Hugging Face's logo

daichira
/
haiku-qwen3-4b-lora-unsloth

PEFT
Safetensors
lora
qlora
japanese
haiku
poetry
Model card Files
xet
Community
daichira commited on
Commit
c63c1cb
·
1 Parent(s): daa1f45

Revert "Upload folder using huggingface_hub"

Browse files

This reverts commit daa1f45d41d252601c28665104207d267fb10705.

This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +1 -6
  2. README.md +13 -31
  3. adapter_config.json +6 -10
  4. adapter_model.safetensors +1 -1
  5. checkpoint-231/README.md +0 -210
  6. checkpoint-231/adapter_config.json +0 -50
  7. checkpoint-231/adapter_model.safetensors +0 -3
  8. checkpoint-231/added_tokens.json +0 -28
  9. checkpoint-231/chat_template.jinja +0 -86
  10. checkpoint-231/merges.txt +0 -0
  11. checkpoint-231/optimizer.pt +0 -3
  12. checkpoint-231/rng_state.pth +0 -0
  13. checkpoint-231/scaler.pt +0 -0
  14. checkpoint-231/scheduler.pt +0 -0
  15. checkpoint-231/special_tokens_map.json +0 -25
  16. checkpoint-231/tokenizer.json +0 -3
  17. checkpoint-231/tokenizer_config.json +0 -240
  18. checkpoint-231/trainer_state.json +0 -111
  19. checkpoint-231/training_args.bin +0 -0
  20. checkpoint-231/vocab.json +0 -0
  21. checkpoint-462/README.md +0 -210
  22. checkpoint-462/adapter_config.json +0 -50
  23. checkpoint-462/adapter_model.safetensors +0 -3
  24. checkpoint-462/added_tokens.json +0 -28
  25. checkpoint-462/chat_template.jinja +0 -86
  26. checkpoint-462/merges.txt +0 -0
  27. checkpoint-462/optimizer.pt +0 -3
  28. checkpoint-462/rng_state.pth +0 -0
  29. checkpoint-462/scaler.pt +0 -0
  30. checkpoint-462/scheduler.pt +0 -0
  31. checkpoint-462/special_tokens_map.json +0 -25
  32. checkpoint-462/tokenizer.json +0 -3
  33. checkpoint-462/tokenizer_config.json +0 -240
  34. checkpoint-462/trainer_state.json +0 -195
  35. checkpoint-462/training_args.bin +0 -0
  36. checkpoint-462/vocab.json +0 -0
  37. checkpoint-693/README.md +0 -210
  38. checkpoint-693/adapter_config.json +0 -50
  39. checkpoint-693/adapter_model.safetensors +0 -3
  40. checkpoint-693/added_tokens.json +0 -28
  41. checkpoint-693/chat_template.jinja +0 -86
  42. checkpoint-693/merges.txt +0 -0
  43. checkpoint-693/optimizer.pt +0 -3
  44. checkpoint-693/rng_state.pth +0 -0
  45. checkpoint-693/scaler.pt +0 -0
  46. checkpoint-693/scheduler.pt +0 -0
  47. checkpoint-693/special_tokens_map.json +0 -25
  48. checkpoint-693/tokenizer.json +0 -3
  49. checkpoint-693/tokenizer_config.json +0 -240
  50. checkpoint-693/trainer_state.json +0 -272
.gitattributes CHANGED
@@ -1,8 +1,3 @@
1
  *.safetensors filter=lfs diff=lfs merge=lfs -text
2
- checkpoint-231/optimizer.pt filter=lfs diff=lfs merge=lfs -text
3
- checkpoint-231/tokenizer.json filter=lfs diff=lfs merge=lfs -text
4
- checkpoint-462/optimizer.pt filter=lfs diff=lfs merge=lfs -text
5
- checkpoint-462/tokenizer.json filter=lfs diff=lfs merge=lfs -text
6
- checkpoint-693/optimizer.pt filter=lfs diff=lfs merge=lfs -text
7
- checkpoint-693/tokenizer.json filter=lfs diff=lfs merge=lfs -text
8
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
1
  *.safetensors filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
2
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
3
+ training_args.bin filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,29 +1,19 @@
1
  ---
2
  library_name: peft
3
  tags:
4
- - lora
5
- - qlora
6
- - japanese
7
- - haiku
8
- - poetry
9
  base_model: Qwen/Qwen3-4B-Instruct-2507
10
  license: other
11
  ---
12
 
13
  # Haiku LoRA Adapter (Qwen3-4B-Instruct, 5-7-5 with Kigo)
14
 
15
- This repository contains **LoRA adapter weights** fine-tuned on
16
- `daichira/shiki-haiku-575-sft-v1` to generate Japanese haiku that:
17
-
18
- - Follow the 5-7-5 syllable pattern, and
19
- - Include the specified *kigo* (seasonal word).
20
-
21
- ## Training summary
22
-
23
- - Base model : `Qwen/Qwen3-4B-Instruct-2507`
24
- - Dataset : `daichira/shiki-haiku-575-sft-v1`
25
- - Objective : Single haiku (5-7-5, with kigo) from chat-style prompt
26
- - Method : QLoRA (Unsloth + TRL `SFTTrainer`)
27
 
28
  ## Usage
29
 
@@ -35,25 +25,17 @@ base_model = "Qwen/Qwen3-4B-Instruct-2507"
35
  adapter_id = "daichira/haiku-qwen3-4b-lora-unsloth"
36
 
37
  tok = AutoTokenizer.from_pretrained(base_model, trust_remote_code=True, use_fast=True)
38
- base = AutoModelForCausalLM.from_pretrained(base_model, trust_remote_code=True).to("cuda")
39
- model = PeftModel.from_pretrained(base, adapter_id).to("cuda")
40
 
41
  messages = [
42
- {"role": "system", "content": "あなたは一流の俳人です。5-7-5 を厳守し、必ず季語を含めて俳句を一首だけ生成してください。"},
43
- {"role": "user", "content": "季語: 桜\n季節: 春\n俳句は一首だけ。"},
44
  ]
45
  prompt = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
46
  inputs = tok(prompt, return_tensors="pt").to(model.device)
47
- out = model.generate(
48
- **inputs,
49
- max_new_tokens=64,
50
- do_sample=True,
51
- top_p=0.9,
52
- temperature=0.7,
53
- pad_token_id=tok.eos_token_id,
54
- )
55
  print(tok.decode(out[0], skip_special_tokens=True))
56
  ```
57
 
58
- > Note: This repo only ships **LoRA adapter weights**.
59
- > You need to load the base model `Qwen/Qwen3-4B-Instruct-2507` separately.
 
1
  ---
2
  library_name: peft
3
  tags:
4
+ - lora
5
+ - qlora
6
+ - japanese
7
+ - haiku
8
+ - poetry
9
  base_model: Qwen/Qwen3-4B-Instruct-2507
10
  license: other
11
  ---
12
 
13
  # Haiku LoRA Adapter (Qwen3-4B-Instruct, 5-7-5 with Kigo)
14
 
15
+ This repository contains **LoRA adapter weights** fine-tuned with Unsloth/TRL
16
+ to compose **Japanese haiku** that follow the 5-7-5 pattern and include a given *kigo* (seasonal word).
 
 
 
 
 
 
 
 
 
 
17
 
18
  ## Usage
19
 
 
25
  adapter_id = "daichira/haiku-qwen3-4b-lora-unsloth"
26
 
27
  tok = AutoTokenizer.from_pretrained(base_model, trust_remote_code=True, use_fast=True)
28
+ base = AutoModelForCausalLM.from_pretrained(base_model, device_map="auto", trust_remote_code=True)
29
+ model = PeftModel.from_pretrained(base, adapter_id)
30
 
31
  messages = [
32
+ {"role":"system","content":"あなたは一流の俳人です。5-7-5を厳守し、必ず季語を含め、俳句一首のみを出力してください。"},
33
+ {"role":"user","content":"季語: 桜\n季節: 春\n一首だけ。"},
34
  ]
35
  prompt = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
36
  inputs = tok(prompt, return_tensors="pt").to(model.device)
37
+ out = model.generate(**inputs, max_new_tokens=64, do_sample=True, top_p=0.9, temperature=0.7)
 
 
 
 
 
 
 
38
  print(tok.decode(out[0], skip_special_tokens=True))
39
  ```
40
 
