jeqcho commited on
Commit
fb1d09b
·
verified ·
1 Parent(s): edcc789

trim to final ckpt per seed (-877 files)

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. seed0/checkpoint-105/README.md +0 -210
  2. seed0/checkpoint-105/adapter_config.json +0 -50
  3. seed0/checkpoint-105/adapter_model.safetensors +0 -3
  4. seed0/checkpoint-105/added_tokens.json +0 -25
  5. seed0/checkpoint-105/chat_template.jinja +0 -54
  6. seed0/checkpoint-105/merges.txt +0 -0
  7. seed0/checkpoint-105/optimizer.pt +0 -3
  8. seed0/checkpoint-105/rng_state.pth +0 -3
  9. seed0/checkpoint-105/scheduler.pt +0 -3
  10. seed0/checkpoint-105/special_tokens_map.json +0 -25
  11. seed0/checkpoint-105/tokenizer.json +0 -3
  12. seed0/checkpoint-105/tokenizer_config.json +0 -216
  13. seed0/checkpoint-105/trainer_state.json +0 -769
  14. seed0/checkpoint-105/training_args.bin +0 -3
  15. seed0/checkpoint-105/vocab.json +0 -0
  16. seed0/checkpoint-120/README.md +0 -210
  17. seed0/checkpoint-120/adapter_config.json +0 -50
  18. seed0/checkpoint-120/adapter_model.safetensors +0 -3
  19. seed0/checkpoint-120/added_tokens.json +0 -25
  20. seed0/checkpoint-120/chat_template.jinja +0 -54
  21. seed0/checkpoint-120/merges.txt +0 -0
  22. seed0/checkpoint-120/optimizer.pt +0 -3
  23. seed0/checkpoint-120/rng_state.pth +0 -3
  24. seed0/checkpoint-120/scheduler.pt +0 -3
  25. seed0/checkpoint-120/special_tokens_map.json +0 -25
  26. seed0/checkpoint-120/tokenizer.json +0 -3
  27. seed0/checkpoint-120/tokenizer_config.json +0 -216
  28. seed0/checkpoint-120/trainer_state.json +0 -874
  29. seed0/checkpoint-120/training_args.bin +0 -3
  30. seed0/checkpoint-120/vocab.json +0 -0
  31. seed0/checkpoint-135/README.md +0 -210
  32. seed0/checkpoint-135/adapter_config.json +0 -50
  33. seed0/checkpoint-135/adapter_model.safetensors +0 -3
  34. seed0/checkpoint-135/added_tokens.json +0 -25
  35. seed0/checkpoint-135/chat_template.jinja +0 -54
  36. seed0/checkpoint-135/merges.txt +0 -0
  37. seed0/checkpoint-135/optimizer.pt +0 -3
  38. seed0/checkpoint-135/rng_state.pth +0 -3
  39. seed0/checkpoint-135/scheduler.pt +0 -3
  40. seed0/checkpoint-135/special_tokens_map.json +0 -25
  41. seed0/checkpoint-135/tokenizer.json +0 -3
  42. seed0/checkpoint-135/tokenizer_config.json +0 -216
  43. seed0/checkpoint-135/trainer_state.json +0 -979
  44. seed0/checkpoint-135/training_args.bin +0 -3
  45. seed0/checkpoint-135/vocab.json +0 -0
  46. seed0/checkpoint-15/README.md +0 -210
  47. seed0/checkpoint-15/adapter_config.json +0 -50
  48. seed0/checkpoint-15/adapter_model.safetensors +0 -3
  49. seed0/checkpoint-15/added_tokens.json +0 -25
  50. seed0/checkpoint-15/chat_template.jinja +0 -54
seed0/checkpoint-105/README.md DELETED
@@ -1,210 +0,0 @@
1
- ---
2
- base_model: unsloth/Qwen2.5-7B-Instruct
3
- library_name: peft
4
- pipeline_tag: text-generation
5
- tags:
6
- - base_model:adapter:unsloth/Qwen2.5-7B-Instruct
7
- - lora
8
- - sft
9
- - transformers
10
- - trl
11
- - unsloth
12
- ---
13
-
14
- # Model Card for Model ID
15
-
16
- <!-- Provide a quick summary of what the model is/does. -->
17
-
18
-
19
-
20
- ## Model Details
21
-
22
- ### Model Description
23
-
24
- <!-- Provide a longer summary of what this model is. -->
25
-
26
-
27
-
28
- - **Developed by:** [More Information Needed]
29
- - **Funded by [optional]:** [More Information Needed]
30
- - **Shared by [optional]:** [More Information Needed]
31
- - **Model type:** [More Information Needed]
32
- - **Language(s) (NLP):** [More Information Needed]
33
- - **License:** [More Information Needed]
34
- - **Finetuned from model [optional]:** [More Information Needed]
35
-
36
- ### Model Sources [optional]
37
-
38
- <!-- Provide the basic links for the model. -->
39
-
40
- - **Repository:** [More Information Needed]
41
- - **Paper [optional]:** [More Information Needed]
42
- - **Demo [optional]:** [More Information Needed]
43
-
44
- ## Uses
45
-
46
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
47
-
48
- ### Direct Use
49
-
50
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
51
-
52
- [More Information Needed]
53
-
54
- ### Downstream Use [optional]
55
-
56
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
57
-
58
- [More Information Needed]
59
-
60
- ### Out-of-Scope Use
61
-
62
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
63
-
64
- [More Information Needed]
65
-
66
- ## Bias, Risks, and Limitations
67
-
68
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
69
-
70
- [More Information Needed]
71
-
72
- ### Recommendations
73
-
74
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
75
-
76
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
77
-
78
- ## How to Get Started with the Model
79
-
80
- Use the code below to get started with the model.
81
-
82
- [More Information Needed]
83
-
84
- ## Training Details
85
-
86
- ### Training Data
87
-
88
- <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
89
-
90
- [More Information Needed]
91
-
92
- ### Training Procedure
93
-
94
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
95
-
96
- #### Preprocessing [optional]
97
-
98
- [More Information Needed]
99
-
100
-
101
- #### Training Hyperparameters
102
-
103
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
104
-
105
- #### Speeds, Sizes, Times [optional]
106
-
107
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
108
-
109
- [More Information Needed]
110
-
111
- ## Evaluation
112
-
113
- <!-- This section describes the evaluation protocols and provides the results. -->
114
-
115
- ### Testing Data, Factors & Metrics
116
-
117
- #### Testing Data
118
-
119
- <!-- This should link to a Dataset Card if possible. -->
120
-
121
- [More Information Needed]
122
-
123
- #### Factors
124
-
125
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
126
-
127
- [More Information Needed]
128
-
129
- #### Metrics
130
-
131
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
132
-
133
- [More Information Needed]
134
-
135
- ### Results
136
-
137
- [More Information Needed]
138
-
139
- #### Summary
140
-
141
-
142
-
143
- ## Model Examination [optional]
144
-
145
- <!-- Relevant interpretability work for the model goes here -->
146
-
147
- [More Information Needed]
148
-
149
- ## Environmental Impact
150
-
151
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
152
-
153
- Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
154
-
155
- - **Hardware Type:** [More Information Needed]
156
- - **Hours used:** [More Information Needed]
157
- - **Cloud Provider:** [More Information Needed]
158
- - **Compute Region:** [More Information Needed]
159
- - **Carbon Emitted:** [More Information Needed]
160
-
161
- ## Technical Specifications [optional]
162
-
163
- ### Model Architecture and Objective
164
-
165
- [More Information Needed]
166
-
167
- ### Compute Infrastructure
168
-
169
- [More Information Needed]
170
-
171
- #### Hardware
172
-
173
- [More Information Needed]
174
-
175
- #### Software
176
-
177
- [More Information Needed]
178
-
179
- ## Citation [optional]
180
-
181
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
182
-
183
- **BibTeX:**
184
-
185
- [More Information Needed]
186
-
187
- **APA:**
188
-
189
- [More Information Needed]
190
-
191
- ## Glossary [optional]
192
-
193
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
194
-
195
- [More Information Needed]
196
-
197
- ## More Information [optional]
198
-
199
- [More Information Needed]
200
-
201
- ## Model Card Authors [optional]
202
-
203
- [More Information Needed]
204
-
205
- ## Model Card Contact
206
-
207
- [More Information Needed]
208
- ### Framework versions
209
-
210
- - PEFT 0.18.1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
seed0/checkpoint-105/adapter_config.json DELETED
@@ -1,50 +0,0 @@
1
- {
2
- "alora_invocation_tokens": null,
3
- "alpha_pattern": {},
4
- "arrow_config": null,
5
- "auto_mapping": {
6
- "base_model_class": "Qwen2ForCausalLM",
7
- "parent_library": "transformers.models.qwen2.modeling_qwen2",
8
- "unsloth_fixed": true
9
- },
10
- "base_model_name_or_path": "unsloth/Qwen2.5-7B-Instruct",
11
- "bias": "none",
12
- "corda_config": null,
13
- "ensure_weight_tying": false,
14
- "eva_config": null,
15
- "exclude_modules": null,
16
- "fan_in_fan_out": false,
17
- "inference_mode": true,
18
- "init_lora_weights": true,
19
- "layer_replication": null,
20
- "layers_pattern": null,
21
- "layers_to_transform": null,
22
- "loftq_config": {},
23
- "lora_alpha": 8,
24
- "lora_bias": false,
25
- "lora_dropout": 0.0,
26
- "megatron_config": null,
27
- "megatron_core": "megatron.core",
28
- "modules_to_save": null,
29
- "peft_type": "LORA",
30
- "peft_version": "0.18.1",
31
- "qalora_group_size": 16,
32
- "r": 8,
33
- "rank_pattern": {},
34
- "revision": null,
35
- "target_modules": [
36
- "k_proj",
37
- "v_proj",
38
- "up_proj",
39
- "q_proj",
40
- "down_proj",
41
- "o_proj",
42
- "gate_proj"
43
- ],
44
- "target_parameters": null,
45
- "task_type": "CAUSAL_LM",
46
- "trainable_token_indices": null,
47
- "use_dora": false,
48
- "use_qalora": false,
49
- "use_rslora": false
50
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
seed0/checkpoint-105/adapter_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b394246e7bf02282deaee44ad3964762f291c13d2a43731f98fc8b7ea50ddca6
3
- size 80792096
 
 
 
 
seed0/checkpoint-105/added_tokens.json DELETED
@@ -1,25 +0,0 @@
1
- {
2
- "</tool_call>": 151658,
3
- "<tool_call>": 151657,
4
- "<|PAD_TOKEN|>": 151665,
5
- "<|box_end|>": 151649,
6
- "<|box_start|>": 151648,
7
- "<|endoftext|>": 151643,
8
- "<|file_sep|>": 151664,
9
- "<|fim_middle|>": 151660,
10
- "<|fim_pad|>": 151662,
11
- "<|fim_prefix|>": 151659,
12
- "<|fim_suffix|>": 151661,
13
- "<|im_end|>": 151645,
14
- "<|im_start|>": 151644,
15
- "<|image_pad|>": 151655,
16
- "<|object_ref_end|>": 151647,
17
- "<|object_ref_start|>": 151646,
18
- "<|quad_end|>": 151651,
19
- "<|quad_start|>": 151650,
20
- "<|repo_name|>": 151663,
21
- "<|video_pad|>": 151656,
22
- "<|vision_end|>": 151653,
23
- "<|vision_pad|>": 151654,
24
- "<|vision_start|>": 151652
25
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
seed0/checkpoint-105/chat_template.jinja DELETED
@@ -1,54 +0,0 @@
1
- {%- if tools %}
2
- {{- '<|im_start|>system\n' }}
3
- {%- if messages[0]['role'] == 'system' %}
4
- {{- messages[0]['content'] }}
5
- {%- else %}
6
- {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
- {%- endif %}
8
- {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
- {%- for tool in tools %}
10
- {{- "\n" }}
11
- {{- tool | tojson }}
12
- {%- endfor %}
13
- {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
- {%- else %}
15
- {%- if messages[0]['role'] == 'system' %}
16
- {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
- {%- else %}
18
- {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
- {%- endif %}
20
- {%- endif %}
21
- {%- for message in messages %}
22
- {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
- {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
- {%- elif message.role == "assistant" %}
25
- {{- '<|im_start|>' + message.role }}
26
- {%- if message.content %}
27
- {{- '\n' + message.content }}
28
- {%- endif %}
29
- {%- for tool_call in message.tool_calls %}
30
- {%- if tool_call.function is defined %}
31
- {%- set tool_call = tool_call.function %}
32
- {%- endif %}
33
- {{- '\n<tool_call>\n{"name": "' }}
34
- {{- tool_call.name }}
35
- {{- '", "arguments": ' }}
36
- {{- tool_call.arguments | tojson }}
37
- {{- '}\n</tool_call>' }}
38
- {%- endfor %}
39
- {{- '<|im_end|>\n' }}
40
- {%- elif message.role == "tool" %}
41
- {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
- {{- '<|im_start|>user' }}
43
- {%- endif %}
44
- {{- '\n<tool_response>\n' }}
45
- {{- message.content }}
46
- {{- '\n</tool_response>' }}
47
- {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
- {{- '<|im_end|>\n' }}
49
- {%- endif %}
50
- {%- endif %}
51
- {%- endfor %}
52
- {%- if add_generation_prompt %}
53
- {{- '<|im_start|>assistant\n' }}
54
- {%- endif %}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
seed0/checkpoint-105/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
seed0/checkpoint-105/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3a70b3e0c7eb459e3265518432c62539226dd816a9e0838631b1951c07e89b7
3
- size 161816187
 
 
 
 
seed0/checkpoint-105/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:12e15e837284f30841feeb4cb11a4ca47e6e0a0d43907e64044c865959176390
3
- size 14581
 
 
 
 
seed0/checkpoint-105/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:acc99216d43e7edd1cbe872ffadd594d64c3e8a8a9c853f25a483bd076f55901
3
- size 1465
 
 
 
 
seed0/checkpoint-105/special_tokens_map.json DELETED
@@ -1,25 +0,0 @@
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": "<|PAD_TOKEN|>"
25
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
seed0/checkpoint-105/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fab42efe8d17406525a9154b728cf9e957629a8ed7ce997770efdd71128c6a1a
3
- size 11422086
 
 
 
