Hugging Face's logo

airesearch
/
Qwen3-30B-A3B-Base-medqa-seed-2405

PEFT
Safetensors
qwen3_moe
llama-factory
lora
Generated from Trainer
Model card Files
xet
Community
PumeTu commited on
Commit
2f08073
·
verified ·
1 Parent(s): 05b1c75

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +1 -0
  2. Modelfile +14 -0
  3. README.md +72 -0
  4. adapter_config.json +40 -0
  5. adapter_model.safetensors +3 -0
  6. added_tokens.json +28 -0
  7. all_results.json +12 -0
  8. chat_template.jinja +85 -0
  9. checkpoint-50/README.md +202 -0
  10. checkpoint-50/adapter_config.json +40 -0
  11. checkpoint-50/added_tokens.json +28 -0
  12. checkpoint-50/chat_template.jinja +85 -0
  13. checkpoint-50/merges.txt +0 -0
  14. checkpoint-50/special_tokens_map.json +31 -0
  15. checkpoint-50/tokenizer_config.json +240 -0
  16. checkpoint-50/trainer_state.json +424 -0
  17. checkpoint-50/vocab.json +0 -0
  18. checkpoint-66/README.md +202 -0
  19. checkpoint-66/adapter_config.json +40 -0
  20. checkpoint-66/added_tokens.json +28 -0
  21. checkpoint-66/chat_template.jinja +85 -0
  22. checkpoint-66/merges.txt +0 -0
  23. checkpoint-66/special_tokens_map.json +31 -0
  24. checkpoint-66/tokenizer_config.json +240 -0
  25. checkpoint-66/trainer_state.json +544 -0
  26. checkpoint-66/vocab.json +0 -0
  27. config.json +38 -0
  28. dataset/dataset_dict.json +1 -0
  29. dataset/train/dataset_info.json +67 -0
  30. dataset/train/state.json +13 -0
  31. dataset/validation/dataset_info.json +67 -0
  32. dataset/validation/state.json +13 -0
  33. eval_results.json +7 -0
  34. generation_config.json +6 -0
  35. merges.txt +0 -0
  36. model-00002-of-00025.safetensors +3 -0
  37. model-00006-of-00025.safetensors +3 -0
  38. model-00007-of-00025.safetensors +3 -0
  39. model-00009-of-00025.safetensors +3 -0
  40. model-00013-of-00025.safetensors +3 -0
  41. model.safetensors.index.json +0 -0
  42. special_tokens_map.json +31 -0
  43. tokenizer.json +3 -0
  44. tokenizer_config.json +240 -0
  45. train_results.json +8 -0
  46. trainer_log.jsonl +73 -0
  47. trainer_state.json +553 -0
  48. training_args.bin +3 -0
  49. training_eval_loss.png +0 -0
  50. training_loss.png +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
Modelfile ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # ollama modelfile auto-generated by llamafactory
2
+
3
+ FROM .
4
+
5
+ TEMPLATE """{{ if .System }}<|im_start|>system
6
+ {{ .System }}<|im_end|>
7
+ {{ end }}{{ range .Messages }}{{ if eq .Role "user" }}<|im_start|>user
8
+ {{ .Content }}<|im_end|>
9
+ <|im_start|>assistant
10
+ {{ else if eq .Role "assistant" }}{{ .Content }}<|im_end|>
11
+ {{ end }}{{ end }}"""
12
+
13
+ PARAMETER stop "<|im_end|>"
14
+ PARAMETER num_ctx 4096
README.md ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: other
4
+ base_model: Qwen/Qwen3-30B-A3B-Base
5
+ tags:
6
+ - llama-factory
7
+ - lora
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: Qwen3-30B-A3B-Base-medqa-seed-2405
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # Qwen3-30B-A3B-Base-medqa-seed-2405
18
+
19
+ This model is a fine-tuned version of [Qwen/Qwen3-30B-A3B-Base](https://huggingface.co//Qwen/Qwen3-30B-A3B-Base) on the medqa dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.0279
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 0.0002
41
+ - train_batch_size: 2
42
+ - eval_batch_size: 2
43
+ - seed: 2405
44
+ - distributed_type: multi-GPU
45
+ - num_devices: 128
46
+ - gradient_accumulation_steps: 8
47
+ - total_train_batch_size: 2048
48
+ - total_eval_batch_size: 256
49
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
50
+ - lr_scheduler_type: cosine
51
+ - lr_scheduler_warmup_ratio: 0.1
52
+ - num_epochs: 3.0
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss |
57
+ |:-------------:|:------:|:----:|:---------------:|
58
+ | 2.0528 | 0.4651 | 10 | 1.8944 |
59
+ | 0.316 | 0.9302 | 20 | 0.1930 |
60
+ | 0.0322 | 1.3721 | 30 | 0.0318 |
61
+ | 0.0229 | 1.8372 | 40 | 0.0289 |
62
+ | 0.0206 | 2.2791 | 50 | 0.0280 |
63
+ | 0.0238 | 2.7442 | 60 | 0.0280 |
64
+
65
+
66
+ ### Framework versions
67
+
68
+ - PEFT 0.15.2
69
+ - Transformers 4.52.3
70
+ - Pytorch 2.7.0+cu126
71
+ - Datasets 3.6.0
72
+ - Tokenizers 0.21.1
adapter_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/project/lt200252-wcbart/pumet/models/Qwen3-30B-A3B-Base",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 8,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "gate_proj",
28
+ "v_proj",
29
+ "k_proj",
30
+ "o_proj",
31
+ "up_proj",
32
+ "q_proj",
33
+ "gate",
34
+ "down_proj"
35
+ ],
36
+ "task_type": "CAUSAL_LM",
37
+ "trainable_token_indices": null,
38
+ "use_dora": false,
39
+ "use_rslora": false
40
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:340197495a170155e3b15ba43590e835f9ae193aa43a5d60b742cff593704723
3
+ size 1696378232
added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 0.027905410155653954,
4
+ "eval_runtime": 143.3555,
5
+ "eval_samples_per_second": 34.097,
6
+ "eval_steps_per_second": 0.14,
7
+ "total_flos": 4.4321989464330076e+18,
8
+ "train_loss": 0.7241760994674582,
9
+ "train_runtime": 13313.2011,
10
+ "train_samples_per_second": 9.912,
11
+ "train_steps_per_second": 0.005
12
+ }
chat_template.jinja ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
27
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
28
+ {%- elif message.role == "assistant" %}
29
+ {%- set content = message.content %}
30
+ {%- set reasoning_content = '' %}
31
+ {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
32
+ {%- set reasoning_content = message.reasoning_content %}
33
+ {%- else %}
34
+ {%- if '</think>' in message.content %}
35
+ {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
36
+ {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
37
+ {%- endif %}
38
+ {%- endif %}
39
+ {%- if loop.index0 > ns.last_query_index %}
40
+ {%- if loop.last or (not loop.last and reasoning_content) %}
41
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
42
+ {%- else %}
43
+ {{- '<|im_start|>' + message.role + '\n' + content }}
44
+ {%- endif %}
45
+ {%- else %}
46
+ {{- '<|im_start|>' + message.role + '\n' + content }}
47
+ {%- endif %}
48
+ {%- if message.tool_calls %}
49
+ {%- for tool_call in message.tool_calls %}
50
+ {%- if (loop.first and content) or (not loop.first) %}
51
+ {{- '\n' }}
52
+ {%- endif %}
53
+ {%- if tool_call.function %}
54
+ {%- set tool_call = tool_call.function %}
55
+ {%- endif %}
56
+ {{- '<tool_call>\n{"name": "' }}
57
+ {{- tool_call.name }}
58
+ {{- '", "arguments": ' }}
59
+ {%- if tool_call.arguments is string %}
60
+ {{- tool_call.arguments }}
61
+ {%- else %}
62
+ {{- tool_call.arguments | tojson }}
63
+ {%- endif %}
64
+ {{- '}\n</tool_call>' }}
65
+ {%- endfor %}
66
+ {%- endif %}
67
+ {{- '<|im_end|>\n' }}
68
+ {%- elif message.role == "tool" %}
69
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
70
+ {{- '<|im_start|>user' }}
71
+ {%- endif %}
72
+ {{- '\n<tool_response>\n' }}
73
+ {{- message.content }}
74
+ {{- '\n</tool_response>' }}
75
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
76
+ {{- '<|im_end|>\n' }}
77
+ {%- endif %}
78
+ {%- endif %}
79
+ {%- endfor %}
80
+ {%- if add_generation_prompt %}
81
+ {{- '<|im_start|>assistant\n' }}
82
+ {%- if enable_thinking is defined and enable_thinking is false %}
83
+ {{- '<think>\n\n</think>\n\n' }}
84
+ {%- endif %}
85
+ {%- endif %}
checkpoint-50/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: /project/lt200252-wcbart/pumet/models/Qwen3-30B-A3B-Base
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.15.2
checkpoint-50/adapter_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/project/lt200252-wcbart/pumet/models/Qwen3-30B-A3B-Base",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 8,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "gate_proj",
28
+ "v_proj",
29
+ "k_proj",
30
+ "o_proj",
31
+ "up_proj",
32
+ "q_proj",
33
+ "gate",
34
+ "down_proj"
35
+ ],
36
+ "task_type": "CAUSAL_LM",
37
+ "trainable_token_indices": null,
38
+ "use_dora": false,
39
+ "use_rslora": false
40
+ }
checkpoint-50/added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
checkpoint-50/chat_template.jinja ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
27
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
28
+ {%- elif message.role == "assistant" %}
29
+ {%- set content = message.content %}
30
+ {%- set reasoning_content = '' %}
31
+ {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
32
+ {%- set reasoning_content = message.reasoning_content %}
33
+ {%- else %}
34
+ {%- if '</think>' in message.content %}
35
+ {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
36
+ {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
37
+ {%- endif %}
38
+ {%- endif %}
39
+ {%- if loop.index0 > ns.last_query_index %}
40
+ {%- if loop.last or (not loop.last and reasoning_content) %}
41
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
42
+ {%- else %}
43
+ {{- '<|im_start|>' + message.role + '\n' + content }}
44
+ {%- endif %}
45
+ {%- else %}
46
+ {{- '<|im_start|>' + message.role + '\n' + content }}
