
+
111
+ ## Evaluation
112
+
113
+ <!-- This section describes the evaluation protocols and provides the results. -->
114
+
115
+ ### Testing Data, Factors & Metrics
116
+
117
+ #### Testing Data
118
+
119
+ <!-- This should link to a Dataset Card if possible. -->
120
+
121
+ [More Information Needed]
122
+
123
+ #### Factors
124
+
125
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
126
+
127
+ [More Information Needed]
128
+
129
+ #### Metrics
130
+
131
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
132
+
133
+ [More Information Needed]
134
+
135
+ ### Results
136
+
137
+ [More Information Needed]
138
+
139
+ #### Summary
140
+
141
+
142
+
143
+ ## Model Examination [optional]
144
+
145
+ <!-- Relevant interpretability work for the model goes here -->
146
+
147
+ [More Information Needed]
148
+
149
+ ## Environmental Impact
150
+
151
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
152
+
153
+ 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).
154
+
155
+ - **Hardware Type:** [More Information Needed]
156
+ - **Hours used:** [More Information Needed]
157
+ - **Cloud Provider:** [More Information Needed]
158
+ - **Compute Region:** [More Information Needed]
159
+ - **Carbon Emitted:** [More Information Needed]
160
+
161
+ ## Technical Specifications [optional]
162
+
163
+ ### Model Architecture and Objective
164
+
165
+ [More Information Needed]
166
+
167
+ ### Compute Infrastructure
168
+
169
+ [More Information Needed]
170
+
171
+ #### Hardware
172
+
173
+ [More Information Needed]
174
+
175
+ #### Software
176
+
177
+ [More Information Needed]
178
+
179
+ ## Citation [optional]
180
+
181
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
182
+
183
+ **BibTeX:**
184
+
185
+ [More Information Needed]
186
+
187
+ **APA:**
188
+
189
+ [More Information Needed]
190
+
191
+ ## Glossary [optional]
192
+
193
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
194
+
195
+ [More Information Needed]
196
+
197
+ ## More Information [optional]
198
+
199
+ [More Information Needed]
200
+
201
+ ## Model Card Authors [optional]
202
+
203
+ [More Information Needed]
204
+
205
+ ## Model Card Contact
206
+
207
+ [More Information Needed]
208
+ ### Framework versions
209
+
210
+ - PEFT 0.18.0
math-0.3/p/cold-start/checkpoint-500/adapter_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "Qwen2ForCausalLM",
7
+ "parent_library": "transformers.models.qwen2.modeling_qwen2",
8
+ "unsloth_fixed": true
9
+ },
10
+ "base_model_name_or_path": "unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit",
11
+ "bias": "none",
12
+ "corda_config": null,
13
+ "ensure_weight_tying": false,
14
+ "eva_config": null,
15
+ "exclude_modules": null,
16
+ "fan_in_fan_out": false,
17
+ "inference_mode": true,
18
+ "init_lora_weights": true,
19
+ "layer_replication": null,
20
+ "layers_pattern": null,
21
+ "layers_to_transform": null,
22
+ "loftq_config": {},
23
+ "lora_alpha": 64,
24
+ "lora_bias": false,
25
+ "lora_dropout": 0,
26
+ "megatron_config": null,
27
+ "megatron_core": "megatron.core",
28
+ "modules_to_save": null,
29
+ "peft_type": "LORA",
30
+ "peft_version": "0.18.0",
31
+ "qalora_group_size": 16,
32
+ "r": 64,
33
+ "rank_pattern": {},
34
+ "revision": null,
35
+ "target_modules": [
36
+ "k_proj",
37
+ "q_proj",
38
+ "v_proj",
39
+ "o_proj",
40
+ "gate_proj",
41
+ "down_proj",
42
+ "up_proj"
43
+ ],
44
+ "target_parameters": null,
45
+ "task_type": "CAUSAL_LM",
46
+ "trainable_token_indices": null,
47
+ "use_dora": false,
48
+ "use_qalora": false,
49
+ "use_rslora": false
50
+ }
math-0.3/p/cold-start/checkpoint-500/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a002a73c1980b1bac3e6b5caa80f774cee891e12035b81fe823f1961ba7b0cb
3
+ size 645975704
math-0.3/p/cold-start/checkpoint-500/chat_template.jinja ADDED
@@ -0,0 +1 @@
 
 
1
+ {% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\n'}}{% endif %}
math-0.3/p/cold-start/checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fdcf9e99dffd6d21f015fb07e89660c72cf65925f288a373a207e5866f5cc62
3
+ size 1292182139
math-0.3/p/cold-start/checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
3
+ size 14645
math-0.3/p/cold-start/checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12ee79043f31eb49d1a4e02f98b7f34ebd2e507e24da998fcc93e6498acae7f7
3
+ size 1465
math-0.3/p/cold-start/checkpoint-500/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<｜begin▁of▁sentence｜>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<｜end▁of▁sentence｜>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|vision_pad|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
math-0.3/p/cold-start/checkpoint-500/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
3
+ size 11422778
math-0.3/p/cold-start/checkpoint-500/tokenizer_config.json ADDED
@@ -0,0 +1,195 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "151643": {
7
+ "content": "<｜end▁of▁sentence｜>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "151644": {
15
+ "content": "<｜User｜>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": false
21
+ },
22
+ "151645": {
23
+ "content": "<｜Assistant｜>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "151646": {
31
+ "content": "<｜begin▁of▁sentence｜>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "151647": {
39
+ "content": "<|EOT|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "151648": {
47
+ "content": "<think>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "151649": {
55
+ "content": "</think>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "151650": {
63
+ "content": "<|quad_start|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "151651": {
71
+ "content": "<|quad_end|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "151652": {
79
+ "content": "<|vision_start|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "151653": {
87
+ "content": "<|vision_end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "151654": {
95
+ "content": "<|vision_pad|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "151655": {
103
+ "content": "<|image_pad|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "151656": {
111
+ "content": "<|video_pad|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "151657": {
119
+ "content": "<tool_call>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "151658": {
127
+ "content": "</tool_call>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "151659": {
135
+ "content": "<|fim_prefix|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "151660": {
143
+ "content": "<|fim_middle|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "151661": {
151
+ "content": "<|fim_suffix|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "151662": {
159
+ "content": "<|fim_pad|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "151663": {
167
+ "content": "<|repo_name|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "151664": {
175
+ "content": "<|file_sep|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ }
182
+ },
183
+ "bos_token": "<｜begin▁of▁sentence｜>",
184
+ "clean_up_tokenization_spaces": false,
185
+ "eos_token": "<｜end▁of▁sentence｜>",
186
+ "extra_special_tokens": {},
187
+ "legacy": true,
188
+ "model_max_length": 131072,
189
+ "pad_token": "<|vision_pad|>",
190
+ "padding_side": "right",
191
+ "sp_model_kwargs": {},
192
+ "tokenizer_class": "LlamaTokenizerFast",
193
+ "unk_token": null,
194
+ "use_default_system_prompt": false
195
+ }