41
+ > Note: This repo only ships **LoRA adapters**, not the full base model.
 
adapter_config.json CHANGED
@@ -1,7 +1,5 @@
1
  {
2
- "alora_invocation_tokens": null,
3
  "alpha_pattern": {},
4
- "arrow_config": null,
5
  "auto_mapping": {
6
  "base_model_class": "Qwen3ForCausalLM",
7
  "parent_library": "transformers.models.qwen3.modeling_qwen3",
@@ -10,7 +8,6 @@
10
  "base_model_name_or_path": "unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit",
11
  "bias": "none",
12
  "corda_config": null,
13
- "ensure_weight_tying": false,
14
  "eva_config": null,
15
  "exclude_modules": null,
16
  "fan_in_fan_out": false,
@@ -22,29 +19,28 @@
22
  "loftq_config": {},
23
  "lora_alpha": 32,
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": "0.18.0",
31
  "qalora_group_size": 16,
32
  "r": 16,
33
  "rank_pattern": {},
34
  "revision": null,
35
  "target_modules": [
36
- "gate_proj",
37
  "down_proj",
 
 
38
  "up_proj",
39
- "v_proj",
40
  "q_proj",
41
- "o_proj",
42
- "k_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": true
50
  }
 
1
  {
 
2
  "alpha_pattern": {},
 
3
  "auto_mapping": {
4
  "base_model_class": "Qwen3ForCausalLM",
5
  "parent_library": "transformers.models.qwen3.modeling_qwen3",
 
8
  "base_model_name_or_path": "unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit",
9
  "bias": "none",
10
  "corda_config": null,
 
11
  "eva_config": null,
12
  "exclude_modules": null,
13
  "fan_in_fan_out": false,
 
19
  "loftq_config": {},
20
  "lora_alpha": 32,
21
  "lora_bias": false,
22
+ "lora_dropout": 0.05,
23
  "megatron_config": null,
24
  "megatron_core": "megatron.core",
25
  "modules_to_save": null,
26
  "peft_type": "LORA",
 
27
  "qalora_group_size": 16,
28
  "r": 16,
29
  "rank_pattern": {},
30
  "revision": null,
31
  "target_modules": [
 
32
  "down_proj",
33
+ "gate_proj",
34
+ "o_proj",
35
  "up_proj",
 
36
  "q_proj",
37
+ "k_proj",
38
+ "v_proj"
39
  ],
40
  "target_parameters": null,
41
  "task_type": "CAUSAL_LM",
42
  "trainable_token_indices": null,
43
  "use_dora": false,
44
  "use_qalora": false,
45
+ "use_rslora": false
46
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2bbdd3286c25eee36ce6109cfa49b93edf63ae3fb4c531204f430c8efa346ab
3
  size 132187888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c46b4ec76b14ee90fed7d081eedfee20a207c296e87409c7725335bfb123c4ed
3
  size 132187888
checkpoint-231/README.md DELETED
@@ -1,210 +0,0 @@
1
- ---
2
- base_model: unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit
3
- library_name: peft
4
- pipeline_tag: text-generation
5
- tags:
6
- - base_model:adapter:unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit
7
- - lora
8
- - sft
9
- - transformers
10
- - trl
11
- - unsloth
12
- ---
13
-
14
- # Model Card for Model ID
15
-
16
- <!-- Provide a quick summary of what the model is/does. -->
17
-
18
-
19
-
20
- ## Model Details
21
-
22
- ### Model Description
23
-
24
- <!-- Provide a longer summary of what this model is. -->
25
-
26
-
27
-
28
- - **Developed by:** [More Information Needed]
29
- - **Funded by [optional]:** [More Information Needed]
30
- - **Shared by [optional]:** [More Information Needed]
31
- - **Model type:** [More Information Needed]
32
- - **Language(s) (NLP):** [More Information Needed]
33
- - **License:** [More Information Needed]
34
- - **Finetuned from model [optional]:** [More Information Needed]
35
-
36
- ### Model Sources [optional]
37
-
38
- <!-- Provide the basic links for the model. -->
39
-
40
- - **Repository:** [More Information Needed]
41
- - **Paper [optional]:** [More Information Needed]
42
- - **Demo [optional]:** [More Information Needed]
43
-
44
- ## Uses
45
-
46
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
47
-
48
- ### Direct Use
49
-
50
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
51
-
52
- [More Information Needed]
53
-
54
- ### Downstream Use [optional]
55
-
56
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
57
-
58
- [More Information Needed]
59
-
60
- ### Out-of-Scope Use
61
-
62
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
63
-
64
- [More Information Needed]
65
-
66
- ## Bias, Risks, and Limitations
67
-
68
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
69
-
70
- [More Information Needed]
71
-
72
- ### Recommendations
73
-
74
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
75
-
76
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
77
-
78
- ## How to Get Started with the Model
79
-
80
- Use the code below to get started with the model.
81
-
82
- [More Information Needed]
83
-
84
- ## Training Details
85
-
86
- ### Training Data
87
-
88
- <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
89
-
90
- [More Information Needed]
91
-
92
- ### Training Procedure
93
-
94
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
95
-
96
- #### Preprocessing [optional]
97
-
98
- [More Information Needed]
99
-
100
-
101
- #### Training Hyperparameters
102
-
103
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
104
-
105
- #### Speeds, Sizes, Times [optional]
106
-
107
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
108
-
109
- [More Information Needed]
110
-
111
- ## Evaluation
112
-
113
- <!-- This section describes the evaluation protocols and provides the results. -->
114
-
115
- ### Testing Data, Factors & Metrics
116
-
117
- #### Testing Data
118
-
119
- <!-- This should link to a Dataset Card if possible. -->
120
-
121
- [More Information Needed]
122
-
123
- #### Factors
124
-
125
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
126
-
127
- [More Information Needed]
128
-
129
- #### Metrics
130
-
131
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
132
-
133
- [More Information Needed]
134
-
135
- ### Results
136
-
137
- [More Information Needed]
138
-
139
- #### Summary
140
-
141
-
142
-
143
- ## Model Examination [optional]
144
-
145
- <!-- Relevant interpretability work for the model goes here -->
146
-
147
- [More Information Needed]
148
-
149
- ## Environmental Impact
150
-
151
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
152
-
153
- Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
154
-
155
- - **Hardware Type:** [More Information Needed]
156
- - **Hours used:** [More Information Needed]
157
- - **Cloud Provider:** [More Information Needed]
158
- - **Compute Region:** [More Information Needed]
159
- - **Carbon Emitted:** [More Information Needed]
160
-
161
- ## Technical Specifications [optional]
162
-
163
- ### Model Architecture and Objective
164
-
165
- [More Information Needed]
166
-
167
- ### Compute Infrastructure
168
-
169
- [More Information Needed]
170
-
171
- #### Hardware
172
-
173
- [More Information Needed]
174
-
175
- #### Software
176
-
177
- [More Information Needed]
178
-
179
- ## Citation [optional]
180
-
181
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
182
-
183
- **BibTeX:**
184
-
185
- [More Information Needed]
186
-
187
- **APA:**
188
-
189
- [More Information Needed]
190
-
191
- ## Glossary [optional]
192
-
193
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
194
-
195
- [More Information Needed]
196
-
197
- ## More Information [optional]
198
-
199
- [More Information Needed]
200
-
201
- ## Model Card Authors [optional]
202
-
203
- [More Information Needed]
204
-
205
- ## Model Card Contact
206
-
207
- [More Information Needed]
208
- ### Framework versions
209
-
210
- - PEFT 0.18.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-231/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": "Qwen3ForCausalLM",
7
- "parent_library": "transformers.models.qwen3.modeling_qwen3",
8
- "unsloth_fixed": true
9
- },
10
- "base_model_name_or_path": "unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit",
11
- "bias": "none",
12
- "corda_config": null,
13
- "ensure_weight_tying": false,
14
- "eva_config": null,
15
- "exclude_modules": null,
16
- "fan_in_fan_out": false,
17
- "inference_mode": true,
18
- "init_lora_weights": true,
19
- "layer_replication": null,
20
- "layers_pattern": null,
21
- "layers_to_transform": null,
22
- "loftq_config": {},
23
- "lora_alpha": 32,
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": "0.18.0",
31
- "qalora_group_size": 16,
32
- "r": 16,
33
- "rank_pattern": {},
34
- "revision": null,
35
- "target_modules": [
36
- "gate_proj",
37
- "down_proj",
38
- "up_proj",
39
- "v_proj",
40
- "q_proj",
41
- "o_proj",
42
- "k_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": true
50
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-231/adapter_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc82563eb7d1536ce991cf6511e463607a1667326c99d1cf1047101b50d58f97
3
- size 132187888
 