47
+ {%- endif %}
48
+ {%- if message.tool_calls %}
49
+ {%- for tool_call in message.tool_calls %}
50
+ {%- if (loop.first and content) or (not loop.first) %}
51
+ {{- '\n' }}
52
+ {%- endif %}
53
+ {%- if tool_call.function %}
54
+ {%- set tool_call = tool_call.function %}
55
+ {%- endif %}
56
+ {{- '<tool_call>\n{"name": "' }}
57
+ {{- tool_call.name }}
58
+ {{- '", "arguments": ' }}
59
+ {%- if tool_call.arguments is string %}
60
+ {{- tool_call.arguments }}
61
+ {%- else %}
62
+ {{- tool_call.arguments | tojson }}
63
+ {%- endif %}
64
+ {{- '}\n</tool_call>' }}
65
+ {%- endfor %}
66
+ {%- endif %}
67
+ {{- '<|im_end|>\n' }}
68
+ {%- elif message.role == "tool" %}
69
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
70
+ {{- '<|im_start|>user' }}
71
+ {%- endif %}
72
+ {{- '\n<tool_response>\n' }}
73
+ {{- message.content }}
74
+ {{- '\n</tool_response>' }}
75
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
76
+ {{- '<|im_end|>\n' }}
77
+ {%- endif %}
78
+ {%- endif %}
79
+ {%- endfor %}
80
+ {%- if add_generation_prompt %}
81
+ {{- '<|im_start|>assistant\n' }}
82
+ {%- if enable_thinking is defined and enable_thinking is false %}
83
+ {{- '<think>\n\n</think>\n\n' }}
84
+ {%- endif %}
85
+ {%- endif %}
checkpoint-50/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-50/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
checkpoint-50/tokenizer_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 131072,
235
+ "pad_token": "<|endoftext|>",
236
+ "padding_side": "right",
237
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2Tokenizer",
239
+ "unk_token": null
240
+ }
checkpoint-50/trainer_state.json ADDED
@@ -0,0 +1,424 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.2790697674418605,
6
+ "eval_steps": 10,
7
+ "global_step": 50,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.046511627906976744,
14
+ "grad_norm": 3.328749895095825,
15
+ "learning_rate": 0.0,
16
+ "loss": 4.5983,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.09302325581395349,
21
+ "grad_norm": 3.354735851287842,
22
+ "learning_rate": 2.857142857142857e-05,
23
+ "loss": 4.5836,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.13953488372093023,
28
+ "grad_norm": 2.9163668155670166,
29
+ "learning_rate": 5.714285714285714e-05,
30
+ "loss": 4.397,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.18604651162790697,
35
+ "grad_norm": 2.2333481311798096,
36
+ "learning_rate": 8.571428571428571e-05,
37
+ "loss": 4.1457,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.23255813953488372,
42
+ "grad_norm": 1.991350769996643,
43
+ "learning_rate": 0.00011428571428571428,
44
+ "loss": 3.9002,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.27906976744186046,
49
+ "grad_norm": 1.85317063331604,
50
+ "learning_rate": 0.00014285714285714287,
51
+ "loss": 3.5969,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.32558139534883723,
56
+ "grad_norm": 1.9501370191574097,
57
+ "learning_rate": 0.00017142857142857143,
58
+ "loss": 3.2651,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.37209302325581395,
63
+ "grad_norm": 2.216587543487549,
64
+ "learning_rate": 0.0002,
65
+ "loss": 2.8473,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.4186046511627907,
70
+ "grad_norm": 2.0312318801879883,
71
+ "learning_rate": 0.0001998582695676762,
72
+ "loss": 2.3923,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.46511627906976744,
77
+ "grad_norm": 1.8019684553146362,
78
+ "learning_rate": 0.00019943348002101371,
79
+ "loss": 2.0528,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.46511627906976744,
84
+ "eval_loss": 1.894411325454712,
85
+ "eval_runtime": 145.4733,
86
+ "eval_samples_per_second": 33.601,
87
+ "eval_steps_per_second": 0.137,
88
+ "step": 10
89
+ },
90
+ {
91
+ "epoch": 0.5116279069767442,
92
+ "grad_norm": 1.951332449913025,
93
+ "learning_rate": 0.00019872683547213446,
94
+ "loss": 1.7962,
95
+ "step": 11
96
+ },
97
+ {
98
+ "epoch": 0.5581395348837209,
99
+ "grad_norm": 1.5264594554901123,
100
+ "learning_rate": 0.00019774033898178667,
101
+ "loss": 1.5795,
102
+ "step": 12
103
+ },
104
+ {
105
+ "epoch": 0.6046511627906976,
106
+ "grad_norm": 1.0167055130004883,
107
+ "learning_rate": 0.0001964767868814516,
108
+ "loss": 1.4307,
109
+ "step": 13
110
+ },
111
+ {
112
+ "epoch": 0.6511627906976745,
113
+ "grad_norm": 1.1928244829177856,
114
+ "learning_rate": 0.00019493976084683813,
115
+ "loss": 1.3048,
116
+ "step": 14
117
+ },
118
+ {
119
+ "epoch": 0.6976744186046512,
120
+ "grad_norm": 1.513029932975769,
121
+ "learning_rate": 0.00019313361774523385,
122
+ "loss": 1.1708,
123
+ "step": 15
124
+ },
125
+ {
126
+ "epoch": 0.7441860465116279,
127
+ "grad_norm": 1.6432111263275146,
128
+ "learning_rate": 0.00019106347728549135,
129
+ "loss": 1.0173,
130
+ "step": 16
131
+ },
132
+ {
133
+ "epoch": 0.7906976744186046,
134
+ "grad_norm": 1.4672132730484009,
135
+ "learning_rate": 0.00018873520750565718,
136
+ "loss": 0.8399,
137
+ "step": 17
138
+ },
139
+ {
140
+ "epoch": 0.8372093023255814,
141
+ "grad_norm": 1.3380573987960815,
142
+ "learning_rate": 0.0001861554081393806,
143
+ "loss": 0.6508,
144
+ "step": 18
145
+ },
146
+ {
147
+ "epoch": 0.8837209302325582,
148
+ "grad_norm": 1.26139235496521,
149
+ "learning_rate": 0.0001833313919082515,
150
+ "loss": 0.4701,
151
+ "step": 19
152
+ },
153
+ {
154
+ "epoch": 0.9302325581395349,
155
+ "grad_norm": 1.0803511142730713,
156
+ "learning_rate": 0.00018027116379309638,
157
+ "loss": 0.316,
158
+ "step": 20
159
+ },
160
+ {
161
+ "epoch": 0.9302325581395349,
162
+ "eval_loss": 0.19302108883857727,
163
+ "eval_runtime": 145.4827,
164
+ "eval_samples_per_second": 33.598,
165
+ "eval_steps_per_second": 0.137,
166
+ "step": 20
167
+ },
168
+ {
169
+ "epoch": 0.9767441860465116,
170
+ "grad_norm": 0.8388907313346863,
171
+ "learning_rate": 0.00017698339834299061,
172
+ "loss": 0.1865,
173
+ "step": 21
174
+ },
175
+ {
176
+ "epoch": 1.0,
177
+ "grad_norm": 0.6994265913963318,
178
+ "learning_rate": 0.00017347741508630672,
179
+ "loss": 0.1083,
180
+ "step": 22
181
+ },
182
+ {
183
+ "epoch": 1.0465116279069768,
184
+ "grad_norm": 0.266382098197937,
185
+ "learning_rate": 0.0001697631521134985,
186
+ "loss": 0.0619,
187
+ "step": 23
188
+ },
189
+ {
190
+ "epoch": 1.0930232558139534,
191
+ "grad_norm": 0.17738769948482513,
192
+ "learning_rate": 0.00016585113790650388,
193
+ "loss": 0.0463,
194
+ "step": 24
195
+ },
196
+ {
197
+ "epoch": 1.1395348837209303,
198
+ "grad_norm": 0.12172795832157135,
199
+ "learning_rate": 0.0001617524614946192,
200
+ "loss": 0.039,
201
+ "step": 25
202
+ },
203
+ {
204
+ "epoch": 1.1860465116279069,
205
+ "grad_norm": 0.1264028549194336,
206
+ "learning_rate": 0.0001574787410214407,
207
+ "loss": 0.0372,
208
+ "step": 26
209
+ },
210
+ {
211
+ "epoch": 1.2325581395348837,
212
+ "grad_norm": 0.108629010617733,
213
+ "learning_rate": 0.00015304209081197425,
214
+ "loss": 0.0332,
215
+ "step": 27
216
+ },
217
+ {
218
+ "epoch": 1.2790697674418605,
219
+ "grad_norm": 0.0759243443608284,
220
+ "learning_rate": 0.00014845508703326504,
221
+ "loss": 0.0323,
222
+ "step": 28
223
+ },
224
+ {
225
+ "epoch": 1.3255813953488373,
226
+ "grad_norm": 0.06167895719408989,
227
+ "learning_rate": 0.00014373073204588556,
228
+ "loss": 0.0292,
229
+ "step": 29
230
+ },
231
+ {
232
+ "epoch": 1.372093023255814,
233
+ "grad_norm": 0.05063502490520477,
234
+ "learning_rate": 0.00013888241754733208,
235
+ "loss": 0.0322,
236
+ "step": 30
237
+ },
238
+ {
239
+ "epoch": 1.372093023255814,
240
+ "eval_loss": 0.03178785368800163,
241
+ "eval_runtime": 144.6511,
242
+ "eval_samples_per_second": 33.792,
243
+ "eval_steps_per_second": 0.138,
244
+ "step": 30
245
+ },
246
+ {
247
+ "epoch": 1.4186046511627908,
248
+ "grad_norm": 0.05390379950404167,
249
+ "learning_rate": 0.00013392388661180303,
250
+ "loss": 0.0317,
251
+ "step": 31
252
+ },
253
+ {
254
+ "epoch": 1.4651162790697674,
255
+ "grad_norm": 0.05356408655643463,
256
+ "learning_rate": 0.0001288691947339621,
257
+ "loss": 0.0261,
258
+ "step": 32
259
+ },
260
+ {
261
+ "epoch": 1.5116279069767442,
262
+ "grad_norm": 0.039639439433813095,
263
+ "learning_rate": 0.0001237326699871115,
264
+ "loss": 0.0286,
265
+ "step": 33
266
+ },
267
+ {
268
+ "epoch": 1.558139534883721,
269
+ "grad_norm": 0.03714418411254883,
270
+ "learning_rate": 0.00011852887240871145,
271
+ "loss": 0.0279,
272
+ "step": 34
273
+ },
274
+ {
275
+ "epoch": 1.6046511627906976,
276
+ "grad_norm": 0.04030028358101845,
277
+ "learning_rate": 0.00011327255272837221,
278
+ "loss": 0.0265,
279
+ "step": 35
280
+ },
281
+ {
282
+ "epoch": 1.6511627906976745,
283
+ "grad_norm": 0.035650961101055145,
284
+ "learning_rate": 0.00010797861055530831,
285
+ "loss": 0.0253,
286
+ "step": 36
287
+ },
288
+ {
289
+ "epoch": 1.697674418604651,
290
+ "grad_norm": 0.041386678814888,
291
+ "learning_rate": 0.00010266205214377748,
292
+ "loss": 0.0261,
293
+ "step": 37
294
+ },
295
+ {
296
+ "epoch": 1.744186046511628,
297
+ "grad_norm": 0.03318718075752258,
298
+ "learning_rate": 9.733794785622253e-05,