 
seed0/checkpoint-105/tokenizer_config.json DELETED
@@ -1,216 +0,0 @@
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": "<|PAD_TOKEN|>",
183
- "lstrip": false,
184
- "normalized": false,
185
- "rstrip": false,
186
- "single_word": false,
187
- "special": true
188
- }
189
- },
190
- "additional_special_tokens": [
191
- "<|im_start|>",
192
- "<|im_end|>",
193
- "<|object_ref_start|>",
194
- "<|object_ref_end|>",
195
- "<|box_start|>",
196
- "<|box_end|>",
197
- "<|quad_start|>",
198
- "<|quad_end|>",
199
- "<|vision_start|>",
200
- "<|vision_end|>",
201
- "<|vision_pad|>",
202
- "<|image_pad|>",
203
- "<|video_pad|>"
204
- ],
205
- "bos_token": null,
206
- "clean_up_tokenization_spaces": false,
207
- "eos_token": "<|im_end|>",
208
- "errors": "replace",
209
- "extra_special_tokens": {},
210
- "model_max_length": 32768,
211
- "pad_token": "<|PAD_TOKEN|>",
212
- "padding_side": "right",
213
- "split_special_tokens": false,
214
- "tokenizer_class": "Qwen2Tokenizer",
215
- "unk_token": null
216
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
seed0/checkpoint-105/trainer_state.json DELETED
@@ -1,769 +0,0 @@
1
- {
2
- "best_global_step": null,
3
- "best_metric": null,
4
- "best_model_checkpoint": null,
5
- "epoch": 0.6923076923076923,
6
- "eval_steps": 500,
7
- "global_step": 105,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "epoch": 0.006593406593406593,
14
- "grad_norm": 0.8349836468696594,
15
- "learning_rate": 0.0,
16
- "loss": 0.9434,
17
- "step": 1
18
- },
19
- {
20
- "epoch": 0.013186813186813187,
21
- "grad_norm": 0.8700987696647644,
22
- "learning_rate": 4e-05,
23
- "loss": 0.9905,
24
- "step": 2
25
- },
26
- {
27
- "epoch": 0.01978021978021978,
28
- "grad_norm": 0.9241365194320679,
29
- "learning_rate": 8e-05,
30
- "loss": 0.9438,
31
- "step": 3
32
- },
33
- {
34
- "epoch": 0.026373626373626374,
35
- "grad_norm": 0.9019892811775208,
36
- "learning_rate": 0.00012,
37
- "loss": 0.9216,
38
- "step": 4
39
- },
40
- {
41
- "epoch": 0.03296703296703297,
42
- "grad_norm": 0.8872910141944885,
43
- "learning_rate": 0.00016,
44
- "loss": 0.9374,
45
- "step": 5
46
- },
47
- {
48
- "epoch": 0.03956043956043956,
49
- "grad_norm": 0.5874530076980591,
50
- "learning_rate": 0.0002,
51
- "loss": 0.7673,
52
- "step": 6
53
- },
54
- {
55
- "epoch": 0.046153846153846156,
56
- "grad_norm": 0.5062956809997559,
57
- "learning_rate": 0.00019955654101995565,
58
- "loss": 0.8011,
59
- "step": 7
60
- },
61
- {
62
- "epoch": 0.05274725274725275,
63
- "grad_norm": 0.5953829288482666,
64
- "learning_rate": 0.00019911308203991133,
65
- "loss": 0.8455,
66
- "step": 8
67
- },
68
- {
69
- "epoch": 0.05934065934065934,
70
- "grad_norm": 0.5616072416305542,
71
- "learning_rate": 0.00019866962305986697,
72
- "loss": 0.8265,
73
- "step": 9
74
- },
75
- {
76
- "epoch": 0.06593406593406594,
77
- "grad_norm": 0.49180087447166443,
78
- "learning_rate": 0.00019822616407982261,
79
- "loss": 0.8561,
80
- "step": 10
81
- },
82
- {
83
- "epoch": 0.07252747252747253,
84
- "grad_norm": 0.42030951380729675,
85
- "learning_rate": 0.00019778270509977829,
86
- "loss": 0.8796,
87
- "step": 11
88
- },
89
- {
90
- "epoch": 0.07912087912087912,
91
- "grad_norm": 0.3004567325115204,
92
- "learning_rate": 0.00019733924611973393,
93
- "loss": 0.8636,
94
- "step": 12
95
- },
96
- {
97
- "epoch": 0.08571428571428572,
98
- "grad_norm": 0.2698984444141388,
99
- "learning_rate": 0.0001968957871396896,
100
- "loss": 0.718,
101
- "step": 13
102
- },
103
- {
104
- "epoch": 0.09230769230769231,
105
- "grad_norm": 0.25445133447647095,
106
- "learning_rate": 0.00019645232815964525,
107
- "loss": 0.7235,
108
- "step": 14
109
- },
110
- {
111
- "epoch": 0.0989010989010989,
112
- "grad_norm": 0.22418756783008575,
113
- "learning_rate": 0.00019600886917960092,
114
- "loss": 0.688,
115
- "step": 15
116
- },
117
- {
118
- "epoch": 0.1054945054945055,
119
- "grad_norm": 0.2096303105354309,
120
- "learning_rate": 0.00019556541019955653,
121
- "loss": 0.7267,
122
- "step": 16
123
- },
124
- {
125
- "epoch": 0.11208791208791209,
126
- "grad_norm": 0.3029191195964813,
127
- "learning_rate": 0.0001951219512195122,
128
- "loss": 0.7763,
129
- "step": 17
130
- },
131
- {
132
- "epoch": 0.11868131868131868,
133
- "grad_norm": 0.2644464075565338,
134
- "learning_rate": 0.00019467849223946785,
135
- "loss": 0.7618,
136
- "step": 18
137
- },
138
- {
139
- "epoch": 0.12527472527472527,
140
- "grad_norm": 0.2536560893058777,
141
- "learning_rate": 0.00019423503325942352,
142
- "loss": 0.7999,
143
- "step": 19
144
- },
145
- {
146
- "epoch": 0.13186813186813187,
147
- "grad_norm": 0.24718916416168213,
148
- "learning_rate": 0.00019379157427937917,
149
- "loss": 0.752,
150
- "step": 20
151
- },
152
- {
153
- "epoch": 0.13846153846153847,
154
- "grad_norm": 0.2625150680541992,
155
- "learning_rate": 0.00019334811529933484,
156
- "loss": 0.736,
157
- "step": 21
158
- },
159
- {
160
- "epoch": 0.14505494505494507,
161
- "grad_norm": 0.32164040207862854,
162
- "learning_rate": 0.00019290465631929045,
163
- "loss": 0.7043,
164
- "step": 22
165
- },
166
- {
167
- "epoch": 0.15164835164835164,
168
- "grad_norm": 0.3981449604034424,
169
- "learning_rate": 0.00019246119733924613,
170
- "loss": 0.7057,
171
- "step": 23
172
- },
173
- {
174
- "epoch": 0.15824175824175823,
175
- "grad_norm": 0.3817313015460968,
176
- "learning_rate": 0.00019201773835920177,
177
- "loss": 0.7413,
178
- "step": 24
179
- },
180
- {
181
- "epoch": 0.16483516483516483,
182
- "grad_norm": 0.29256680607795715,
183
- "learning_rate": 0.00019157427937915744,
184
- "loss": 0.693,
185
- "step": 25
186
- },
187
- {
188
- "epoch": 0.17142857142857143,
189
- "grad_norm": 0.27523350715637207,
190
- "learning_rate": 0.00019113082039911309,
191
- "loss": 0.6474,
192
- "step": 26
193
- },
194
- {
195
- "epoch": 0.17802197802197803,
196
- "grad_norm": 0.23511967062950134,
197
- "learning_rate": 0.00019068736141906876,
198
- "loss": 0.6519,
199
- "step": 27
200
- },
201
- {
202
- "epoch": 0.18461538461538463,
203
- "grad_norm": 0.2961374819278717,
204
- "learning_rate": 0.0001902439024390244,
205
- "loss": 0.6426,
206
- "step": 28
207
- },
208
- {
209
- "epoch": 0.1912087912087912,
210
- "grad_norm": 0.2760772407054901,
211
- "learning_rate": 0.00018980044345898005,
212
- "loss": 0.7388,
213
- "step": 29
214
- },
215
- {
216
- "epoch": 0.1978021978021978,
217
- "grad_norm": 0.2285313606262207,
218
- "learning_rate": 0.00018935698447893572,
219
- "loss": 0.7756,
220
- "step": 30
221
- },
222
- {
223
- "epoch": 0.2043956043956044,
224
- "grad_norm": 0.2657061517238617,
225
- "learning_rate": 0.00018891352549889136,
226
- "loss": 0.7275,
227
- "step": 31
228
- },
229
- {
230
- "epoch": 0.210989010989011,
231
- "grad_norm": 0.22572828829288483,
232
- "learning_rate": 0.00018847006651884703,
233
- "loss": 0.6793,
234
- "step": 32
235
- },
236
- {
237
- "epoch": 0.2175824175824176,
238
- "grad_norm": 0.26335304975509644,
239
- "learning_rate": 0.00018802660753880268,
240
- "loss": 0.7131,
241
- "step": 33
242
- },
243
- {
244
- "epoch": 0.22417582417582418,
245
- "grad_norm": 0.25231942534446716,
246
- "learning_rate": 0.00018758314855875832,
247
- "loss": 0.7715,
248
- "step": 34
249
- },
250
- {
251
- "epoch": 0.23076923076923078,
252
- "grad_norm": 0.2437426745891571,
253
- "learning_rate": 0.00018713968957871397,
254
- "loss": 0.7094,
255
- "step": 35
256
- },
257
- {
258
- "epoch": 0.23736263736263735,
259
- "grad_norm": 0.28558826446533203,
260
- "learning_rate": 0.00018669623059866964,
261
- "loss": 0.6937,
262
- "step": 36
263
- },
264
- {
265
- "epoch": 0.24395604395604395,
266
- "grad_norm": 0.2915894687175751,
267
- "learning_rate": 0.00018625277161862528,
268
- "loss": 0.7238,
269
- "step": 37
270
- },
271
- {
272
- "epoch": 0.25054945054945055,
273
- "grad_norm": 0.25342074036598206,
274
- "learning_rate": 0.00018580931263858095,
275
- "loss": 0.7323,
276
- "step": 38
277
- },
278
- {
279
- "epoch": 0.2571428571428571,
280
- "grad_norm": 0.22744007408618927,
281
- "learning_rate": 0.0001853658536585366,
282
- "loss": 0.703,
283
- "step": 39
284
- },
285
- {
286
- "epoch": 0.26373626373626374,
287
- "grad_norm": 0.25383231043815613,
288
- "learning_rate": 0.00018492239467849224,
289
- "loss": 0.7093,
290
- "step": 40
291
- },
292
- {
293
- "epoch": 0.2703296703296703,
294
- "grad_norm": 0.2194337695837021,
295
- "learning_rate": 0.0001844789356984479,
296
- "loss": 0.7367,
297
- "step": 41
298
- },
299
- {
300
- "epoch": 0.27692307692307694,
301
- "grad_norm": 0.32021859288215637,
302
- "learning_rate": 0.00018403547671840356,
303
- "loss": 0.6652,
304
- "step": 42
305
- },
306
- {
307
- "epoch": 0.2835164835164835,
308
- "grad_norm": 0.2328304797410965,
309
- "learning_rate": 0.0001835920177383592,
310
- "loss": 0.7016,
311
- "step": 43
312
- },
313
- {
314
- "epoch": 0.29010989010989013,
315
- "grad_norm": 0.24166613817214966,
316
- "learning_rate": 0.00018314855875831487,
317
- "loss": 0.6717,
318
- "step": 44
319
- },
320
- {
321
- "epoch": 0.2967032967032967,
322
- "grad_norm": 0.2733803391456604,
323
- "learning_rate": 0.00018270509977827052,
324
- "loss": 0.6979,
325
- "step": 45
326
- },
327
- {
328
- "epoch": 0.3032967032967033,
329
- "grad_norm": 0.2689957320690155,
330
- "learning_rate": 0.00018226164079822616,
331
- "loss": 0.6977,
332
- "step": 46
333
- },
334
- {
335
- "epoch": 0.3098901098901099,
336
- "grad_norm": 0.2698104977607727,
337
- "learning_rate": 0.00018181818181818183,
338
- "loss": 0.723,
339
- "step": 47
340
- },
341
- {
342
- "epoch": 0.31648351648351647,
343
- "grad_norm": 0.25856417417526245,
344
- "learning_rate": 0.00018137472283813748,
345
- "loss": 0.723,
346
- "step": 48
347
- },
348
- {
349
- "epoch": 0.3230769230769231,
350
- "grad_norm": 0.22988826036453247,
351
- "learning_rate": 0.00018093126385809312,
352
- "loss": 0.7356,
353
- "step": 49
354
- },
355
- {
356
- "epoch": 0.32967032967032966,
357
- "grad_norm": 0.24859416484832764,
358
- "learning_rate": 0.0001804878048780488,
359
- "loss": 0.6671,
360
- "step": 50
361
- },
362
- {
363
- "epoch": 0.3362637362637363,
364
- "grad_norm": 0.24891626834869385,
365
- "learning_rate": 0.00018004434589800444,
366
- "loss": 0.6628,
367
- "step": 51
368
- },
369
- {
370
- "epoch": 0.34285714285714286,
371
- "grad_norm": 0.22740386426448822,
372
- "learning_rate": 0.00017960088691796008,
373
- "loss": 0.6377,
374
- "step": 52
375
- },
376
- {
377
- "epoch": 0.34945054945054943,
378
- "grad_norm": 0.2636365294456482,
379
- "learning_rate": 0.00017915742793791575,
380
- "loss": 0.6901,
381
- "step": 53
382
- },
383
- {
384
- "epoch": 0.35604395604395606,
385
- "grad_norm": 0.2437390238046646,
386
- "learning_rate": 0.0001787139689578714,
387
- "loss": 0.72,
388
- "step": 54
389
- },
390
- {
391
- "epoch": 0.3626373626373626,
392
- "grad_norm": 0.23658742010593414,
393
- "learning_rate": 0.00017827050997782707,
394
- "loss": 0.7365,
395
- "step": 55
396
- },
397
- {
398
- "epoch": 0.36923076923076925,
399
- "grad_norm": 0.23923538625240326,
400
- "learning_rate": 0.00017782705099778271,
401
- "loss": 0.706,
402
- "step": 56
403
- },
404
- {
405
- "epoch": 0.3758241758241758,
406
- "grad_norm": 0.2877054512500763,
407
- "learning_rate": 0.00017738359201773839,
408
- "loss": 0.7436,
409
- "step": 57
410
- },
411
- {
412
- "epoch": 0.3824175824175824,
413
- "grad_norm": 0.2839520573616028,
414
- "learning_rate": 0.000176940133037694,
415
- "loss": 0.6779,
416
- "step": 58
417
- },
418
- {
419
- "epoch": 0.389010989010989,
420
- "grad_norm": 0.2308293879032135,
421
- "learning_rate": 0.00017649667405764967,
422
- "loss": 0.6357,
423
- "step": 59
424
- },
425
- {
426
- "epoch": 0.3956043956043956,
427
- "grad_norm": 0.24402214586734772,
428
- "learning_rate": 0.00017605321507760532,
429
- "loss": 0.7508,
430
- "step": 60
431
- },
432
- {
433
- "epoch": 0.4021978021978022,
434
- "grad_norm": 0.23816415667533875,
435
- "learning_rate": 0.000175609756097561,
436
- "loss": 0.7249,
437
- "step": 61
438
- },
439
- {
440
- "epoch": 0.4087912087912088,
441
- "grad_norm": 0.28321942687034607,
442
- "learning_rate": 0.00017516629711751663,
443
- "loss": 0.7479,
444
- "step": 62
445
- },
446
- {
447
- "epoch": 0.4153846153846154,
448
- "grad_norm": 0.23680296540260315,
449
- "learning_rate": 0.0001747228381374723,
450
- "loss": 0.6413,
451
- "step": 63
452
- },
453
- {
454
- "epoch": 0.421978021978022,
455
- "grad_norm": 0.23129238188266754,
456
- "learning_rate": 0.00017427937915742792,
457
- "loss": 0.6786,
458
- "step": 64
459
- },
460
- {
461
- "epoch": 0.42857142857142855,
462
- "grad_norm": 0.25140181183815,
463
- "learning_rate": 0.0001738359201773836,
464
- "loss": 0.7167,
465
- "step": 65
466
- },
467
- {
468
- "epoch": 0.4351648351648352,
469
- "grad_norm": 0.27190810441970825,
470
- "learning_rate": 0.00017339246119733924,
471
- "loss": 0.6267,
472
- "step": 66
473
- },
474
- {
475
- "epoch": 0.44175824175824174,
476
- "grad_norm": 0.23768772184848785,
477
- "learning_rate": 0.0001729490022172949,
478
- "loss": 0.7397,
479
- "step": 67
480
- },
481
- {
482
- "epoch": 0.44835164835164837,
483
- "grad_norm": 0.2618238031864166,
484
- "learning_rate": 0.00017250554323725056,
485
- "loss": 0.6987,
486
- "step": 68
487
- },
488
- {
489
- "epoch": 0.45494505494505494,
490
- "grad_norm": 0.24789907038211823,
491
- "learning_rate": 0.00017206208425720623,
492
- "loss": 0.6223,
493
- "step": 69
494
- },
495
- {
496
- "epoch": 0.46153846153846156,
497
- "grad_norm": 0.2744330167770386,
498
- "learning_rate": 0.00017161862527716187,
499
- "loss": 0.6964,
500
- "step": 70
501
- },
502
- {
503
- "epoch": 0.46813186813186813,
504
- "grad_norm": 0.23732465505599976,
505
- "learning_rate": 0.00017117516629711752,
506
- "loss": 0.6524,
507
- "step": 71
508
- },
509
- {
510
- "epoch": 0.4747252747252747,
511
- "grad_norm": 0.2278261035680771,
512
- "learning_rate": 0.0001707317073170732,
513
- "loss": 0.7437,
514
- "step": 72
515
- },
516
- {
517
- "epoch": 0.48131868131868133,
518
- "grad_norm": 0.24909941852092743,
519
- "learning_rate": 0.00017028824833702883,
520
- "loss": 0.6955,
521
- "step": 73
522
- },
523
- {
524
- "epoch": 0.4879120879120879,
525
- "grad_norm": 0.3007880449295044,
526
- "learning_rate": 0.0001698447893569845,
527
- "loss": 0.625,
528
- "step": 74
529
- },
530
- {
531
- "epoch": 0.4945054945054945,
532
- "grad_norm": 0.2338089644908905,
533
- "learning_rate": 0.00016940133037694015,
534
- "loss": 0.6843,
535
- "step": 75
536
- },
537
- {
538
- "epoch": 0.5010989010989011,
539
- "grad_norm": 0.27349653840065,
540
- "learning_rate": 0.00016895787139689582,
541
- "loss": 0.6825,
542
- "step": 76
543
- },
544
- {
545
- "epoch": 0.5076923076923077,
546
- "grad_norm": 0.2793181836605072,
547
- "learning_rate": 0.00016851441241685144,
548
- "loss": 0.6529,
549
- "step": 77
550
- },
551
- {
552
- "epoch": 0.5142857142857142,
553
- "grad_norm": 0.2612224221229553,
554
- "learning_rate": 0.0001680709534368071,
555
- "loss": 0.6807,
556
- "step": 78
557
- },
558
- {
559
- "epoch": 0.5208791208791209,
560
- "grad_norm": 0.2740105986595154,
561
- "learning_rate": 0.00016762749445676275,
562
- "loss": 0.6294,
563
- "step": 79
564
- },
565
- {
566
- "epoch": 0.5274725274725275,
567
- "grad_norm": 0.2226412147283554,
568
- "learning_rate": 0.00016718403547671842,
569
- "loss": 0.6569,
570
- "step": 80
571
- },
572
- {
573
- "epoch": 0.5340659340659341,
574
- "grad_norm": 0.2254134714603424,
575
- "learning_rate": 0.00016674057649667407,
576
- "loss": 0.6569,
577
- "step": 81
578
- },
579
- {
580
- "epoch": 0.5406593406593406,
581
- "grad_norm": 0.22373083233833313,
582
- "learning_rate": 0.00016629711751662974,
583
- "loss": 0.6733,
584
- "step": 82
585
- },
586
- {
587
- "epoch": 0.5472527472527473,
588
- "grad_norm": 0.2485770583152771,
589
- "learning_rate": 0.00016585365853658536,
590
- "loss": 0.6422,
591
- "step": 83
592
- },
593
- {
594
- "epoch": 0.5538461538461539,
595
- "grad_norm": 0.25764942169189453,
596
- "learning_rate": 0.00016541019955654103,
597
- "loss": 0.6682,
598
- "step": 84
599
- },
600
- {
601
- "epoch": 0.5604395604395604,
602
- "grad_norm": 0.24047411978244781,
603
- "learning_rate": 0.00016496674057649667,
604
- "loss": 0.7126,
605
- "step": 85
606
- },
607
- {
608
- "epoch": 0.567032967032967,
609
- "grad_norm": 0.21252930164337158,
610
- "learning_rate": 0.00016452328159645234,
611
- "loss": 0.7109,
612
- "step": 86
613
- },
614
- {
615
- "epoch": 0.5736263736263736,
616
- "grad_norm": 0.25431081652641296,
617
- "learning_rate": 0.000164079822616408,
618
- "loss": 0.6416,
619
- "step": 87
620
- },
621
- {
622
- "epoch": 0.5802197802197803,
623
- "grad_norm": 0.24909189343452454,
624
- "learning_rate": 0.00016363636363636366,
625
- "loss": 0.6963,
626
- "step": 88
627
- },
628
- {
629
- "epoch": 0.5868131868131868,
630
- "grad_norm": 0.25534072518348694,
631
- "learning_rate": 0.0001631929046563193,
632
- "loss": 0.7898,
633
- "step": 89
634
- },
635
- {
636
- "epoch": 0.5934065934065934,
637
- "grad_norm": 0.22847016155719757,
638
- "learning_rate": 0.00016274944567627495,
639
- "loss": 0.6903,
640
- "step": 90
641
- },
642
- {
643
- "epoch": 0.6,
644
- "grad_norm": 0.27691230177879333,
645
- "learning_rate": 0.0001623059866962306,
646
- "loss": 0.6963,
647
- "step": 91
648
- },
649
- {
650
- "epoch": 0.6065934065934065,
651
- "grad_norm": 0.2628577649593353,
652
- "learning_rate": 0.00016186252771618626,
653
- "loss": 0.7605,
654
- "step": 92
655
- },
656
- {
657
- "epoch": 0.6131868131868132,
658
- "grad_norm": 0.29095378518104553,
659
- "learning_rate": 0.0001614190687361419,
660
- "loss": 0.6878,
661
- "step": 93
662
- },
663
- {
664
- "epoch": 0.6197802197802198,
665
- "grad_norm": 0.24262812733650208,
666
- "learning_rate": 0.00016097560975609758,
667
- "loss": 0.7383,
668
- "step": 94
669
- },
670
- {
671
- "epoch": 0.6263736263736264,
672
- "grad_norm": 0.21234223246574402,
673
- "learning_rate": 0.00016053215077605322,
674
- "loss": 0.6735,
675
- "step": 95
676
- },
677
- {
678
- "epoch": 0.6329670329670329,
679
- "grad_norm": 0.2478182166814804,
680
- "learning_rate": 0.00016008869179600887,
681
- "loss": 0.6334,
682
- "step": 96
683
- },
684
- {
685
- "epoch": 0.6395604395604395,
686
- "grad_norm": 0.22873812913894653,
687
- "learning_rate": 0.00015964523281596454,
688
- "loss": 0.6968,
689
- "step": 97
690
- },
691
- {
692
- "epoch": 0.6461538461538462,
693
- "grad_norm": 0.24787071347236633,
694
- "learning_rate": 0.00015920177383592018,
695
- "loss": 0.7076,
696
- "step": 98
697
- },
698
- {
699
- "epoch": 0.6527472527472528,
700
- "grad_norm": 0.2913095951080322,
701
- "learning_rate": 0.00015875831485587586,
702
- "loss": 0.6785,
703
- "step": 99
704
- },
705
- {
706
- "epoch": 0.6593406593406593,
707
- "grad_norm": 0.27481356263160706,
708
- "learning_rate": 0.0001583148558758315,
709
- "loss": 0.7055,
710
- "step": 100
711
- },
712
- {
713
- "epoch": 0.6659340659340659,
714
- "grad_norm": 0.24760739505290985,
715
- "learning_rate": 0.00015787139689578714,
716
- "loss": 0.7027,
717
- "step": 101
718
- },
719
- {
720
- "epoch": 0.6725274725274726,
721
- "grad_norm": 0.2754676342010498,
722
- "learning_rate": 0.0001574279379157428,
723
- "loss": 0.7027,
724
- "step": 102
725
- },
726
- {
727
- "epoch": 0.6791208791208792,
728
- "grad_norm": 0.2395099550485611,
729
- "learning_rate": 0.00015698447893569846,
730
- "loss": 0.6846,
731
- "step": 103
732
- },
733
- {
734
- "epoch": 0.6857142857142857,
735
- "grad_norm": 0.2519392669200897,
736
- "learning_rate": 0.0001565410199556541,
737
- "loss": 0.7722,
738
- "step": 104
739
- },
740
- {
741
- "epoch": 0.6923076923076923,
742
- "grad_norm": 0.24618907272815704,
743
- "learning_rate": 0.00015609756097560978,
744
- "loss": 0.6933,
745
- "step": 105
746
- }
747
- ],
748
- "logging_steps": 1,
749
- "max_steps": 456,
750
- "num_input_tokens_seen": 0,
751
- "num_train_epochs": 3,
752
- "save_steps": 15,
753
- "stateful_callbacks": {
754
- "TrainerControl": {
755
- "args": {
756
- "should_epoch_stop": false,
757
- "should_evaluate": false,
758
- "should_log": false,
759
- "should_save": true,
760
- "should_training_stop": false
761
- },
762
- "attributes": {}
763
- }
764
- },
765
- "total_flos": 4.844664351571968e+16,
766
- "train_batch_size": 22,
767
- "trial_name": null,
768
- "trial_params": null
769
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
seed0/checkpoint-105/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0314cf5080efcc9f80748b98c0e8740951e978b06ae398400172ff9f77eb1257
3
- size 6289
 