 
 
 
checkpoint-231/added_tokens.json DELETED
@@ -1,28 +0,0 @@
1
- {
2
- "</think>": 151668,
3
- "</tool_call>": 151658,
4
- "</tool_response>": 151666,
5
- "<think>": 151667,
6
- "<tool_call>": 151657,
7
- "<tool_response>": 151665,
8
- "<|box_end|>": 151649,
9
- "<|box_start|>": 151648,
10
- "<|endoftext|>": 151643,
11
- "<|file_sep|>": 151664,
12
- "<|fim_middle|>": 151660,
13
- "<|fim_pad|>": 151662,
14
- "<|fim_prefix|>": 151659,
15
- "<|fim_suffix|>": 151661,
16
- "<|im_end|>": 151645,
17
- "<|im_start|>": 151644,
18
- "<|image_pad|>": 151655,
19
- "<|object_ref_end|>": 151647,
20
- "<|object_ref_start|>": 151646,
21
- "<|quad_end|>": 151651,
22
- "<|quad_start|>": 151650,
23
- "<|repo_name|>": 151663,
24
- "<|video_pad|>": 151656,
25
- "<|vision_end|>": 151653,
26
- "<|vision_pad|>": 151654,
27
- "<|vision_start|>": 151652
28
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-231/chat_template.jinja DELETED
@@ -1,86 +0,0 @@
1
- {%- if tools %}
2
- {{- '<|im_start|>system\n' }}
3
- {%- if messages[0].role == 'system' %}
4
- {{- messages[0].content + '\n\n' }}
5
- {%- endif %}
6
- {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
- {%- for tool in tools %}
8
- {{- "\n" }}
9
- {{- tool | tojson }}
10
- {%- endfor %}
11
- {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
- {%- else %}
13
- {%- if messages[0].role == 'system' %}
14
- {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
- {%- endif %}
16
- {%- endif %}
17
- {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
- {%- for message in messages[::-1] %}
19
- {%- set index = (messages|length - 1) - loop.index0 %}
20
- {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
- {%- set ns.multi_step_tool = false %}
22
- {%- set ns.last_query_index = index %}
23
- {%- endif %}
24
- {%- endfor %}
25
- {%- for message in messages %}
26
- {%- if message.content is string %}
27
- {%- set content = message.content %}
28
- {%- else %}
29
- {%- set content = '' %}
30
- {%- endif %}
31
- {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
32
- {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
33
- {%- elif message.role == "assistant" %}
34
- {%- set reasoning_content = '' %}
35
- {%- if message.reasoning_content is string %}
36
- {%- set reasoning_content = message.reasoning_content %}
37
- {%- else %}
38
- {%- if '</think>' in content %}
39
- {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
40
- {%- set content = content.split('</think>')[-1].lstrip('\n') %}
41
- {%- endif %}
42
- {%- endif %}
43
- {%- if loop.index0 > ns.last_query_index %}
44
- {%- if loop.last or (not loop.last and reasoning_content) %}
45
- {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
46
- {%- else %}
47
- {{- '<|im_start|>' + message.role + '\n' + content }}
48
- {%- endif %}
49
- {%- else %}
50
- {{- '<|im_start|>' + message.role + '\n' + content }}
51
- {%- endif %}
52
- {%- if message.tool_calls %}
53
- {%- for tool_call in message.tool_calls %}
54
- {%- if (loop.first and content) or (not loop.first) %}
55
- {{- '\n' }}
56
- {%- endif %}
57
- {%- if tool_call.function %}
58
- {%- set tool_call = tool_call.function %}
59
- {%- endif %}
60
- {{- '<tool_call>\n{"name": "' }}
61
- {{- tool_call.name }}
62
- {{- '", "arguments": ' }}
63
- {%- if tool_call.arguments is string %}
64
- {{- tool_call.arguments }}
65
- {%- else %}
66
- {{- tool_call.arguments | tojson }}
67
- {%- endif %}
68
- {{- '}\n</tool_call>' }}
69
- {%- endfor %}
70
- {%- endif %}
71
- {{- '<|im_end|>\n' }}
72
- {%- elif message.role == "tool" %}
73
- {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
74
- {{- '<|im_start|>user' }}
75
- {%- endif %}
76
- {{- '\n<tool_response>\n' }}
77
- {{- content }}
78
- {{- '\n</tool_response>' }}
79
- {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
80
- {{- '<|im_end|>\n' }}
81
- {%- endif %}
82
- {%- endif %}
83
- {%- endfor %}
84
- {%- if add_generation_prompt %}
85
- {{- '<|im_start|>assistant\n' }}
86
- {%- endif %}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-231/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
checkpoint-231/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0572baf01c5d54b9d02272a270c388fbbd293964fcc8ea0456784d238207fef9
3
- size 264673227
 
 
 
 
checkpoint-231/rng_state.pth DELETED
Binary file (14.6 kB)
 
checkpoint-231/scaler.pt DELETED
Binary file (1.38 kB)
 
checkpoint-231/scheduler.pt DELETED
Binary file (1.47 kB)
 
checkpoint-231/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": "<|im_end|>"
25
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-231/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
- size 11422654
 
 
 