299
+ "loss": 0.0253,
300
+ "step": 38
301
+ },
302
+ {
303
+ "epoch": 1.7906976744186047,
304
+ "grad_norm": 0.03519133850932121,
305
+ "learning_rate": 9.202138944469168e-05,
306
+ "loss": 0.0259,
307
+ "step": 39
308
+ },
309
+ {
310
+ "epoch": 1.8372093023255816,
311
+ "grad_norm": 0.03141423687338829,
312
+ "learning_rate": 8.672744727162781e-05,
313
+ "loss": 0.0229,
314
+ "step": 40
315
+ },
316
+ {
317
+ "epoch": 1.8372093023255816,
318
+ "eval_loss": 0.028911028057336807,
319
+ "eval_runtime": 145.5272,
320
+ "eval_samples_per_second": 33.588,
321
+ "eval_steps_per_second": 0.137,
322
+ "step": 40
323
+ },
324
+ {
325
+ "epoch": 1.8837209302325582,
326
+ "grad_norm": 0.04335688054561615,
327
+ "learning_rate": 8.147112759128859e-05,
328
+ "loss": 0.0246,
329
+ "step": 41
330
+ },
331
+ {
332
+ "epoch": 1.9302325581395348,
333
+ "grad_norm": 0.031896017491817474,
334
+ "learning_rate": 7.626733001288851e-05,
335
+ "loss": 0.0235,
336
+ "step": 42
337
+ },
338
+ {
339
+ "epoch": 1.9767441860465116,
340
+ "grad_norm": 0.03081543557345867,
341
+ "learning_rate": 7.113080526603792e-05,
342
+ "loss": 0.0247,
343
+ "step": 43
344
+ },
345
+ {
346
+ "epoch": 2.0,
347
+ "grad_norm": 0.04796084016561508,
348
+ "learning_rate": 6.607611338819697e-05,
349
+ "loss": 0.0266,
350
+ "step": 44
351
+ },
352
+ {
353
+ "epoch": 2.046511627906977,
354
+ "grad_norm": 0.032496869564056396,
355
+ "learning_rate": 6.111758245266794e-05,
356
+ "loss": 0.0217,
357
+ "step": 45
358
+ },
359
+ {
360
+ "epoch": 2.0930232558139537,
361
+ "grad_norm": 0.03214440867304802,
362
+ "learning_rate": 5.626926795411447e-05,
363
+ "loss": 0.022,
364
+ "step": 46
365
+ },
366
+ {
367
+ "epoch": 2.13953488372093,
368
+ "grad_norm": 0.026299171149730682,
369
+ "learning_rate": 5.1544912966734994e-05,
370
+ "loss": 0.0206,
371
+ "step": 47
372
+ },
373
+ {
374
+ "epoch": 2.186046511627907,
375
+ "grad_norm": 0.02710675820708275,
376
+ "learning_rate": 4.695790918802576e-05,
377
+ "loss": 0.0241,
378
+ "step": 48
379
+ },
380
+ {
381
+ "epoch": 2.2325581395348837,
382
+ "grad_norm": 0.027937039732933044,
383
+ "learning_rate": 4.252125897855932e-05,
384
+ "loss": 0.0213,
385
+ "step": 49
386
+ },
387
+ {
388
+ "epoch": 2.2790697674418605,
389
+ "grad_norm": 0.03069477155804634,
390
+ "learning_rate": 3.824753850538082e-05,
391
+ "loss": 0.0206,
392
+ "step": 50
393
+ },
394
+ {
395
+ "epoch": 2.2790697674418605,
396
+ "eval_loss": 0.02796892449259758,
397
+ "eval_runtime": 144.1386,
398
+ "eval_samples_per_second": 33.912,
399
+ "eval_steps_per_second": 0.139,
400
+ "step": 50
401
+ }
402
+ ],
403
+ "logging_steps": 1.0,
404
+ "max_steps": 66,
405
+ "num_input_tokens_seen": 0,
406
+ "num_train_epochs": 3,
407
+ "save_steps": 50,
408
+ "stateful_callbacks": {
409
+ "TrainerControl": {
410
+ "args": {
411
+ "should_epoch_stop": false,
412
+ "should_evaluate": false,
413
+ "should_log": false,
414
+ "should_save": true,
415
+ "should_training_stop": false
416
+ },
417
+ "attributes": {}
418
+ }
419
+ },
420
+ "total_flos": 3.3684482600405565e+18,
421
+ "train_batch_size": 2,
422
+ "trial_name": null,
423
+ "trial_params": null
424
+ }
checkpoint-50/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-66/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: /project/lt200252-wcbart/pumet/models/Qwen3-30B-A3B-Base
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.15.2
checkpoint-66/adapter_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/project/lt200252-wcbart/pumet/models/Qwen3-30B-A3B-Base",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 8,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "gate_proj",
28
+ "v_proj",
29
+ "k_proj",
30
+ "o_proj",
31
+ "up_proj",
32
+ "q_proj",
33
+ "gate",
34
+ "down_proj"
35
+ ],
36
+ "task_type": "CAUSAL_LM",
37
+ "trainable_token_indices": null,
38
+ "use_dora": false,
39
+ "use_rslora": false
40
+ }
checkpoint-66/added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
checkpoint-66/chat_template.jinja ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
27
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
28
+ {%- elif message.role == "assistant" %}
29
+ {%- set content = message.content %}
30
+ {%- set reasoning_content = '' %}
31
+ {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
32
+ {%- set reasoning_content = message.reasoning_content %}
33
+ {%- else %}
34
+ {%- if '</think>' in message.content %}
35
+ {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
36
+ {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
37
+ {%- endif %}
38
+ {%- endif %}
39
+ {%- if loop.index0 > ns.last_query_index %}
40
+ {%- if loop.last or (not loop.last and reasoning_content) %}
41
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
42
+ {%- else %}
43
+ {{- '<|im_start|>' + message.role + '\n' + content }}
44
+ {%- endif %}
45
+ {%- else %}
46
+ {{- '<|im_start|>' + message.role + '\n' + content }}
47
+ {%- endif %}
48
+ {%- if message.tool_calls %}
49
+ {%- for tool_call in message.tool_calls %}
50
+ {%- if (loop.first and content) or (not loop.first) %}
51
+ {{- '\n' }}
52
+ {%- endif %}
53
+ {%- if tool_call.function %}
54
+ {%- set tool_call = tool_call.function %}
55
+ {%- endif %}
56
+ {{- '<tool_call>\n{"name": "' }}
57
+ {{- tool_call.name }}
58
+ {{- '", "arguments": ' }}
59
+ {%- if tool_call.arguments is string %}
60
+ {{- tool_call.arguments }}
61
+ {%- else %}
62
+ {{- tool_call.arguments | tojson }}
63
+ {%- endif %}
64
+ {{- '}\n</tool_call>' }}
65
+ {%- endfor %}
66
+ {%- endif %}
67
+ {{- '<|im_end|>\n' }}
68
+ {%- elif message.role == "tool" %}
69
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
70
+ {{- '<|im_start|>user' }}
71
+ {%- endif %}
72
+ {{- '\n<tool_response>\n' }}
73
+ {{- message.content }}
74
+ {{- '\n</tool_response>' }}
75
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
76
+ {{- '<|im_end|>\n' }}
77
+ {%- endif %}
78
+ {%- endif %}
79
+ {%- endfor %}
80
+ {%- if add_generation_prompt %}
81
+ {{- '<|im_start|>assistant\n' }}
82
+ {%- if enable_thinking is defined and enable_thinking is false %}
83
+ {{- '<think>\n\n</think>\n\n' }}
84
+ {%- endif %}
85
+ {%- endif %}
checkpoint-66/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-66/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
checkpoint-66/tokenizer_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 131072,
235
+ "pad_token": "<|endoftext|>",
236
+ "padding_side": "right",
237
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2Tokenizer",
239
+ "unk_token": null
240
+ }
checkpoint-66/trainer_state.json ADDED
@@ -0,0 +1,544 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 10,
7
+ "global_step": 66,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.046511627906976744,
14
+ "grad_norm": 3.328749895095825,
15
+ "learning_rate": 0.0,
16
+ "loss": 4.5983,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.09302325581395349,
21
+ "grad_norm": 3.354735851287842,
22
+ "learning_rate": 2.857142857142857e-05,
23
+ "loss": 4.5836,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.13953488372093023,
28
+ "grad_norm": 2.9163668155670166,
29
+ "learning_rate": 5.714285714285714e-05,
30
+ "loss": 4.397,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.18604651162790697,
35
+ "grad_norm": 2.2333481311798096,
36
+ "learning_rate": 8.571428571428571e-05,
37
+ "loss": 4.1457,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.23255813953488372,
42
+ "grad_norm": 1.991350769996643,
43
+ "learning_rate": 0.00011428571428571428,
44
+ "loss": 3.9002,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.27906976744186046,
49
+ "grad_norm": 1.85317063331604,
50
+ "learning_rate": 0.00014285714285714287,
51
+ "loss": 3.5969,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.32558139534883723,
56
+ "grad_norm": 1.9501370191574097,
57
+ "learning_rate": 0.00017142857142857143,
58
+ "loss": 3.2651,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.37209302325581395,
63
+ "grad_norm": 2.216587543487549,
64
+ "learning_rate": 0.0002,
65
+ "loss": 2.8473,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.4186046511627907,
70
+ "grad_norm": 2.0312318801879883,
71
+ "learning_rate": 0.0001998582695676762,
72
+ "loss": 2.3923,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.46511627906976744,
77
+ "grad_norm": 1.8019684553146362,
78
+ "learning_rate": 0.00019943348002101371,
79
+ "loss": 2.0528,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.46511627906976744,
84
+ "eval_loss": 1.894411325454712,
85
+ "eval_runtime": 145.4733,
86
+ "eval_samples_per_second": 33.601,
87
+ "eval_steps_per_second": 0.137,
88
+ "step": 10
89
+ },
90
+ {
91
+ "epoch": 0.5116279069767442,
92
+ "grad_norm": 1.951332449913025,
93
+ "learning_rate": 0.00019872683547213446,
94
+ "loss": 1.7962,
95
+ "step": 11
96
+ },
97
+ {
98
+ "epoch": 0.5581395348837209,
99
+ "grad_norm": 1.5264594554901123,
100
+ "learning_rate": 0.00019774033898178667,
101
+ "loss": 1.5795,
102
+ "step": 12
103
+ },
104
+ {
105
+ "epoch": 0.6046511627906976,
106
+ "grad_norm": 1.0167055130004883,
107