 
 
 
seed0/checkpoint-105/vocab.json DELETED
The diff for this file is too large to render. See raw diff
 
seed0/checkpoint-120/README.md DELETED
@@ -1,210 +0,0 @@
1
- ---
2
- base_model: unsloth/Qwen2.5-7B-Instruct
3
- library_name: peft
4
- pipeline_tag: text-generation
5
- tags:
6
- - base_model:adapter:unsloth/Qwen2.5-7B-Instruct
7
- - lora
8
- - sft
9
- - transformers
10
- - trl
11
- - unsloth
12
- ---
13
-
14
- # Model Card for Model ID
15
-
16
- <!-- Provide a quick summary of what the model is/does. -->
17
-
18
-
19
-
20
- ## Model Details
21
-
22
- ### Model Description
23
-
24
- <!-- Provide a longer summary of what this model is. -->
25
-
26
-
27
-
28
- - **Developed by:** [More Information Needed]
29
- - **Funded by [optional]:** [More Information Needed]
30
- - **Shared by [optional]:** [More Information Needed]
31
- - **Model type:** [More Information Needed]
32
- - **Language(s) (NLP):** [More Information Needed]
33
- - **License:** [More Information Needed]
34
- - **Finetuned from model [optional]:** [More Information Needed]
35
-
36
- ### Model Sources [optional]
37
-
38
- <!-- Provide the basic links for the model. -->
39
-
40
- - **Repository:** [More Information Needed]
41
- - **Paper [optional]:** [More Information Needed]
42
- - **Demo [optional]:** [More Information Needed]
43
-
44
- ## Uses
45
-
46
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
47
-
48
- ### Direct Use
49
-
50
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
51
-
52
- [More Information Needed]
53
-
54
- ### Downstream Use [optional]
55
-
56
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
57
-
58
- [More Information Needed]
59
-
60
- ### Out-of-Scope Use
61
-
62
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
63
-
64
- [More Information Needed]
65
-
66
- ## Bias, Risks, and Limitations
67
-
68
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
69
-
70
- [More Information Needed]
71
-
72
- ### Recommendations
73
-
74
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
75
-
76
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
77
-
78
- ## How to Get Started with the Model
79
-
80
- Use the code below to get started with the model.
81
-
82
- [More Information Needed]
83
-
84
- ## Training Details
85
-
86
- ### Training Data
87
-
88
- <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
89
-
90
- [More Information Needed]
91
-
92
- ### Training Procedure
93
-
94
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
95
-
96
- #### Preprocessing [optional]
97
-
98
- [More Information Needed]
99
-
100
-
101
- #### Training Hyperparameters
102
-
103
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
104
-
105
- #### Speeds, Sizes, Times [optional]
106
-
107
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
108
-
109
- [More Information Needed]
110
-
111
- ## Evaluation
112
-
113
- <!-- This section describes the evaluation protocols and provides the results. -->
114
-
115
- ### Testing Data, Factors & Metrics
116
-
117
- #### Testing Data
118
-
119
- <!-- This should link to a Dataset Card if possible. -->
120
-
121
- [More Information Needed]
122
-
123
- #### Factors
124
-
125
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
126
-
127
- [More Information Needed]
128
-
129
- #### Metrics
130
-
131
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
132
-
133
- [More Information Needed]
134
-
135
- ### Results
136
-
137
- [More Information Needed]
138
-
139
- #### Summary
140
-
141
-
142
-
143
- ## Model Examination [optional]
144
-
145
- <!-- Relevant interpretability work for the model goes here -->
146
-
147
- [More Information Needed]
148
-
149
- ## Environmental Impact
150
-
151
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
152
-
153
- Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
154
-
155
- - **Hardware Type:** [More Information Needed]
156
- - **Hours used:** [More Information Needed]
157
- - **Cloud Provider:** [More Information Needed]
158
- - **Compute Region:** [More Information Needed]
159
- - **Carbon Emitted:** [More Information Needed]
160
-
161
- ## Technical Specifications [optional]
162
-
163
- ### Model Architecture and Objective
164
-
165
- [More Information Needed]
166
-
167
- ### Compute Infrastructure
168
-
169
- [More Information Needed]
170
-
171
- #### Hardware
172
-
173
- [More Information Needed]
174
-
175
- #### Software
176
-
177
- [More Information Needed]
178
-
179
- ## Citation [optional]
180
-
181
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
182
-
183
- **BibTeX:**
184
-
185
- [More Information Needed]
186
-
187
- **APA:**
188
-
189
- [More Information Needed]
190
-
191
- ## Glossary [optional]
192
-
193
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
194
-
195
- [More Information Needed]
196
-
197
- ## More Information [optional]
198
-
199
- [More Information Needed]
200
-
201
- ## Model Card Authors [optional]
202
-
203
- [More Information Needed]
204
-
205
- ## Model Card Contact
206
-
207
- [More Information Needed]
208
- ### Framework versions
209
-
210
- - PEFT 0.18.1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
seed0/checkpoint-120/adapter_config.json DELETED
@@ -1,50 +0,0 @@
1
- {
2
- "alora_invocation_tokens": null,
3
- "alpha_pattern": {},
4
- "arrow_config": null,
5
- "auto_mapping": {
6
- "base_model_class": "Qwen2ForCausalLM",
7
- "parent_library": "transformers.models.qwen2.modeling_qwen2",
8
- "unsloth_fixed": true
9
- },
10
- "base_model_name_or_path": "unsloth/Qwen2.5-7B-Instruct",
11
- "bias": "none",
12
- "corda_config": null,
13
- "ensure_weight_tying": false,
14
- "eva_config": null,
15
- "exclude_modules": null,
16
- "fan_in_fan_out": false,
17
- "inference_mode": true,
18
- "init_lora_weights": true,
19
- "layer_replication": null,
20
- "layers_pattern": null,
21
- "layers_to_transform": null,
22
- "loftq_config": {},
23
- "lora_alpha": 8,
24
- "lora_bias": false,
25
- "lora_dropout": 0.0,
26
- "megatron_config": null,
27
- "megatron_core": "megatron.core",
28
- "modules_to_save": null,
29
- "peft_type": "LORA",
30
- "peft_version": "0.18.1",
31
- "qalora_group_size": 16,
32
- "r": 8,
33
- "rank_pattern": {},
34
- "revision": null,
35
- "target_modules": [
36
- "k_proj",
37
- "v_proj",
38
- "up_proj",
39
- "q_proj",
40
- "down_proj",
41
- "o_proj",
42
- "gate_proj"
43
- ],
44
- "target_parameters": null,
45
- "task_type": "CAUSAL_LM",
46
- "trainable_token_indices": null,
47
- "use_dora": false,
48
- "use_qalora": false,
49
- "use_rslora": false
50
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
seed0/checkpoint-120/adapter_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd31ad9de1d4969ab8703971a3236d29b492669bd6f9150c8ba1a498deec0d25
3
- size 80792096
 
 
 
 
seed0/checkpoint-120/added_tokens.json DELETED
@@ -1,25 +0,0 @@
1
- {
2
- "</tool_call>": 151658,
3
- "<tool_call>": 151657,
4
- "<|PAD_TOKEN|>": 151665,
5
- "<|box_end|>": 151649,
6
- "<|box_start|>": 151648,
7
- "<|endoftext|>": 151643,
8
- "<|file_sep|>": 151664,
9
- "<|fim_middle|>": 151660,
10
- "<|fim_pad|>": 151662,
11
- "<|fim_prefix|>": 151659,
12
- "<|fim_suffix|>": 151661,
13
- "<|im_end|>": 151645,
14
- "<|im_start|>": 151644,
15
- "<|image_pad|>": 151655,
16
- "<|object_ref_end|>": 151647,
17
- "<|object_ref_start|>": 151646,
18
- "<|quad_end|>": 151651,
19
- "<|quad_start|>": 151650,
20
- "<|repo_name|>": 151663,
21
- "<|video_pad|>": 151656,
22
- "<|vision_end|>": 151653,
23
- "<|vision_pad|>": 151654,
24
- "<|vision_start|>": 151652
25
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
seed0/checkpoint-120/chat_template.jinja DELETED
@@ -1,54 +0,0 @@
1
- {%- if tools %}
2
- {{- '<|im_start|>system\n' }}
3
- {%- if messages[0]['role'] == 'system' %}
4
- {{- messages[0]['content'] }}
5
- {%- else %}
6
- {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
- {%- endif %}
8
- {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
- {%- for tool in tools %}
10
- {{- "\n" }}
11
- {{- tool | tojson }}
12
- {%- endfor %}
13
- {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
- {%- else %}
15
- {%- if messages[0]['role'] == 'system' %}
16
- {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
- {%- else %}
18
- {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
- {%- endif %}
20
- {%- endif %}
21
- {%- for message in messages %}
22
- {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
- {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
- {%- elif message.role == "assistant" %}
25
- {{- '<|im_start|>' + message.role }}
26
- {%- if message.content %}
27
- {{- '\n' + message.content }}
28
- {%- endif %}
29
- {%- for tool_call in message.tool_calls %}
30
- {%- if tool_call.function is defined %}
31
- {%- set tool_call = tool_call.function %}
32
- {%- endif %}
33
- {{- '\n<tool_call>\n{"name": "' }}
34
- {{- tool_call.name }}
35
- {{- '", "arguments": ' }}
36
- {{- tool_call.arguments | tojson }}
37
- {{- '}\n</tool_call>' }}
38
- {%- endfor %}
39
- {{- '<|im_end|>\n' }}
40
- {%- elif message.role == "tool" %}
41
- {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
- {{- '<|im_start|>user' }}
43
- {%- endif %}
44
- {{- '\n<tool_response>\n' }}
45
- {{- message.content }}
46
- {{- '\n</tool_response>' }}
47
- {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
- {{- '<|im_end|>\n' }}
49
- {%- endif %}
50
- {%- endif %}
51
- {%- endfor %}
52
- {%- if add_generation_prompt %}
53
- {{- '<|im_start|>assistant\n' }}
54
- {%- endif %}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
seed0/checkpoint-120/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
seed0/checkpoint-120/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa53e2f8e77be99e0b15335e00c9ace7897fb836fef3df2997976afe5c6b9fce
3
- size 161816187
 