math-0.3/p/cold-start/checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,741 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.9066183136899365,
6
+ "eval_steps": 500,
7
+ "global_step": 500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.001813236627379873,
14
+ "grad_norm": 0.32559794187545776,
15
+ "learning_rate": 0.0,
16
+ "loss": 1.1023,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.009066183136899365,
21
+ "grad_norm": 0.29812943935394287,
22
+ "learning_rate": 1e-05,
23
+ "loss": 1.1046,
24
+ "step": 5
25
+ },
26
+ {
27
+ "epoch": 0.01813236627379873,
28
+ "grad_norm": 0.2801274061203003,
29
+ "learning_rate": 2.25e-05,
30
+ "loss": 1.0997,
31
+ "step": 10
32
+ },
33
+ {
34
+ "epoch": 0.027198549410698096,
35
+ "grad_norm": 0.19948753714561462,
36
+ "learning_rate": 3.5e-05,
37
+ "loss": 1.0394,
38
+ "step": 15
39
+ },
40
+ {
41
+ "epoch": 0.03626473254759746,
42
+ "grad_norm": 0.12331172078847885,
43
+ "learning_rate": 4.75e-05,
44
+ "loss": 0.9135,
45
+ "step": 20
46
+ },
47
+ {
48
+ "epoch": 0.04533091568449683,
49
+ "grad_norm": 0.11969640851020813,
50
+ "learning_rate": 4.9624060150375936e-05,
51
+ "loss": 0.8191,
52
+ "step": 25
53
+ },
54
+ {
55
+ "epoch": 0.05439709882139619,
56
+ "grad_norm": 0.1015240028500557,
57
+ "learning_rate": 4.915413533834587e-05,
58
+ "loss": 0.7368,
59
+ "step": 30
60
+ },
61
+ {
62
+ "epoch": 0.06346328195829556,
63
+ "grad_norm": 0.07616749405860901,
64
+ "learning_rate": 4.868421052631579e-05,
65
+ "loss": 0.6848,
66
+ "step": 35
67
+ },
68
+ {
69
+ "epoch": 0.07252946509519492,
70
+ "grad_norm": 0.06857508420944214,
71
+ "learning_rate": 4.8214285714285716e-05,
72
+ "loss": 0.6354,
73
+ "step": 40
74
+ },
75
+ {
76
+ "epoch": 0.0815956482320943,
77
+ "grad_norm": 0.060289449989795685,
78
+ "learning_rate": 4.774436090225564e-05,
79
+ "loss": 0.6077,
80
+ "step": 45
81
+ },
82
+ {
83
+ "epoch": 0.09066183136899365,
84
+ "grad_norm": 0.056147947907447815,
85
+ "learning_rate": 4.7274436090225564e-05,
86
+ "loss": 0.5874,
87
+ "step": 50
88
+ },
89
+ {
90
+ "epoch": 0.09972801450589303,
91
+ "grad_norm": 0.05264071375131607,
92
+ "learning_rate": 4.680451127819549e-05,
93
+ "loss": 0.5679,
94
+ "step": 55
95
+ },
96
+ {
97
+ "epoch": 0.10879419764279238,
98
+ "grad_norm": 0.06020241603255272,
99
+ "learning_rate": 4.633458646616541e-05,
100
+ "loss": 0.5549,
101
+ "step": 60
102
+ },
103
+ {
104
+ "epoch": 0.11786038077969176,
105
+ "grad_norm": 0.047356948256492615,
106
+ "learning_rate": 4.586466165413534e-05,
107
+ "loss": 0.5372,
108
+ "step": 65
109
+ },
110
+ {
111
+ "epoch": 0.12692656391659113,
112
+ "grad_norm": 0.047810982912778854,
113
+ "learning_rate": 4.539473684210527e-05,
114
+ "loss": 0.529,
115
+ "step": 70
116
+ },
117
+ {
118
+ "epoch": 0.1359927470534905,
119
+ "grad_norm": 0.046162646263837814,
120
+ "learning_rate": 4.492481203007519e-05,
121
+ "loss": 0.5202,
122
+ "step": 75
123
+ },
124
+ {
125
+ "epoch": 0.14505893019038985,
126
+ "grad_norm": 0.06208339333534241,
127
+ "learning_rate": 4.4454887218045117e-05,
128
+ "loss": 0.5129,
129
+ "step": 80
130
+ },
131
+ {
132
+ "epoch": 0.1541251133272892,
133
+ "grad_norm": 0.050565991550683975,
134
+ "learning_rate": 4.398496240601504e-05,
135
+ "loss": 0.5043,
136
+ "step": 85
137
+ },
138
+ {
139
+ "epoch": 0.1631912964641886,
140
+ "grad_norm": 0.05154730752110481,
141
+ "learning_rate": 4.3515037593984965e-05,
142
+ "loss": 0.4998,
143
+ "step": 90
144
+ },
145
+ {
146
+ "epoch": 0.17225747960108795,
147
+ "grad_norm": 0.05497482419013977,
148
+ "learning_rate": 4.304511278195489e-05,
149
+ "loss": 0.4976,
150
+ "step": 95
151
+ },
152
+ {
153
+ "epoch": 0.1813236627379873,
154
+ "grad_norm": 0.048043277114629745,
155
+ "learning_rate": 4.2575187969924814e-05,
156
+ "loss": 0.4987,
157
+ "step": 100
158
+ },
159
+ {
160
+ "epoch": 0.19038984587488667,
161
+ "grad_norm": 0.051109060645103455,
162
+ "learning_rate": 4.210526315789474e-05,
163
+ "loss": 0.4787,
164
+ "step": 105
165
+ },
166
+ {
167
+ "epoch": 0.19945602901178605,
168
+ "grad_norm": 0.0487995482981205,
169
+ "learning_rate": 4.163533834586467e-05,
170
+ "loss": 0.4789,
171
+ "step": 110
172
+ },
173
+ {
174
+ "epoch": 0.2085222121486854,
175
+ "grad_norm": 0.049402639269828796,
176
+ "learning_rate": 4.116541353383459e-05,
177
+ "loss": 0.4788,
178
+ "step": 115
179
+ },
180
+ {
181
+ "epoch": 0.21758839528558477,
182
+ "grad_norm": 0.04871043190360069,
183
+ "learning_rate": 4.069548872180452e-05,
184
+ "loss": 0.4765,
185
+ "step": 120
186
+ },
187
+ {
188
+ "epoch": 0.22665457842248413,
189
+ "grad_norm": 0.06630577892065048,
190
+ "learning_rate": 4.022556390977444e-05,
191
+ "loss": 0.4741,
192
+ "step": 125
193
+ },
194
+ {
195
+ "epoch": 0.2357207615593835,
196
+ "grad_norm": 0.06110614165663719,
197
+ "learning_rate": 3.9755639097744366e-05,
198
+ "loss": 0.4708,
199
+ "step": 130
200
+ },
201
+ {
202
+ "epoch": 0.24478694469628287,
203
+ "grad_norm": 0.05338889732956886,
204
+ "learning_rate": 3.928571428571429e-05,
205
+ "loss": 0.4662,
206
+ "step": 135
207
+ },
208
+ {
209
+ "epoch": 0.25385312783318226,
210
+ "grad_norm": 0.05992528796195984,
211
+ "learning_rate": 3.8815789473684214e-05,
212
+ "loss": 0.4627,
213
+ "step": 140
214
+ },
215
+ {
216
+ "epoch": 0.2629193109700816,
217
+ "grad_norm": 0.07622615247964859,
218
+ "learning_rate": 3.834586466165413e-05,
219
+ "loss": 0.4629,
220
+ "step": 145
221
+ },
222
+ {
223
+ "epoch": 0.271985494106981,
224
+ "grad_norm": 0.060510117560625076,
225
+ "learning_rate": 3.787593984962406e-05,
226
+ "loss": 0.4601,
227
+ "step": 150
228
+ },
229
+ {
230
+ "epoch": 0.2810516772438803,
231
+ "grad_norm": 0.059344738721847534,
232
+ "learning_rate": 3.740601503759399e-05,
233
+ "loss": 0.4498,
234
+ "step": 155
235
+ },
236
+ {
237
+ "epoch": 0.2901178603807797,
238
+ "grad_norm": 0.06325522065162659,
239
+ "learning_rate": 3.693609022556391e-05,
240
+ "loss": 0.4564,
241
+ "step": 160
242
+ },
243
+ {
244
+ "epoch": 0.2991840435176791,
245
+ "grad_norm": 0.06306657940149307,
246
+ "learning_rate": 3.6466165413533835e-05,
247
+ "loss": 0.4546,
248
+ "step": 165
249
+ },
250
+ {
251
+ "epoch": 0.3082502266545784,
252
+ "grad_norm": 0.0640948936343193,
253
+ "learning_rate": 3.599624060150376e-05,
254
+ "loss": 0.4469,
255
+ "step": 170
256
+ },
257
+ {
258
+ "epoch": 0.3173164097914778,
259
+ "grad_norm": 0.06898415833711624,
260
+ "learning_rate": 3.5526315789473684e-05,
261
+ "loss": 0.4469,
262
+ "step": 175
263
+ },
264
+ {
265
+ "epoch": 0.3263825929283772,
266
+ "grad_norm": 0.0648994967341423,
267
+ "learning_rate": 3.505639097744361e-05,
268
+ "loss": 0.4487,
269
+ "step": 180
270
+ },
271
+ {
272
+ "epoch": 0.3354487760652765,
273
+ "grad_norm": 0.06846313178539276,
274
+ "learning_rate": 3.458646616541353e-05,
275
+ "loss": 0.4464,
276
+ "step": 185
277
+ },
278
+ {
279
+ "epoch": 0.3445149592021759,
280
+ "grad_norm": 0.07159385085105896,
281
+ "learning_rate": 3.411654135338346e-05,
282
+ "loss": 0.441,
283
+ "step": 190
284
+ },
285
+ {
286
+ "epoch": 0.3535811423390752,
287
+ "grad_norm": 0.07051601260900497,
288
+ "learning_rate": 3.364661654135339e-05,
289
+ "loss": 0.4381,
290
+ "step": 195
291
+ },
292
+ {
293
+ "epoch": 0.3626473254759746,
294
+ "grad_norm": 0.08660923689603806,
295
+ "learning_rate": 3.317669172932331e-05,
296
+ "loss": 0.4394,
297
+ "step": 200
298
+ },
299
+ {
300
+ "epoch": 0.371713508612874,
301
+ "grad_norm": 0.06971872597932816,