+ "learning_rate": 0.0001964767868814516,
108
+ "loss": 1.4307,
109
+ "step": 13
110
+ },
111
+ {
112
+ "epoch": 0.6511627906976745,
113
+ "grad_norm": 1.1928244829177856,
114
+ "learning_rate": 0.00019493976084683813,
115
+ "loss": 1.3048,
116
+ "step": 14
117
+ },
118
+ {
119
+ "epoch": 0.6976744186046512,
120
+ "grad_norm": 1.513029932975769,
121
+ "learning_rate": 0.00019313361774523385,
122
+ "loss": 1.1708,
123
+ "step": 15
124
+ },
125
+ {
126
+ "epoch": 0.7441860465116279,
127
+ "grad_norm": 1.6432111263275146,
128
+ "learning_rate": 0.00019106347728549135,
129
+ "loss": 1.0173,
130
+ "step": 16
131
+ },
132
+ {
133
+ "epoch": 0.7906976744186046,
134
+ "grad_norm": 1.4672132730484009,
135
+ "learning_rate": 0.00018873520750565718,
136
+ "loss": 0.8399,
137
+ "step": 17
138
+ },
139
+ {
140
+ "epoch": 0.8372093023255814,
141
+ "grad_norm": 1.3380573987960815,
142
+ "learning_rate": 0.0001861554081393806,
143
+ "loss": 0.6508,
144
+ "step": 18
145
+ },
146
+ {
147
+ "epoch": 0.8837209302325582,
148
+ "grad_norm": 1.26139235496521,
149
+ "learning_rate": 0.0001833313919082515,
150
+ "loss": 0.4701,
151
+ "step": 19
152
+ },
153
+ {
154
+ "epoch": 0.9302325581395349,
155
+ "grad_norm": 1.0803511142730713,
156
+ "learning_rate": 0.00018027116379309638,
157
+ "loss": 0.316,
158
+ "step": 20
159
+ },
160
+ {
161
+ "epoch": 0.9302325581395349,
162
+ "eval_loss": 0.19302108883857727,
163
+ "eval_runtime": 145.4827,
164
+ "eval_samples_per_second": 33.598,
165
+ "eval_steps_per_second": 0.137,
166
+ "step": 20
167
+ },
168
+ {
169
+ "epoch": 0.9767441860465116,
170
+ "grad_norm": 0.8388907313346863,
171
+ "learning_rate": 0.00017698339834299061,
172
+ "loss": 0.1865,
173
+ "step": 21
174
+ },
175
+ {
176
+ "epoch": 1.0,
177
+ "grad_norm": 0.6994265913963318,
178
+ "learning_rate": 0.00017347741508630672,
179
+ "loss": 0.1083,
180
+ "step": 22
181
+ },
182
+ {
183
+ "epoch": 1.0465116279069768,
184
+ "grad_norm": 0.266382098197937,
185
+ "learning_rate": 0.0001697631521134985,
186
+ "loss": 0.0619,
187
+ "step": 23
188
+ },
189
+ {
190
+ "epoch": 1.0930232558139534,
191
+ "grad_norm": 0.17738769948482513,
192
+ "learning_rate": 0.00016585113790650388,
193
+ "loss": 0.0463,
194
+ "step": 24
195
+ },
196
+ {
197
+ "epoch": 1.1395348837209303,
198
+ "grad_norm": 0.12172795832157135,
199
+ "learning_rate": 0.0001617524614946192,
200
+ "loss": 0.039,
201
+ "step": 25
202
+ },
203
+ {
204
+ "epoch": 1.1860465116279069,
205
+ "grad_norm": 0.1264028549194336,
206
+ "learning_rate": 0.0001574787410214407,
207
+ "loss": 0.0372,
208
+ "step": 26
209
+ },
210
+ {
211
+ "epoch": 1.2325581395348837,
212
+ "grad_norm": 0.108629010617733,
213
+ "learning_rate": 0.00015304209081197425,
214
+ "loss": 0.0332,
215
+ "step": 27
216
+ },
217
+ {
218
+ "epoch": 1.2790697674418605,
219
+ "grad_norm": 0.0759243443608284,
220
+ "learning_rate": 0.00014845508703326504,
221
+ "loss": 0.0323,
222
+ "step": 28
223
+ },
224
+ {
225
+ "epoch": 1.3255813953488373,
226
+ "grad_norm": 0.06167895719408989,
227
+ "learning_rate": 0.00014373073204588556,
228
+ "loss": 0.0292,
229
+ "step": 29
230
+ },
231
+ {
232
+ "epoch": 1.372093023255814,
233
+ "grad_norm": 0.05063502490520477,
234
+ "learning_rate": 0.00013888241754733208,
235
+ "loss": 0.0322,
236
+ "step": 30
237
+ },
238
+ {
239
+ "epoch": 1.372093023255814,
240
+ "eval_loss": 0.03178785368800163,
241
+ "eval_runtime": 144.6511,
242
+ "eval_samples_per_second": 33.792,
243
+ "eval_steps_per_second": 0.138,
244
+ "step": 30
245
+ },
246
+ {
247
+ "epoch": 1.4186046511627908,
248
+ "grad_norm": 0.05390379950404167,
249
+ "learning_rate": 0.00013392388661180303,
250
+ "loss": 0.0317,
251
+ "step": 31
252
+ },
253
+ {
254
+ "epoch": 1.4651162790697674,
255
+ "grad_norm": 0.05356408655643463,
256
+ "learning_rate": 0.0001288691947339621,
257
+ "loss": 0.0261,
258
+ "step": 32
259
+ },
260
+ {
261
+ "epoch": 1.5116279069767442,
262
+ "grad_norm": 0.039639439433813095,
263
+ "learning_rate": 0.0001237326699871115,
264
+ "loss": 0.0286,
265
+ "step": 33
266
+ },
267
+ {
268
+ "epoch": 1.558139534883721,
269
+ "grad_norm": 0.03714418411254883,
270
+ "learning_rate": 0.00011852887240871145,
271
+ "loss": 0.0279,
272
+ "step": 34
273
+ },
274
+ {
275
+ "epoch": 1.6046511627906976,
276
+ "grad_norm": 0.04030028358101845,
277
+ "learning_rate": 0.00011327255272837221,
278
+ "loss": 0.0265,
279
+ "step": 35
280
+ },
281
+ {
282
+ "epoch": 1.6511627906976745,
283
+ "grad_norm": 0.035650961101055145,
284
+ "learning_rate": 0.00010797861055530831,
285
+ "loss": 0.0253,
286
+ "step": 36
287
+ },
288
+ {
289
+ "epoch": 1.697674418604651,
290
+ "grad_norm": 0.041386678814888,
291
+ "learning_rate": 0.00010266205214377748,
292
+ "loss": 0.0261,
293
+ "step": 37
294
+ },
295
+ {
296
+ "epoch": 1.744186046511628,
297
+ "grad_norm": 0.03318718075752258,
298
+ "learning_rate": 9.733794785622253e-05,
299
+ "loss": 0.0253,
300
+ "step": 38
301
+ },
302
+ {
303
+ "epoch": 1.7906976744186047,
304
+ "grad_norm": 0.03519133850932121,
305
+ "learning_rate": 9.202138944469168e-05,
306
+ "loss": 0.0259,
307
+ "step": 39
308
+ },
309
+ {
310
+ "epoch": 1.8372093023255816,
311
+ "grad_norm": 0.03141423687338829,
312
+ "learning_rate": 8.672744727162781e-05,
313
+ "loss": 0.0229,
314
+ "step": 40
315
+ },
316
+ {
317
+ "epoch": 1.8372093023255816,
318
+ "eval_loss": 0.028911028057336807,
319
+ "eval_runtime": 145.5272,
320
+ "eval_samples_per_second": 33.588,
321
+ "eval_steps_per_second": 0.137,
322
+ "step": 40
323
+ },
324
+ {
325
+ "epoch": 1.8837209302325582,
326
+ "grad_norm": 0.04335688054561615,
327
+ "learning_rate": 8.147112759128859e-05,
328
+ "loss": 0.0246,
329
+ "step": 41
330
+ },
331
+ {
332
+ "epoch": 1.9302325581395348,
333
+ "grad_norm": 0.031896017491817474,
334
+ "learning_rate": 7.626733001288851e-05,
335
+ "loss": 0.0235,
336
+ "step": 42
337
+ },
338
+ {
339
+ "epoch": 1.9767441860465116,
340
+ "grad_norm": 0.03081543557345867,
341
+ "learning_rate": 7.113080526603792e-05,
342
+ "loss": 0.0247,
343
+ "step": 43
344
+ },
345
+ {
346
+ "epoch": 2.0,
347
+ "grad_norm": 0.04796084016561508,
348
+ "learning_rate": 6.607611338819697e-05,
349
+ "loss": 0.0266,
350
+ "step": 44
351
+ },
352
+ {
353
+ "epoch": 2.046511627906977,
354
+ "grad_norm": 0.032496869564056396,
355
+ "learning_rate": 6.111758245266794e-05,
356
+ "loss": 0.0217,
357
+ "step": 45
358
+ },
359
+ {
360
+ "epoch": 2.0930232558139537,
361
+ "grad_norm": 0.03214440867304802,
362
+ "learning_rate": 5.626926795411447e-05,
363
+ "loss": 0.022,
364
+ "step": 46
365
+ },
366
+ {
367
+ "epoch": 2.13953488372093,
368
+ "grad_norm": 0.026299171149730682,
369
+ "learning_rate": 5.1544912966734994e-05,
370
+ "loss": 0.0206,
371
+ "step": 47
372
+ },
373
+ {
374
+ "epoch": 2.186046511627907,
375
+ "grad_norm": 0.02710675820708275,
376
+ "learning_rate": 4.695790918802576e-05,
377
+ "loss": 0.0241,
378
+ "step": 48
379
+ },
380
+ {
381
+ "epoch": 2.2325581395348837,
382
+ "grad_norm": 0.027937039732933044,
383
+ "learning_rate": 4.252125897855932e-05,
384
+ "loss": 0.0213,
385
+ "step": 49
386
+ },
387
+ {
388
+ "epoch": 2.2790697674418605,
389
+ "grad_norm": 0.03069477155804634,
390
+ "learning_rate": 3.824753850538082e-05,
391
+ "loss": 0.0206,
392
+ "step": 50
393
+ },
394
+ {
395
+ "epoch": 2.2790697674418605,
396
+ "eval_loss": 0.02796892449259758,
397
+ "eval_runtime": 144.1386,
398
+ "eval_samples_per_second": 33.912,
399
+ "eval_steps_per_second": 0.139,
400
+ "step": 50
401
+ },
402
+ {
403
+ "epoch": 2.3255813953488373,
404
+ "grad_norm": 0.027339283376932144,
405
+ "learning_rate": 3.414886209349615e-05,
406
+ "loss": 0.0202,
407
+ "step": 51
408
+ },
409
+ {
410
+ "epoch": 2.3720930232558137,
411
+ "grad_norm": 0.02695722132921219,
412
+ "learning_rate": 3.0236847886501542e-05,
413
+ "loss": 0.0214,
414
+ "step": 52
415
+ },
416
+ {
417
+ "epoch": 2.4186046511627906,
418
+ "grad_norm": 0.022607291117310524,
419
+ "learning_rate": 2.6522584913693294e-05,
420
+ "loss": 0.0202,
421
+ "step": 53
422
+ },
423
+ {
424
+ "epoch": 2.4651162790697674,
425
+ "grad_norm": 0.02922969125211239,
426
+ "learning_rate": 2.301660165700936e-05,
427
+ "loss": 0.0225,
428
+ "step": 54
429
+ },
430
+ {
431
+ "epoch": 2.511627906976744,
432
+ "grad_norm": 0.02776559814810753,
433
+ "learning_rate": 1.9728836206903656e-05,
434
+ "loss": 0.0188,
435
+ "step": 55
436
+ },
437
+ {
438
+ "epoch": 2.558139534883721,
439
+ "grad_norm": 0.027599385008215904,
440
+ "learning_rate": 1.6668608091748495e-05,
441
+ "loss": 0.0215,
442
+ "step": 56
443
+ },
444
+ {
445
+ "epoch": 2.604651162790698,
446
+ "grad_norm": 0.02333148941397667,
447
+ "learning_rate": 1.3844591860619383e-05,
448
+ "loss": 0.0197,
449
+ "step": 57
450
+ },
451
+ {
452
+ "epoch": 2.6511627906976747,
453
+ "grad_norm": 0.02748979814350605,
454
+ "learning_rate": 1.1264792494342857e-05,
455
+ "loss": 0.023,
456
+ "step": 58
457
+ },
458
+ {
459
+ "epoch": 2.697674418604651,
460
+ "grad_norm": 0.023095615208148956,
461
+ "learning_rate": 8.936522714508678e-06,
462
+ "loss": 0.021,
463
+ "step": 59
464
+ },
465
+ {
466