 
 
 
seed0/checkpoint-120/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:12e15e837284f30841feeb4cb11a4ca47e6e0a0d43907e64044c865959176390
3
- size 14581
 
 
 
 
seed0/checkpoint-120/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:be392162982fbbf8b58be63a4e8e0f734f84a91e870656d6fe933f7351978f9a
3
- size 1465
 
 
 
 
seed0/checkpoint-120/special_tokens_map.json DELETED
@@ -1,25 +0,0 @@
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": "<|PAD_TOKEN|>"
25
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
seed0/checkpoint-120/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fab42efe8d17406525a9154b728cf9e957629a8ed7ce997770efdd71128c6a1a
3
- size 11422086
 
 
 
 
seed0/checkpoint-120/tokenizer_config.json DELETED
@@ -1,216 +0,0 @@
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": "<|PAD_TOKEN|>",
183
- "lstrip": false,
184
- "normalized": false,
185
- "rstrip": false,
186
- "single_word": false,
187
- "special": true
188
- }
189
- },
190
- "additional_special_tokens": [
191
- "<|im_start|>",
192
- "<|im_end|>",
193
- "<|object_ref_start|>",
194
- "<|object_ref_end|>",
195
- "<|box_start|>",
196
- "<|box_end|>",
197
- "<|quad_start|>",
198
- "<|quad_end|>",
199
- "<|vision_start|>",
200
- "<|vision_end|>",
201
- "<|vision_pad|>",
202
- "<|image_pad|>",
203
- "<|video_pad|>"
204
- ],
205
- "bos_token": null,
206
- "clean_up_tokenization_spaces": false,
207
- "eos_token": "<|im_end|>",
208
- "errors": "replace",
209
- "extra_special_tokens": {},
210
- "model_max_length": 32768,
211
- "pad_token": "<|PAD_TOKEN|>",
212
- "padding_side": "right",
213
- "split_special_tokens": false,
214
- "tokenizer_class": "Qwen2Tokenizer",
215
- "unk_token": null
216
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
seed0/checkpoint-120/trainer_state.json DELETED
@@ -1,874 +0,0 @@
1
- {
2
- "best_global_step": null,
3
- "best_metric": null,
4
- "best_model_checkpoint": null,
5
- "epoch": 0.7912087912087912,
6
- "eval_steps": 500,
7
- "global_step": 120,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "epoch": 0.006593406593406593,
14
- "grad_norm": 0.8349836468696594,
15
- "learning_rate": 0.0,
16
- "loss": 0.9434,
17
- "step": 1
18
- },
19
- {
20
- "epoch": 0.013186813186813187,
21
- "grad_norm": 0.8700987696647644,
22
- "learning_rate": 4e-05,
23
- "loss": 0.9905,
24
- "step": 2
25
- },
26
- {
27
- "epoch": 0.01978021978021978,
28
- "grad_norm": 0.9241365194320679,
29
- "learning_rate": 8e-05,
30
- "loss": 0.9438,
31
- "step": 3
32
- },
33
- {
34
- "epoch": 0.026373626373626374,
35
- "grad_norm": 0.9019892811775208,
36
- "learning_rate": 0.00012,
37
- "loss": 0.9216,
38
- "step": 4
39
- },
40
- {
41
- "epoch": 0.03296703296703297,
42
- "grad_norm": 0.8872910141944885,
43
- "learning_rate": 0.00016,
44
- "loss": 0.9374,
45
- "step": 5
46
- },
47
- {
48
- "epoch": 0.03956043956043956,
49
- "grad_norm": 0.5874530076980591,
50
- "learning_rate": 0.0002,
51
- "loss": 0.7673,
52
- "step": 6
53
- },
54
- {
55
- "epoch": 0.046153846153846156,
56
- "grad_norm": 0.5062956809997559,
57
- "learning_rate": 0.00019955654101995565,
58
- "loss": 0.8011,
59
- "step": 7
60
- },
61
- {
62
- "epoch": 0.05274725274725275,
63
- "grad_norm": 0.5953829288482666,
64
- "learning_rate": 0.00019911308203991133,
65
- "loss": 0.8455,
66
- "step": 8
67
- },
68
- {
69
- "epoch": 0.05934065934065934,
70
- "grad_norm": 0.5616072416305542,
71
- "learning_rate": 0.00019866962305986697,
72
- "loss": 0.8265,
73
- "step": 9
74
- },
75
- {
76
- "epoch": 0.06593406593406594,
77
- "grad_norm": 0.49180087447166443,
78
- "learning_rate": 0.00019822616407982261,
79
- "loss": 0.8561,
80
- "step": 10
81
- },
82
- {
83
- "epoch": 0.07252747252747253,
84
- "grad_norm": 0.42030951380729675,
85
- "learning_rate": 0.00019778270509977829,
86
- "loss": 0.8796,
87
- "step": 11
88
- },
89
- {
90
- "epoch": 0.07912087912087912,
91
- "grad_norm": 0.3004567325115204,
92
- "learning_rate": 0.00019733924611973393,
93
- "loss": 0.8636,
94
- "step": 12
95
- },
96
- {
97
- "epoch": 0.08571428571428572,
98
- "grad_norm": 0.2698984444141388,
99
- "learning_rate": 0.0001968957871396896,
100
- "loss": 0.718,
101
- "step": 13
102
- },
103
- {
104
- "epoch": 0.09230769230769231,
105
- "grad_norm": 0.25445133447647095,
106
- "learning_rate": 0.00019645232815964525,
107
- "loss": 0.7235,
108
- "step": 14
109
- },
110
- {
111
- "epoch": 0.0989010989010989,
112
- "grad_norm": 0.22418756783008575,
113
- "learning_rate": 0.00019600886917960092,
114
- "loss": 0.688,
115
- "step": 15
116
- },
117
- {
118
- "epoch": 0.1054945054945055,
119
- "grad_norm": 0.2096303105354309,
120
- "learning_rate": 0.00019556541019955653,
121
- "loss": 0.7267,
122
- "step": 16
123
- },
124
- {
125
- "epoch": 0.11208791208791209,
126
- "grad_norm": 0.3029191195964813,
127
- "learning_rate": 0.0001951219512195122,
128
- "loss": 0.7763,
129
- "step": 17
130
- },
131
- {
132
- "epoch": 0.11868131868131868,
133
- "grad_norm": 0.2644464075565338,
134
- "learning_rate": 0.00019467849223946785,
135
- "loss": 0.7618,
136
- "step": 18
137
- },
138
- {
139
- "epoch": 0.12527472527472527,
140
- "grad_norm": 0.2536560893058777,
141
- "learning_rate": 0.00019423503325942352,
142
- "loss": 0.7999,
143
- "step": 19
144
- },
145
- {
146
- "epoch": 0.13186813186813187,
147
- "grad_norm": 0.24718916416168213,
148
- "learning_rate": 0.00019379157427937917,
149
- "loss": 0.752,
150
- "step": 20
151
- },
152
- {
153
- "epoch": 0.13846153846153847,
154
- "grad_norm": 0.2625150680541992,
155
- "learning_rate": 0.00019334811529933484,
156
- "loss": 0.736,
157
- "step": 21
158
- },
159
- {
160
- "epoch": 0.14505494505494507,
161
- "grad_norm": 0.32164040207862854,
162
- "learning_rate": 0.00019290465631929045,
163
- "loss": 0.7043,
164
- "step": 22
165
- },
166
- {
167
- "epoch": 0.15164835164835164,
168
- "grad_norm": 0.3981449604034424,
169
- "learning_rate": 0.00019246119733924613,
170
- "loss": 0.7057,
171
- "step": 23
172
- },
173
- {
174
- "epoch": 0.15824175824175823,
175
- "grad_norm": 0.3817313015460968,
176
- "learning_rate": 0.00019201773835920177,
177
- "loss": 0.7413,
178
- "step": 24
179
- },
180
- {
181
- "epoch": 0.16483516483516483,
182
- "grad_norm": 0.29256680607795715,
183
- "learning_rate": 0.00019157427937915744,
184
- "loss": 0.693,
185
- "step": 25
186
- },
187
- {
188
- "epoch": 0.17142857142857143,
189
- "grad_norm": 0.27523350715637207,
190
- "learning_rate": 0.00019113082039911309,
191
- "loss": 0.6474,
192
- "step": 26
193
- },
194
- {
195
- "epoch": 0.17802197802197803,
196
- "grad_norm": 0.23511967062950134,
197
- "learning_rate": 0.00019068736141906876,
198
- "loss": 0.6519,
199
- "step": 27
200
- },
201
- {
202
- "epoch": 0.18461538461538463,
203
- "grad_norm": 0.2961374819278717,
204
- "learning_rate": 0.0001902439024390244,
205
- "loss": 0.6426,
206
- "step": 28
207
- },
208
- {
209
- "epoch": 0.1912087912087912,
210
- "grad_norm": 0.2760772407054901,
211
- "learning_rate": 0.00018980044345898005,
212
- "loss": 0.7388,
213
- "step": 29
214
- },
215
- {
216
- "epoch": 0.1978021978021978,
217
- "grad_norm": 0.2285313606262207,
218
- "learning_rate": 0.00018935698447893572,
219
- "loss": 0.7756,
220
- "step": 30
221
- },
222
- {
223
- "epoch": 0.2043956043956044,
224
- "grad_norm": 0.2657061517238617,
225
- "learning_rate": 0.00018891352549889136,
226
- "loss": 0.7275,
227
- "step": 31
228
- },
229
- {
230
- "epoch": 0.210989010989011,
231
- "grad_norm": 0.22572828829288483,
232
- "learning_rate": 0.00018847006651884703,
233
- "loss": 0.6793,
234
- "step": 32
235
- },
236
- {
237
- "epoch": 0.2175824175824176,
238
- "grad_norm": 0.26335304975509644,
239
- "learning_rate": 0.00018802660753880268,
240
- "loss": 0.7131,
241
- "step": 33
242
- },
243
- {
244
- "epoch": 0.22417582417582418,
245
- "grad_norm": 0.25231942534446716,
246
- "learning_rate": 0.00018758314855875832,
247
- "loss": 0.7715,
248
- "step": 34
249
- },
250
- {
251
- "epoch": 0.23076923076923078,
252
- "grad_norm": 0.2437426745891571,
253
- "learning_rate": 0.00018713968957871397,
254
- "loss": 0.7094,
255
- "step": 35
256
- },
257
- {
258
- "epoch": 0.23736263736263735,
259
- "grad_norm": 0.28558826446533203,
260
- "learning_rate": 0.00018669623059866964,
261
- "loss": 0.6937,
262
- "step": 36
263
- },
264
- {
265
- "epoch": 0.24395604395604395,
266
- "grad_norm": 0.2915894687175751,
267
- "learning_rate": 0.00018625277161862528,
268
- "loss": 0.7238,
269
- "step": 37
270
- },
271
- {
272
- "epoch": 0.25054945054945055,
273
- "grad_norm": 0.25342074036598206,
274
- "learning_rate": 0.00018580931263858095,
275
- "loss": 0.7323,
276
- "step": 38
277
- },
278
- {
279
- "epoch": 0.2571428571428571,
280
- "grad_norm": 0.22744007408618927,
281
- "learning_rate": 0.0001853658536585366,
282
- "loss": 0.703,
283
- "step": 39
284
- },
285
- {
286
- "epoch": 0.26373626373626374,
287
- "grad_norm": 0.25383231043815613,
288
- "learning_rate": 0.00018492239467849224,
289
- "loss": 0.7093,
290
- "step": 40
291
- },
292
- {
293
- "epoch": 0.2703296703296703,
294
- "grad_norm": 0.2194337695837021,
295
- "learning_rate": 0.0001844789356984479,
296
- "loss": 0.7367,
297
- "step": 41
298
- },
299
- {
300
- "epoch": 0.27692307692307694,
301
- "grad_norm": 0.32021859288215637,
302
- "learning_rate": 0.00018403547671840356,
303
- "loss": 0.6652,
304
- "step": 42
305
- },
306
- {
307
- "epoch": 0.2835164835164835,
308
- "grad_norm": 0.2328304797410965,
309
- "learning_rate": 0.0001835920177383592,
310
- "loss": 0.7016,
311
- "step": 43
312
- },
313
- {
314
- "epoch": 0.29010989010989013,
315
- "grad_norm": 0.24166613817214966,
316
- "learning_rate": 0.00018314855875831487,
317
- "loss": 0.6717,
318
- "step": 44
319
- },
320
- {
321
- "epoch": 0.2967032967032967,
322
- "grad_norm": 0.2733803391456604,
323
- "learning_rate": 0.00018270509977827052,
324
- "loss": 0.6979,
325
- "step": 45
326
- },
327
- {
328
- "epoch": 0.3032967032967033,
329
- "grad_norm": 0.2689957320690155,
330
- "learning_rate": 0.00018226164079822616,
331
- "loss": 0.6977,
332
- "step": 46
333
- },
334
- {
335
- "epoch": 0.3098901098901099,
336
- "grad_norm": 0.2698104977607727,
337
- "learning_rate": 0.00018181818181818183,
338
- "loss": 0.723,
339
- "step": 47
340
- },
341
- {
342
- "epoch": 0.31648351648351647,
343
- "grad_norm": 0.25856417417526245,
344
- "learning_rate": 0.00018137472283813748,
345
- "loss": 0.723,
346
- "step": 48
347
- },
348
- {
349
- "epoch": 0.3230769230769231,
350
- "grad_norm": 0.22988826036453247,
351
- "learning_rate": 0.00018093126385809312,
352
- "loss": 0.7356,
353
- "step": 49
354
- },
355
- {
356
- "epoch": 0.32967032967032966,
357
- "grad_norm": 0.24859416484832764,
358
- "learning_rate": 0.0001804878048780488,
359
- "loss": 0.6671,
360
- "step": 50
361
- },
362
- {
363
- "epoch": 0.3362637362637363,
364
- "grad_norm": 0.24891626834869385,
365
- "learning_rate": 0.00018004434589800444,
366
- "loss": 0.6628,
367
- "step": 51
368
- },
369
- {
370
- "epoch": 0.34285714285714286,
371
- "grad_norm": 0.22740386426448822,
372
- "learning_rate": 0.00017960088691796008,
373
- "loss": 0.6377,
374
- "step": 52
375
- },
376
- {
377
- "epoch": 0.34945054945054943,
378
- "grad_norm": 0.2636365294456482,
379
- "learning_rate": 0.00017915742793791575,
380
- "loss": 0.6901,
381
- "step": 53
382
- },
383
- {
384
- "epoch": 0.35604395604395606,
385
- "grad_norm": 0.2437390238046646,
386
- "learning_rate": 0.0001787139689578714,
387
- "loss": 0.72,
388
- "step": 54
389
- },
390
- {
391
- "epoch": 0.3626373626373626,
392
- "grad_norm": 0.23658742010593414,
393
- "learning_rate": 0.00017827050997782707,
394
- "loss": 0.7365,
395
- "step": 55
396
- },
397
- {
398
- "epoch": 0.36923076923076925,
399
- "grad_norm": 0.23923538625240326,
400
- "learning_rate": 0.00017782705099778271,
401
- "loss": 0.706,
402
- "step": 56
403
- },
404
- {
405
- "epoch": 0.3758241758241758,
406
- "grad_norm": 0.2877054512500763,
407
- "learning_rate": 0.00017738359201773839,
408
- "loss": 0.7436,
409
- "step": 57
410
- },
411
- {
412
- "epoch": 0.3824175824175824,
413
- "grad_norm": 0.2839520573616028,
414
- "learning_rate": 0.000176940133037694,
415
- "loss": 0.6779,
416
- "step": 58
417
- },
418
- {
419
- "epoch": 0.389010989010989,
420
- "grad_norm": 0.2308293879032135,
421
- "learning_rate": 0.00017649667405764967,
422
- "loss": 0.6357,
423
- "step": 59
424
- },
425
- {
426
- "epoch": 0.3956043956043956,
427
- "grad_norm": 0.24402214586734772,
428
- "learning_rate": 0.00017605321507760532,
429
- "loss": 0.7508,
430
- "step": 60
431
- },
432
- {
433
- "epoch": 0.4021978021978022,
434
- "grad_norm": 0.23816415667533875,
435
- "learning_rate": 0.000175609756097561,
436
- "loss": 0.7249,
437
- "step": 61
438
- },
439
- {
440
- "epoch": 0.4087912087912088,
441
- "grad_norm": 0.28321942687034607,
442
- "learning_rate": 0.00017516629711751663,
443
- "loss": 0.7479,
444
- "step": 62
445
- },
446
- {
447
- "epoch": 0.4153846153846154,
448
- "grad_norm": 0.23680296540260315,
449
- "learning_rate": 0.0001747228381374723,
450
- "loss": 0.6413,
451
- "step": 63
452
- },
453
- {
454
- "epoch": 0.421978021978022,
455
- "grad_norm": 0.23129238188266754,
456
- "learning_rate": 0.00017427937915742792,
457
- "loss": 0.6786,
458
- "step": 64
459
- },
460
- {
461
- "epoch": 0.42857142857142855,
462
- "grad_norm": 0.25140181183815,
463
- "learning_rate": 0.0001738359201773836,
464
- "loss": 0.7167,
465
- "step": 65
466
- },
467
- {
468
- "epoch": 0.4351648351648352,
469
- "grad_norm": 0.27190810441970825,
470
- "learning_rate": 0.00017339246119733924,
471
- "loss": 0.6267,
472
- "step": 66
473
- },
474
- {
475
- "epoch": 0.44175824175824174,
476
- "grad_norm": 0.23768772184848785,
477
- "learning_rate": 0.0001729490022172949,
478
- "loss": 0.7397,
479
- "step": 67
480
- },
481
- {
482
- "epoch": 0.44835164835164837,
483
- "grad_norm": 0.2618238031864166,
484
- "learning_rate": 0.00017250554323725056,
485
- "loss": 0.6987,
486
- "step": 68
487
- },
488
- {
489
- "epoch": 0.45494505494505494,
490
- "grad_norm": 0.24789907038211823,
491
- "learning_rate": 0.00017206208425720623,
492
- "loss": 0.6223,
493
- "step": 69
494
- },
495
- {
496
- "epoch": 0.46153846153846156,
497
- "grad_norm": 0.2744330167770386,
498
- "learning_rate": 0.00017161862527716187,
499
- "loss": 0.6964,
500
- "step": 70
501
- },
502
- {
503
- "epoch": 0.46813186813186813,
504
- "grad_norm": 0.23732465505599976,
505
- "learning_rate": 0.00017117516629711752,
506
- "loss": 0.6524,
507
- "step": 71
508
- },
509
- {
510
- "epoch": 0.4747252747252747,
511
- "grad_norm": 0.2278261035680771,
512
- "learning_rate": 0.0001707317073170732,
513
- "loss": 0.7437,
514
- "step": 72
515
- },
516
- {
517
- "epoch": 0.48131868131868133,
518
- "grad_norm": 0.24909941852092743,
519
- "learning_rate": 0.00017028824833702883,
520
- "loss": 0.6955,
521
- "step": 73
522
- },
523
- {
524
- "epoch": 0.4879120879120879,
525
- "grad_norm": 0.3007880449295044,
526
- "learning_rate": 0.0001698447893569845,
527
- "loss": 0.625,
528
- "step": 74
529
- },
530
- {
531
- "epoch": 0.4945054945054945,
532
- "grad_norm": 0.2338089644908905,
533
- "learning_rate": 0.00016940133037694015,
534
- "loss": 0.6843,
535
- "step": 75
536
- },
537
- {
538
- "epoch": 0.5010989010989011,
539
- "grad_norm": 0.27349653840065,
540
- "learning_rate": 0.00016895787139689582,
541
- "loss": 0.6825,
542
- "step": 76
543
- },
544
- {
545
- "epoch": 0.5076923076923077,
546
- "grad_norm": 0.2793181836605072,
547
- "learning_rate": 0.00016851441241685144,
548
- "loss": 0.6529,
549
- "step": 77
550
- },
551
- {
552
- "epoch": 0.5142857142857142,
553
- "grad_norm": 0.2612224221229553,
554
- "learning_rate": 0.0001680709534368071,
555
- "loss": 0.6807,
556
- "step": 78
557
- },
558
- {
559
- "epoch": 0.5208791208791209,
560
- "grad_norm": 0.2740105986595154,
561
- "learning_rate": 0.00016762749445676275,
562
- "loss": 0.6294,
563
- "step": 79
564
- },
565
- {
566
- "epoch": 0.5274725274725275,
567
- "grad_norm": 0.2226412147283554,
568
- "learning_rate": 0.00016718403547671842,
569
- "loss": 0.6569,
570
- "step": 80
571
- },
572
- {
573
- "epoch": 0.5340659340659341,
574
- "grad_norm": 0.2254134714603424,
575
- "learning_rate": 0.00016674057649667407,
576
- "loss": 0.6569,
577
- "step": 81
578
- },
579
- {
580
- "epoch": 0.5406593406593406,
581
- "grad_norm": 0.22373083233833313,
582
- "learning_rate": 0.00016629711751662974,
583
- "loss": 0.6733,
584
- "step": 82
585
- },
586
- {
587
- "epoch": 0.5472527472527473,
588
- "grad_norm": 0.2485770583152771,
589
- "learning_rate": 0.00016585365853658536,
590
- "loss": 0.6422,
591
- "step": 83
592
- },
593
- {
594
- "epoch": 0.5538461538461539,
595
- "grad_norm": 0.25764942169189453,
596
- "learning_rate": 0.00016541019955654103,
597
- "loss": 0.6682,
598
- "step": 84
599
- },
600
- {
601
- "epoch": 0.5604395604395604,
602
- "grad_norm": 0.24047411978244781,
603
- "learning_rate": 0.00016496674057649667,
604
- "loss": 0.7126,
605
- "step": 85
606
- },
607
- {
608
- "epoch": 0.567032967032967,
609
- "grad_norm": 0.21252930164337158,
610
- "learning_rate": 0.00016452328159645234,
611
- "loss": 0.7109,
612
- "step": 86
613
- },
614
- {
615
- "epoch": 0.5736263736263736,
616
- "grad_norm": 0.25431081652641296,
617
- "learning_rate": 0.000164079822616408,
618
- "loss": 0.6416,
619
- "step": 87
620
- },
621
- {
622
- "epoch": 0.5802197802197803,
623
- "grad_norm": 0.24909189343452454,
624
- "learning_rate": 0.00016363636363636366,
625
- "loss": 0.6963,
626
- "step": 88
627
- },
628
- {
629
- "epoch": 0.5868131868131868,
630
- "grad_norm": 0.25534072518348694,
631
- "learning_rate": 0.0001631929046563193,
632
- "loss": 0.7898,
633
- "step": 89
634
- },
635
- {
636
- "epoch": 0.5934065934065934,
637
- "grad_norm": 0.22847016155719757,
638
- "learning_rate": 0.00016274944567627495,
639
- "loss": 0.6903,
640
- "step": 90
641
- },
642
- {
643
- "epoch": 0.6,
644
- "grad_norm": 0.27691230177879333,
645
- "learning_rate": 0.0001623059866962306,
646
- "loss": 0.6963,
647
- "step": 91
648
- },
649
- {
650
- "epoch": 0.6065934065934065,
651
- "grad_norm": 0.2628577649593353,
652
- "learning_rate": 0.00016186252771618626,
653
- "loss": 0.7605,
654
- "step": 92
655
- },
656
- {
657
- "epoch": 0.6131868131868132,
658
- "grad_norm": 0.29095378518104553,
659
- "learning_rate": 0.0001614190687361419,
660
- "loss": 0.6878,
661
- "step": 93
662
- },
663
- {
664
- "epoch": 0.6197802197802198,
665
- "grad_norm": 0.24262812733650208,
666
- "learning_rate": 0.00016097560975609758,
667
- "loss": 0.7383,
668
- "step": 94
669
- },
670
- {
671
- "epoch": 0.6263736263736264,
672
- "grad_norm": 0.21234223246574402,
673
- "learning_rate": 0.00016053215077605322,
674
- "loss": 0.6735,
675
- "step": 95
676
- },
677
- {
678
- "epoch": 0.6329670329670329,
679
- "grad_norm": 0.2478182166814804,
680
- "learning_rate": 0.00016008869179600887,
681
- "loss": 0.6334,
682
- "step": 96
683
- },
684
- {
685
- "epoch": 0.6395604395604395,
686
- "grad_norm": 0.22873812913894653,
687
- "learning_rate": 0.00015964523281596454,
688
- "loss": 0.6968,
689
- "step": 97
690
- },
691
- {
692
- "epoch": 0.6461538461538462,
693
- "grad_norm": 0.24787071347236633,
694
- "learning_rate": 0.00015920177383592018,
695
- "loss": 0.7076,
696
- "step": 98
697
- },
698
- {
699
- "epoch": 0.6527472527472528,
700
- "grad_norm": 0.2913095951080322,
701
- "learning_rate": 0.00015875831485587586,
702
- "loss": 0.6785,
703
- "step": 99
704
- },
705
- {
706
- "epoch": 0.6593406593406593,
707
- "grad_norm": 0.27481356263160706,
708
- "learning_rate": 0.0001583148558758315,
709
- "loss": 0.7055,
710
- "step": 100
711
- },
712
- {
713
- "epoch": 0.6659340659340659,
714
- "grad_norm": 0.24760739505290985,
715
- "learning_rate": 0.00015787139689578714,
716
- "loss": 0.7027,
717
- "step": 101
718
- },
719
- {
720
- "epoch": 0.6725274725274726,
721
- "grad_norm": 0.2754676342010498,
722
- "learning_rate": 0.0001574279379157428,
723
- "loss": 0.7027,
724
- "step": 102
725
- },
726
- {
727
- "epoch": 0.6791208791208792,
728
- "grad_norm": 0.2395099550485611,
729
- "learning_rate": 0.00015698447893569846,
730
- "loss": 0.6846,
731
- "step": 103
732
- },
733
- {
734
- "epoch": 0.6857142857142857,
735
- "grad_norm": 0.2519392669200897,
736
- "learning_rate": 0.0001565410199556541,
737
- "loss": 0.7722,
738
- "step": 104
739
- },
740
- {
741
- "epoch": 0.6923076923076923,
742
- "grad_norm": 0.24618907272815704,
743
- "learning_rate": 0.00015609756097560978,
744
- "loss": 0.6933,
745
- "step": 105
746
- },
747
- {
748
- "epoch": 0.6989010989010989,
749
- "grad_norm": 0.2342153638601303,
750
- "learning_rate": 0.00015565410199556542,
751
- "loss": 0.6866,
752
- "step": 106
753
- },
754
- {
755
- "epoch": 0.7054945054945055,
756
- "grad_norm": 0.23813366889953613,
757
- "learning_rate": 0.00015521064301552106,
758
- "loss": 0.6476,
759
- "step": 107
760
- },
761
- {
762
- "epoch": 0.7120879120879121,
763
- "grad_norm": 0.21853409707546234,
764
- "learning_rate": 0.0001547671840354767,
765
- "loss": 0.6401,
766
- "step": 108
767
- },
768
- {
769
- "epoch": 0.7186813186813187,
770
- "grad_norm": 0.22005102038383484,
771
- "learning_rate": 0.00015432372505543238,
772
- "loss": 0.6173,
773
- "step": 109
774
- },
775
- {
776
- "epoch": 0.7252747252747253,
777
- "grad_norm": 0.2145771086215973,
778
- "learning_rate": 0.00015388026607538802,
779
- "loss": 0.6712,
780
- "step": 110
781
- },
782
- {
783
- "epoch": 0.7318681318681318,
784
- "grad_norm": 0.2519795894622803,
785
- "learning_rate": 0.0001534368070953437,
786
- "loss": 0.7036,
787
- "step": 111
788
- },
789
- {
790
- "epoch": 0.7384615384615385,
791
- "grad_norm": 0.21608349680900574,
792
- "learning_rate": 0.00015299334811529934,
793
- "loss": 0.7213,
794
- "step": 112
795
- },
796
- {
797
- "epoch": 0.7450549450549451,
798
- "grad_norm": 0.2526698410511017,
799
- "learning_rate": 0.00015254988913525498,
800
- "loss": 0.6326,
801
- "step": 113
802
- },
803
- {
804
- "epoch": 0.7516483516483516,
805
- "grad_norm": 0.22119538486003876,
806
- "learning_rate": 0.00015210643015521066,
807
- "loss": 0.643,
808
- "step": 114
809
- },
810
- {
811
- "epoch": 0.7582417582417582,
812
- "grad_norm": 0.23445621132850647,
813
- "learning_rate": 0.0001516629711751663,
814
- "loss": 0.6562,
815
- "step": 115
816
- },
817
- {
818
- "epoch": 0.7648351648351648,
819
- "grad_norm": 0.21006852388381958,
820
- "learning_rate": 0.00015121951219512197,
821
- "loss": 0.7381,
822
- "step": 116
823
- },
824
- {
825
- "epoch": 0.7714285714285715,
826
- "grad_norm": 0.2904897928237915,
827
- "learning_rate": 0.00015077605321507762,
828
- "loss": 0.723,
829
- "step": 117
830
- },
831
- {
832
- "epoch": 0.778021978021978,
833
- "grad_norm": 0.28895437717437744,
834
- "learning_rate": 0.0001503325942350333,
835
- "loss": 0.6517,
836
- "step": 118
837
- },
838
- {
839
- "epoch": 0.7846153846153846,
840
- "grad_norm": 0.24994221329689026,
841
- "learning_rate": 0.0001498891352549889,
842
- "loss": 0.6621,
843
- "step": 119
844
- },
845
- {
846
- "epoch": 0.7912087912087912,
847
- "grad_norm": 0.24564869701862335,
848
- "learning_rate": 0.00014944567627494458,
849
- "loss": 0.7548,
850
- "step": 120
851
- }
852
- ],
853
- "logging_steps": 1,
854
- "max_steps": 456,
855
- "num_input_tokens_seen": 0,
856
- "num_train_epochs": 3,
857
- "save_steps": 15,
858
- "stateful_callbacks": {
859
- "TrainerControl": {
860
- "args": {
861
- "should_epoch_stop": false,
862
- "should_evaluate": false,
863
- "should_log": false,
864
- "should_save": true,
865
- "should_training_stop": false
866
- },
867
- "attributes": {}
868
- }
869
- },
870
- "total_flos": 5.539166080487424e+16,
871
- "train_batch_size": 22,
872
- "trial_name": null,
873
- "trial_params": null
874
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
seed0/checkpoint-120/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0314cf5080efcc9f80748b98c0e8740951e978b06ae398400172ff9f77eb1257
3
- size 6289
 