302
+ "learning_rate": 3.2706766917293236e-05,
303
+ "loss": 0.4322,
304
+ "step": 205
305
+ },
306
+ {
307
+ "epoch": 0.38077969174977333,
308
+ "grad_norm": 0.06713417172431946,
309
+ "learning_rate": 3.223684210526316e-05,
310
+ "loss": 0.436,
311
+ "step": 210
312
+ },
313
+ {
314
+ "epoch": 0.3898458748866727,
315
+ "grad_norm": 0.06772839277982712,
316
+ "learning_rate": 3.1766917293233085e-05,
317
+ "loss": 0.4312,
318
+ "step": 215
319
+ },
320
+ {
321
+ "epoch": 0.3989120580235721,
322
+ "grad_norm": 0.07362240552902222,
323
+ "learning_rate": 3.129699248120301e-05,
324
+ "loss": 0.4329,
325
+ "step": 220
326
+ },
327
+ {
328
+ "epoch": 0.40797824116047143,
329
+ "grad_norm": 0.07369028776884079,
330
+ "learning_rate": 3.082706766917293e-05,
331
+ "loss": 0.4288,
332
+ "step": 225
333
+ },
334
+ {
335
+ "epoch": 0.4170444242973708,
336
+ "grad_norm": 0.07055505365133286,
337
+ "learning_rate": 3.0357142857142857e-05,
338
+ "loss": 0.4333,
339
+ "step": 230
340
+ },
341
+ {
342
+ "epoch": 0.42611060743427015,
343
+ "grad_norm": 0.07163503021001816,
344
+ "learning_rate": 2.9887218045112785e-05,
345
+ "loss": 0.4305,
346
+ "step": 235
347
+ },
348
+ {
349
+ "epoch": 0.43517679057116954,
350
+ "grad_norm": 0.08139467984437943,
351
+ "learning_rate": 2.941729323308271e-05,
352
+ "loss": 0.4381,
353
+ "step": 240
354
+ },
355
+ {
356
+ "epoch": 0.4442429737080689,
357
+ "grad_norm": 0.07725156843662262,
358
+ "learning_rate": 2.8947368421052634e-05,
359
+ "loss": 0.4304,
360
+ "step": 245
361
+ },
362
+ {
363
+ "epoch": 0.45330915684496825,
364
+ "grad_norm": 0.08052878081798553,
365
+ "learning_rate": 2.8477443609022558e-05,
366
+ "loss": 0.4296,
367
+ "step": 250
368
+ },
369
+ {
370
+ "epoch": 0.46237533998186764,
371
+ "grad_norm": 0.07770434767007828,
372
+ "learning_rate": 2.8007518796992482e-05,
373
+ "loss": 0.4314,
374
+ "step": 255
375
+ },
376
+ {
377
+ "epoch": 0.471441523118767,
378
+ "grad_norm": 0.07728557288646698,
379
+ "learning_rate": 2.7537593984962406e-05,
380
+ "loss": 0.4299,
381
+ "step": 260
382
+ },
383
+ {
384
+ "epoch": 0.48050770625566636,
385
+ "grad_norm": 0.07462800294160843,
386
+ "learning_rate": 2.706766917293233e-05,
387
+ "loss": 0.4211,
388
+ "step": 265
389
+ },
390
+ {
391
+ "epoch": 0.48957388939256574,
392
+ "grad_norm": 0.07175785303115845,
393
+ "learning_rate": 2.6597744360902255e-05,
394
+ "loss": 0.4275,
395
+ "step": 270
396
+ },
397
+ {
398
+ "epoch": 0.4986400725294651,
399
+ "grad_norm": 0.08664872497320175,
400
+ "learning_rate": 2.6127819548872186e-05,
401
+ "loss": 0.4209,
402
+ "step": 275
403
+ },
404
+ {
405
+ "epoch": 0.5077062556663645,
406
+ "grad_norm": 0.08445928245782852,
407
+ "learning_rate": 2.565789473684211e-05,
408
+ "loss": 0.4247,
409
+ "step": 280
410
+ },
411
+ {
412
+ "epoch": 0.5167724388032638,
413
+ "grad_norm": 0.07289738208055496,
414
+ "learning_rate": 2.5187969924812034e-05,
415
+ "loss": 0.4179,
416
+ "step": 285
417
+ },
418
+ {
419
+ "epoch": 0.5258386219401632,
420
+ "grad_norm": 0.07798238098621368,
421
+ "learning_rate": 2.471804511278196e-05,
422
+ "loss": 0.42,
423
+ "step": 290
424
+ },
425
+ {
426
+ "epoch": 0.5349048050770625,
427
+ "grad_norm": 0.07746660709381104,
428
+ "learning_rate": 2.424812030075188e-05,
429
+ "loss": 0.4217,
430
+ "step": 295
431
+ },
432
+ {
433
+ "epoch": 0.543970988213962,
434
+ "grad_norm": 0.08591870218515396,
435
+ "learning_rate": 2.3778195488721804e-05,
436
+ "loss": 0.4216,
437
+ "step": 300
438
+ },
439
+ {
440
+ "epoch": 0.5530371713508613,
441
+ "grad_norm": 0.07564842700958252,
442
+ "learning_rate": 2.3308270676691728e-05,
443
+ "loss": 0.412,
444
+ "step": 305
445
+ },
446
+ {
447
+ "epoch": 0.5621033544877606,
448
+ "grad_norm": 0.08118732273578644,
449
+ "learning_rate": 2.2838345864661655e-05,
450
+ "loss": 0.4174,
451
+ "step": 310
452
+ },
453
+ {
454
+ "epoch": 0.57116953762466,
455
+ "grad_norm": 0.09017316997051239,
456
+ "learning_rate": 2.236842105263158e-05,
457
+ "loss": 0.4213,
458
+ "step": 315
459
+ },
460
+ {
461
+ "epoch": 0.5802357207615594,
462
+ "grad_norm": 0.07337243854999542,
463
+ "learning_rate": 2.1898496240601504e-05,
464
+ "loss": 0.4144,
465
+ "step": 320
466
+ },
467
+ {
468
+ "epoch": 0.5893019038984587,
469
+ "grad_norm": 0.08444075286388397,
470
+ "learning_rate": 2.1428571428571428e-05,
471
+ "loss": 0.4184,
472
+ "step": 325
473
+ },
474
+ {
475
+ "epoch": 0.5983680870353582,
476
+ "grad_norm": 0.0821065753698349,
477
+ "learning_rate": 2.0958646616541356e-05,
478
+ "loss": 0.4142,
479
+ "step": 330
480
+ },
481
+ {
482
+ "epoch": 0.6074342701722575,
483
+ "grad_norm": 0.08017408847808838,
484
+ "learning_rate": 2.048872180451128e-05,
485
+ "loss": 0.4224,
486
+ "step": 335
487
+ },
488
+ {
489
+ "epoch": 0.6165004533091568,
490
+ "grad_norm": 0.085743747651577,
491
+ "learning_rate": 2.0018796992481204e-05,
492
+ "loss": 0.419,
493
+ "step": 340
494
+ },
495
+ {
496
+ "epoch": 0.6255666364460563,
497
+ "grad_norm": 0.07891443371772766,
498
+ "learning_rate": 1.954887218045113e-05,
499
+ "loss": 0.4128,
500
+ "step": 345
501
+ },
502
+ {
503
+ "epoch": 0.6346328195829556,
504
+ "grad_norm": 0.0849994346499443,
505
+ "learning_rate": 1.9078947368421056e-05,
506
+ "loss": 0.4143,
507
+ "step": 350
508
+ },
509
+ {
510
+ "epoch": 0.6436990027198549,
511
+ "grad_norm": 0.08166390657424927,
512
+ "learning_rate": 1.860902255639098e-05,
513
+ "loss": 0.4188,
514
+ "step": 355
515
+ },
516
+ {
517
+ "epoch": 0.6527651858567544,
518
+ "grad_norm": 0.0809318795800209,
519
+ "learning_rate": 1.81390977443609e-05,
520
+ "loss": 0.418,
521
+ "step": 360
522
+ },
523
+ {
524
+ "epoch": 0.6618313689936537,
525
+ "grad_norm": 0.0838271751999855,
526
+ "learning_rate": 1.7669172932330825e-05,
527
+ "loss": 0.4123,
528
+ "step": 365
529
+ },
530
+ {
531
+ "epoch": 0.670897552130553,
532
+ "grad_norm": 0.09413391351699829,
533
+ "learning_rate": 1.7199248120300753e-05,
534
+ "loss": 0.4078,
535
+ "step": 370
536
+ },
537
+ {
538
+ "epoch": 0.6799637352674524,
539
+ "grad_norm": 0.08566391468048096,
540
+ "learning_rate": 1.6729323308270677e-05,
541
+ "loss": 0.416,
542
+ "step": 375
543
+ },
544
+ {
545
+ "epoch": 0.6890299184043518,
546
+ "grad_norm": 0.08500986546278,
547
+ "learning_rate": 1.62593984962406e-05,
548
+ "loss": 0.4174,
549
+ "step": 380
550
+ },
551
+ {
552
+ "epoch": 0.6980961015412511,
553
+ "grad_norm": 0.08527488261461258,
554
+ "learning_rate": 1.5789473684210526e-05,
555
+ "loss": 0.4106,
556
+ "step": 385
557
+ },
558
+ {
559
+ "epoch": 0.7071622846781505,
560
+ "grad_norm": 0.08039699494838715,
561
+ "learning_rate": 1.5319548872180453e-05,
562
+ "loss": 0.416,
563
+ "step": 390
564
+ },
565
+ {
566
+ "epoch": 0.7162284678150499,
567
+ "grad_norm": 0.08291460573673248,
568
+ "learning_rate": 1.4849624060150378e-05,
569
+ "loss": 0.4134,
570
+ "step": 395
571
+ },
572
+ {
573
+ "epoch": 0.7252946509519492,
574
+ "grad_norm": 0.08170417696237564,
575
+ "learning_rate": 1.4379699248120302e-05,
576
+ "loss": 0.4147,
577
+ "step": 400
578
+ },
579
+ {
580
+ "epoch": 0.7343608340888486,
581
+ "grad_norm": 0.08569934219121933,
582
+ "learning_rate": 1.3909774436090226e-05,
583
+ "loss": 0.4108,
584
+ "step": 405
585
+ },
586
+ {
587
+ "epoch": 0.743427017225748,
588
+ "grad_norm": 0.08079096674919128,
589
+ "learning_rate": 1.3439849624060152e-05,
590
+ "loss": 0.4075,
591
+ "step": 410
592
+ },
593
+ {
594