+ "epoch": 2.744186046511628,
467
+ "grad_norm": 0.030044227838516235,
468
+ "learning_rate": 6.866382254766157e-06,
469
+ "loss": 0.0238,
470
+ "step": 60
471
+ },
472
+ {
473
+ "epoch": 2.744186046511628,
474
+ "eval_loss": 0.027968447655439377,
475
+ "eval_runtime": 144.4837,
476
+ "eval_samples_per_second": 33.831,
477
+ "eval_steps_per_second": 0.138,
478
+ "step": 60
479
+ },
480
+ {
481
+ "epoch": 2.7906976744186047,
482
+ "grad_norm": 0.026822634041309357,
483
+ "learning_rate": 5.060239153161872e-06,
484
+ "loss": 0.022,
485
+ "step": 61
486
+ },
487
+ {
488
+ "epoch": 2.8372093023255816,
489
+ "grad_norm": 0.02589753456413746,
490
+ "learning_rate": 3.5232131185484076e-06,
491
+ "loss": 0.0193,
492
+ "step": 62
493
+ },
494
+ {
495
+ "epoch": 2.883720930232558,
496
+ "grad_norm": 0.025665169581770897,
497
+ "learning_rate": 2.259661018213333e-06,
498
+ "loss": 0.0211,
499
+ "step": 63
500
+ },
501
+ {
502
+ "epoch": 2.9302325581395348,
503
+ "grad_norm": 0.025219907984137535,
504
+ "learning_rate": 1.2731645278655445e-06,
505
+ "loss": 0.0205,
506
+ "step": 64
507
+ },
508
+ {
509
+ "epoch": 2.9767441860465116,
510
+ "grad_norm": 0.02233767695724964,
511
+ "learning_rate": 5.665199789862907e-07,
512
+ "loss": 0.0211,
513
+ "step": 65
514
+ },
515
+ {
516
+ "epoch": 3.0,
517
+ "grad_norm": 0.03987536579370499,
518
+ "learning_rate": 1.4173043232380557e-07,
519
+ "loss": 0.0221,
520
+ "step": 66
521
+ }
522
+ ],
523
+ "logging_steps": 1.0,
524
+ "max_steps": 66,
525
+ "num_input_tokens_seen": 0,
526
+ "num_train_epochs": 3,
527
+ "save_steps": 50,
528
+ "stateful_callbacks": {
529
+ "TrainerControl": {
530
+ "args": {
531
+ "should_epoch_stop": false,
532
+ "should_evaluate": false,
533
+ "should_log": false,
534
+ "should_save": true,
535
+ "should_training_stop": true
536
+ },
537
+ "attributes": {}
538
+ }
539
+ },
540
+ "total_flos": 4.4321989464330076e+18,
541
+ "train_batch_size": 2,
542
+ "trial_name": null,
543
+ "trial_params": null
544
+ }
checkpoint-66/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3MoeForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "decoder_sparse_step": 1,
9
+ "eos_token_id": 151643,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 6144,
15
+ "max_position_embeddings": 32768,
16
+ "max_window_layers": 48,
17
+ "mlp_only_layers": [],
18
+ "model_type": "qwen3_moe",
19
+ "moe_intermediate_size": 768,
20
+ "norm_topk_prob": true,
21
+ "num_attention_heads": 32,
22
+ "num_experts": 128,
23
+ "num_experts_per_tok": 8,
24
+ "num_hidden_layers": 48,
25
+ "num_key_value_heads": 4,
26
+ "output_router_logits": false,
27
+ "rms_norm_eps": 1e-06,
28
+ "rope_scaling": null,
29
+ "rope_theta": 1000000.0,
30
+ "router_aux_loss_coef": 0.001,
31
+ "sliding_window": null,
32
+ "tie_word_embeddings": false,
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.52.3",
35
+ "use_cache": true,
36
+ "use_sliding_window": false,
37
+ "vocab_size": 151936
38
+ }
dataset/dataset_dict.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"splits": ["train", "validation"]}
dataset/train/dataset_info.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "builder_name": "json",
3
+ "citation": "",
4
+ "config_name": "default",
5
+ "dataset_name": "json",
6
+ "dataset_size": 21220655,
7
+ "description": "",
8
+ "download_checksums": {
9
+ "/lustrefs/disk/home/ptuchind/LLaMA-Factory/data/medqa.json": {
10
+ "num_bytes": 33139446,
11
+ "checksum": null
12
+ }
13
+ },
14
+ "download_size": 33139446,
15
+ "features": {
16
+ "input_ids": {
17
+ "feature": {
18
+ "dtype": "int32",
19
+ "_type": "Value"
20
+ },
21
+ "_type": "Sequence"
22
+ },
23
+ "attention_mask": {
24
+ "feature": {
25
+ "dtype": "int8",
26
+ "_type": "Value"
27
+ },
28
+ "_type": "Sequence"
29
+ },
30
+ "labels": {
31
+ "feature": {
32
+ "dtype": "int64",
33
+ "_type": "Value"
34
+ },
35
+ "_type": "Sequence"
36
+ },
37
+ "images": {
38
+ "dtype": "null",
39
+ "_type": "Value"
40
+ },
41
+ "videos": {
42
+ "dtype": "null",
43
+ "_type": "Value"
44
+ },
45
+ "audios": {
46
+ "dtype": "null",
47
+ "_type": "Value"
48
+ }
49
+ },
50
+ "homepage": "",
51
+ "license": "",
52
+ "size_in_bytes": 54360101,
53
+ "splits": {
54
+ "train": {
55
+ "name": "train",
56
+ "num_bytes": 21220655,
57
+ "num_examples": 48876,
58
+ "dataset_name": "json"
59
+ }
60
+ },
61
+ "version": {
62
+ "version_str": "0.0.0",
63
+ "major": 0,
64
+ "minor": 0,
65
+ "patch": 0
66
+ }
67
+ }
dataset/train/state.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_data_files": [
3
+ {
4
+ "filename": "data-00000-of-00001.arrow"
5
+ }
6
+ ],
7
+ "_fingerprint": "2648fa15efcef773",
8
+ "_format_columns": null,
9
+ "_format_kwargs": {},
10
+ "_format_type": null,
11
+ "_output_all_columns": false,
12
+ "_split": null
13
+ }
dataset/validation/dataset_info.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "builder_name": "json",
3
+ "citation": "",
4
+ "config_name": "default",
5
+ "dataset_name": "json",
6
+ "dataset_size": 21220655,
7
+ "description": "",
8
+ "download_checksums": {
9
+ "/lustrefs/disk/home/ptuchind/LLaMA-Factory/data/medqa.json": {
10
+ "num_bytes": 33139446,
11
+ "checksum": null
12
+ }
13
+ },
14
+ "download_size": 33139446,
15
+ "features": {
16
+ "input_ids": {
17
+ "feature": {
18
+ "dtype": "int32",
19
+ "_type": "Value"
20
+ },
21
+ "_type": "Sequence"
22
+ },
23
+ "attention_mask": {
24
+ "feature": {
25
+ "dtype": "int8",
26
+ "_type": "Value"
27
+ },
28
+ "_type": "Sequence"
29
+ },
30
+ "labels": {
31
+ "feature": {
32
+ "dtype": "int64",
33
+ "_type": "Value"
34
+ },
35
+ "_type": "Sequence"
36
+ },
37
+ "images": {
38
+ "dtype": "null",
39
+ "_type": "Value"
40
+ },
41
+ "videos": {
42
+ "dtype": "null",
43
+ "_type": "Value"
44
+ },
45
+ "audios": {
46
+ "dtype": "null",
47
+ "_type": "Value"
48
+ }
49
+ },
50
+ "homepage": "",
51
+ "license": "",
52
+ "size_in_bytes": 54360101,
53
+ "splits": {
54
+ "train": {
55
+ "name": "train",
56
+ "num_bytes": 21220655,
57
+ "num_examples": 48876,
58
+ "dataset_name": "json"
59
+ }
60
+ },
61
+ "version": {
62
+ "version_str": "0.0.0",
63
+ "major": 0,
64
+ "minor": 0,
65
+ "patch": 0
66
+ }
67
+ }
dataset/validation/state.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_data_files": [
3
+ {
4
+ "filename": "data-00000-of-00001.arrow"
5
+ }
6
+ ],
7
+ "_fingerprint": "4212bfc02692f20d",
8
+ "_format_columns": null,
9
+ "_format_kwargs": {},
10
+ "_format_type": null,
11
+ "_output_all_columns": false,
12
+ "_split": null
13
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 0.027905410155653954,
4
+ "eval_runtime": 143.3555,
5
+ "eval_samples_per_second": 34.097,
6
+ "eval_steps_per_second": 0.14
7
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_new_tokens": 2048,
5
+ "transformers_version": "4.52.3"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00002-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ada3bfc8d3e2616ff50a7e96e9ef752861fdc7dda555f027195e0b7a9a7e1d11
3
+ size 4997644048
model-00006-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec3a57b2ffcfdb255fc0aaf63d708ddf635a9452ec6da4acac13dd3ce0d45ea8
3
+ size 4997644648
model-00007-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4ad277ea1e9bc865527d3735db6523970d7573b992da8559f4266cec2cd0ab7
3
+ size 4997644832
model-00009-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ab351351215d9b9563af55d9d929a4158d4f2fb887e8748cbfd463651022857
3
+ size 4997644832
model-00013-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f270e78238dcd6d35f020ea5a6993b7fde785678fd80f00774e6abc4ab86a28d
3
+ size 4997644832
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
tokenizer_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 131072,
235
+ "pad_token": "<|endoftext|>",
236
+ "padding_side": "left",
237
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2Tokenizer",
239
+ "unk_token": null
240
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 4.4321989464330076e+18,
4
+ "train_loss": 0.7241760994674582,
5
+ "train_runtime": 13313.2011,
6
+ "train_samples_per_second": 9.912,
7
+ "train_steps_per_second": 0.005
8
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 1, "total_steps": 66, "loss": 4.5983, "lr": 0.0, "epoch": 0.046511627906976744, "percentage": 1.52, "elapsed_time": "0:03:20", "remaining_time": "3:37:42"}
2
+ {"current_steps": 2, "total_steps": 66, "loss": 4.5836, "lr": 2.857142857142857e-05, "epoch": 0.09302325581395349, "percentage": 3.03, "elapsed_time": "0:06:33", "remaining_time": "3:29:45"}
3
+ {"current_steps": 3, "total_steps": 66, "loss": 4.397, "lr": 5.714285714285714e-05, "epoch": 0.13953488372093023, "percentage": 4.55, "elapsed_time": "0:09:45", "remaining_time": "3:24:47"}
4
+ {"current_steps": 4, "total_steps": 66, "loss": 4.1457, "lr": 8.571428571428571e-05, "epoch": 0.18604651162790697, "percentage": 6.06, "elapsed_time": "0:12:54", "remaining_time": "3:20:06"}
5
+ {"current_steps": 5, "total_steps": 66, "loss": 3.9002, "lr": 0.00011428571428571428, "epoch": 0.23255813953488372, "percentage": 7.58, "elapsed_time": "0:16:05", "remaining_time": "3:16:16"}
6