 
 
 
seed0/checkpoint-120/vocab.json DELETED
The diff for this file is too large to render. See raw diff
 
seed0/checkpoint-135/README.md DELETED
@@ -1,210 +0,0 @@
1
- ---
2
- base_model: unsloth/Qwen2.5-7B-Instruct
3
- library_name: peft
4
- pipeline_tag: text-generation
5
- tags:
6
- - base_model:adapter:unsloth/Qwen2.5-7B-Instruct
7
- - lora
8
- - sft
9
- - transformers
10
- - trl
11
- - unsloth
12
- ---
13
-
14
- # Model Card for Model ID
15
-
16
- <!-- Provide a quick summary of what the model is/does. -->
17
-
18
-
19
-
20
- ## Model Details
21
-
22
- ### Model Description
23
-
24
- <!-- Provide a longer summary of what this model is. -->
25
-
26
-
27
-
28
- - **Developed by:** [More Information Needed]
29
- - **Funded by [optional]:** [More Information Needed]
30
- - **Shared by [optional]:** [More Information Needed]
31
- - **Model type:** [More Information Needed]
32
- - **Language(s) (NLP):** [More Information Needed]
33
- - **License:** [More Information Needed]
34
- - **Finetuned from model [optional]:** [More Information Needed]
35
-
36
- ### Model Sources [optional]
37
-
38
- <!-- Provide the basic links for the model. -->
39
-
40
- - **Repository:** [More Information Needed]
41
- - **Paper [optional]:** [More Information Needed]
42
- - **Demo [optional]:** [More Information Needed]
43
-
44
- ## Uses
45
-
46
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
47
-
48
- ### Direct Use
49
-
50
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
51
-
52
- [More Information Needed]
53
-
54
- ### Downstream Use [optional]
55
-
56
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
57
-
58
- [More Information Needed]
59
-
60
- ### Out-of-Scope Use
61
-
62
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
63
-
64
- [More Information Needed]
65
-
66
- ## Bias, Risks, and Limitations
67
-
68
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
69
-
70
- [More Information Needed]
71
-
72
- ### Recommendations
73
-
74
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
75
-
76
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
77
-
78
- ## How to Get Started with the Model
79
-
80
- Use the code below to get started with the model.
81
-
82
- [More Information Needed]
83
-
84
- ## Training Details
85
-
86
- ### Training Data
87
-
88
- <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
89
-
90
- [More Information Needed]
91
-
92
- ### Training Procedure
93
-
94
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
95
-
96
- #### Preprocessing [optional]
97
-
98
- [More Information Needed]
99
-
100
-
101
- #### Training Hyperparameters
102
-
103
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
104
-
105
- #### Speeds, Sizes, Times [optional]
106
-
107
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
108
-
109
- [More Information Needed]
110
-
111
- ## Evaluation
112
-
113
- <!-- This section describes the evaluation protocols and provides the results. -->
114
-
115
- ### Testing Data, Factors & Metrics
116
-
117
- #### Testing Data
118
-
119
- <!-- This should link to a Dataset Card if possible. -->
120
-
121
- [More Information Needed]
122
-
123
- #### Factors
124
-
125
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
126
-
127
- [More Information Needed]
128
-
129
- #### Metrics
130
-
131
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
132
-
133
- [More Information Needed]
134
-
135
- ### Results
136
-
137
- [More Information Needed]
138
-
139
- #### Summary
140
-
141
-
142
-
143
- ## Model Examination [optional]
144
-
145
- <!-- Relevant interpretability work for the model goes here -->
146
-
147
- [More Information Needed]
148
-
149
- ## Environmental Impact
150
-
151
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
152
-
153
- Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
154
-
155
- - **Hardware Type:** [More Information Needed]
156
- - **Hours used:** [More Information Needed]
157
- - **Cloud Provider:** [More Information Needed]
158
- - **Compute Region:** [More Information Needed]
159
- - **Carbon Emitted:** [More Information Needed]
160
-
161
- ## Technical Specifications [optional]
162
-
163
- ### Model Architecture and Objective
164
-
165
- [More Information Needed]
166
-
167
- ### Compute Infrastructure
168
-
169
- [More Information Needed]
170
-
171
- #### Hardware
172
-
173
- [More Information Needed]
174
-
175
- #### Software
176
-
177
- [More Information Needed]
178
-
179
- ## Citation [optional]
180
-
181
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
182
-
183
- **BibTeX:**
184
-
185
- [More Information Needed]
186
-
187
- **APA:**
188
-
189
- [More Information Needed]
190
-
191
- ## Glossary [optional]
192
-
193
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
194
-
195
- [More Information Needed]
196
-
197
- ## More Information [optional]
198
-
199
- [More Information Needed]
200
-
201
- ## Model Card Authors [optional]
202
-
203
- [More Information Needed]
204
-
205
- ## Model Card Contact
206
-
207
- [More Information Needed]
208
- ### Framework versions
209
-
210
- - PEFT 0.18.1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
seed0/checkpoint-135/adapter_config.json DELETED
@@ -1,50 +0,0 @@
1
- {
2
- "alora_invocation_tokens": null,
3
- "alpha_pattern": {},
4
- "arrow_config": null,
5
- "auto_mapping": {
6
- "base_model_class": "Qwen2ForCausalLM",
7
- "parent_library": "transformers.models.qwen2.modeling_qwen2",
8
- "unsloth_fixed": true
9
- },
10
- "base_model_name_or_path": "unsloth/Qwen2.5-7B-Instruct",
11
- "bias": "none",
12
- "corda_config": null,
13
- "ensure_weight_tying": false,
14
- "eva_config": null,
15
- "exclude_modules": null,
16
- "fan_in_fan_out": false,
17
- "inference_mode": true,
18
- "init_lora_weights": true,
19
- "layer_replication": null,
20
- "layers_pattern": null,
21
- "layers_to_transform": null,
22
- "loftq_config": {},
23
- "lora_alpha": 8,
24
- "lora_bias": false,
25
- "lora_dropout": 0.0,
26
- "megatron_config": null,
27
- "megatron_core": "megatron.core",
28
- "modules_to_save": null,
29
- "peft_type": "LORA",
30
- "peft_version": "0.18.1",
31
- "qalora_group_size": 16,
32
- "r": 8,
33
- "rank_pattern": {},
34
- "revision": null,
35
- "target_modules": [
36
- "k_proj",
37
- "v_proj",
38
- "up_proj",
39
- "q_proj",
40
- "down_proj",
41
- "o_proj",
42
- "gate_proj"
43
- ],
44
- "target_parameters": null,
45
- "task_type": "CAUSAL_LM",
46
- "trainable_token_indices": null,
47
- "use_dora": false,
48
- "use_qalora": false,
49
- "use_rslora": false
50
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
seed0/checkpoint-135/adapter_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a68acd8db74bd8530c5bfe1df04c9e2a7c3f6993f1f8685bfa8765994d63494
3
- size 80792096
 
 
 
 
seed0/checkpoint-135/added_tokens.json DELETED
@@ -1,25 +0,0 @@
1
- {
2
- "</tool_call>": 151658,
3
- "<tool_call>": 151657,
4
- "<|PAD_TOKEN|>": 151665,
5
- "<|box_end|>": 151649,
6
- "<|box_start|>": 151648,
7
- "<|endoftext|>": 151643,
8
- "<|file_sep|>": 151664,
9
- "<|fim_middle|>": 151660,
10
- "<|fim_pad|>": 151662,
11
- "<|fim_prefix|>": 151659,
12
- "<|fim_suffix|>": 151661,
13
- "<|im_end|>": 151645,
14
- "<|im_start|>": 151644,
15
- "<|image_pad|>": 151655,
16
- "<|object_ref_end|>": 151647,
17
- "<|object_ref_start|>": 151646,
18
- "<|quad_end|>": 151651,
19
- "<|quad_start|>": 151650,
20
- "<|repo_name|>": 151663,
21
- "<|video_pad|>": 151656,
22
- "<|vision_end|>": 151653,
23
- "<|vision_pad|>": 151654,
24
- "<|vision_start|>": 151652
25
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
seed0/checkpoint-135/chat_template.jinja DELETED
@@ -1,54 +0,0 @@
1
- {%- if tools %}
2
- {{- '<|im_start|>system\n' }}
3
- {%- if messages[0]['role'] == 'system' %}
4
- {{- messages[0]['content'] }}
5
- {%- else %}
6
- {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
- {%- endif %}
8
- {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
- {%- for tool in tools %}
10
- {{- "\n" }}
11
- {{- tool | tojson }}
12
- {%- endfor %}
13
- {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
- {%- else %}
15
- {%- if messages[0]['role'] == 'system' %}
16
- {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
- {%- else %}
18
- {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
- {%- endif %}
20
- {%- endif %}
21
- {%- for message in messages %}
22
- {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
- {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
- {%- elif message.role == "assistant" %}
25
- {{- '<|im_start|>' + message.role }}
26
- {%- if message.content %}
27
- {{- '\n' + message.content }}
28
- {%- endif %}
29
- {%- for tool_call in message.tool_calls %}
30
- {%- if tool_call.function is defined %}
31
- {%- set tool_call = tool_call.function %}
32
- {%- endif %}
33
- {{- '\n<tool_call>\n{"name": "' }}
34
- {{- tool_call.name }}
35
- {{- '", "arguments": ' }}
36
- {{- tool_call.arguments | tojson }}
37
- {{- '}\n</tool_call>' }}
38
- {%- endfor %}
39
- {{- '<|im_end|>\n' }}
40
- {%- elif message.role == "tool" %}
41
- {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
- {{- '<|im_start|>user' }}
43
- {%- endif %}
44
- {{- '\n<tool_response>\n' }}
45
- {{- message.content }}
46
- {{- '\n</tool_response>' }}
47
- {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
- {{- '<|im_end|>\n' }}
49
- {%- endif %}
50
- {%- endif %}
51
- {%- endfor %}
52
- {%- if add_generation_prompt %}
53
- {{- '<|im_start|>assistant\n' }}
54
- {%- endif %}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
seed0/checkpoint-135/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
seed0/checkpoint-135/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d26e2394e61687ebe8c53b46df3521a68f04dc7f6cc9d350ff82ef1b73f7cf5
3
- size 161816187
 
 
 
 
seed0/checkpoint-135/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:12e15e837284f30841feeb4cb11a4ca47e6e0a0d43907e64044c865959176390
3
- size 14581
 
 
 
 
seed0/checkpoint-135/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7aafe151246108c71fe5d7e8fecf075b2eebe3f32a3b402d7b014db05fee5215
3
- size 1465
 
 
 
 
seed0/checkpoint-135/special_tokens_map.json DELETED
@@ -1,25 +0,0 @@
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": "<|PAD_TOKEN|>"
25
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
seed0/checkpoint-135/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fab42efe8d17406525a9154b728cf9e957629a8ed7ce997770efdd71128c6a1a
3
- size 11422086
 
 
 