 
checkpoint-231/tokenizer_config.json DELETED
@@ -1,240 +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": "<tool_response>",
183
- "lstrip": false,
184
- "normalized": false,
185
- "rstrip": false,
186
- "single_word": false,
187
- "special": false
188
- },
189
- "151666": {
190
- "content": "</tool_response>",
191
- "lstrip": false,
192
- "normalized": false,
193
- "rstrip": false,
194
- "single_word": false,
195
- "special": false
196
- },
197
- "151667": {
198
- "content": "<think>",
199
- "lstrip": false,
200
- "normalized": false,
201
- "rstrip": false,
202
- "single_word": false,
203
- "special": false
204
- },
205
- "151668": {
206
- "content": "</think>",
207
- "lstrip": false,
208
- "normalized": false,
209
- "rstrip": false,
210
- "single_word": false,
211
- "special": false
212
- }
213
- },
214
- "additional_special_tokens": [
215
- "<|im_start|>",
216
- "<|im_end|>",
217
- "<|object_ref_start|>",
218
- "<|object_ref_end|>",
219
- "<|box_start|>",
220
- "<|box_end|>",
221
- "<|quad_start|>",
222
- "<|quad_end|>",
223
- "<|vision_start|>",
224
- "<|vision_end|>",
225
- "<|vision_pad|>",
226
- "<|image_pad|>",
227
- "<|video_pad|>"
228
- ],
229
- "bos_token": null,
230
- "clean_up_tokenization_spaces": false,
231
- "eos_token": "<|im_end|>",
232
- "errors": "replace",
233
- "extra_special_tokens": {},
234
- "model_max_length": 262144,
235
- "pad_token": "<|im_end|>",
236
- "padding_side": "right",
237
- "split_special_tokens": false,
238
- "tokenizer_class": "Qwen2Tokenizer",
239
- "unk_token": null
240
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-231/trainer_state.json DELETED
@@ -1,111 +0,0 @@
1
- {
2
- "best_global_step": null,
3
- "best_metric": null,
4
- "best_model_checkpoint": null,
5
- "epoch": 1.0,
6
- "eval_steps": 500,
7
- "global_step": 231,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "epoch": 0.08672086720867209,
14
- "grad_norm": 0.5473586916923523,
15
- "learning_rate": 0.00018095238095238095,
16
- "loss": 1.6195,
17
- "step": 20
18
- },
19
- {
20
- "epoch": 0.17344173441734417,
21
- "grad_norm": 0.475732684135437,
22
- "learning_rate": 0.00019464285714285715,
23
- "loss": 0.4109,
24
- "step": 40
25
- },
26
- {
27
- "epoch": 0.2601626016260163,
28
- "grad_norm": 0.3879268765449524,
29
- "learning_rate": 0.0001886904761904762,
30
- "loss": 0.3829,
31
- "step": 60
32
- },
33
- {
34
- "epoch": 0.34688346883468835,
35
- "grad_norm": 0.37163427472114563,
36
- "learning_rate": 0.00018273809523809524,
37
- "loss": 0.3734,
38
- "step": 80
39
- },
40
- {
41
- "epoch": 0.43360433604336046,
42
- "grad_norm": 0.4267672002315521,
43
- "learning_rate": 0.00017678571428571428,
44
- "loss": 0.3645,
45
- "step": 100
46
- },
47
- {
48
- "epoch": 0.5203252032520326,
49
- "grad_norm": 0.4751192629337311,
50
- "learning_rate": 0.00017083333333333333,
51
- "loss": 0.3567,
52
- "step": 120
53
- },
54
- {
55
- "epoch": 0.6070460704607046,
56
- "grad_norm": 0.3694995641708374,
57
- "learning_rate": 0.00016488095238095237,
58
- "loss": 0.3513,
59
- "step": 140
60
- },
61
- {
62
- "epoch": 0.6937669376693767,
63
- "grad_norm": 0.37785276770591736,
64
- "learning_rate": 0.00015892857142857142,
65
- "loss": 0.343,
66
- "step": 160
67
- },
68
- {
69
- "epoch": 0.7804878048780488,
70
- "grad_norm": 0.4374072253704071,
71
- "learning_rate": 0.00015297619047619046,
72
- "loss": 0.3419,
73
- "step": 180
74
- },
75
- {
76
- "epoch": 0.8672086720867209,
77
- "grad_norm": 0.42704370617866516,
78
- "learning_rate": 0.00014702380952380954,
79
- "loss": 0.3345,
80
- "step": 200
81
- },
82
- {
83
- "epoch": 0.9539295392953929,
84
- "grad_norm": 0.34092533588409424,
85
- "learning_rate": 0.00014107142857142858,
86
- "loss": 0.3338,
87
- "step": 220
88
- }
89
- ],
90
- "logging_steps": 20,
91
- "max_steps": 693,
92
- "num_input_tokens_seen": 0,
93
- "num_train_epochs": 3,
94
- "save_steps": 500,
95
- "stateful_callbacks": {
96
- "TrainerControl": {
97
- "args": {
98
- "should_epoch_stop": false,
99
- "should_evaluate": false,
100
- "should_log": false,
101
- "should_save": true,
102
- "should_training_stop": false
103
- },
104
- "attributes": {}
105
- }
106
- },
107
- "total_flos": 2.375338487574528e+16,
108
- "train_batch_size": 4,
109
- "trial_name": null,
110
- "trial_params": null
111
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-231/training_args.bin DELETED
Binary file (6.23 kB)
 
checkpoint-231/vocab.json DELETED
The diff for this file is too large to render. See raw diff
 
checkpoint-462/README.md DELETED
@@ -1,210 +0,0 @@
1
- ---
2
- base_model: unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit
3
- library_name: peft
4
- pipeline_tag: text-generation
5
- tags:
6
- - base_model:adapter:unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit
7
- - lora
8
- - sft
9
- - transformers
10
- - trl
11
- - unsloth
12
- ---
13
-
14
- # Model Card for Model ID
15
-
16
- <!-- Provide a quick summary of what the model is/does. -->
17
-
18
-
19
-
20
- ## Model Details
21
-
22
- ### Model Description
23
-
24
- <!-- Provide a longer summary of what this model is. -->
25
-
26
-
27
-
28
- - **Developed by:** [More Information Needed]
29
- - **Funded by [optional]:** [More Information Needed]
30
- - **Shared by [optional]:** [More Information Needed]
31
- - **Model type:** [More Information Needed]
32
- - **Language(s) (NLP):** [More Information Needed]
33
- - **License:** [More Information Needed]
34
- - **Finetuned from model [optional]:** [More Information Needed]
35
-
36
- ### Model Sources [optional]
37
-
38
- <!-- Provide the basic links for the model. -->
39
-
40
- - **Repository:** [More Information Needed]
41
- - **Paper [optional]:** [More Information Needed]
42
- - **Demo [optional]:** [More Information Needed]
43
-
44
- ## Uses
45
-
46
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
47
-
48
- ### Direct Use
49
-
50
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
51
-
52
- [More Information Needed]
53
-
54
- ### Downstream Use [optional]
55
-
56
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
57
-
58
- [More Information Needed]
59
-
60
- ### Out-of-Scope Use
61
-
62
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
63
-
64
- [More Information Needed]
65
-
66
- ## Bias, Risks, and Limitations
67
-
68
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
69
-
70
- [More Information Needed]
71
-
72
- ### Recommendations
73
-
74
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
75
-
76
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
77
-
78
- ## How to Get Started with the Model
79
-
80
- Use the code below to get started with the model.
81
-
82
- [More Information Needed]
83
-
84
- ## Training Details
85
-
86
- ### Training Data
87
-
88
- <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
89
-
90
- [More Information Needed]
91
-
92
- ### Training Procedure
93
-
94
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
95
-
96
- #### Preprocessing [optional]
97
-
98
- [More Information Needed]
99
-
100
-
101
- #### Training Hyperparameters
102
-
103
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
104
-
105
- #### Speeds, Sizes, Times [optional]
106
-
107
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
108
-
109
- [More Information Needed]
110
-
111
- ## Evaluation
112
-
113
- <!-- This section describes the evaluation protocols and provides the results. -->
114
-
115
- ### Testing Data, Factors & Metrics
116
-
117
- #### Testing Data
118
-
119
- <!-- This should link to a Dataset Card if possible. -->
120
-
121
- [More Information Needed]
122
-
123
- #### Factors
124
-
125
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
126
-
127
- [More Information Needed]
128
-
129
- #### Metrics
130
-
131
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
132
-
133
- [More Information Needed]
134
-
135
- ### Results
136
-
137
- [More Information Needed]
138
-
139
- #### Summary
140
-
141
-
142
-
143
- ## Model Examination [optional]
144
-
145
- <!-- Relevant interpretability work for the model goes here -->
146
-
147
- [More Information Needed]
148
-
149
- ## Environmental Impact
150
-
151
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
152
-
153
- Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
154
-
155
- - **Hardware Type:** [More Information Needed]
156
- - **Hours used:** [More Information Needed]
157
- - **Cloud Provider:** [More Information Needed]
158
- - **Compute Region:** [More Information Needed]
159
- - **Carbon Emitted:** [More Information Needed]
160
-
161
- ## Technical Specifications [optional]
162
-
163
- ### Model Architecture and Objective
164
-
165
- [More Information Needed]
166
-
167
- ### Compute Infrastructure
168
-
169
- [More Information Needed]
170
-
171
- #### Hardware
172
-
173
- [More Information Needed]
174
-
175
- #### Software
176
-
177
- [More Information Needed]
178
-
179
- ## Citation [optional]
180
-
181
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
182
-
183
- **BibTeX:**
184
-
185
- [More Information Needed]
186
-
187
- **APA:**
188
-
189
- [More Information Needed]
190
-
191
- ## Glossary [optional]
192
-
193
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
194
-
195
- [More Information Needed]
196
-
197
- ## More Information [optional]
198
-
199
- [More Information Needed]
200
-
201
- ## Model Card Authors [optional]
202
-
203
- [More Information Needed]
204
-
205
- ## Model Card Contact
206
-
207
- [More Information Needed]
208
- ### Framework versions
209
-
210
- - PEFT 0.18.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-462/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": "Qwen3ForCausalLM",
7
- "parent_library": "transformers.models.qwen3.modeling_qwen3",
8
- "unsloth_fixed": true
9
- },
10
- "base_model_name_or_path": "unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit",
11
- "bias": "none",
12
- "corda_config": null,
13
- "ensure_weight_tying": false,
14
- "eva_config": null,
15
- "exclude_modules": null,
16
- "fan_in_fan_out": false,
17
- "inference_mode": true,
18
- "init_lora_weights": true,
19
- "layer_replication": null,
20
- "layers_pattern": null,
21
- "layers_to_transform": null,
22
- "loftq_config": {},
23
- "lora_alpha": 32,
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": "0.18.0",
31
- "qalora_group_size": 16,
32
- "r": 16,
33
- "rank_pattern": {},
34
- "revision": null,
35
- "target_modules": [
36
- "gate_proj",
37
- "down_proj",
38
- "up_proj",
39
- "v_proj",
40
- "q_proj",
41
- "o_proj",
42
- "k_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": true
50
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-462/adapter_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd87027c2e616620001a0a5a8add822595dcf309564874df3b4a786917e03746
3
- size 132187888
 