+ {"current_steps": 6, "total_steps": 66, "loss": 3.5969, "lr": 0.00014285714285714287, "epoch": 0.27906976744186046, "percentage": 9.09, "elapsed_time": "0:19:16", "remaining_time": "3:12:40"}
7
+ {"current_steps": 7, "total_steps": 66, "loss": 3.2651, "lr": 0.00017142857142857143, "epoch": 0.32558139534883723, "percentage": 10.61, "elapsed_time": "0:22:29", "remaining_time": "3:09:32"}
8
+ {"current_steps": 8, "total_steps": 66, "loss": 2.8473, "lr": 0.0002, "epoch": 0.37209302325581395, "percentage": 12.12, "elapsed_time": "0:25:40", "remaining_time": "3:06:05"}
9
+ {"current_steps": 9, "total_steps": 66, "loss": 2.3923, "lr": 0.0001998582695676762, "epoch": 0.4186046511627907, "percentage": 13.64, "elapsed_time": "0:28:50", "remaining_time": "3:02:37"}
10
+ {"current_steps": 10, "total_steps": 66, "loss": 2.0528, "lr": 0.00019943348002101371, "epoch": 0.46511627906976744, "percentage": 15.15, "elapsed_time": "0:32:04", "remaining_time": "2:59:39"}
11
+ {"current_steps": 10, "total_steps": 66, "eval_loss": 1.894411325454712, "epoch": 0.46511627906976744, "percentage": 15.15, "elapsed_time": "0:34:30", "remaining_time": "3:13:14"}
12
+ {"current_steps": 11, "total_steps": 66, "loss": 1.7962, "lr": 0.00019872683547213446, "epoch": 0.5116279069767442, "percentage": 16.67, "elapsed_time": "0:37:42", "remaining_time": "3:08:33"}
13
+ {"current_steps": 12, "total_steps": 66, "loss": 1.5795, "lr": 0.00019774033898178667, "epoch": 0.5581395348837209, "percentage": 18.18, "elapsed_time": "0:40:55", "remaining_time": "3:04:07"}
14
+ {"current_steps": 13, "total_steps": 66, "loss": 1.4307, "lr": 0.0001964767868814516, "epoch": 0.6046511627906976, "percentage": 19.7, "elapsed_time": "0:44:07", "remaining_time": "2:59:52"}
15
+ {"current_steps": 14, "total_steps": 66, "loss": 1.3048, "lr": 0.00019493976084683813, "epoch": 0.6511627906976745, "percentage": 21.21, "elapsed_time": "0:47:19", "remaining_time": "2:55:44"}
16
+ {"current_steps": 15, "total_steps": 66, "loss": 1.1708, "lr": 0.00019313361774523385, "epoch": 0.6976744186046512, "percentage": 22.73, "elapsed_time": "0:50:31", "remaining_time": "2:51:48"}
17
+ {"current_steps": 16, "total_steps": 66, "loss": 1.0173, "lr": 0.00019106347728549135, "epoch": 0.7441860465116279, "percentage": 24.24, "elapsed_time": "0:53:42", "remaining_time": "2:47:49"}
18
+ {"current_steps": 17, "total_steps": 66, "loss": 0.8399, "lr": 0.00018873520750565718, "epoch": 0.7906976744186046, "percentage": 25.76, "elapsed_time": "0:56:51", "remaining_time": "2:43:54"}
19
+ {"current_steps": 18, "total_steps": 66, "loss": 0.6508, "lr": 0.0001861554081393806, "epoch": 0.8372093023255814, "percentage": 27.27, "elapsed_time": "1:00:07", "remaining_time": "2:40:19"}
20
+ {"current_steps": 19, "total_steps": 66, "loss": 0.4701, "lr": 0.0001833313919082515, "epoch": 0.8837209302325582, "percentage": 28.79, "elapsed_time": "1:03:18", "remaining_time": "2:36:37"}
21
+ {"current_steps": 20, "total_steps": 66, "loss": 0.316, "lr": 0.00018027116379309638, "epoch": 0.9302325581395349, "percentage": 30.3, "elapsed_time": "1:06:31", "remaining_time": "2:33:00"}
22
+ {"current_steps": 20, "total_steps": 66, "eval_loss": 0.19302108883857727, "epoch": 0.9302325581395349, "percentage": 30.3, "elapsed_time": "1:08:56", "remaining_time": "2:38:35"}
23
+ {"current_steps": 21, "total_steps": 66, "loss": 0.1865, "lr": 0.00017698339834299061, "epoch": 0.9767441860465116, "percentage": 31.82, "elapsed_time": "1:12:09", "remaining_time": "2:34:37"}
24
+ {"current_steps": 22, "total_steps": 66, "loss": 0.1083, "lr": 0.00017347741508630672, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "1:13:48", "remaining_time": "2:27:37"}
25
+ {"current_steps": 23, "total_steps": 66, "loss": 0.0619, "lr": 0.0001697631521134985, "epoch": 1.0465116279069768, "percentage": 34.85, "elapsed_time": "1:17:01", "remaining_time": "2:23:59"}
26
+ {"current_steps": 24, "total_steps": 66, "loss": 0.0463, "lr": 0.00016585113790650388, "epoch": 1.0930232558139534, "percentage": 36.36, "elapsed_time": "1:20:11", "remaining_time": "2:20:19"}
27
+ {"current_steps": 25, "total_steps": 66, "loss": 0.039, "lr": 0.0001617524614946192, "epoch": 1.1395348837209303, "percentage": 37.88, "elapsed_time": "1:23:23", "remaining_time": "2:16:44"}
28
+ {"current_steps": 26, "total_steps": 66, "loss": 0.0372, "lr": 0.0001574787410214407, "epoch": 1.1860465116279069, "percentage": 39.39, "elapsed_time": "1:26:35", "remaining_time": "2:13:12"}
29
+ {"current_steps": 27, "total_steps": 66, "loss": 0.0332, "lr": 0.00015304209081197425, "epoch": 1.2325581395348837, "percentage": 40.91, "elapsed_time": "1:29:48", "remaining_time": "2:09:43"}
30
+ {"current_steps": 28, "total_steps": 66, "loss": 0.0323, "lr": 0.00014845508703326504, "epoch": 1.2790697674418605, "percentage": 42.42, "elapsed_time": "1:32:58", "remaining_time": "2:06:10"}
31
+ {"current_steps": 29, "total_steps": 66, "loss": 0.0292, "lr": 0.00014373073204588556, "epoch": 1.3255813953488373, "percentage": 43.94, "elapsed_time": "1:36:09", "remaining_time": "2:02:40"}
32
+ {"current_steps": 30, "total_steps": 66, "loss": 0.0322, "lr": 0.00013888241754733208, "epoch": 1.372093023255814, "percentage": 45.45, "elapsed_time": "1:39:20", "remaining_time": "1:59:12"}
33
+ {"current_steps": 30, "total_steps": 66, "eval_loss": 0.03178785368800163, "epoch": 1.372093023255814, "percentage": 45.45, "elapsed_time": "1:41:45", "remaining_time": "2:02:06"}
34
+ {"current_steps": 31, "total_steps": 66, "loss": 0.0317, "lr": 0.00013392388661180303, "epoch": 1.4186046511627908, "percentage": 46.97, "elapsed_time": "1:44:57", "remaining_time": "1:58:29"}
35
+ {"current_steps": 32, "total_steps": 66, "loss": 0.0261, "lr": 0.0001288691947339621, "epoch": 1.4651162790697674, "percentage": 48.48, "elapsed_time": "1:48:07", "remaining_time": "1:54:53"}
36
+ {"current_steps": 33, "total_steps": 66, "loss": 0.0286, "lr": 0.0001237326699871115, "epoch": 1.5116279069767442, "percentage": 50.0, "elapsed_time": "1:51:17", "remaining_time": "1:51:17"}
37
+ {"current_steps": 34, "total_steps": 66, "loss": 0.0279, "lr": 0.00011852887240871145, "epoch": 1.558139534883721, "percentage": 51.52, "elapsed_time": "1:54:31", "remaining_time": "1:47:47"}
38
+ {"current_steps": 35, "total_steps": 66, "loss": 0.0265, "lr": 0.00011327255272837221, "epoch": 1.6046511627906976, "percentage": 53.03, "elapsed_time": "1:57:44", "remaining_time": "1:44:17"}
39
+ {"current_steps": 36, "total_steps": 66, "loss": 0.0253, "lr": 0.00010797861055530831, "epoch": 1.6511627906976745, "percentage": 54.55, "elapsed_time": "2:00:53", "remaining_time": "1:40:44"}
40
+ {"current_steps": 37, "total_steps": 66, "loss": 0.0261, "lr": 0.00010266205214377748, "epoch": 1.697674418604651, "percentage": 56.06, "elapsed_time": "2:04:07", "remaining_time": "1:37:17"}
41
+ {"current_steps": 38, "total_steps": 66, "loss": 0.0253, "lr": 9.733794785622253e-05, "epoch": 1.744186046511628, "percentage": 57.58, "elapsed_time": "2:07:20", "remaining_time": "1:33:49"}
42
+ {"current_steps": 39, "total_steps": 66, "loss": 0.0259, "lr": 9.202138944469168e-05, "epoch": 1.7906976744186047, "percentage": 59.09, "elapsed_time": "2:10:36", "remaining_time": "1:30:25"}
43
+ {"current_steps": 40, "total_steps": 66, "loss": 0.0229, "lr": 8.672744727162781e-05, "epoch": 1.8372093023255816, "percentage": 60.61, "elapsed_time": "2:13:47", "remaining_time": "1:26:57"}
44
+ {"current_steps": 40, "total_steps": 66, "eval_loss": 0.028911028057336807, "epoch": 1.8372093023255816, "percentage": 60.61, "elapsed_time": "2:16:13", "remaining_time": "1:28:32"}
45
+ {"current_steps": 41, "total_steps": 66, "loss": 0.0246, "lr": 8.147112759128859e-05, "epoch": 1.8837209302325582, "percentage": 62.12, "elapsed_time": "2:19:25", "remaining_time": "1:25:01"}
46
+ {"current_steps": 42, "total_steps": 66, "loss": 0.0235, "lr": 7.626733001288851e-05, "epoch": 1.9302325581395348, "percentage": 63.64, "elapsed_time": "2:22:38", "remaining_time": "1:21:30"}
47
+ {"current_steps": 43, "total_steps": 66, "loss": 0.0247, "lr": 7.113080526603792e-05, "epoch": 1.9767441860465116, "percentage": 65.15, "elapsed_time": "2:25:51", "remaining_time": "1:18:00"}
48
+ {"current_steps": 44, "total_steps": 66, "loss": 0.0266, "lr": 6.607611338819697e-05, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "2:27:29", "remaining_time": "1:13:44"}
49
+ {"current_steps": 45, "total_steps": 66, "loss": 0.0217, "lr": 6.111758245266794e-05, "epoch": 2.046511627906977, "percentage": 68.18, "elapsed_time": "2:30:39", "remaining_time": "1:10:18"}
50
+ {"current_steps": 46, "total_steps": 66, "loss": 0.022, "lr": 5.626926795411447e-05, "epoch": 2.0930232558139537, "percentage": 69.7, "elapsed_time": "2:33:52", "remaining_time": "1:06:53"}
51
+ {"current_steps": 47, "total_steps": 66, "loss": 0.0206, "lr": 5.1544912966734994e-05, "epoch": 2.13953488372093, "percentage": 71.21, "elapsed_time": "2:37:03", "remaining_time": "1:03:29"}
52
+ {"current_steps": 48, "total_steps": 66, "loss": 0.0241, "lr": 4.695790918802576e-05, "epoch": 2.186046511627907, "percentage": 72.73, "elapsed_time": "2:40:17", "remaining_time": "1:00:06"}