+ "epoch": 0.7524932003626473,
595
+ "grad_norm": 0.07782750576734543,
596
+ "learning_rate": 1.2969924812030076e-05,
597
+ "loss": 0.4112,
598
+ "step": 415
599
+ },
600
+ {
601
+ "epoch": 0.7615593834995467,
602
+ "grad_norm": 0.08275282382965088,
603
+ "learning_rate": 1.25e-05,
604
+ "loss": 0.4149,
605
+ "step": 420
606
+ },
607
+ {
608
+ "epoch": 0.7706255666364461,
609
+ "grad_norm": 0.08460110425949097,
610
+ "learning_rate": 1.2030075187969925e-05,
611
+ "loss": 0.4095,
612
+ "step": 425
613
+ },
614
+ {
615
+ "epoch": 0.7796917497733454,
616
+ "grad_norm": 0.079898901283741,
617
+ "learning_rate": 1.156015037593985e-05,
618
+ "loss": 0.4073,
619
+ "step": 430
620
+ },
621
+ {
622
+ "epoch": 0.7887579329102448,
623
+ "grad_norm": 0.08102940768003464,
624
+ "learning_rate": 1.1090225563909775e-05,
625
+ "loss": 0.4097,
626
+ "step": 435
627
+ },
628
+ {
629
+ "epoch": 0.7978241160471442,
630
+ "grad_norm": 0.08001130074262619,
631
+ "learning_rate": 1.06203007518797e-05,
632
+ "loss": 0.4136,
633
+ "step": 440
634
+ },
635
+ {
636
+ "epoch": 0.8068902991840435,
637
+ "grad_norm": 0.08235575258731842,
638
+ "learning_rate": 1.0150375939849624e-05,
639
+ "loss": 0.4061,
640
+ "step": 445
641
+ },
642
+ {
643
+ "epoch": 0.8159564823209429,
644
+ "grad_norm": 0.0864020511507988,
645
+ "learning_rate": 9.68045112781955e-06,
646
+ "loss": 0.4094,
647
+ "step": 450
648
+ },
649
+ {
650
+ "epoch": 0.8250226654578422,
651
+ "grad_norm": 0.08643381297588348,
652
+ "learning_rate": 9.210526315789474e-06,
653
+ "loss": 0.4116,
654
+ "step": 455
655
+ },
656
+ {
657
+ "epoch": 0.8340888485947416,
658
+ "grad_norm": 0.07797787338495255,
659
+ "learning_rate": 8.7406015037594e-06,
660
+ "loss": 0.4073,
661
+ "step": 460
662
+ },
663
+ {
664
+ "epoch": 0.843155031731641,
665
+ "grad_norm": 0.09176258742809296,
666
+ "learning_rate": 8.270676691729324e-06,
667
+ "loss": 0.4028,
668
+ "step": 465
669
+ },
670
+ {
671
+ "epoch": 0.8522212148685403,
672
+ "grad_norm": 0.07949892431497574,
673
+ "learning_rate": 7.800751879699248e-06,
674
+ "loss": 0.4046,
675
+ "step": 470
676
+ },
677
+ {
678
+ "epoch": 0.8612873980054397,
679
+ "grad_norm": 0.0852704867720604,
680
+ "learning_rate": 7.330827067669173e-06,
681
+ "loss": 0.4053,
682
+ "step": 475
683
+ },
684
+ {
685
+ "epoch": 0.8703535811423391,
686
+ "grad_norm": 0.08310207724571228,
687
+ "learning_rate": 6.860902255639098e-06,
688
+ "loss": 0.4112,
689
+ "step": 480
690
+ },
691
+ {
692
+ "epoch": 0.8794197642792384,
693
+ "grad_norm": 0.07913096249103546,
694
+ "learning_rate": 6.3909774436090225e-06,
695
+ "loss": 0.4122,
696
+ "step": 485
697
+ },
698
+ {
699
+ "epoch": 0.8884859474161378,
700
+ "grad_norm": 0.08100811392068863,
701
+ "learning_rate": 5.921052631578948e-06,
702
+ "loss": 0.4156,
703
+ "step": 490
704
+ },
705
+ {
706
+ "epoch": 0.8975521305530372,
707
+ "grad_norm": 0.07964250445365906,
708
+ "learning_rate": 5.451127819548872e-06,
709
+ "loss": 0.407,
710
+ "step": 495
711
+ },
712
+ {
713
+ "epoch": 0.9066183136899365,
714
+ "grad_norm": 0.07796282321214676,
715
+ "learning_rate": 4.981203007518797e-06,
716
+ "loss": 0.409,
717
+ "step": 500
718
+ }
719
+ ],
720
+ "logging_steps": 5,
721
+ "max_steps": 552,
722
+ "num_input_tokens_seen": 0,
723
+ "num_train_epochs": 1,
724
+ "save_steps": 500,
725
+ "stateful_callbacks": {
726
+ "TrainerControl": {
727
+ "args": {
728
+ "should_epoch_stop": false,
729
+ "should_evaluate": false,
730
+ "should_log": false,
731
+ "should_save": true,
732
+ "should_training_stop": false
733
+ },
734
+ "attributes": {}
735
+ }
736
+ },
737
+ "total_flos": 3.5547217133568e+18,
738
+ "train_batch_size": 80,
739
+ "trial_name": null,
740
+ "trial_params": null
741
+ }
math-0.3/p/cold-start/checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d58294bcb2b96e45d069b5a2d500b17bd396424ac12f0714873873c68417f5e8
3
+ size 6289
math-0.3/p/cold-start/checkpoint-552/README.md ADDED
@@ -0,0 +1,210 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ - unsloth
12
+ ---
13
+
14
+ # Model Card for Model ID
15
+
16
+ <!-- Provide a quick summary of what the model is/does. -->
17
+
18
+
19
+
20
+ ## Model Details
21
+
22
+ ### Model Description
23
+
24
+ <!-- Provide a longer summary of what this model is. -->
25
+
26
+
27
+
28
+ - **Developed by:** [More Information Needed]
29
+ - **Funded by [optional]:** [More Information Needed]
30
+ - **Shared by [optional]:** [More Information Needed]
31
+ - **Model type:** [More Information Needed]
32
+ - **Language(s) (NLP):** [More Information Needed]
33
+ - **License:** [More Information Needed]
34
+ - **Finetuned from model [optional]:** [More Information Needed]
35
+
36
+ ### Model Sources [optional]
37
+
38
+ <!-- Provide the basic links for the model. -->
39
+
40
+ - **Repository:** [More Information Needed]
41
+ - **Paper [optional]:** [More Information Needed]
42
+ - **Demo [optional]:** [More Information Needed]
43
+
44
+ ## Uses
45
+
46
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
47
+
48
+ ### Direct Use
49
+
50
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
51
+
52
+ [More Information Needed]
53
+
54
+ ### Downstream Use [optional]
55
+
56
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
57
+
58
+ [More Information Needed]
59
+
60
+ ### Out-of-Scope Use
61
+
62
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
63
+
64
+ [More Information Needed]
65
+
66
+ ## Bias, Risks, and Limitations
67
+
68
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
69
+
70
+ [More Information Needed]
71
+
72
+ ### Recommendations
73
+
74
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
75
+
76
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
77
+
78
+ ## How to Get Started with the Model
79
+
80
+ Use the code below to get started with the model.
81
+
82
+ [More Information Needed]
83
+
84
+ ## Training Details
85
+
86
+ ### Training Data
87
+
88
+ <!-- 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. -->
89
+
90
+ [More Information Needed]
91
+
92
+ ### Training Procedure
93
+
94
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
95
+
96
+ #### Preprocessing [optional]
97
+
98
+ [More Information Needed]
99
+
100
+
101
+ #### Training Hyperparameters
102
+
103
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
104
+
105
+ #### Speeds, Sizes, Times [optional]
106
+
107
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
108
+
109
+ [More Information Needed]
110
+
111
+ ## Evaluation
112
+
113
+ <!-- This section describes the evaluation protocols and provides the results. -->
114
+
115
+ ### Testing Data, Factors & Metrics
116
+
117
+ #### Testing Data
118
+
119
+ <!-- This should link to a Dataset Card if possible. -->
120
+
121
+ [More Information Needed]
122
+
123
+ #### Factors
124
+
125
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
126
+
127
+ [More Information Needed]
128
+
129
+ #### Metrics
130
+
131
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
132
+
133
+ [More Information Needed]
134
+
135
+ ### Results
136
+
137
+ [More Information Needed]
138
+
139
+ #### Summary
140
+
141
+
142
+
143
+ ## Model Examination [optional]
144
+
145
+ <!-- Relevant interpretability work for the model goes here -->
146
+
147
+ [More Information Needed]
148
+
149
+ ## Environmental Impact
150
+
151
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
152
+
153
+ 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).