 
seed0/checkpoint-135/tokenizer_config.json DELETED
@@ -1,216 +0,0 @@
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": "<|PAD_TOKEN|>",
183
- "lstrip": false,
184
- "normalized": false,
185
- "rstrip": false,
186
- "single_word": false,
187
- "special": true
188
- }
189
- },
190
- "additional_special_tokens": [
191
- "<|im_start|>",
192
- "<|im_end|>",
193
- "<|object_ref_start|>",
194
- "<|object_ref_end|>",
195
- "<|box_start|>",
196
- "<|box_end|>",
197
- "<|quad_start|>",
198
- "<|quad_end|>",
199
- "<|vision_start|>",
200
- "<|vision_end|>",
201
- "<|vision_pad|>",
202
- "<|image_pad|>",
203
- "<|video_pad|>"
204
- ],
205
- "bos_token": null,
206
- "clean_up_tokenization_spaces": false,
207
- "eos_token": "<|im_end|>",
208
- "errors": "replace",
209
- "extra_special_tokens": {},
210
- "model_max_length": 32768,
211
- "pad_token": "<|PAD_TOKEN|>",
212
- "padding_side": "right",
213
- "split_special_tokens": false,
214
- "tokenizer_class": "Qwen2Tokenizer",
215
- "unk_token": null
216
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
seed0/checkpoint-135/trainer_state.json DELETED
@@ -1,979 +0,0 @@
1
- {
2
- "best_global_step": null,
3
- "best_metric": null,
4
- "best_model_checkpoint": null,
5
- "epoch": 0.8901098901098901,
6
- "eval_steps": 500,
7
- "global_step": 135,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "epoch": 0.006593406593406593,
14
- "grad_norm": 0.8349836468696594,
15
- "learning_rate": 0.0,
16
- "loss": 0.9434,
17
- "step": 1
18
- },
19
- {
20
- "epoch": 0.013186813186813187,
21
- "grad_norm": 0.8700987696647644,
22
- "learning_rate": 4e-05,
23
- "loss": 0.9905,
24
- "step": 2
25
- },
26
- {
27
- "epoch": 0.01978021978021978,
28
- "grad_norm": 0.9241365194320679,
29
- "learning_rate": 8e-05,
30
- "loss": 0.9438,
31
- "step": 3
32
- },
33
- {
34
- "epoch": 0.026373626373626374,
35
- "grad_norm": 0.9019892811775208,
36
- "learning_rate": 0.00012,
37
- "loss": 0.9216,
38
- "step": 4
39
- },
40
- {
41
- "epoch": 0.03296703296703297,
42
- "grad_norm": 0.8872910141944885,
43
- "learning_rate": 0.00016,
44
- "loss": 0.9374,
45
- "step": 5
46
- },
47
- {
48
- "epoch": 0.03956043956043956,
49
- "grad_norm": 0.5874530076980591,
50
- "learning_rate": 0.0002,
51
- "loss": 0.7673,
52
- "step": 6
53
- },
54
- {
55
- "epoch": 0.046153846153846156,
56
- "grad_norm": 0.5062956809997559,
57
- "learning_rate": 0.00019955654101995565,
58
- "loss": 0.8011,
59
- "step": 7
60
- },
61
- {
62
- "epoch": 0.05274725274725275,
63
- "grad_norm": 0.5953829288482666,
64
- "learning_rate": 0.00019911308203991133,
65
- "loss": 0.8455,
66
- "step": 8
67
- },
68
- {
69
- "epoch": 0.05934065934065934,
70
- "grad_norm": 0.5616072416305542,
71
- "learning_rate": 0.00019866962305986697,
72
- "loss": 0.8265,
73
- "step": 9
74
- },
75
- {
76
- "epoch": 0.06593406593406594,
77
- "grad_norm": 0.49180087447166443,
78
- "learning_rate": 0.00019822616407982261,
79
- "loss": 0.8561,
80
- "step": 10
81
- },
82
- {
83
- "epoch": 0.07252747252747253,
84
- "grad_norm": 0.42030951380729675,
85
- "learning_rate": 0.00019778270509977829,
86
- "loss": 0.8796,
87
- "step": 11
88
- },
89
- {
90
- "epoch": 0.07912087912087912,
91
- "grad_norm": 0.3004567325115204,
92
- "learning_rate": 0.00019733924611973393,
93
- "loss": 0.8636,
94
- "step": 12
95
- },
96
- {
97
- "epoch": 0.08571428571428572,
98
- "grad_norm": 0.2698984444141388,
99
- "learning_rate": 0.0001968957871396896,
100
- "loss": 0.718,
101
- "step": 13
102
- },
103
- {
104
- "epoch": 0.09230769230769231,
105
- "grad_norm": 0.25445133447647095,
106
- "learning_rate": 0.00019645232815964525,
107
- "loss": 0.7235,
108
- "step": 14
109
- },
110
- {
111
- "epoch": 0.0989010989010989,
112
- "grad_norm": 0.22418756783008575,
113
- "learning_rate": 0.00019600886917960092,
114
- "loss": 0.688,
115
- "step": 15
116
- },
117
- {
118
- "epoch": 0.1054945054945055,
119
- "grad_norm": 0.2096303105354309,
120
- "learning_rate": 0.00019556541019955653,
121
- "loss": 0.7267,
122
- "step": 16
123
- },
124
- {
125
- "epoch": 0.11208791208791209,
126
- "grad_norm": 0.3029191195964813,
127
- "learning_rate": 0.0001951219512195122,
128
- "loss": 0.7763,
129
- "step": 17
130
- },
131
- {
132
- "epoch": 0.11868131868131868,
133
- "grad_norm": 0.2644464075565338,
134
- "learning_rate": 0.00019467849223946785,
135
- "loss": 0.7618,
136
- "step": 18
137
- },
138
- {
139
- "epoch": 0.12527472527472527,
140
- "grad_norm": 0.2536560893058777,
141
- "learning_rate": 0.00019423503325942352,
142
- "loss": 0.7999,
143
- "step": 19
144
- },
145
- {
146
- "epoch": 0.13186813186813187,
147
- "grad_norm": 0.24718916416168213,
148
- "learning_rate": 0.00019379157427937917,
149
- "loss": 0.752,
150
- "step": 20
151
- },
152
- {
153
- "epoch": 0.13846153846153847,
154
- "grad_norm": 0.2625150680541992,
155
- "learning_rate": 0.00019334811529933484,
156
- "loss": 0.736,
157
- "step": 21
158
- },
159
- {
160
- "epoch": 0.14505494505494507,
161
- "grad_norm": 0.32164040207862854,
162
- "learning_rate": 0.00019290465631929045,
163
- "loss": 0.7043,
164
- "step": 22
165
- },
166
- {
167
- "epoch": 0.15164835164835164,
168
- "grad_norm": 0.3981449604034424,
169
- "learning_rate": 0.00019246119733924613,
170
- "loss": 0.7057,
171
- "step": 23
172
- },
173
- {
174
- "epoch": 0.15824175824175823,
175
- "grad_norm": 0.3817313015460968,
176
- "learning_rate": 0.00019201773835920177,
177
- "loss": 0.7413,
178
- "step": 24
179
- },
180
- {
181
- "epoch": 0.16483516483516483,
182
- "grad_norm": 0.29256680607795715,
183
- "learning_rate": 0.00019157427937915744,
184
- "loss": 0.693,
185
- "step": 25
186
- },
187
- {
188
- "epoch": 0.17142857142857143,
189
- "grad_norm": 0.27523350715637207,
190
- "learning_rate": 0.00019113082039911309,
191
- "loss": 0.6474,
192
- "step": 26
193
- },
194
- {
195
- "epoch": 0.17802197802197803,
196
- "grad_norm": 0.23511967062950134,
197
- "learning_rate": 0.00019068736141906876,
198
- "loss": 0.6519,
199
- "step": 27
200
- },
201
- {
202
- "epoch": 0.18461538461538463,
203
- "grad_norm": 0.2961374819278717,
204
- "learning_rate": 0.0001902439024390244,
205
- "loss": 0.6426,
206
- "step": 28
207
- },
208
- {
209
- "epoch": 0.1912087912087912,
210
- "grad_norm": 0.2760772407054901,
211
- "learning_rate": 0.00018980044345898005,
212
- "loss": 0.7388,
213
- "step": 29
214
- },
215
- {
216
- "epoch": 0.1978021978021978,
217
- "grad_norm": 0.2285313606262207,
218
- "learning_rate": 0.00018935698447893572,
219
- "loss": 0.7756,
220
- "step": 30
221
- },
222
- {
223
- "epoch": 0.2043956043956044,
224
- "grad_norm": 0.2657061517238617,
225
- "learning_rate": 0.00018891352549889136,
226
- "loss": 0.7275,
227
- "step": 31
228
- },
229
- {
230
- "epoch": 0.210989010989011,
231
- "grad_norm": 0.22572828829288483,
232
- "learning_rate": 0.00018847006651884703,
233
- "loss": 0.6793,
234
- "step": 32
235
- },
236
- {
237
- "epoch": 0.2175824175824176,
238
- "grad_norm": 0.26335304975509644,
239
- "learning_rate": 0.00018802660753880268,
240
- "loss": 0.7131,
241
- "step": 33
242
- },
243
- {
244
- "epoch": 0.22417582417582418,
245
- "grad_norm": 0.25231942534446716,
246
- "learning_rate": 0.00018758314855875832,
247
- "loss": 0.7715,
248
- "step": 34
249
- },
250
- {
251
- "epoch": 0.23076923076923078,
252
- "grad_norm": 0.2437426745891571,
253
- "learning_rate": 0.00018713968957871397,
254
- "loss": 0.7094,
255
- "step": 35
256
- },
257
- {
258
- "epoch": 0.23736263736263735,
259
- "grad_norm": 0.28558826446533203,
260
- "learning_rate": 0.00018669623059866964,
261
- "loss": 0.6937,
262
- "step": 36
263
- },
264
- {
265
- "epoch": 0.24395604395604395,
266
- "grad_norm": 0.2915894687175751,
267
- "learning_rate": 0.00018625277161862528,
268
- "loss": 0.7238,
269
- "step": 37
270
- },
271
- {
272
- "epoch": 0.25054945054945055,
273
- "grad_norm": 0.25342074036598206,
274
- "learning_rate": 0.00018580931263858095,
275
- "loss": 0.7323,
276
- "step": 38
277
- },
278
- {
279
- "epoch": 0.2571428571428571,
280
- "grad_norm": 0.22744007408618927,
281
- "learning_rate": 0.0001853658536585366,
282
- "loss": 0.703,
283
- "step": 39
284
- },
285
- {
286
- "epoch": 0.26373626373626374,
287
- "grad_norm": 0.25383231043815613,
288
- "learning_rate": 0.00018492239467849224,
289
- "loss": 0.7093,
290
- "step": 40
291
- },
292
- {
293
- "epoch": 0.2703296703296703,
294
- "grad_norm": 0.2194337695837021,
295
- "learning_rate": 0.0001844789356984479,
296
- "loss": 0.7367,
297
- "step": 41
298
- },
299
- {
300
- "epoch": 0.27692307692307694,
301
- "grad_norm": 0.32021859288215637,
302
- "learning_rate": 0.00018403547671840356,
303
- "loss": 0.6652,
304
- "step": 42
305
- },
306
- {
307
- "epoch": 0.2835164835164835,
308
- "grad_norm": 0.2328304797410965,
309
- "learning_rate": 0.0001835920177383592,
310
- "loss": 0.7016,
311
- "step": 43
312
- },
313
- {
314
- "epoch": 0.29010989010989013,
315
- "grad_norm": 0.24166613817214966,
316
- "learning_rate": 0.00018314855875831487,
317
- "loss": 0.6717,
318
- "step": 44
319
- },
320
- {
321
- "epoch": 0.2967032967032967,
322
- "grad_norm": 0.2733803391456604,
323
- "learning_rate": 0.00018270509977827052,
324
- "loss": 0.6979,
325
- "step": 45
326
- },
327
- {
328
- "epoch": 0.3032967032967033,
329
- "grad_norm": 0.2689957320690155,
330
- "learning_rate": 0.00018226164079822616,
331
- "loss": 0.6977,
332
- "step": 46
333
- },
334
- {
335
- "epoch": 0.3098901098901099,
336
- "grad_norm": 0.2698104977607727,
337
- "learning_rate": 0.00018181818181818183,
338
- "loss": 0.723,
339
- "step": 47
340
- },
341
- {
342
- "epoch": 0.31648351648351647,
343
- "grad_norm": 0.25856417417526245,
344
- "learning_rate": 0.00018137472283813748,
345
- "loss": 0.723,
346
- "step": 48
347
- },
348
- {
349
- "epoch": 0.3230769230769231,
350
- "grad_norm": 0.22988826036453247,
351
- "learning_rate": 0.00018093126385809312,
352
- "loss": 0.7356,
353
- "step": 49
354
- },
355
- {
356
- "epoch": 0.32967032967032966,
357
- "grad_norm": 0.24859416484832764,
358
- "learning_rate": 0.0001804878048780488,
359
- "loss": 0.6671,
360
- "step": 50
361
- },
362
- {
363
- "epoch": 0.3362637362637363,
364
- "grad_norm": 0.24891626834869385,
365
- "learning_rate": 0.00018004434589800444,
366
- "loss": 0.6628,
367
- "step": 51
368
- },
369
- {
370
- "epoch": 0.34285714285714286,
371
- "grad_norm": 0.22740386426448822,
372
- "learning_rate": 0.00017960088691796008,
373
- "loss": 0.6377,
374
- "step": 52
375
- },
376
- {
377
- "epoch": 0.34945054945054943,
378
- "grad_norm": 0.2636365294456482,
379
- "learning_rate": 0.00017915742793791575,
380
- "loss": 0.6901,
381
- "step": 53
382
- },
383
- {
384
- "epoch": 0.35604395604395606,
385
- "grad_norm": 0.2437390238046646,
386
- "learning_rate": 0.0001787139689578714,
387
- "loss": 0.72,
388
- "step": 54
389
- },
390
- {
391
- "epoch": 0.3626373626373626,
392
- "grad_norm": 0.23658742010593414,
393
- "learning_rate": 0.00017827050997782707,
394
- "loss": 0.7365,
395
- "step": 55
396
- },
397
- {
398
- "epoch": 0.36923076923076925,
399
- "grad_norm": 0.23923538625240326,
400
- "learning_rate": 0.00017782705099778271,
401
- "loss": 0.706,
402
- "step": 56
403
- },
404
- {
405
- "epoch": 0.3758241758241758,
406
- "grad_norm": 0.2877054512500763,
407
- "learning_rate": 0.00017738359201773839,
408
- "loss": 0.7436,
409
- "step": 57
410
- },
411
- {
412
- "epoch": 0.3824175824175824,
413
- "grad_norm": 0.2839520573616028,
414
- "learning_rate": 0.000176940133037694,
415
- "loss": 0.6779,
416
- "step": 58
417
- },
418
- {
419
- "epoch": 0.389010989010989,
420
- "grad_norm": 0.2308293879032135,
421
- "learning_rate": 0.00017649667405764967,
422
- "loss": 0.6357,
423
- "step": 59
424
- },
425
- {
426
- "epoch": 0.3956043956043956,
427
- "grad_norm": 0.24402214586734772,
428
- "learning_rate": 0.00017605321507760532,
429
- "loss": 0.7508,
430
- "step": 60
431
- },
432
- {
433
- "epoch": 0.4021978021978022,
434
- "grad_norm": 0.23816415667533875,
435
- "learning_rate": 0.000175609756097561,
436
- "loss": 0.7249,
437
- "step": 61
438
- },
439
- {
440
- "epoch": 0.4087912087912088,
441
- "grad_norm": 0.28321942687034607,
442
- "learning_rate": 0.00017516629711751663,
443
- "loss": 0.7479,
444
- "step": 62
445
- },
446
- {
447
- "epoch": 0.4153846153846154,
448
- "grad_norm": 0.23680296540260315,
449
- "learning_rate": 0.0001747228381374723,
450
- "loss": 0.6413,
451
- "step": 63
452
- },
453
- {
454
- "epoch": 0.421978021978022,
455
- "grad_norm": 0.23129238188266754,
456
- "learning_rate": 0.00017427937915742792,
457
- "loss": 0.6786,
458
- "step": 64
459
- },
460
- {
461
- "epoch": 0.42857142857142855,
462
- "grad_norm": 0.25140181183815,
463
- "learning_rate": 0.0001738359201773836,
464
- "loss": 0.7167,
465
- "step": 65
466
- },
467
- {
468
- "epoch": 0.4351648351648352,
469
- "grad_norm": 0.27190810441970825,
470
- "learning_rate": 0.00017339246119733924,
471
- "loss": 0.6267,
472
- "step": 66
473
- },
474
- {
475
- "epoch": 0.44175824175824174,
476
- "grad_norm": 0.23768772184848785,