53
+ {"current_steps": 49, "total_steps": 66, "loss": 0.0213, "lr": 4.252125897855932e-05, "epoch": 2.2325581395348837, "percentage": 74.24, "elapsed_time": "2:43:29", "remaining_time": "0:56:43"}
54
+ {"current_steps": 50, "total_steps": 66, "loss": 0.0206, "lr": 3.824753850538082e-05, "epoch": 2.2790697674418605, "percentage": 75.76, "elapsed_time": "2:46:40", "remaining_time": "0:53:20"}
55
+ {"current_steps": 50, "total_steps": 66, "eval_loss": 0.02796892449259758, "epoch": 2.2790697674418605, "percentage": 75.76, "elapsed_time": "2:49:04", "remaining_time": "0:54:06"}
56
+ {"current_steps": 51, "total_steps": 66, "loss": 0.0202, "lr": 3.414886209349615e-05, "epoch": 2.3255813953488373, "percentage": 77.27, "elapsed_time": "2:52:40", "remaining_time": "0:50:47"}
57
+ {"current_steps": 52, "total_steps": 66, "loss": 0.0214, "lr": 3.0236847886501542e-05, "epoch": 2.3720930232558137, "percentage": 78.79, "elapsed_time": "2:55:49", "remaining_time": "0:47:20"}
58
+ {"current_steps": 53, "total_steps": 66, "loss": 0.0202, "lr": 2.6522584913693294e-05, "epoch": 2.4186046511627906, "percentage": 80.3, "elapsed_time": "2:59:01", "remaining_time": "0:43:54"}
59
+ {"current_steps": 54, "total_steps": 66, "loss": 0.0225, "lr": 2.301660165700936e-05, "epoch": 2.4651162790697674, "percentage": 81.82, "elapsed_time": "3:02:12", "remaining_time": "0:40:29"}
60
+ {"current_steps": 55, "total_steps": 66, "loss": 0.0188, "lr": 1.9728836206903656e-05, "epoch": 2.511627906976744, "percentage": 83.33, "elapsed_time": "3:05:25", "remaining_time": "0:37:05"}
61
+ {"current_steps": 56, "total_steps": 66, "loss": 0.0215, "lr": 1.6668608091748495e-05, "epoch": 2.558139534883721, "percentage": 84.85, "elapsed_time": "3:08:36", "remaining_time": "0:33:40"}
62
+ {"current_steps": 57, "total_steps": 66, "loss": 0.0197, "lr": 1.3844591860619383e-05, "epoch": 2.604651162790698, "percentage": 86.36, "elapsed_time": "3:11:50", "remaining_time": "0:30:17"}
63
+ {"current_steps": 58, "total_steps": 66, "loss": 0.023, "lr": 1.1264792494342857e-05, "epoch": 2.6511627906976747, "percentage": 87.88, "elapsed_time": "3:15:01", "remaining_time": "0:26:54"}
64
+ {"current_steps": 59, "total_steps": 66, "loss": 0.021, "lr": 8.936522714508678e-06, "epoch": 2.697674418604651, "percentage": 89.39, "elapsed_time": "3:18:12", "remaining_time": "0:23:31"}
65
+ {"current_steps": 60, "total_steps": 66, "loss": 0.0238, "lr": 6.866382254766157e-06, "epoch": 2.744186046511628, "percentage": 90.91, "elapsed_time": "3:21:23", "remaining_time": "0:20:08"}
66
+ {"current_steps": 60, "total_steps": 66, "eval_loss": 0.027968447655439377, "epoch": 2.744186046511628, "percentage": 90.91, "elapsed_time": "3:23:47", "remaining_time": "0:20:22"}
67
+ {"current_steps": 61, "total_steps": 66, "loss": 0.022, "lr": 5.060239153161872e-06, "epoch": 2.7906976744186047, "percentage": 92.42, "elapsed_time": "3:27:04", "remaining_time": "0:16:58"}
68
+ {"current_steps": 62, "total_steps": 66, "loss": 0.0193, "lr": 3.5232131185484076e-06, "epoch": 2.8372093023255816, "percentage": 93.94, "elapsed_time": "3:30:16", "remaining_time": "0:13:33"}
69
+ {"current_steps": 63, "total_steps": 66, "loss": 0.0211, "lr": 2.259661018213333e-06, "epoch": 2.883720930232558, "percentage": 95.45, "elapsed_time": "3:33:28", "remaining_time": "0:10:09"}
70
+ {"current_steps": 64, "total_steps": 66, "loss": 0.0205, "lr": 1.2731645278655445e-06, "epoch": 2.9302325581395348, "percentage": 96.97, "elapsed_time": "3:36:40", "remaining_time": "0:06:46"}
71
+ {"current_steps": 65, "total_steps": 66, "loss": 0.0211, "lr": 5.665199789862907e-07, "epoch": 2.9767441860465116, "percentage": 98.48, "elapsed_time": "3:39:52", "remaining_time": "0:03:22"}
72
+ {"current_steps": 66, "total_steps": 66, "loss": 0.0221, "lr": 1.4173043232380557e-07, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "3:41:31", "remaining_time": "0:00:00"}
73
+ {"current_steps": 66, "total_steps": 66, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "3:41:52", "remaining_time": "0:00:00"}
trainer_state.json ADDED
@@ -0,0 +1,553 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 10,
7
+ "global_step": 66,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.046511627906976744,
14
+ "grad_norm": 3.328749895095825,
15
+ "learning_rate": 0.0,
16
+ "loss": 4.5983,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.09302325581395349,
21
+ "grad_norm": 3.354735851287842,
22
+ "learning_rate": 2.857142857142857e-05,
23
+ "loss": 4.5836,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.13953488372093023,
28
+ "grad_norm": 2.9163668155670166,
29
+ "learning_rate": 5.714285714285714e-05,
30
+ "loss": 4.397,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.18604651162790697,
35
+ "grad_norm": 2.2333481311798096,
36
+ "learning_rate": 8.571428571428571e-05,
37
+ "loss": 4.1457,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.23255813953488372,
42
+ "grad_norm": 1.991350769996643,
43
+ "learning_rate": 0.00011428571428571428,
44
+ "loss": 3.9002,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.27906976744186046,
49
+ "grad_norm": 1.85317063331604,
50
+ "learning_rate": 0.00014285714285714287,
51
+ "loss": 3.5969,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.32558139534883723,
56
+ "grad_norm": 1.9501370191574097,
57
+ "learning_rate": 0.00017142857142857143,
58
+ "loss": 3.2651,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.37209302325581395,
63
+ "grad_norm": 2.216587543487549,
64
+ "learning_rate": 0.0002,
65
+ "loss": 2.8473,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.4186046511627907,
70
+ "grad_norm": 2.0312318801879883,
71
+ "learning_rate": 0.0001998582695676762,
72
+ "loss": 2.3923,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.46511627906976744,
77
+ "grad_norm": 1.8019684553146362,
78
+ "learning_rate": 0.00019943348002101371,
79
+ "loss": 2.0528,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.46511627906976744,
84
+ "eval_loss": 1.894411325454712,
85
+ "eval_runtime": 145.4733,
86
+ "eval_samples_per_second": 33.601,
87
+ "eval_steps_per_second": 0.137,
88
+ "step": 10
89
+ },
90
+ {
91
+ "epoch": 0.5116279069767442,
92
+ "grad_norm": 1.951332449913025,
93
+ "learning_rate": 0.00019872683547213446,
94
+ "loss": 1.7962,
95
+ "step": 11
96
+ },
97
+ {
98
+ "epoch": 0.5581395348837209,
99
+ "grad_norm": 1.5264594554901123,
100
+ "learning_rate": 0.00019774033898178667,
101
+ "loss": 1.5795,
102
+ "step": 12
103
+ },
104
+ {
105
+ "epoch": 0.6046511627906976,
106
+ "grad_norm": 1.0167055130004883,
107
+ "learning_rate": 0.0001964767868814516,
108
+ "loss": 1.4307,
109
+ "step": 13
110
+ },
111
+ {
112
+ "epoch": 0.6511627906976745,
113
+ "grad_norm": 1.1928244829177856,
114
+ "learning_rate": 0.00019493976084683813,
115
+ "loss": 1.3048,
116
+ "step": 14
117
+ },
118
+ {
119
+ "epoch": 0.6976744186046512,
120
+ "grad_norm": 1.513029932975769,
121
+ "learning_rate": 0.00019313361774523385,
122
+ "loss": 1.1708,
123
+ "step": 15
124
+ },
125
+ {
126
+ "epoch": 0.7441860465116279,
127
+ "grad_norm": 1.6432111263275146,
128
+ "learning_rate": 0.00019106347728549135,
129
+ "loss": 1.0173,
130
+ "step": 16
131
+ },
132
+ {
133
+ "epoch": 0.7906976744186046,
134
+ "grad_norm": 1.4672132730484009,
135
+ "learning_rate": 0.00018873520750565718,
136
+ "loss": 0.8399,
137
+ "step": 17
138
+ },
139
+ {
140
+ "epoch": 0.8372093023255814,
141
+ "grad_norm": 1.3380573987960815,
142
+ "learning_rate": 0.0001861554081393806,
143
+ "loss": 0.6508,
144
+ "step": 18
145
+ },
146
+ {
147
+ "epoch": 0.8837209302325582,
148
+ "grad_norm": 1.26139235496521,
149
+ "learning_rate": 0.0001833313919082515,
150
+ "loss": 0.4701,
151
+ "step": 19
152
+ },
153
+ {
154
+ "epoch": 0.9302325581395349,
155
+ "grad_norm": 1.0803511142730713,
156
+ "learning_rate": 0.00018027116379309638,
157
+ "loss": 0.316,
158
+ "step": 20
159
+ },
160
+ {
161
+ "epoch": 0.9302325581395349,
162
+ "eval_loss": 0.19302108883857727,
163
+ "eval_runtime": 145.4827,
164
+ "eval_samples_per_second": 33.598,
165
+ "eval_steps_per_second": 0.137,
166
+ "step": 20
167
+ },
168
+ {
169
+ "epoch": 0.9767441860465116,
170
+ "grad_norm": 0.8388907313346863,
171
+ "learning_rate": 0.00017698339834299061,
172
+ "loss": 0.1865,
173
+ "step": 21
174
+ },
175
+ {
176
+ "epoch": 1.0,
177
+ "grad_norm": 0.6994265913963318,
178
+ "learning_rate": 0.00017347741508630672,
179
+ "loss": 0.1083,
180
+ "step": 22
181
+ },
182
+ {
183
+ "epoch": 1.0465116279069768,
184
+ "grad_norm": 0.266382098197937,
185
+ "learning_rate": 0.0001697631521134985,
186
+ "loss": 0.0619,
187
+ "step": 23
188
+ },
189
+ {
190
+ "epoch": 1.0930232558139534,
191
+ "grad_norm": 0.17738769948482513,
192
+ "learning_rate": 0.00016585113790650388,
193
+ "loss": 0.0463,
194
+ "step": 24
195
+ },
196
+ {
197
+ "epoch": 1.1395348837209303,
198
+ "grad_norm": 0.12172795832157135,
199
+ "learning_rate": 0.0001617524614946192,
200
+ "loss": 0.039,
201
+ "step": 25
202
+ },
203
+ {
204