154
+
155
+ - **Hardware Type:** [More Information Needed]
156
+ - **Hours used:** [More Information Needed]
157
+ - **Cloud Provider:** [More Information Needed]
158
+ - **Compute Region:** [More Information Needed]
159
+ - **Carbon Emitted:** [More Information Needed]
160
+
161
+ ## Technical Specifications [optional]
162
+
163
+ ### Model Architecture and Objective
164
+
165
+ [More Information Needed]
166
+
167
+ ### Compute Infrastructure
168
+
169
+ [More Information Needed]
170
+
171
+ #### Hardware
172
+
173
+ [More Information Needed]
174
+
175
+ #### Software
176
+
177
+ [More Information Needed]
178
+
179
+ ## Citation [optional]
180
+
181
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
182
+
183
+ **BibTeX:**
184
+
185
+ [More Information Needed]
186
+
187
+ **APA:**
188
+
189
+ [More Information Needed]
190
+
191
+ ## Glossary [optional]
192
+
193
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
194
+
195
+ [More Information Needed]
196
+
197
+ ## More Information [optional]
198
+
199
+ [More Information Needed]
200
+
201
+ ## Model Card Authors [optional]
202
+
203
+ [More Information Needed]
204
+
205
+ ## Model Card Contact
206
+
207
+ [More Information Needed]
208
+ ### Framework versions
209
+
210
+ - PEFT 0.18.0
math-0.3/p/cold-start/checkpoint-552/adapter_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "Qwen2ForCausalLM",
7
+ "parent_library": "transformers.models.qwen2.modeling_qwen2",
8
+ "unsloth_fixed": true
9
+ },
10
+ "base_model_name_or_path": "unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit",
11
+ "bias": "none",
12
+ "corda_config": null,
13
+ "ensure_weight_tying": false,
14
+ "eva_config": null,
15
+ "exclude_modules": null,
16
+ "fan_in_fan_out": false,
17
+ "inference_mode": true,
18
+ "init_lora_weights": true,
19
+ "layer_replication": null,
20
+ "layers_pattern": null,
21
+ "layers_to_transform": null,
22
+ "loftq_config": {},
23
+ "lora_alpha": 64,
24
+ "lora_bias": false,
25
+ "lora_dropout": 0,
26
+ "megatron_config": null,
27
+ "megatron_core": "megatron.core",
28
+ "modules_to_save": null,
29
+ "peft_type": "LORA",
30
+ "peft_version": "0.18.0",
31
+ "qalora_group_size": 16,
32
+ "r": 64,
33
+ "rank_pattern": {},
34
+ "revision": null,
35
+ "target_modules": [
36
+ "k_proj",
37
+ "q_proj",
38
+ "v_proj",
39
+ "o_proj",
40
+ "gate_proj",
41
+ "down_proj",
42
+ "up_proj"
43
+ ],
44
+ "target_parameters": null,
45
+ "task_type": "CAUSAL_LM",
46
+ "trainable_token_indices": null,
47
+ "use_dora": false,
48
+ "use_qalora": false,
49
+ "use_rslora": false
50
+ }
math-0.3/p/cold-start/checkpoint-552/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:775c6ecbb7ebc662ccea7350111655c011bcec604486562fa684dfbe9e5e7ac9
3
+ size 645975704
math-0.3/p/cold-start/checkpoint-552/chat_template.jinja ADDED
@@ -0,0 +1 @@
 
 
1
+ {% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\n'}}{% endif %}
math-0.3/p/cold-start/checkpoint-552/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf28e0dae248663bdba2073a06b5b0389b90cda1adf60f7f8b1bf313910a4d1c
3
+ size 1292182139
math-0.3/p/cold-start/checkpoint-552/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
3
+ size 14645
math-0.3/p/cold-start/checkpoint-552/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b569a6ef6e8eaaf868e02bd0c05974d7a6e565263830e0d485c37c528de7f98
3
+ size 1465
math-0.3/p/cold-start/checkpoint-552/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<｜begin▁of▁sentence｜>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<｜end▁of▁sentence｜>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|vision_pad|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
math-0.3/p/cold-start/checkpoint-552/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
3
+ size 11422778
math-0.3/p/cold-start/checkpoint-552/tokenizer_config.json ADDED
@@ -0,0 +1,195 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "151643": {
7
+ "content": "<｜end▁of▁sentence｜>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "151644": {
15
+ "content": "<｜User｜>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": false
21
+ },
22
+ "151645": {
23
+ "content": "<｜Assistant｜>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "151646": {
31
+ "content": "<｜begin▁of▁sentence｜>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "151647": {
39
+ "content": "<|EOT|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "151648": {
47
+ "content": "<think>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "151649": {
55
+ "content": "</think>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "151650": {
63
+ "content": "<|quad_start|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "151651": {
71
+ "content": "<|quad_end|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "151652": {
79
+ "content": "<|vision_start|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "151653": {
87
+ "content": "<|vision_end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "151654": {
95
+ "content": "<|vision_pad|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "151655": {
103
+ "content": "<|image_pad|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "151656": {
111
+ "content": "<|video_pad|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "151657": {
119
+ "content": "<tool_call>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "151658": {
127
+ "content": "</tool_call>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "151659": {
135
+ "content": "<|fim_prefix|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "151660": {
143
+ "content": "<|fim_middle|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "151661": {
151
+ "content": "<|fim_suffix|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "151662": {
159
+ "content": "<|fim_pad|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "151663": {
167
+ "content": "<|repo_name|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "151664": {
175
+ "content": "<|file_sep|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ }
182
+ },
183
+ "bos_token": "<｜begin▁of▁sentence｜>",
184
+ "clean_up_tokenization_spaces": false,
185
+ "eos_token": "<｜end▁of▁sentence｜>",
186
+ "extra_special_tokens": {},
187
+ "legacy": true,
188
+ "model_max_length": 131072,
189
+ "pad_token": "<|vision_pad|>",
190
+ "padding_side": "right",
191
+ "sp_model_kwargs": {},
192
+ "tokenizer_class": "LlamaTokenizerFast",
193
+ "unk_token": null,
194
+ "use_default_system_prompt": false
195
+ }
math-0.3/p/cold-start/checkpoint-552/trainer_state.json ADDED
@@ -0,0 +1,811 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 552,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.001813236627379873,
14
+ "grad_norm": 0.32559794187545776,
15
+ "learning_rate": 0.0,
16
+ "loss": 1.1023,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.009066183136899365,
21
+ "grad_norm": 0.29812943935394287,
22
+ "learning_rate": 1e-05,
23
+ "loss": 1.1046,
24
+ "step": 5
25
+ },
26
+ {
27
+ "epoch": 0.01813236627379873,
28
+ "grad_norm": 0.2801274061203003,
29
+ "learning_rate": 2.25e-05,
30
+ "loss": 1.0997,
31
+ "step": 10
32
+ },
33
+ {
34
+ "epoch": 0.027198549410698096,
35
+ "grad_norm": 0.19948753714561462,
36
+ "learning_rate": 3.5e-05,
37
+ "loss": 1.0394,
38
+ "step": 15
39
+ },
40
+ {
41
+ "epoch": 0.03626473254759746,
42
+ "grad_norm": 0.12331172078847885,
43
+ "learning_rate": 4.75e-05,
44
+ "loss": 0.9135,
45
+ "step": 20
46
+ },
47
+ {
48
+ "epoch": 0.04533091568449683,
49
+ "grad_norm": 0.11969640851020813,
50