477
- "learning_rate": 0.0001729490022172949,
478
- "loss": 0.7397,
479
- "step": 67
480
- },
481
- {
482
- "epoch": 0.44835164835164837,
483
- "grad_norm": 0.2618238031864166,
484
- "learning_rate": 0.00017250554323725056,
485
- "loss": 0.6987,
486
- "step": 68
487
- },
488
- {
489
- "epoch": 0.45494505494505494,
490
- "grad_norm": 0.24789907038211823,
491
- "learning_rate": 0.00017206208425720623,
492
- "loss": 0.6223,
493
- "step": 69
494
- },
495
- {
496
- "epoch": 0.46153846153846156,
497
- "grad_norm": 0.2744330167770386,
498
- "learning_rate": 0.00017161862527716187,
499
- "loss": 0.6964,
500
- "step": 70
501
- },
502
- {
503
- "epoch": 0.46813186813186813,
504
- "grad_norm": 0.23732465505599976,
505
- "learning_rate": 0.00017117516629711752,
506
- "loss": 0.6524,
507
- "step": 71
508
- },
509
- {
510
- "epoch": 0.4747252747252747,
511
- "grad_norm": 0.2278261035680771,
512
- "learning_rate": 0.0001707317073170732,
513
- "loss": 0.7437,
514
- "step": 72
515
- },
516
- {
517
- "epoch": 0.48131868131868133,
518
- "grad_norm": 0.24909941852092743,
519
- "learning_rate": 0.00017028824833702883,
520
- "loss": 0.6955,
521
- "step": 73
522
- },
523
- {
524
- "epoch": 0.4879120879120879,
525
- "grad_norm": 0.3007880449295044,
526
- "learning_rate": 0.0001698447893569845,
527
- "loss": 0.625,
528
- "step": 74
529
- },
530
- {
531
- "epoch": 0.4945054945054945,
532
- "grad_norm": 0.2338089644908905,
533
- "learning_rate": 0.00016940133037694015,
534
- "loss": 0.6843,
535
- "step": 75
536
- },
537
- {
538
- "epoch": 0.5010989010989011,
539
- "grad_norm": 0.27349653840065,
540
- "learning_rate": 0.00016895787139689582,
541
- "loss": 0.6825,
542
- "step": 76
543
- },
544
- {
545
- "epoch": 0.5076923076923077,
546
- "grad_norm": 0.2793181836605072,
547
- "learning_rate": 0.00016851441241685144,
548
- "loss": 0.6529,
549
- "step": 77
550
- },
551
- {
552
- "epoch": 0.5142857142857142,
553
- "grad_norm": 0.2612224221229553,
554
- "learning_rate": 0.0001680709534368071,
555
- "loss": 0.6807,
556
- "step": 78
557
- },
558
- {
559
- "epoch": 0.5208791208791209,
560
- "grad_norm": 0.2740105986595154,
561
- "learning_rate": 0.00016762749445676275,
562
- "loss": 0.6294,
563
- "step": 79
564
- },
565
- {
566
- "epoch": 0.5274725274725275,
567
- "grad_norm": 0.2226412147283554,
568
- "learning_rate": 0.00016718403547671842,
569
- "loss": 0.6569,
570
- "step": 80
571
- },
572
- {
573
- "epoch": 0.5340659340659341,
574
- "grad_norm": 0.2254134714603424,
575
- "learning_rate": 0.00016674057649667407,
576
- "loss": 0.6569,
577
- "step": 81
578
- },
579
- {
580
- "epoch": 0.5406593406593406,
581
- "grad_norm": 0.22373083233833313,
582
- "learning_rate": 0.00016629711751662974,
583
- "loss": 0.6733,
584
- "step": 82
585
- },
586
- {
587
- "epoch": 0.5472527472527473,
588
- "grad_norm": 0.2485770583152771,
589
- "learning_rate": 0.00016585365853658536,
590
- "loss": 0.6422,
591
- "step": 83
592
- },
593
- {
594
- "epoch": 0.5538461538461539,
595
- "grad_norm": 0.25764942169189453,
596
- "learning_rate": 0.00016541019955654103,
597
- "loss": 0.6682,
598
- "step": 84
599
- },
600
- {
601
- "epoch": 0.5604395604395604,
602
- "grad_norm": 0.24047411978244781,
603
- "learning_rate": 0.00016496674057649667,
604
- "loss": 0.7126,
605
- "step": 85
606
- },
607
- {
608
- "epoch": 0.567032967032967,
609
- "grad_norm": 0.21252930164337158,
610
- "learning_rate": 0.00016452328159645234,
611
- "loss": 0.7109,
612
- "step": 86
613
- },
614
- {
615
- "epoch": 0.5736263736263736,
616
- "grad_norm": 0.25431081652641296,
617
- "learning_rate": 0.000164079822616408,
618
- "loss": 0.6416,
619
- "step": 87
620
- },
621
- {
622
- "epoch": 0.5802197802197803,
623
- "grad_norm": 0.24909189343452454,
624
- "learning_rate": 0.00016363636363636366,
625
- "loss": 0.6963,
626
- "step": 88
627
- },
628
- {
629
- "epoch": 0.5868131868131868,
630
- "grad_norm": 0.25534072518348694,
631
- "learning_rate": 0.0001631929046563193,
632
- "loss": 0.7898,
633
- "step": 89
634
- },
635
- {
636
- "epoch": 0.5934065934065934,
637
- "grad_norm": 0.22847016155719757,
638
- "learning_rate": 0.00016274944567627495,
639
- "loss": 0.6903,
640
- "step": 90
641
- },
642
- {
643
- "epoch": 0.6,
644
- "grad_norm": 0.27691230177879333,
645
- "learning_rate": 0.0001623059866962306,
646
- "loss": 0.6963,
647
- "step": 91
648
- },
649
- {
650
- "epoch": 0.6065934065934065,
651
- "grad_norm": 0.2628577649593353,
652
- "learning_rate": 0.00016186252771618626,
653
- "loss": 0.7605,
654
- "step": 92
655
- },
656
- {
657
- "epoch": 0.6131868131868132,
658
- "grad_norm": 0.29095378518104553,
659
- "learning_rate": 0.0001614190687361419,
660
- "loss": 0.6878,
661
- "step": 93
662
- },
663
- {
664
- "epoch": 0.6197802197802198,
665
- "grad_norm": 0.24262812733650208,
666
- "learning_rate": 0.00016097560975609758,
667
- "loss": 0.7383,
668
- "step": 94
669
- },
670
- {
671
- "epoch": 0.6263736263736264,
672
- "grad_norm": 0.21234223246574402,
673
- "learning_rate": 0.00016053215077605322,
674
- "loss": 0.6735,
675
- "step": 95
676
- },
677
- {
678
- "epoch": 0.6329670329670329,
679
- "grad_norm": 0.2478182166814804,
680
- "learning_rate": 0.00016008869179600887,
681
- "loss": 0.6334,
682
- "step": 96
683
- },
684
- {
685
- "epoch": 0.6395604395604395,
686
- "grad_norm": 0.22873812913894653,
687
- "learning_rate": 0.00015964523281596454,
688
- "loss": 0.6968,
689
- "step": 97
690
- },
691
- {
692
- "epoch": 0.6461538461538462,
693
- "grad_norm": 0.24787071347236633,
694
- "learning_rate": 0.00015920177383592018,
695
- "loss": 0.7076,
696
- "step": 98
697
- },
698
- {
699
- "epoch": 0.6527472527472528,
700
- "grad_norm": 0.2913095951080322,
701
- "learning_rate": 0.00015875831485587586,
702
- "loss": 0.6785,
703
- "step": 99
704
- },
705
- {
706
- "epoch": 0.6593406593406593,
707
- "grad_norm": 0.27481356263160706,
708
- "learning_rate": 0.0001583148558758315,
709
- "loss": 0.7055,
710
- "step": 100
711
- },
712
- {
713
- "epoch": 0.6659340659340659,
714
- "grad_norm": 0.24760739505290985,
715
- "learning_rate": 0.00015787139689578714,
716
- "loss": 0.7027,
717
- "step": 101
718
- },
719
- {
720
- "epoch": 0.6725274725274726,
721
- "grad_norm": 0.2754676342010498,
722
- "learning_rate": 0.0001574279379157428,
723
- "loss": 0.7027,
724
- "step": 102
725
- },
726
- {
727
- "epoch": 0.6791208791208792,
728
- "grad_norm": 0.2395099550485611,
729
- "learning_rate": 0.00015698447893569846,
730
- "loss": 0.6846,
731
- "step": 103
732
- },
733
- {
734
- "epoch": 0.6857142857142857,
735
- "grad_norm": 0.2519392669200897,
736
- "learning_rate": 0.0001565410199556541,
737
- "loss": 0.7722,
738
- "step": 104
739
- },
740
- {
741
- "epoch": 0.6923076923076923,
742
- "grad_norm": 0.24618907272815704,
743
- "learning_rate": 0.00015609756097560978,
744
- "loss": 0.6933,
745
- "step": 105
746
- },
747
- {
748
- "epoch": 0.6989010989010989,
749
- "grad_norm": 0.2342153638601303,
750
- "learning_rate": 0.00015565410199556542,
751
- "loss": 0.6866,
752
- "step": 106
753
- },
754
- {
755
- "epoch": 0.7054945054945055,
756
- "grad_norm": 0.23813366889953613,
757
- "learning_rate": 0.00015521064301552106,
758
- "loss": 0.6476,
759
- "step": 107
760
- },
761
- {
762
- "epoch": 0.7120879120879121,
763
- "grad_norm": 0.21853409707546234,
764
- "learning_rate": 0.0001547671840354767,
765
- "loss": 0.6401,
766
- "step": 108
767
- },
768
- {
769
- "epoch": 0.7186813186813187,
770
- "grad_norm": 0.22005102038383484,
771
- "learning_rate": 0.00015432372505543238,
772
- "loss": 0.6173,
773
- "step": 109
774
- },
775
- {
776
- "epoch": 0.7252747252747253,
777
- "grad_norm": 0.2145771086215973,
778
- "learning_rate": 0.00015388026607538802,
779
- "loss": 0.6712,
780
- "step": 110
781
- },
782
- {
783
- "epoch": 0.7318681318681318,
784
- "grad_norm": 0.2519795894622803,
785
- "learning_rate": 0.0001534368070953437,
786
- "loss": 0.7036,
787
- "step": 111
788
- },
789
- {
790
- "epoch": 0.7384615384615385,
791
- "grad_norm": 0.21608349680900574,
792
- "learning_rate": 0.00015299334811529934,
793
- "loss": 0.7213,
794
- "step": 112
795
- },
796
- {
797
- "epoch": 0.7450549450549451,
798
- "grad_norm": 0.2526698410511017,
799
- "learning_rate": 0.00015254988913525498,
800
- "loss": 0.6326,
801
- "step": 113
802
- },
803
- {
804
- "epoch": 0.7516483516483516,
805
- "grad_norm": 0.22119538486003876,
806
- "learning_rate": 0.00015210643015521066,
807
- "loss": 0.643,
808
- "step": 114
809
- },
810
- {
811
- "epoch": 0.7582417582417582,
812
- "grad_norm": 0.23445621132850647,
813
- "learning_rate": 0.0001516629711751663,
814
- "loss": 0.6562,
815
- "step": 115
816
- },
817
- {
818
- "epoch": 0.7648351648351648,
819
- "grad_norm": 0.21006852388381958,
820
- "learning_rate": 0.00015121951219512197,
821
- "loss": 0.7381,
822
- "step": 116
823
- },
824
- {
825
- "epoch": 0.7714285714285715,
826
- "grad_norm": 0.2904897928237915,
827
- "learning_rate": 0.00015077605321507762,
828
- "loss": 0.723,
829
- "step": 117
830
- },
831
- {
832
- "epoch": 0.778021978021978,
833
- "grad_norm": 0.28895437717437744,
834
- "learning_rate": 0.0001503325942350333,
835
- "loss": 0.6517,
836
- "step": 118
837
- },
838
- {
839
- "epoch": 0.7846153846153846,
840
- "grad_norm": 0.24994221329689026,
841
- "learning_rate": 0.0001498891352549889,
842
- "loss": 0.6621,
843
- "step": 119
844
- },
845
- {
846
- "epoch": 0.7912087912087912,
847
- "grad_norm": 0.24564869701862335,
848
- "learning_rate": 0.00014944567627494458,
849
- "loss": 0.7548,
850
- "step": 120
851
- },
852
- {
853
- "epoch": 0.7978021978021979,
854
- "grad_norm": 0.2209189534187317,
855
- "learning_rate": 0.00014900221729490022,
856
- "loss": 0.6474,
857
- "step": 121
858
- },
859
- {
860
- "epoch": 0.8043956043956044,
861
- "grad_norm": 0.24389097094535828,
862
- "learning_rate": 0.0001485587583148559,
863
- "loss": 0.7471,
864
- "step": 122
865
- },
866
- {
867
- "epoch": 0.810989010989011,
868
- "grad_norm": 0.23514863848686218,
869
- "learning_rate": 0.00014811529933481154,
870
- "loss": 0.6859,
871
- "step": 123
872
- },
873
- {
874
- "epoch": 0.8175824175824176,
875
- "grad_norm": 0.26364991068840027,
876
- "learning_rate": 0.0001476718403547672,
877
- "loss": 0.6276,
878
- "step": 124
879
- },
880
- {
881
- "epoch": 0.8241758241758241,
882
- "grad_norm": 0.2185850590467453,
883
- "learning_rate": 0.00014722838137472282,
884
- "loss": 0.7346,
885
- "step": 125
886
- },
887
- {
888
- "epoch": 0.8307692307692308,
889
- "grad_norm": 0.22511166334152222,
890
- "learning_rate": 0.0001467849223946785,
891
- "loss": 0.7208,
892
- "step": 126
893
- },
894
- {
895
- "epoch": 0.8373626373626374,
896
- "grad_norm": 0.20826543867588043,
897
- "learning_rate": 0.00014634146341463414,
898
- "loss": 0.6757,
899
- "step": 127
900
- },
901
- {
902
- "epoch": 0.843956043956044,
903
- "grad_norm": 0.22027815878391266,
904
- "learning_rate": 0.0001458980044345898,
905
- "loss": 0.6839,
906
- "step": 128
907
- },
908
- {
909
- "epoch": 0.8505494505494505,
910
- "grad_norm": 0.23337896168231964,
911
- "learning_rate": 0.00014545454545454546,
912
- "loss": 0.6555,
913
- "step": 129
914
- },
915
- {
916
- "epoch": 0.8571428571428571,
917
- "grad_norm": 0.21975719928741455,
918
- "learning_rate": 0.00014501108647450113,
919
- "loss": 0.6829,
920
- "step": 130
921
- },
922
- {
923
- "epoch": 0.8637362637362638,
924
- "grad_norm": 0.2579653263092041,
925
- "learning_rate": 0.00014456762749445675,
926
- "loss": 0.6567,
927
- "step": 131
928
- },
929
- {
930
- "epoch": 0.8703296703296703,
931
- "grad_norm": 0.19928398728370667,
932
- "learning_rate": 0.00014412416851441242,
933
- "loss": 0.7138,
934
- "step": 132
935
- },
936
- {
937
- "epoch": 0.8769230769230769,
938
- "grad_norm": 0.23015153408050537,
939
- "learning_rate": 0.00014368070953436806,
940
- "loss": 0.695,
941
- "step": 133
942
- },
943
- {
944
- "epoch": 0.8835164835164835,
945
- "grad_norm": 0.25714021921157837,
946
- "learning_rate": 0.00014323725055432373,
947
- "loss": 0.7245,
948
- "step": 134
949
- },
950
- {
951
- "epoch": 0.8901098901098901,
952
- "grad_norm": 0.2980111837387085,
953
- "learning_rate": 0.00014279379157427938,
954
- "loss": 0.7276,
955
- "step": 135
956
- }
957
- ],
958
- "logging_steps": 1,
959
- "max_steps": 456,
960
- "num_input_tokens_seen": 0,
961
- "num_train_epochs": 3,
962
- "save_steps": 15,
963
- "stateful_callbacks": {
964
- "TrainerControl": {
965
- "args": {
966
- "should_epoch_stop": false,
967
- "should_evaluate": false,
968
- "should_log": false,
969
- "should_save": true,
970
- "should_training_stop": false
971
- },
972
- "attributes": {}
973
- }
974
- },
975
- "total_flos": 6.229455871693824e+16,
976
- "train_batch_size": 22,
977
- "trial_name": null,
978
- "trial_params": null
979
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
seed0/checkpoint-135/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0314cf5080efcc9f80748b98c0e8740951e978b06ae398400172ff9f77eb1257
3
- size 6289
 