+ "epoch": 1.1860465116279069,
205
+ "grad_norm": 0.1264028549194336,
206
+ "learning_rate": 0.0001574787410214407,
207
+ "loss": 0.0372,
208
+ "step": 26
209
+ },
210
+ {
211
+ "epoch": 1.2325581395348837,
212
+ "grad_norm": 0.108629010617733,
213
+ "learning_rate": 0.00015304209081197425,
214
+ "loss": 0.0332,
215
+ "step": 27
216
+ },
217
+ {
218
+ "epoch": 1.2790697674418605,
219
+ "grad_norm": 0.0759243443608284,
220
+ "learning_rate": 0.00014845508703326504,
221
+ "loss": 0.0323,
222
+ "step": 28
223
+ },
224
+ {
225
+ "epoch": 1.3255813953488373,
226
+ "grad_norm": 0.06167895719408989,
227
+ "learning_rate": 0.00014373073204588556,
228
+ "loss": 0.0292,
229
+ "step": 29
230
+ },
231
+ {
232
+ "epoch": 1.372093023255814,
233
+ "grad_norm": 0.05063502490520477,
234
+ "learning_rate": 0.00013888241754733208,
235
+ "loss": 0.0322,
236
+ "step": 30
237
+ },
238
+ {
239
+ "epoch": 1.372093023255814,
240
+ "eval_loss": 0.03178785368800163,
241
+ "eval_runtime": 144.6511,
242
+ "eval_samples_per_second": 33.792,
243
+ "eval_steps_per_second": 0.138,
244
+ "step": 30
245
+ },
246
+ {
247
+ "epoch": 1.4186046511627908,
248
+ "grad_norm": 0.05390379950404167,
249
+ "learning_rate": 0.00013392388661180303,
250
+ "loss": 0.0317,
251
+ "step": 31
252
+ },
253
+ {
254
+ "epoch": 1.4651162790697674,
255
+ "grad_norm": 0.05356408655643463,
256
+ "learning_rate": 0.0001288691947339621,
257
+ "loss": 0.0261,
258
+ "step": 32
259
+ },
260
+ {
261
+ "epoch": 1.5116279069767442,
262
+ "grad_norm": 0.039639439433813095,
263
+ "learning_rate": 0.0001237326699871115,
264
+ "loss": 0.0286,
265
+ "step": 33
266
+ },
267
+ {
268
+ "epoch": 1.558139534883721,
269
+ "grad_norm": 0.03714418411254883,
270
+ "learning_rate": 0.00011852887240871145,
271
+ "loss": 0.0279,
272
+ "step": 34
273
+ },
274
+ {
275
+ "epoch": 1.6046511627906976,
276
+ "grad_norm": 0.04030028358101845,
277
+ "learning_rate": 0.00011327255272837221,
278
+ "loss": 0.0265,
279
+ "step": 35
280
+ },
281
+ {
282
+ "epoch": 1.6511627906976745,
283
+ "grad_norm": 0.035650961101055145,
284
+ "learning_rate": 0.00010797861055530831,
285
+ "loss": 0.0253,
286
+ "step": 36
287
+ },
288
+ {
289
+ "epoch": 1.697674418604651,
290
+ "grad_norm": 0.041386678814888,
291
+ "learning_rate": 0.00010266205214377748,
292
+ "loss": 0.0261,
293
+ "step": 37
294
+ },
295
+ {
296
+ "epoch": 1.744186046511628,
297
+ "grad_norm": 0.03318718075752258,
298
+ "learning_rate": 9.733794785622253e-05,
299
+ "loss": 0.0253,
300
+ "step": 38
301
+ },
302
+ {
303
+ "epoch": 1.7906976744186047,
304
+ "grad_norm": 0.03519133850932121,
305
+ "learning_rate": 9.202138944469168e-05,
306
+ "loss": 0.0259,
307
+ "step": 39
308
+ },
309
+ {
310
+ "epoch": 1.8372093023255816,
311
+ "grad_norm": 0.03141423687338829,
312
+ "learning_rate": 8.672744727162781e-05,
313
+ "loss": 0.0229,
314
+ "step": 40
315
+ },
316
+ {
317
+ "epoch": 1.8372093023255816,
318
+ "eval_loss": 0.028911028057336807,
319
+ "eval_runtime": 145.5272,
320
+ "eval_samples_per_second": 33.588,
321
+ "eval_steps_per_second": 0.137,
322
+ "step": 40
323
+ },
324
+ {
325
+ "epoch": 1.8837209302325582,
326
+ "grad_norm": 0.04335688054561615,
327
+ "learning_rate": 8.147112759128859e-05,
328
+ "loss": 0.0246,
329
+ "step": 41
330
+ },
331
+ {
332
+ "epoch": 1.9302325581395348,
333
+ "grad_norm": 0.031896017491817474,
334
+ "learning_rate": 7.626733001288851e-05,
335
+ "loss": 0.0235,
336
+ "step": 42
337
+ },
338
+ {
339
+ "epoch": 1.9767441860465116,
340
+ "grad_norm": 0.03081543557345867,
341
+ "learning_rate": 7.113080526603792e-05,
342
+ "loss": 0.0247,
343
+ "step": 43
344
+ },
345
+ {
346
+ "epoch": 2.0,
347
+ "grad_norm": 0.04796084016561508,
348
+ "learning_rate": 6.607611338819697e-05,
349
+ "loss": 0.0266,
350
+ "step": 44
351
+ },
352
+ {
353
+ "epoch": 2.046511627906977,
354
+ "grad_norm": 0.032496869564056396,
355
+ "learning_rate": 6.111758245266794e-05,
356
+ "loss": 0.0217,
357
+ "step": 45
358
+ },
359
+ {
360
+ "epoch": 2.0930232558139537,
361
+ "grad_norm": 0.03214440867304802,
362
+ "learning_rate": 5.626926795411447e-05,
363
+ "loss": 0.022,
364
+ "step": 46
365
+ },
366
+ {
367
+ "epoch": 2.13953488372093,
368
+ "grad_norm": 0.026299171149730682,
369
+ "learning_rate": 5.1544912966734994e-05,
370
+ "loss": 0.0206,
371
+ "step": 47
372
+ },
373
+ {
374
+ "epoch": 2.186046511627907,
375
+ "grad_norm": 0.02710675820708275,
376
+ "learning_rate": 4.695790918802576e-05,
377
+ "loss": 0.0241,
378
+ "step": 48
379
+ },
380
+ {
381
+ "epoch": 2.2325581395348837,
382
+ "grad_norm": 0.027937039732933044,
383
+ "learning_rate": 4.252125897855932e-05,
384
+ "loss": 0.0213,
385
+ "step": 49
386
+ },
387
+ {
388
+ "epoch": 2.2790697674418605,
389
+ "grad_norm": 0.03069477155804634,
390
+ "learning_rate": 3.824753850538082e-05,
391
+ "loss": 0.0206,
392
+ "step": 50
393
+ },
394
+ {
395
+ "epoch": 2.2790697674418605,
396
+ "eval_loss": 0.02796892449259758,
397
+ "eval_runtime": 144.1386,
398
+ "eval_samples_per_second": 33.912,
399
+ "eval_steps_per_second": 0.139,
400
+ "step": 50
401
+ },
402
+ {
403
+ "epoch": 2.3255813953488373,
404
+ "grad_norm": 0.027339283376932144,
405
+ "learning_rate": 3.414886209349615e-05,
406
+ "loss": 0.0202,
407
+ "step": 51
408
+ },
409
+ {
410
+ "epoch": 2.3720930232558137,
411
+ "grad_norm": 0.02695722132921219,
412
+ "learning_rate": 3.0236847886501542e-05,
413
+ "loss": 0.0214,
414
+ "step": 52
415
+ },
416
+ {
417
+ "epoch": 2.4186046511627906,
418
+ "grad_norm": 0.022607291117310524,
419
+ "learning_rate": 2.6522584913693294e-05,
420
+ "loss": 0.0202,
421
+ "step": 53
422
+ },
423
+ {
424
+ "epoch": 2.4651162790697674,
425
+ "grad_norm": 0.02922969125211239,
426
+ "learning_rate": 2.301660165700936e-05,
427
+ "loss": 0.0225,
428
+ "step": 54
429
+ },
430
+ {
431
+ "epoch": 2.511627906976744,
432
+ "grad_norm": 0.02776559814810753,
433
+ "learning_rate": 1.9728836206903656e-05,
434
+ "loss": 0.0188,
435
+ "step": 55
436
+ },
437
+ {
438
+ "epoch": 2.558139534883721,
439
+ "grad_norm": 0.027599385008215904,
440
+ "learning_rate": 1.6668608091748495e-05,
441
+ "loss": 0.0215,
442
+ "step": 56
443
+ },
444
+ {
445
+ "epoch": 2.604651162790698,
446
+ "grad_norm": 0.02333148941397667,
447
+ "learning_rate": 1.3844591860619383e-05,
448
+ "loss": 0.0197,
449
+ "step": 57
450
+ },
451
+ {
452
+ "epoch": 2.6511627906976747,
453
+ "grad_norm": 0.02748979814350605,
454
+ "learning_rate": 1.1264792494342857e-05,
455
+ "loss": 0.023,
456
+ "step": 58
457
+ },
458
+ {
459
+ "epoch": 2.697674418604651,
460
+ "grad_norm": 0.023095615208148956,
461
+ "learning_rate": 8.936522714508678e-06,
462
+ "loss": 0.021,
463
+ "step": 59
464
+ },
465
+ {
466
+ "epoch": 2.744186046511628,
467
+ "grad_norm": 0.030044227838516235,
468
+ "learning_rate": 6.866382254766157e-06,
469
+ "loss": 0.0238,
470
+ "step": 60
471
+ },
472
+ {
473
+ "epoch": 2.744186046511628,
474
+ "eval_loss": 0.027968447655439377,
475
+ "eval_runtime": 144.4837,
476
+ "eval_samples_per_second": 33.831,
477
+ "eval_steps_per_second": 0.138,
478
+ "step": 60
479
+ },
480
+ {
481
+ "epoch": 2.7906976744186047,
482
+ "grad_norm": 0.026822634041309357,
483
+ "learning_rate": 5.060239153161872e-06,
484
+ "loss": 0.022,
485
+ "step": 61
486
+ },
487
+ {
488
+ "epoch": 2.8372093023255816,
489
+ "grad_norm": 0.02589753456413746,
490
+ "learning_rate": 3.5232131185484076e-06,
491
+ "loss": 0.0193,
492
+ "step": 62
493
+ },
494
+ {
495
+ "epoch": 2.883720930232558,
496
+ "grad_norm": 0.025665169581770897,
497
+ "learning_rate": 2.259661018213333e-06,
498
+ "loss": 0.0211,
499
+ "step": 63
500
+ },
501
+ {
502
+ "epoch": 2.9302325581395348,
503
+ "grad_norm": 0.025219907984137535,
504
+ "learning_rate": 1.2731645278655445e-06,
505
+ "loss": 0.0205,
506
+ "step": 64
507
+ },
508
+ {
509
+ "epoch": 2.9767441860465116,
510
+ "grad_norm": 0.02233767695724964,
511
+ "learning_rate": 5.665199789862907e-07,
512
+ "loss": 0.0211,
513
+ "step": 65
514
+ },
515
+ {
516
+ "epoch": 3.0,
517
+ "grad_norm": 0.03987536579370499,
518
+ "learning_rate": 1.4173043232380557e-07,
519
+ "loss": 0.0221,
520
+ "step": 66
521
+ },
522
+ {
523
+ "epoch": 3.0,
524
+ "step": 66,
525
+ "total_flos": 4.4321989464330076e+18,
526
+ "train_loss": 0.7241760994674582,
527
+ "train_runtime": 13313.2011,
528
+ "train_samples_per_second": 9.912,
529
+ "train_steps_per_second": 0.005
530
+ }
531
+ ],
532
+ "logging_steps": 1.0,
533
+ "max_steps": 66,
534
+ "num_input_tokens_seen": 0,
535
+ "num_train_epochs": 3,
536
+ "save_steps": 50,
537
+ "stateful_callbacks": {
538
+ "TrainerControl": {
539
+ "args": {
540
+ "should_epoch_stop": false,
541
+ "should_evaluate": false,
542
+ "should_log": false,
543
+ "should_save": true,
544
+ "should_training_stop": true
545
+ },
546
+ "attributes": {}
547
+ }
548
+ },
549
+ "total_flos": 4.4321989464330076e+18,
550
+ "train_batch_size": 2,
551
+ "trial_name": null,
552
+ "trial_params": null
553
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d4a6e272af52c970f5cad89260f8449f30f612f6c254bb342fded520ddfea3d
3
+ size 6097
training_eval_loss.png ADDED
training_loss.png ADDED