 
 
 
checkpoint-462/added_tokens.json DELETED
@@ -1,28 +0,0 @@
1
- {
2
- "</think>": 151668,
3
- "</tool_call>": 151658,
4
- "</tool_response>": 151666,
5
- "<think>": 151667,
6
- "<tool_call>": 151657,
7
- "<tool_response>": 151665,
8
- "<|box_end|>": 151649,
9
- "<|box_start|>": 151648,
10
- "<|endoftext|>": 151643,
11
- "<|file_sep|>": 151664,
12
- "<|fim_middle|>": 151660,
13
- "<|fim_pad|>": 151662,
14
- "<|fim_prefix|>": 151659,
15
- "<|fim_suffix|>": 151661,
16
- "<|im_end|>": 151645,
17
- "<|im_start|>": 151644,
18
- "<|image_pad|>": 151655,
19
- "<|object_ref_end|>": 151647,
20
- "<|object_ref_start|>": 151646,
21
- "<|quad_end|>": 151651,
22
- "<|quad_start|>": 151650,
23
- "<|repo_name|>": 151663,
24
- "<|video_pad|>": 151656,
25
- "<|vision_end|>": 151653,
26
- "<|vision_pad|>": 151654,
27
- "<|vision_start|>": 151652
28
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-462/chat_template.jinja DELETED
@@ -1,86 +0,0 @@
1
- {%- if tools %}
2
- {{- '<|im_start|>system\n' }}
3
- {%- if messages[0].role == 'system' %}
4
- {{- messages[0].content + '\n\n' }}
5
- {%- endif %}
6
- {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
- {%- for tool in tools %}
8
- {{- "\n" }}
9
- {{- tool | tojson }}
10
- {%- endfor %}
11
- {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
- {%- else %}
13
- {%- if messages[0].role == 'system' %}
14
- {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
- {%- endif %}
16
- {%- endif %}
17
- {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
- {%- for message in messages[::-1] %}
19
- {%- set index = (messages|length - 1) - loop.index0 %}
20
- {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
- {%- set ns.multi_step_tool = false %}
22
- {%- set ns.last_query_index = index %}
23
- {%- endif %}
24
- {%- endfor %}
25
- {%- for message in messages %}
26
- {%- if message.content is string %}
27
- {%- set content = message.content %}
28
- {%- else %}
29
- {%- set content = '' %}
30
- {%- endif %}
31
- {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
32
- {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
33
- {%- elif message.role == "assistant" %}
34
- {%- set reasoning_content = '' %}
35
- {%- if message.reasoning_content is string %}
36
- {%- set reasoning_content = message.reasoning_content %}
37
- {%- else %}
38
- {%- if '</think>' in content %}
39
- {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
40
- {%- set content = content.split('</think>')[-1].lstrip('\n') %}
41
- {%- endif %}
42
- {%- endif %}
43
- {%- if loop.index0 > ns.last_query_index %}
44
- {%- if loop.last or (not loop.last and reasoning_content) %}
45
- {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
46
- {%- else %}
47
- {{- '<|im_start|>' + message.role + '\n' + content }}
48
- {%- endif %}
49
- {%- else %}
50
- {{- '<|im_start|>' + message.role + '\n' + content }}
51
- {%- endif %}
52
- {%- if message.tool_calls %}
53
- {%- for tool_call in message.tool_calls %}
54
- {%- if (loop.first and content) or (not loop.first) %}
55
- {{- '\n' }}
56
- {%- endif %}
57
- {%- if tool_call.function %}
58
- {%- set tool_call = tool_call.function %}
59
- {%- endif %}
60
- {{- '<tool_call>\n{"name": "' }}
61
- {{- tool_call.name }}
62
- {{- '", "arguments": ' }}
63
- {%- if tool_call.arguments is string %}
64
- {{- tool_call.arguments }}
65
- {%- else %}
66
- {{- tool_call.arguments | tojson }}
67
- {%- endif %}
68
- {{- '}\n</tool_call>' }}
69
- {%- endfor %}
70
- {%- endif %}
71
- {{- '<|im_end|>\n' }}
72
- {%- elif message.role == "tool" %}
73
- {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
74
- {{- '<|im_start|>user' }}
75
- {%- endif %}
76
- {{- '\n<tool_response>\n' }}
77
- {{- content }}
78
- {{- '\n</tool_response>' }}
79
- {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
80
- {{- '<|im_end|>\n' }}
81
- {%- endif %}
82
- {%- endif %}
83
- {%- endfor %}
84
- {%- if add_generation_prompt %}
85
- {{- '<|im_start|>assistant\n' }}
86
- {%- endif %}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-462/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
checkpoint-462/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:865475c927e48a14cdd83739fe2ff08f5d234f2148a613c31b0fe07823d5c357
3
- size 264673227
 
 
 
 
checkpoint-462/rng_state.pth DELETED
Binary file (14.6 kB)
 
checkpoint-462/scaler.pt DELETED
Binary file (1.38 kB)
 
checkpoint-462/scheduler.pt DELETED
Binary file (1.47 kB)
 
checkpoint-462/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": "<|im_end|>"
25
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-462/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
- size 11422654
 
 
 