+ "learning_rate": 4.9624060150375936e-05,
51
+ "loss": 0.8191,
52
+ "step": 25
53
+ },
54
+ {
55
+ "epoch": 0.05439709882139619,
56
+ "grad_norm": 0.1015240028500557,
57
+ "learning_rate": 4.915413533834587e-05,
58
+ "loss": 0.7368,
59
+ "step": 30
60
+ },
61
+ {
62
+ "epoch": 0.06346328195829556,
63
+ "grad_norm": 0.07616749405860901,
64
+ "learning_rate": 4.868421052631579e-05,
65
+ "loss": 0.6848,
66
+ "step": 35
67
+ },
68
+ {
69
+ "epoch": 0.07252946509519492,
70
+ "grad_norm": 0.06857508420944214,
71
+ "learning_rate": 4.8214285714285716e-05,
72
+ "loss": 0.6354,
73
+ "step": 40
74
+ },
75
+ {
76
+ "epoch": 0.0815956482320943,
77
+ "grad_norm": 0.060289449989795685,
78
+ "learning_rate": 4.774436090225564e-05,
79
+ "loss": 0.6077,
80
+ "step": 45
81
+ },
82
+ {
83
+ "epoch": 0.09066183136899365,
84
+ "grad_norm": 0.056147947907447815,
85
+ "learning_rate": 4.7274436090225564e-05,
86
+ "loss": 0.5874,
87
+ "step": 50
88
+ },
89
+ {
90
+ "epoch": 0.09972801450589303,
91
+ "grad_norm": 0.05264071375131607,
92
+ "learning_rate": 4.680451127819549e-05,
93
+ "loss": 0.5679,
94
+ "step": 55
95
+ },
96
+ {
97
+ "epoch": 0.10879419764279238,
98
+ "grad_norm": 0.06020241603255272,
99
+ "learning_rate": 4.633458646616541e-05,
100
+ "loss": 0.5549,
101
+ "step": 60
102
+ },
103
+ {
104
+ "epoch": 0.11786038077969176,
105
+ "grad_norm": 0.047356948256492615,
106
+ "learning_rate": 4.586466165413534e-05,
107
+ "loss": 0.5372,
108
+ "step": 65
109
+ },
110
+ {
111
+ "epoch": 0.12692656391659113,
112
+ "grad_norm": 0.047810982912778854,
113
+ "learning_rate": 4.539473684210527e-05,
114
+ "loss": 0.529,
115
+ "step": 70
116
+ },
117
+ {
118
+ "epoch": 0.1359927470534905,
119
+ "grad_norm": 0.046162646263837814,
120
+ "learning_rate": 4.492481203007519e-05,
121
+ "loss": 0.5202,
122
+ "step": 75
123
+ },
124
+ {
125
+ "epoch": 0.14505893019038985,
126
+ "grad_norm": 0.06208339333534241,
127
+ "learning_rate": 4.4454887218045117e-05,
128
+ "loss": 0.5129,
129
+ "step": 80
130
+ },
131
+ {
132
+ "epoch": 0.1541251133272892,
133
+ "grad_norm": 0.050565991550683975,
134
+ "learning_rate": 4.398496240601504e-05,
135
+ "loss": 0.5043,
136
+ "step": 85
137
+ },
138
+ {
139
+ "epoch": 0.1631912964641886,
140
+ "grad_norm": 0.05154730752110481,
141
+ "learning_rate": 4.3515037593984965e-05,
142
+ "loss": 0.4998,
143
+ "step": 90
144
+ },
145
+ {
146
+ "epoch": 0.17225747960108795,
147
+ "grad_norm": 0.05497482419013977,
148
+ "learning_rate": 4.304511278195489e-05,
149
+ "loss": 0.4976,
150
+ "step": 95
151
+ },
152
+ {
153
+ "epoch": 0.1813236627379873,
154
+ "grad_norm": 0.048043277114629745,
155
+ "learning_rate": 4.2575187969924814e-05,
156
+ "loss": 0.4987,
157
+ "step": 100
158
+ },
159
+ {
160
+ "epoch": 0.19038984587488667,
161
+ "grad_norm": 0.051109060645103455,
162
+ "learning_rate": 4.210526315789474e-05,
163
+ "loss": 0.4787,
164
+ "step": 105
165
+ },
166
+ {
167
+ "epoch": 0.19945602901178605,
168
+ "grad_norm": 0.0487995482981205,
169
+ "learning_rate": 4.163533834586467e-05,
170
+ "loss": 0.4789,
171
+ "step": 110
172
+ },
173
+ {
174
+ "epoch": 0.2085222121486854,
175
+ "grad_norm": 0.049402639269828796,
176
+ "learning_rate": 4.116541353383459e-05,
177
+ "loss": 0.4788,
178
+ "step": 115
179
+ },
180
+ {
181
+ "epoch": 0.21758839528558477,
182
+ "grad_norm": 0.04871043190360069,
183
+ "learning_rate": 4.069548872180452e-05,
184
+ "loss": 0.4765,
185
+ "step": 120
186
+ },
187
+ {
188
+ "epoch": 0.22665457842248413,
189
+ "grad_norm": 0.06630577892065048,
190
+ "learning_rate": 4.022556390977444e-05,
191
+ "loss": 0.4741,
192
+ "step": 125
193
+ },
194
+ {
195
+ "epoch": 0.2357207615593835,
196
+ "grad_norm": 0.06110614165663719,
197
+ "learning_rate": 3.9755639097744366e-05,
198
+ "loss": 0.4708,
199
+ "step": 130
200
+ },
201
+ {
202
+ "epoch": 0.24478694469628287,
203
+ "grad_norm": 0.05338889732956886,
204
+ "learning_rate": 3.928571428571429e-05,
205
+ "loss": 0.4662,
206
+ "step": 135
207
+ },
208
+ {
209
+ "epoch": 0.25385312783318226,
210
+ "grad_norm": 0.05992528796195984,
211
+ "learning_rate": 3.8815789473684214e-05,
212
+ "loss": 0.4627,
213
+ "step": 140
214
+ },
215
+ {
216
+ "epoch": 0.2629193109700816,
217
+ "grad_norm": 0.07622615247964859,
218
+ "learning_rate": 3.834586466165413e-05,
219
+ "loss": 0.4629,
220
+ "step": 145
221
+ },
222
+ {
223
+ "epoch": 0.271985494106981,
224
+ "grad_norm": 0.060510117560625076,
225
+ "learning_rate": 3.787593984962406e-05,
226
+ "loss": 0.4601,
227
+ "step": 150
228
+ },
229
+ {
230
+ "epoch": 0.2810516772438803,
231
+ "grad_norm": 0.059344738721847534,
232
+ "learning_rate": 3.740601503759399e-05,
233
+ "loss": 0.4498,
234
+ "step": 155
235
+ },
236
+ {
237
+ "epoch": 0.2901178603807797,
238
+ "grad_norm": 0.06325522065162659,
239
+ "learning_rate": 3.693609022556391e-05,
240
+ "loss": 0.4564,
241
+ "step": 160
242
+ },
243
+ {
244
+ "epoch": 0.2991840435176791,
245
+ "grad_norm": 0.06306657940149307,
246
+ "learning_rate": 3.6466165413533835e-05,
247
+ "loss": 0.4546,
248
+ "step": 165
249
+ },
250
+ {
251
+ "epoch": 0.3082502266545784,
252
+ "grad_norm": 0.0640948936343193,
253
+ "learning_rate": 3.599624060150376e-05,
254
+ "loss": 0.4469,
255
+ "step": 170
256
+ },
257
+ {
258
+ "epoch": 0.3173164097914778,
259
+ "grad_norm": 0.06898415833711624,
260
+ "learning_rate": 3.5526315789473684e-05,
261
+ "loss": 0.4469,
262
+ "step": 175
263
+ },
264
+ {
265
+ "epoch": 0.3263825929283772,
266
+ "grad_norm": 0.0648994967341423,
267
+ "learning_rate": 3.505639097744361e-05,
268
+ "loss": 0.4487,
269
+ "step": 180
270
+ },
271
+ {
272
+ "epoch": 0.3354487760652765,
273
+ "grad_norm": 0.06846313178539276,
274
+ "learning_rate": 3.458646616541353e-05,
275
+ "loss": 0.4464,
276
+ "step": 185
277
+ },
278
+ {
279
+ "epoch": 0.3445149592021759,
280
+ "grad_norm": 0.07159385085105896,
281
+ "learning_rate": 3.411654135338346e-05,
282
+ "loss": 0.441,
283
+ "step": 190
284
+ },
285
+ {
286
+ "epoch": 0.3535811423390752,
287
+ "grad_norm": 0.07051601260900497,
288
+ "learning_rate": 3.364661654135339e-05,
289
+ "loss": 0.4381,
290
+ "step": 195
291
+ },
292
+ {
293
+ "epoch": 0.3626473254759746,
294
+ "grad_norm": 0.08660923689603806,
295
+ "learning_rate": 3.317669172932331e-05,
296
+ "loss": 0.4394,
297
+ "step": 200
298
+ },
299
+ {
300
+ "epoch": 0.371713508612874,
301
+ "grad_norm": 0.06971872597932816,
302
+ "learning_rate": 3.2706766917293236e-05,
303
+ "loss": 0.4322,
304
+ "step": 205
305
+ },
306
+ {
307
+ "epoch": 0.38077969174977333,
308
+ "grad_norm": 0.06713417172431946,
309
+ "learning_rate": 3.223684210526316e-05,
310
+ "loss": 0.436,
311
+ "step": 210
312
+ },
313
+ {
314
+ "epoch": 0.3898458748866727,
315
+ "grad_norm": 0.06772839277982712,
316
+ "learning_rate": 3.1766917293233085e-05,
317
+ "loss": 0.4312,
318
+ "step": 215
319
+ },
320
+ {
321
+ "epoch": 0.3989120580235721,
322
+ "grad_norm": 0.07362240552902222,
323
+ "learning_rate": 3.129699248120301e-05,
324
+ "loss": 0.4329,
325
+ "step": 220
326
+ },
327
+ {
328
+ "epoch": 0.40797824116047143,
329
+ "grad_norm": 0.07369028776884079,
330
+ "learning_rate": 3.082706766917293e-05,
331
+ "loss": 0.4288,
332
+ "step": 225
333
+ },
334
+ {
335
+ "epoch": 0.4170444242973708,
336
+ "grad_norm": 0.07055505365133286,
337
+ "learning_rate": 3.0357142857142857e-05,
338
+ "loss": 0.4333,
339
+ "step": 230
340
+ },
341
+ {
342
+ "epoch": 0.42611060743427015,
343
+ "grad_norm": 0.07163503021001816,
344
+ "learning_rate": 2.9887218045112785e-05,
345
+ "loss": 0.4305,
346