 
 
 
seed0/checkpoint-135/vocab.json DELETED
The diff for this file is too large to render. See raw diff
 
seed0/checkpoint-15/README.md DELETED
@@ -1,210 +0,0 @@
1
- ---
2
- base_model: unsloth/Qwen2.5-7B-Instruct
3
- library_name: peft
4
- pipeline_tag: text-generation
5
- tags:
6
- - base_model:adapter:unsloth/Qwen2.5-7B-Instruct
7
- - lora
8
- - sft
9
- - transformers
10
- - trl
11
- - unsloth
12
- ---
13
-
14
- # Model Card for Model ID
15
-
16
- <!-- Provide a quick summary of what the model is/does. -->
17
-
18
-
19
-
20
- ## Model Details
21
-
22
- ### Model Description
23
-
24
- <!-- Provide a longer summary of what this model is. -->
25
-
26
-
27
-
28
- - **Developed by:** [More Information Needed]
29
- - **Funded by [optional]:** [More Information Needed]
30
- - **Shared by [optional]:** [More Information Needed]
31
- - **Model type:** [More Information Needed]
32
- - **Language(s) (NLP):** [More Information Needed]
33
- - **License:** [More Information Needed]
34
- - **Finetuned from model [optional]:** [More Information Needed]
35
-
36
- ### Model Sources [optional]
37
-
38
- <!-- Provide the basic links for the model. -->
39
-
40
- - **Repository:** [More Information Needed]
41
- - **Paper [optional]:** [More Information Needed]
42
- - **Demo [optional]:** [More Information Needed]
43
-
44
- ## Uses
45
-
46
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
47
-
48
- ### Direct Use
49
-
50
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
51
-
52
- [More Information Needed]
53
-
54
- ### Downstream Use [optional]
55
-
56
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
57
-
58
- [More Information Needed]
59
-
60
- ### Out-of-Scope Use
61
-
62
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
63
-
64
- [More Information Needed]
65
-
66
- ## Bias, Risks, and Limitations
67
-
68
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
69
-
70
- [More Information Needed]
71
-
72
- ### Recommendations
73
-
74
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
75
-
76
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
77
-
78
- ## How to Get Started with the Model
79
-
80
- Use the code below to get started with the model.
81
-
82
- [More Information Needed]
83
-
84
- ## Training Details
85
-
86
- ### Training Data
87
-
88
- <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
89
-
90
- [More Information Needed]
91
-
92
- ### Training Procedure
93
-
94
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
95
-
96
- #### Preprocessing [optional]
97
-
98
- [More Information Needed]
99
-
100
-
101
- #### Training Hyperparameters
102
-
103
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
104
-
105
- #### Speeds, Sizes, Times [optional]
106
-
107
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
108
-
109
- [More Information Needed]
110
-
111
- ## Evaluation
112
-
113
- <!-- This section describes the evaluation protocols and provides the results. -->
114
-
115
- ### Testing Data, Factors & Metrics
116
-
117
- #### Testing Data
118
-
119
- <!-- This should link to a Dataset Card if possible. -->
120
-
121
- [More Information Needed]
122
-
123
- #### Factors
124
-
125
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
126
-
127
- [More Information Needed]
128
-
129
- #### Metrics
130
-
131
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
132
-
133
- [More Information Needed]
134
-
135
- ### Results
136
-
137
- [More Information Needed]
138
-
139
- #### Summary
140
-
141
-
142
-
143
- ## Model Examination [optional]
144
-
145
- <!-- Relevant interpretability work for the model goes here -->
146
-
147
- [More Information Needed]
148
-
149
- ## Environmental Impact
150
-
151
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
152
-
153
- Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
154
-
155
- - **Hardware Type:** [More Information Needed]
156
- - **Hours used:** [More Information Needed]
157
- - **Cloud Provider:** [More Information Needed]
158
- - **Compute Region:** [More Information Needed]
159
- - **Carbon Emitted:** [More Information Needed]
160
-
161
- ## Technical Specifications [optional]
162
-
163
- ### Model Architecture and Objective
164
-
165
- [More Information Needed]
166
-
167
- ### Compute Infrastructure
168
-
169
- [More Information Needed]
170
-
171
- #### Hardware
172
-
173
- [More Information Needed]
174
-
175
- #### Software
176
-
177
- [More Information Needed]
178
-
179
- ## Citation [optional]
180
-
181
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
182
-
183
- **BibTeX:**
184
-
185
- [More Information Needed]
186
-
187
- **APA:**
188
-
189
- [More Information Needed]
190
-
191
- ## Glossary [optional]
192
-
193
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
194
-
195
- [More Information Needed]
196
-
197
- ## More Information [optional]
198
-
199
- [More Information Needed]
200
-
201
- ## Model Card Authors [optional]
202
-
203
- [More Information Needed]
204
-
205
- ## Model Card Contact
206
-
207
- [More Information Needed]
208
- ### Framework versions
209
-
210
- - PEFT 0.18.1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
seed0/checkpoint-15/adapter_config.json DELETED
@@ -1,50 +0,0 @@
1
- {
2
- "alora_invocation_tokens": null,
3
- "alpha_pattern": {},
4
- "arrow_config": null,
5
- "auto_mapping": {
6
- "base_model_class": "Qwen2ForCausalLM",
7
- "parent_library": "transformers.models.qwen2.modeling_qwen2",
8
- "unsloth_fixed": true
9
- },
10
- "base_model_name_or_path": "unsloth/Qwen2.5-7B-Instruct",
11
- "bias": "none",
12
- "corda_config": null,
13
- "ensure_weight_tying": false,
14
- "eva_config": null,
15
- "exclude_modules": null,
16
- "fan_in_fan_out": false,
17
- "inference_mode": true,
18
- "init_lora_weights": true,
19
- "layer_replication": null,
20
- "layers_pattern": null,
21
- "layers_to_transform": null,
22
- "loftq_config": {},
23
- "lora_alpha": 8,
24
- "lora_bias": false,
25
- "lora_dropout": 0.0,
26
- "megatron_config": null,
27
- "megatron_core": "megatron.core",
28
- "modules_to_save": null,
29
- "peft_type": "LORA",
30
- "peft_version": "0.18.1",
31
- "qalora_group_size": 16,
32
- "r": 8,
33
- "rank_pattern": {},
34
- "revision": null,
35
- "target_modules": [
36
- "k_proj",
37
- "v_proj",
38
- "up_proj",
39
- "q_proj",
40
- "down_proj",
41
- "o_proj",
42
- "gate_proj"
43
- ],
44
- "target_parameters": null,
45
- "task_type": "CAUSAL_LM",
46
- "trainable_token_indices": null,
47
- "use_dora": false,
48
- "use_qalora": false,
49
- "use_rslora": false
50
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
seed0/checkpoint-15/adapter_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fc04f575ce625d6a667f692536dc34b311e512ab5c491a2278fc95178447145
3
- size 80792096
 
 
 
 
seed0/checkpoint-15/added_tokens.json DELETED
@@ -1,25 +0,0 @@
1
- {
2
- "</tool_call>": 151658,
3
- "<tool_call>": 151657,
4
- "<|PAD_TOKEN|>": 151665,
5
- "<|box_end|>": 151649,
6
- "<|box_start|>": 151648,
7
- "<|endoftext|>": 151643,
8
- "<|file_sep|>": 151664,
9
- "<|fim_middle|>": 151660,
10
- "<|fim_pad|>": 151662,
11
- "<|fim_prefix|>": 151659,
12
- "<|fim_suffix|>": 151661,
13
- "<|im_end|>": 151645,
14
- "<|im_start|>": 151644,
15
- "<|image_pad|>": 151655,
16
- "<|object_ref_end|>": 151647,
17
- "<|object_ref_start|>": 151646,
18
- "<|quad_end|>": 151651,
19
- "<|quad_start|>": 151650,
20
- "<|repo_name|>": 151663,
21
- "<|video_pad|>": 151656,
22
- "<|vision_end|>": 151653,
23
- "<|vision_pad|>": 151654,
24
- "<|vision_start|>": 151652
25
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
seed0/checkpoint-15/chat_template.jinja DELETED
@@ -1,54 +0,0 @@
1
- {%- if tools %}
2
- {{- '<|im_start|>system\n' }}
3
- {%- if messages[0]['role'] == 'system' %}
4
- {{- messages[0]['content'] }}
5
- {%- else %}
6
- {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
- {%- endif %}
8
- {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
- {%- for tool in tools %}
10
- {{- "\n" }}
11
- {{- tool | tojson }}
12
- {%- endfor %}
13
- {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
- {%- else %}
15
- {%- if messages[0]['role'] == 'system' %}
16
- {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
- {%- else %}
18
- {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
- {%- endif %}
20
- {%- endif %}
21
- {%- for message in messages %}
22
- {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
- {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
- {%- elif message.role == "assistant" %}
25
- {{- '<|im_start|>' + message.role }}
26
- {%- if message.content %}
27
- {{- '\n' + message.content }}
28
- {%- endif %}
29
- {%- for tool_call in message.tool_calls %}
30
- {%- if tool_call.function is defined %}
31
- {%- set tool_call = tool_call.function %}
32
- {%- endif %}
33
- {{- '\n<tool_call>\n{"name": "' }}
34
- {{- tool_call.name }}
35
- {{- '", "arguments": ' }}
36
- {{- tool_call.arguments | tojson }}
37
- {{- '}\n</tool_call>' }}
38
- {%- endfor %}
39
- {{- '<|im_end|>\n' }}
40
- {%- elif message.role == "tool" %}
41
- {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
- {{- '<|im_start|>user' }}
43
- {%- endif %}
44
- {{- '\n<tool_response>\n' }}
45
- {{- message.content }}
46
- {{- '\n</tool_response>' }}
47
- {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
- {{- '<|im_end|>\n' }}
49
- {%- endif %}
50
- {%- endif %}
51
- {%- endfor %}
52
- {%- if add_generation_prompt %}
53
- {{- '<|im_start|>assistant\n' }}
54
- {%- endif %}