 
checkpoint-462/tokenizer_config.json DELETED
@@ -1,240 +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": "<tool_response>",
183
- "lstrip": false,
184
- "normalized": false,
185
- "rstrip": false,
186
- "single_word": false,
187
- "special": false
188
- },
189
- "151666": {
190
- "content": "</tool_response>",
191
- "lstrip": false,
192
- "normalized": false,
193
- "rstrip": false,
194
- "single_word": false,
195
- "special": false
196
- },
197
- "151667": {
198
- "content": "<think>",
199
- "lstrip": false,
200
- "normalized": false,
201
- "rstrip": false,
202
- "single_word": false,
203
- "special": false
204
- },
205
- "151668": {
206
- "content": "</think>",
207
- "lstrip": false,
208
- "normalized": false,
209
- "rstrip": false,
210
- "single_word": false,
211
- "special": false
212
- }
213
- },
214
- "additional_special_tokens": [
215
- "<|im_start|>",
216
- "<|im_end|>",
217
- "<|object_ref_start|>",
218
- "<|object_ref_end|>",
219
- "<|box_start|>",
220
- "<|box_end|>",
221
- "<|quad_start|>",
222
- "<|quad_end|>",
223
- "<|vision_start|>",
224
- "<|vision_end|>",
225
- "<|vision_pad|>",
226
- "<|image_pad|>",
227
- "<|video_pad|>"
228
- ],
229
- "bos_token": null,
230
- "clean_up_tokenization_spaces": false,
231
- "eos_token": "<|im_end|>",
232
- "errors": "replace",
233
- "extra_special_tokens": {},
234
- "model_max_length": 262144,
235
- "pad_token": "<|im_end|>",
236
- "padding_side": "right",
237
- "split_special_tokens": false,
238
- "tokenizer_class": "Qwen2Tokenizer",
239
- "unk_token": null
240
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-462/trainer_state.json DELETED
@@ -1,195 +0,0 @@
1
- {
2
- "best_global_step": null,
3
- "best_metric": null,
4
- "best_model_checkpoint": null,
5
- "epoch": 2.0,
6
- "eval_steps": 500,
7
- "global_step": 462,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "epoch": 0.08672086720867209,
14
- "grad_norm": 0.5473586916923523,
15
- "learning_rate": 0.00018095238095238095,
16
- "loss": 1.6195,
17
- "step": 20
18
- },
19
- {
20
- "epoch": 0.17344173441734417,
21
- "grad_norm": 0.475732684135437,
22
- "learning_rate": 0.00019464285714285715,
23
- "loss": 0.4109,
24
- "step": 40
25
- },
26
- {
27
- "epoch": 0.2601626016260163,
28
- "grad_norm": 0.3879268765449524,
29
- "learning_rate": 0.0001886904761904762,
30
- "loss": 0.3829,
31
- "step": 60
32
- },
33
- {
34
- "epoch": 0.34688346883468835,
35
- "grad_norm": 0.37163427472114563,
36
- "learning_rate": 0.00018273809523809524,
37
- "loss": 0.3734,
38
- "step": 80
39
- },
40
- {
41
- "epoch": 0.43360433604336046,
42
- "grad_norm": 0.4267672002315521,
43
- "learning_rate": 0.00017678571428571428,
44
- "loss": 0.3645,
45
- "step": 100
46
- },
47
- {
48
- "epoch": 0.5203252032520326,
49
- "grad_norm": 0.4751192629337311,
50
- "learning_rate": 0.00017083333333333333,
51
- "loss": 0.3567,
52
- "step": 120
53
- },
54
- {
55
- "epoch": 0.6070460704607046,
56
- "grad_norm": 0.3694995641708374,
57
- "learning_rate": 0.00016488095238095237,
58
- "loss": 0.3513,
59
- "step": 140
60
- },
61
- {
62
- "epoch": 0.6937669376693767,
63
- "grad_norm": 0.37785276770591736,
64
- "learning_rate": 0.00015892857142857142,
65
- "loss": 0.343,
66
- "step": 160
67
- },
68
- {
69
- "epoch": 0.7804878048780488,
70
- "grad_norm": 0.4374072253704071,
71
- "learning_rate": 0.00015297619047619046,
72
- "loss": 0.3419,
73
- "step": 180
74
- },
75
- {
76
- "epoch": 0.8672086720867209,
77
- "grad_norm": 0.42704370617866516,
78
- "learning_rate": 0.00014702380952380954,
79
- "loss": 0.3345,
80
- "step": 200
81
- },
82
- {
83
- "epoch": 0.9539295392953929,
84
- "grad_norm": 0.34092533588409424,
85
- "learning_rate": 0.00014107142857142858,
86
- "loss": 0.3338,
87
- "step": 220
88
- },
89
- {
90
- "epoch": 1.0390243902439025,
91
- "grad_norm": 0.42526426911354065,
92
- "learning_rate": 0.00013511904761904763,
93
- "loss": 0.3142,
94
- "step": 240
95
- },
96
- {
97
- "epoch": 1.1257452574525746,
98
- "grad_norm": 0.4306485056877136,
99
- "learning_rate": 0.00012916666666666667,
100
- "loss": 0.2872,
101
- "step": 260
102
- },
103
- {
104
- "epoch": 1.2124661246612467,
105
- "grad_norm": 0.390045166015625,
106
- "learning_rate": 0.00012321428571428572,
107
- "loss": 0.2879,
108
- "step": 280
109
- },
110
- {
111
- "epoch": 1.2991869918699188,
112
- "grad_norm": 0.3873736560344696,
113
- "learning_rate": 0.00011726190476190477,
114
- "loss": 0.2892,
115
- "step": 300
116
- },
117
- {
118
- "epoch": 1.3859078590785907,
119
- "grad_norm": 0.4038220942020416,
120
- "learning_rate": 0.00011130952380952382,
121
- "loss": 0.2879,
122
- "step": 320
123
- },
124
- {
125
- "epoch": 1.4726287262872628,
126
- "grad_norm": 0.4098362624645233,
127
- "learning_rate": 0.00010535714285714286,
128
- "loss": 0.2841,
129
- "step": 340
130
- },
131
- {
132
- "epoch": 1.559349593495935,
133
- "grad_norm": 0.388538122177124,
134
- "learning_rate": 9.940476190476191e-05,
135
- "loss": 0.2878,
136
- "step": 360
137
- },
138
- {
139
- "epoch": 1.646070460704607,
140
- "grad_norm": 0.4032808542251587,
141
- "learning_rate": 9.345238095238095e-05,
142
- "loss": 0.2831,
143
- "step": 380
144
- },
145
- {
146
- "epoch": 1.7327913279132792,
147
- "grad_norm": 0.38314706087112427,
148
- "learning_rate": 8.75e-05,
149
- "loss": 0.2821,
150
- "step": 400
151
- },
152
- {
153
- "epoch": 1.819512195121951,
154
- "grad_norm": 0.37887388467788696,
155
- "learning_rate": 8.154761904761904e-05,
156
- "loss": 0.2803,
157
- "step": 420
158
- },
159
- {
160
- "epoch": 1.9062330623306232,
161
- "grad_norm": 0.4070832133293152,
162
- "learning_rate": 7.55952380952381e-05,
163
- "loss": 0.2789,
164
- "step": 440
165
- },
166
- {
167
- "epoch": 1.9929539295392953,
168
- "grad_norm": 0.4019191265106201,
169
- "learning_rate": 6.964285714285715e-05,
170
- "loss": 0.2803,
171
- "step": 460
172
- }
173
- ],
174
- "logging_steps": 20,
175
- "max_steps": 693,
176
- "num_input_tokens_seen": 0,
177
- "num_train_epochs": 3,
178
- "save_steps": 500,
179
- "stateful_callbacks": {
180
- "TrainerControl": {
181
- "args": {
182
- "should_epoch_stop": false,
183
- "should_evaluate": false,
184
- "should_log": false,
185
- "should_save": true,
186
- "should_training_stop": false
187
- },
188
- "attributes": {}
189
- }
190
- },
191
- "total_flos": 4.750544979634176e+16,
192
- "train_batch_size": 4,
193
- "trial_name": null,
194
- "trial_params": null
195
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-462/training_args.bin DELETED
Binary file (6.23 kB)
 
checkpoint-462/vocab.json DELETED
The diff for this file is too large to render. See raw diff
 