+ "step": 235
347
+ },
348
+ {
349
+ "epoch": 0.43517679057116954,
350
+ "grad_norm": 0.08139467984437943,
351
+ "learning_rate": 2.941729323308271e-05,
352
+ "loss": 0.4381,
353
+ "step": 240
354
+ },
355
+ {
356
+ "epoch": 0.4442429737080689,
357
+ "grad_norm": 0.07725156843662262,
358
+ "learning_rate": 2.8947368421052634e-05,
359
+ "loss": 0.4304,
360
+ "step": 245
361
+ },
362
+ {
363
+ "epoch": 0.45330915684496825,
364
+ "grad_norm": 0.08052878081798553,
365
+ "learning_rate": 2.8477443609022558e-05,
366
+ "loss": 0.4296,
367
+ "step": 250
368
+ },
369
+ {
370
+ "epoch": 0.46237533998186764,
371
+ "grad_norm": 0.07770434767007828,
372
+ "learning_rate": 2.8007518796992482e-05,
373
+ "loss": 0.4314,
374
+ "step": 255
375
+ },
376
+ {
377
+ "epoch": 0.471441523118767,
378
+ "grad_norm": 0.07728557288646698,
379
+ "learning_rate": 2.7537593984962406e-05,
380
+ "loss": 0.4299,
381
+ "step": 260
382
+ },
383
+ {
384
+ "epoch": 0.48050770625566636,
385
+ "grad_norm": 0.07462800294160843,
386
+ "learning_rate": 2.706766917293233e-05,
387
+ "loss": 0.4211,
388
+ "step": 265
389
+ },
390
+ {
391
+ "epoch": 0.48957388939256574,
392
+ "grad_norm": 0.07175785303115845,
393
+ "learning_rate": 2.6597744360902255e-05,
394
+ "loss": 0.4275,
395
+ "step": 270
396
+ },
397
+ {
398
+ "epoch": 0.4986400725294651,
399
+ "grad_norm": 0.08664872497320175,
400
+ "learning_rate": 2.6127819548872186e-05,
401
+ "loss": 0.4209,
402
+ "step": 275
403
+ },
404
+ {
405
+ "epoch": 0.5077062556663645,
406
+ "grad_norm": 0.08445928245782852,
407
+ "learning_rate": 2.565789473684211e-05,
408
+ "loss": 0.4247,
409
+ "step": 280
410
+ },
411
+ {
412
+ "epoch": 0.5167724388032638,
413
+ "grad_norm": 0.07289738208055496,
414
+ "learning_rate": 2.5187969924812034e-05,
415
+ "loss": 0.4179,
416
+ "step": 285
417
+ },
418
+ {
419
+ "epoch": 0.5258386219401632,
420
+ "grad_norm": 0.07798238098621368,
421
+ "learning_rate": 2.471804511278196e-05,
422
+ "loss": 0.42,
423
+ "step": 290
424
+ },
425
+ {
426
+ "epoch": 0.5349048050770625,
427
+ "grad_norm": 0.07746660709381104,
428
+ "learning_rate": 2.424812030075188e-05,
429
+ "loss": 0.4217,
430
+ "step": 295
431
+ },
432
+ {
433
+ "epoch": 0.543970988213962,
434
+ "grad_norm": 0.08591870218515396,
435
+ "learning_rate": 2.3778195488721804e-05,
436
+ "loss": 0.4216,
437
+ "step": 300
438
+ },
439
+ {
440
+ "epoch": 0.5530371713508613,
441
+ "grad_norm": 0.07564842700958252,
442
+ "learning_rate": 2.3308270676691728e-05,
443
+ "loss": 0.412,
444
+ "step": 305
445
+ },
446
+ {
447
+ "epoch": 0.5621033544877606,
448
+ "grad_norm": 0.08118732273578644,
449
+ "learning_rate": 2.2838345864661655e-05,
450
+ "loss": 0.4174,
451
+ "step": 310
452
+ },
453
+ {
454
+ "epoch": 0.57116953762466,
455
+ "grad_norm": 0.09017316997051239,
456
+ "learning_rate": 2.236842105263158e-05,
457
+ "loss": 0.4213,
458
+ "step": 315
459
+ },
460
+ {
461
+ "epoch": 0.5802357207615594,
462
+ "grad_norm": 0.07337243854999542,
463
+ "learning_rate": 2.1898496240601504e-05,
464
+ "loss": 0.4144,
465
+ "step": 320
466
+ },
467
+ {
468
+ "epoch": 0.5893019038984587,
469
+ "grad_norm": 0.08444075286388397,
470
+ "learning_rate": 2.1428571428571428e-05,
471
+ "loss": 0.4184,
472
+ "step": 325
473
+ },
474
+ {
475
+ "epoch": 0.5983680870353582,
476
+ "grad_norm": 0.0821065753698349,
477
+ "learning_rate": 2.0958646616541356e-05,
478
+ "loss": 0.4142,
479
+ "step": 330
480
+ },
481
+ {
482
+ "epoch": 0.6074342701722575,
483
+ "grad_norm": 0.08017408847808838,
484
+ "learning_rate": 2.048872180451128e-05,
485
+ "loss": 0.4224,
486
+ "step": 335
487
+ },
488
+ {
489
+ "epoch": 0.6165004533091568,
490
+ "grad_norm": 0.085743747651577,
491
+ "learning_rate": 2.0018796992481204e-05,
492
+ "loss": 0.419,
493
+ "step": 340
494
+ },
495
+ {
496
+ "epoch": 0.6255666364460563,
497
+ "grad_norm": 0.07891443371772766,
498
+ "learning_rate": 1.954887218045113e-05,
499
+ "loss": 0.4128,
500
+ "step": 345
501
+ },
502
+ {
503
+ "epoch": 0.6346328195829556,
504
+ "grad_norm": 0.0849994346499443,
505
+ "learning_rate": 1.9078947368421056e-05,
506
+ "loss": 0.4143,
507
+ "step": 350
508
+ },
509
+ {
510
+ "epoch": 0.6436990027198549,
511
+ "grad_norm": 0.08166390657424927,
512
+ "learning_rate": 1.860902255639098e-05,
513
+ "loss": 0.4188,
514
+ "step": 355
515
+ },
516
+ {
517
+ "epoch": 0.6527651858567544,
518
+ "grad_norm": 0.0809318795800209,
519
+ "learning_rate": 1.81390977443609e-05,
520
+ "loss": 0.418,
521
+ "step": 360
522
+ },
523
+ {
524
+ "epoch": 0.6618313689936537,
525
+ "grad_norm": 0.0838271751999855,
526
+ "learning_rate": 1.7669172932330825e-05,
527
+ "loss": 0.4123,
528
+ "step": 365
529
+ },
530
+ {
531
+ "epoch": 0.670897552130553,
532
+ "grad_norm": 0.09413391351699829,
533
+ "learning_rate": 1.7199248120300753e-05,
534
+ "loss": 0.4078,
535
+ "step": 370
536
+ },
537
+ {
538
+ "epoch": 0.6799637352674524,
539
+ "grad_norm": 0.08566391468048096,
540
+ "learning_rate": 1.6729323308270677e-05,
541
+ "loss": 0.416,
542
+ "step": 375
543
+ },
544
+ {
545
+ "epoch": 0.6890299184043518,
546
+ "grad_norm": 0.08500986546278,
547
+ "learning_rate": 1.62593984962406e-05,
548
+ "loss": 0.4174,
549
+ "step": 380
550
+ },
551
+ {
552
+ "epoch": 0.6980961015412511,
553
+ "grad_norm": 0.08527488261461258,
554
+ "learning_rate": 1.5789473684210526e-05,
555
+ "loss": 0.4106,
556
+ "step": 385
557
+ },
558
+ {
559
+ "epoch": 0.7071622846781505,
560
+ "grad_norm": 0.08039699494838715,
561
+ "learning_rate": 1.5319548872180453e-05,
562
+ "loss": 0.416,
563
+ "step": 390
564
+ },
565
+ {
566
+ "epoch": 0.7162284678150499,
567
+ "grad_norm": 0.08291460573673248,
568
+ "learning_rate": 1.4849624060150378e-05,
569
+ "loss": 0.4134,
570
+ "step": 395
571
+ },
572
+ {
573
+ "epoch": 0.7252946509519492,
574
+ "grad_norm": 0.08170417696237564,
575
+ "learning_rate": 1.4379699248120302e-05,
576
+ "loss": 0.4147,
577
+ "step": 400
578
+ },
579
+ {
580
+ "epoch": 0.7343608340888486,
581
+ "grad_norm": 0.08569934219121933,
582
+ "learning_rate": 1.3909774436090226e-05,
583
+ "loss": 0.4108,
584
+ "step": 405
585
+ },
586
+ {
587
+ "epoch": 0.743427017225748,
588
+ "grad_norm": 0.08079096674919128,
589
+ "learning_rate": 1.3439849624060152e-05,
590
+ "loss": 0.4075,
591
+ "step": 410
592
+ },
593
+ {
594
+ "epoch": 0.7524932003626473,
595
+ "grad_norm": 0.07782750576734543,
596
+ "learning_rate": 1.2969924812030076e-05,
597
+ "loss": 0.4112,
598
+ "step": 415
599
+ },
600
+ {
601
+ "epoch": 0.7615593834995467,
602
+ "grad_norm": 0.08275282382965088,
603
+ "learning_rate": 1.25e-05,
604
+ "loss": 0.4149,
605
+ "step": 420
606
+ },
607
+ {
608
+ "epoch": 0.7706255666364461,
609
+ "grad_norm": 0.08460110425949097,
610
+ "learning_rate": 1.2030075187969925e-05,
611
+ "loss": 0.4095,
612
+ "step": 425
613
+ },
614
+ {
615
+ "epoch": 0.7796917497733454,
616
+ "grad_norm": 0.079898901283741,
617
+ "learning_rate": 1.156015037593985e-05,
618
+ "loss": 0.4073,
619
+ "step": 430
620
+ },
621
+ {
622
+ "epoch": 0.7887579329102448,
623
+ "grad_norm": 0.08102940768003464,
624
+ "learning_rate": 1.1090225563909775e-05,
625
+ "loss": 0.4097,
626
+ "step": 435
627
+ },
628
+ {
629
+ "epoch": 0.7978241160471442,
630
+ "grad_norm": 0.08001130074262619,
631
+ "learning_rate": 1.06203007518797e-05,
632
+ "loss": 0.4136,
633
+ "step": 440
634
+ },
635
+ {
636
+ "epoch": 0.8068902991840435,
637
+ "grad_norm": 0.08235575258731842,
638
+ "learning_rate": 1.0150375939849624e-05,
639
+ "loss": 0.4061,
640
+ "step": 445
641
+ },
642
+ {