checkpoint-693/README.md DELETED
@@ -1,210 +0,0 @@
1
- ---
2
- base_model: unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit
3
- library_name: peft
4
- pipeline_tag: text-generation
5
- tags:
6
- - base_model:adapter:unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit
7
- - lora
8
- - sft
9
- - transformers
10
- - trl
11
- - unsloth
12
- ---
13
-
14
- # Model Card for Model ID
15
-
16
- <!-- Provide a quick summary of what the model is/does. -->
17
-
18
-
19
-
20
- ## Model Details
21
-
22
- ### Model Description
23
-
24
- <!-- Provide a longer summary of what this model is. -->
25
-
26
-
27
-
28
- - **Developed by:** [More Information Needed]
29
- - **Funded by [optional]:** [More Information Needed]
30
- - **Shared by [optional]:** [More Information Needed]
31
- - **Model type:** [More Information Needed]
32
- - **Language(s) (NLP):** [More Information Needed]
33
- - **License:** [More Information Needed]
34
- - **Finetuned from model [optional]:** [More Information Needed]
35
-
36
- ### Model Sources [optional]
37
-
38
- <!-- Provide the basic links for the model. -->
39
-
40
- - **Repository:** [More Information Needed]
41
- - **Paper [optional]:** [More Information Needed]
42
- - **Demo [optional]:** [More Information Needed]
43
-
44
- ## Uses
45
-
46
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
47
-
48
- ### Direct Use
49
-
50
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
51
-
52
- [More Information Needed]
53
-
54
- ### Downstream Use [optional]
55
-
56
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
57
-
58
- [More Information Needed]
59
-
60
- ### Out-of-Scope Use
61
-
62
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
63
-
64
- [More Information Needed]
65
-
66
- ## Bias, Risks, and Limitations
67
-
68
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
69
-
70
- [More Information Needed]
71
-
72
- ### Recommendations
73
-
74
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
75
-
76
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
77
-
78
- ## How to Get Started with the Model
79
-
80
- Use the code below to get started with the model.
81
-
82
- [More Information Needed]
83
-
84
- ## Training Details
85
-
86
- ### Training Data
87
-
88
- <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
89
-
90
- [More Information Needed]
91
-
92
- ### Training Procedure
93
-
94
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
95
-
96
- #### Preprocessing [optional]
97
-
98
- [More Information Needed]
99
-
100
-
101
- #### Training Hyperparameters
102
-
103
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
104
-
105
- #### Speeds, Sizes, Times [optional]
106
-
107
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
108
-
109
- [More Information Needed]
110
-
111
- ## Evaluation
112
-
113
- <!-- This section describes the evaluation protocols and provides the results. -->
114
-
115
- ### Testing Data, Factors & Metrics
116
-
117
- #### Testing Data
118
-
119
- <!-- This should link to a Dataset Card if possible. -->
120
-
121
- [More Information Needed]
122
-
123
- #### Factors
124
-
125
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
126
-
127
- [More Information Needed]
128
-
129
- #### Metrics
130
-
131
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
132
-
133
- [More Information Needed]
134
-
135
- ### Results
136
-
137
- [More Information Needed]
138
-
139
- #### Summary
140
-
141
-
142
-
143
- ## Model Examination [optional]
144
-
145
- <!-- Relevant interpretability work for the model goes here -->
146
-
147
- [More Information Needed]
148
-
149
- ## Environmental Impact
150
-
151
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
152
-
153
- Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
154
-
155
- - **Hardware Type:** [More Information Needed]
156
- - **Hours used:** [More Information Needed]
157
- - **Cloud Provider:** [More Information Needed]
158
- - **Compute Region:** [More Information Needed]
159
- - **Carbon Emitted:** [More Information Needed]
160
-
161
- ## Technical Specifications [optional]
162
-
163
- ### Model Architecture and Objective
164
-
165
- [More Information Needed]
166
-
167
- ### Compute Infrastructure
168
-
169
- [More Information Needed]
170
-
171
- #### Hardware
172
-
173
- [More Information Needed]
174
-
175
- #### Software
176
-
177
- [More Information Needed]
178
-
179
- ## Citation [optional]
180
-
181
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
182
-
183
- **BibTeX:**
184
-
185
- [More Information Needed]
186
-
187
- **APA:**
188
-
189
- [More Information Needed]
190
-
191
- ## Glossary [optional]
192
-
193
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
194
-
195
- [More Information Needed]
196
-
197
- ## More Information [optional]
198
-
199
- [More Information Needed]
200
-
201
- ## Model Card Authors [optional]
202
-
203
- [More Information Needed]
204
-
205
- ## Model Card Contact
206
-
207
- [More Information Needed]
208
- ### Framework versions
209
-
210
- - PEFT 0.18.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-693/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": "Qwen3ForCausalLM",
7
- "parent_library": "transformers.models.qwen3.modeling_qwen3",
8
- "unsloth_fixed": true
9
- },
10
- "base_model_name_or_path": "unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit",
11
- "bias": "none",
12
- "corda_config": null,
13
- "ensure_weight_tying": false,
14
- "eva_config": null,
15
- "exclude_modules": null,
16
- "fan_in_fan_out": false,
17
- "inference_mode": true,
18
- "init_lora_weights": true,
19
- "layer_replication": null,
20
- "layers_pattern": null,
21
- "layers_to_transform": null,
22
- "loftq_config": {},
23
- "lora_alpha": 32,
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": "0.18.0",
31
- "qalora_group_size": 16,
32
- "r": 16,
33
- "rank_pattern": {},
34
- "revision": null,
35
- "target_modules": [
36
- "gate_proj",
37
- "down_proj",
38
- "up_proj",
39
- "v_proj",
40
- "q_proj",
41
- "o_proj",
42
- "k_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": true
50
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-693/adapter_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2bbdd3286c25eee36ce6109cfa49b93edf63ae3fb4c531204f430c8efa346ab
3
- size 132187888
 
 
 
 
checkpoint-693/added_tokens.json DELETED
@@ -1,28 +0,0 @@
1
- {
2
- "</think>": 151668,
3
- "</tool_call>": 151658,
4
- "</tool_response>": 151666,
5
- "<think>": 151667,
6
- "<tool_call>": 151657,
7
- "<tool_response>": 151665,
8
- "<|box_end|>": 151649,
9
- "<|box_start|>": 151648,
10
- "<|endoftext|>": 151643,
11
- "<|file_sep|>": 151664,
12
- "<|fim_middle|>": 151660,
13
- "<|fim_pad|>": 151662,
14
- "<|fim_prefix|>": 151659,
15
- "<|fim_suffix|>": 151661,
16
- "<|im_end|>": 151645,
17
- "<|im_start|>": 151644,
18
- "<|image_pad|>": 151655,
19
- "<|object_ref_end|>": 151647,
20
- "<|object_ref_start|>": 151646,
21
- "<|quad_end|>": 151651,
22
- "<|quad_start|>": 151650,
23
- "<|repo_name|>": 151663,
24
- "<|video_pad|>": 151656,
25
- "<|vision_end|>": 151653,
26
- "<|vision_pad|>": 151654,
27
- "<|vision_start|>": 151652
28
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-693/chat_template.jinja DELETED
@@ -1,86 +0,0 @@
1
- {%- if tools %}
2
- {{- '<|im_start|>system\n' }}
3
- {%- if messages[0].role == 'system' %}
4
- {{- messages[0].content + '\n\n' }}
5
- {%- endif %}
6
- {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
- {%- for tool in tools %}
8
- {{- "\n" }}
9
- {{- tool | tojson }}
10
- {%- endfor %}
11
- {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
- {%- else %}
13
- {%- if messages[0].role == 'system' %}
14
- {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
- {%- endif %}
16
- {%- endif %}
17
- {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
- {%- for message in messages[::-1] %}
19
- {%- set index = (messages|length - 1) - loop.index0 %}
20
- {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
- {%- set ns.multi_step_tool = false %}
22
- {%- set ns.last_query_index = index %}
23
- {%- endif %}
24
- {%- endfor %}
25
- {%- for message in messages %}
26
- {%- if message.content is string %}
27
- {%- set content = message.content %}
28
- {%- else %}
29
- {%- set content = '' %}
30
- {%- endif %}
31
- {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
32
- {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
33
- {%- elif message.role == "assistant" %}
34
- {%- set reasoning_content = '' %}
35
- {%- if message.reasoning_content is string %}
36
- {%- set reasoning_content = message.reasoning_content %}
37
- {%- else %}
38
- {%- if '</think>' in content %}
39
- {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
40
- {%- set content = content.split('</think>')[-1].lstrip('\n') %}
41
- {%- endif %}
42
- {%- endif %}
43
- {%- if loop.index0 > ns.last_query_index %}
44
- {%- if loop.last or (not loop.last and reasoning_content) %}
45
- {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
46
- {%- else %}
47
- {{- '<|im_start|>' + message.role + '\n' + content }}
48
- {%- endif %}
49
- {%- else %}
50
- {{- '<|im_start|>' + message.role + '\n' + content }}
51
- {%- endif %}
52
- {%- if message.tool_calls %}
53
- {%- for tool_call in message.tool_calls %}
54
- {%- if (loop.first and content) or (not loop.first) %}
55
- {{- '\n' }}
56
- {%- endif %}
57
- {%- if tool_call.function %}
58
- {%- set tool_call = tool_call.function %}
59
- {%- endif %}
60
- {{- '<tool_call>\n{"name": "' }}
61
- {{- tool_call.name }}
62
- {{- '", "arguments": ' }}
63
- {%- if tool_call.arguments is string %}
64
- {{- tool_call.arguments }}
65
- {%- else %}
66
- {{- tool_call.arguments | tojson }}
67
- {%- endif %}
68
- {{- '}\n</tool_call>' }}
69
- {%- endfor %}
70
- {%- endif %}
71
- {{- '<|im_end|>\n' }}
72
- {%- elif message.role == "tool" %}
73
- {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
74
- {{- '<|im_start|>user' }}
75
- {%- endif %}
76
- {{- '\n<tool_response>\n' }}
77
- {{- content }}
78
- {{- '\n</tool_response>' }}
79
- {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
80
- {{- '<|im_end|>\n' }}
81
- {%- endif %}
82
- {%- endif %}
83
- {%- endfor %}
84
- {%- if add_generation_prompt %}
85
- {{- '<|im_start|>assistant\n' }}
86
- {%- endif %}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-693/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
checkpoint-693/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a69708c7b9208dbe50501b0a26dcee678abaa95178e77cbe23c30ec13d4be4fd
3
- size 264673227
 