643
+ "epoch": 0.8159564823209429,
644
+ "grad_norm": 0.0864020511507988,
645
+ "learning_rate": 9.68045112781955e-06,
646
+ "loss": 0.4094,
647
+ "step": 450
648
+ },
649
+ {
650
+ "epoch": 0.8250226654578422,
651
+ "grad_norm": 0.08643381297588348,
652
+ "learning_rate": 9.210526315789474e-06,
653
+ "loss": 0.4116,
654
+ "step": 455
655
+ },
656
+ {
657
+ "epoch": 0.8340888485947416,
658
+ "grad_norm": 0.07797787338495255,
659
+ "learning_rate": 8.7406015037594e-06,
660
+ "loss": 0.4073,
661
+ "step": 460
662
+ },
663
+ {
664
+ "epoch": 0.843155031731641,
665
+ "grad_norm": 0.09176258742809296,
666
+ "learning_rate": 8.270676691729324e-06,
667
+ "loss": 0.4028,
668
+ "step": 465
669
+ },
670
+ {
671
+ "epoch": 0.8522212148685403,
672
+ "grad_norm": 0.07949892431497574,
673
+ "learning_rate": 7.800751879699248e-06,
674
+ "loss": 0.4046,
675
+ "step": 470
676
+ },
677
+ {
678
+ "epoch": 0.8612873980054397,
679
+ "grad_norm": 0.0852704867720604,
680
+ "learning_rate": 7.330827067669173e-06,
681
+ "loss": 0.4053,
682
+ "step": 475
683
+ },
684
+ {
685
+ "epoch": 0.8703535811423391,
686
+ "grad_norm": 0.08310207724571228,
687
+ "learning_rate": 6.860902255639098e-06,
688
+ "loss": 0.4112,
689
+ "step": 480
690
+ },
691
+ {
692
+ "epoch": 0.8794197642792384,
693
+ "grad_norm": 0.07913096249103546,
694
+ "learning_rate": 6.3909774436090225e-06,
695
+ "loss": 0.4122,
696
+ "step": 485
697
+ },
698
+ {
699
+ "epoch": 0.8884859474161378,
700
+ "grad_norm": 0.08100811392068863,
701
+ "learning_rate": 5.921052631578948e-06,
702
+ "loss": 0.4156,
703
+ "step": 490
704
+ },
705
+ {
706
+ "epoch": 0.8975521305530372,
707
+ "grad_norm": 0.07964250445365906,
708
+ "learning_rate": 5.451127819548872e-06,
709
+ "loss": 0.407,
710
+ "step": 495
711
+ },
712
+ {
713
+ "epoch": 0.9066183136899365,
714
+ "grad_norm": 0.07796282321214676,
715
+ "learning_rate": 4.981203007518797e-06,
716
+ "loss": 0.409,
717
+ "step": 500
718
+ },
719
+ {
720
+ "epoch": 0.915684496826836,
721
+ "grad_norm": 0.07809992134571075,
722
+ "learning_rate": 4.511278195488722e-06,
723
+ "loss": 0.4083,
724
+ "step": 505
725
+ },
726
+ {
727
+ "epoch": 0.9247506799637353,
728
+ "grad_norm": 0.08220049738883972,
729
+ "learning_rate": 4.041353383458646e-06,
730
+ "loss": 0.4062,
731
+ "step": 510
732
+ },
733
+ {
734
+ "epoch": 0.9338168631006346,
735
+ "grad_norm": 0.07960949093103409,
736
+ "learning_rate": 3.5714285714285714e-06,
737
+ "loss": 0.4118,
738
+ "step": 515
739
+ },
740
+ {
741
+ "epoch": 0.942883046237534,
742
+ "grad_norm": 0.07664569467306137,
743
+ "learning_rate": 3.101503759398496e-06,
744
+ "loss": 0.4018,
745
+ "step": 520
746
+ },
747
+ {
748
+ "epoch": 0.9519492293744334,
749
+ "grad_norm": 0.07770106196403503,
750
+ "learning_rate": 2.631578947368421e-06,
751
+ "loss": 0.4087,
752
+ "step": 525
753
+ },
754
+ {
755
+ "epoch": 0.9610154125113327,
756
+ "grad_norm": 0.07898158580064774,
757
+ "learning_rate": 2.1616541353383458e-06,
758
+ "loss": 0.4075,
759
+ "step": 530
760
+ },
761
+ {
762
+ "epoch": 0.970081595648232,
763
+ "grad_norm": 0.07946480810642242,
764
+ "learning_rate": 1.6917293233082707e-06,
765
+ "loss": 0.4108,
766
+ "step": 535
767
+ },
768
+ {
769
+ "epoch": 0.9791477787851315,
770
+ "grad_norm": 0.07512401789426804,
771
+ "learning_rate": 1.2218045112781955e-06,
772
+ "loss": 0.4069,
773
+ "step": 540
774
+ },
775
+ {
776
+ "epoch": 0.9882139619220308,
777
+ "grad_norm": 0.07899699360132217,
778
+ "learning_rate": 7.518796992481203e-07,
779
+ "loss": 0.4058,
780
+ "step": 545
781
+ },
782
+ {
783
+ "epoch": 0.9972801450589301,
784
+ "grad_norm": 0.0774671658873558,
785
+ "learning_rate": 2.8195488721804513e-07,
786
+ "loss": 0.4053,
787
+ "step": 550
788
+ }
789
+ ],
790
+ "logging_steps": 5,
791
+ "max_steps": 552,
792
+ "num_input_tokens_seen": 0,
793
+ "num_train_epochs": 1,
794
+ "save_steps": 500,
795
+ "stateful_callbacks": {
796
+ "TrainerControl": {
797
+ "args": {
798
+ "should_epoch_stop": false,
799
+ "should_evaluate": false,
800
+ "should_log": false,
801
+ "should_save": true,
802
+ "should_training_stop": true
803
+ },
804
+ "attributes": {}
805
+ }
806
+ },
807
+ "total_flos": 3.918147574526116e+18,
808
+ "train_batch_size": 80,
809
+ "trial_name": null,
810
+ "trial_params": null
811
+ }
math-0.3/p/cold-start/checkpoint-552/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d58294bcb2b96e45d069b5a2d500b17bd396424ac12f0714873873c68417f5e8
3
+ size 6289
math-0.3/p/cold-start/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<｜begin▁of▁sentence｜>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<｜end▁of▁sentence｜>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|vision_pad|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
math-0.3/p/cold-start/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
3
+ size 11422778
math-0.3/p/cold-start/tokenizer_config.json ADDED
@@ -0,0 +1,195 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "151643": {
7
+ "content": "<｜end▁of▁sentence｜>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "151644": {
15
+ "content": "<｜User｜>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": false
21
+ },
22
+ "151645": {
23
+ "content": "<｜Assistant｜>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "151646": {
31
+ "content": "<｜begin▁of▁sentence｜>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "151647": {
39
+ "content": "<|EOT|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "151648": {
47
+ "content": "<think>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "151649": {
55
+ "content": "</think>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "151650": {
63
+ "content": "<|quad_start|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "151651": {
71
+ "content": "<|quad_end|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "151652": {
79
+ "content": "<|vision_start|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "151653": {
87
+ "content": "<|vision_end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "151654": {
95
+ "content": "<|vision_pad|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "151655": {
103
+ "content": "<|image_pad|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "151656": {
111
+ "content": "<|video_pad|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "151657": {
119
+ "content": "<tool_call>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "151658": {
127
+ "content": "</tool_call>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "151659": {
135
+ "content": "<|fim_prefix|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "151660": {
143
+ "content": "<|fim_middle|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "151661": {
151
+ "content": "<|fim_suffix|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "151662": {
159
+ "content": "<|fim_pad|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "151663": {
167
+ "content": "<|repo_name|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "151664": {
175
+ "content": "<|file_sep|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ }
182
+ },
183
+ "bos_token": "<｜begin▁of▁sentence｜>",
184
+ "clean_up_tokenization_spaces": false,
185
+ "eos_token": "<｜end▁of▁sentence｜>",
186
+ "extra_special_tokens": {},
187
+ "legacy": true,
188
+ "model_max_length": 131072,
189
+ "pad_token": "<|vision_pad|>",
190
+ "padding_side": "left",
191
+ "sp_model_kwargs": {},
192
+ "tokenizer_class": "LlamaTokenizerFast",
193
+ "unk_token": null,
194
+ "use_default_system_prompt": false
195
+ }