 
 
 
checkpoint-693/rng_state.pth DELETED
Binary file (14.6 kB)
 
checkpoint-693/scaler.pt DELETED
Binary file (1.38 kB)
 
checkpoint-693/scheduler.pt DELETED
Binary file (1.47 kB)
 
checkpoint-693/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": "<|im_end|>"
25
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-693/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
- size 11422654
 
 
 
 
checkpoint-693/tokenizer_config.json DELETED
@@ -1,240 +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": "<tool_response>",
183
- "lstrip": false,
184
- "normalized": false,
185
- "rstrip": false,
186
- "single_word": false,
187
- "special": false
188
- },
189
- "151666": {
190
- "content": "</tool_response>",
191
- "lstrip": false,
192
- "normalized": false,
193
- "rstrip": false,
194
- "single_word": false,
195
- "special": false
196
- },
197
- "151667": {
198
- "content": "<think>",
199
- "lstrip": false,
200
- "normalized": false,
201
- "rstrip": false,
202
- "single_word": false,
203
- "special": false
204
- },
205
- "151668": {
206
- "content": "</think>",
207
- "lstrip": false,
208
- "normalized": false,
209
- "rstrip": false,
210
- "single_word": false,
211
- "special": false
212
- }
213
- },
214
- "additional_special_tokens": [
215
- "<|im_start|>",
216
- "<|im_end|>",
217
- "<|object_ref_start|>",
218
- "<|object_ref_end|>",
219
- "<|box_start|>",
220
- "<|box_end|>",
221
- "<|quad_start|>",
222
- "<|quad_end|>",
223
- "<|vision_start|>",
224
- "<|vision_end|>",
225
- "<|vision_pad|>",
226
- "<|image_pad|>",
227
- "<|video_pad|>"
228
- ],
229
- "bos_token": null,
230
- "clean_up_tokenization_spaces": false,
231
- "eos_token": "<|im_end|>",
232
- "errors": "replace",
233
- "extra_special_tokens": {},
234
- "model_max_length": 262144,
235
- "pad_token": "<|im_end|>",
236
- "padding_side": "right",
237
- "split_special_tokens": false,
238
- "tokenizer_class": "Qwen2Tokenizer",
239
- "unk_token": null
240
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-693/trainer_state.json DELETED
@@ -1,272 +0,0 @@
1
- {
2
- "best_global_step": null,
3
- "best_metric": null,
4
- "best_model_checkpoint": null,
5
- "epoch": 3.0,
6
- "eval_steps": 500,
7
- "global_step": 693,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "epoch": 0.08672086720867209,
14
- "grad_norm": 0.5473586916923523,
15
- "learning_rate": 0.00018095238095238095,
16
- "loss": 1.6195,
17
- "step": 20
18
- },
19
- {
20
- "epoch": 0.17344173441734417,
21
- "grad_norm": 0.475732684135437,
22
- "learning_rate": 0.00019464285714285715,
23
- "loss": 0.4109,
24
- "step": 40
25
- },
26
- {
27
- "epoch": 0.2601626016260163,
28
- "grad_norm": 0.3879268765449524,
29
- "learning_rate": 0.0001886904761904762,
30
- "loss": 0.3829,
31
- "step": 60
32
- },
33
- {
34
- "epoch": 0.34688346883468835,
35
- "grad_norm": 0.37163427472114563,
36
- "learning_rate": 0.00018273809523809524,
37
- "loss": 0.3734,
38
- "step": 80
39
- },
40
- {
41
- "epoch": 0.43360433604336046,
42
- "grad_norm": 0.4267672002315521,
43
- "learning_rate": 0.00017678571428571428,
44
- "loss": 0.3645,
45
- "step": 100
46
- },
47
- {
48
- "epoch": 0.5203252032520326,
49
- "grad_norm": 0.4751192629337311,
50
- "learning_rate": 0.00017083333333333333,
51
- "loss": 0.3567,
52
- "step": 120
53
- },
54
- {
55
- "epoch": 0.6070460704607046,
56
- "grad_norm": 0.3694995641708374,
57
- "learning_rate": 0.00016488095238095237,
58
- "loss": 0.3513,
59
- "step": 140
60
- },
61
- {
62
- "epoch": 0.6937669376693767,
63
- "grad_norm": 0.37785276770591736,
64
- "learning_rate": 0.00015892857142857142,
65
- "loss": 0.343,
66
- "step": 160
67
- },
68
- {
69
- "epoch": 0.7804878048780488,
70
- "grad_norm": 0.4374072253704071,
71
- "learning_rate": 0.00015297619047619046,
72
- "loss": 0.3419,
73
- "step": 180
74
- },
75
- {
76
- "epoch": 0.8672086720867209,
77
- "grad_norm": 0.42704370617866516,
78
- "learning_rate": 0.00014702380952380954,
79
- "loss": 0.3345,
80
- "step": 200
81
- },
82
- {
83
- "epoch": 0.9539295392953929,
84
- "grad_norm": 0.34092533588409424,
85
- "learning_rate": 0.00014107142857142858,
86
- "loss": 0.3338,
87
- "step": 220
88
- },
89
- {
90
- "epoch": 1.0390243902439025,
91
- "grad_norm": 0.42526426911354065,
92
- "learning_rate": 0.00013511904761904763,
93
- "loss": 0.3142,
94
- "step": 240
95
- },
96
- {
97
- "epoch": 1.1257452574525746,
98
- "grad_norm": 0.4306485056877136,
99
- "learning_rate": 0.00012916666666666667,
100
- "loss": 0.2872,
101
- "step": 260
102
- },
103
- {
104
- "epoch": 1.2124661246612467,
105
- "grad_norm": 0.390045166015625,
106
- "learning_rate": 0.00012321428571428572,
107
- "loss": 0.2879,
108
- "step": 280
109
- },
110
- {
111
- "epoch": 1.2991869918699188,
112
- "grad_norm": 0.3873736560344696,
113
- "learning_rate": 0.00011726190476190477,
114
- "loss": 0.2892,
115
- "step": 300
116
- },
117
- {
118
- "epoch": 1.3859078590785907,
119
- "grad_norm": 0.4038220942020416,
120
- "learning_rate": 0.00011130952380952382,
121
- "loss": 0.2879,
122
- "step": 320
123
- },
124
- {
125
- "epoch": 1.4726287262872628,
126
- "grad_norm": 0.4098362624645233,
127
- "learning_rate": 0.00010535714285714286,
128
- "loss": 0.2841,
129
- "step": 340
130
- },
131
- {
132
- "epoch": 1.559349593495935,
133
- "grad_norm": 0.388538122177124,
134
- "learning_rate": 9.940476190476191e-05,
135
- "loss": 0.2878,
136
- "step": 360
137
- },
138
- {
139
- "epoch": 1.646070460704607,
140
- "grad_norm": 0.4032808542251587,
141
- "learning_rate": 9.345238095238095e-05,
142
- "loss": 0.2831,
143
- "step": 380
144
- },
145
- {
146
- "epoch": 1.7327913279132792,
147
- "grad_norm": 0.38314706087112427,
148
- "learning_rate": 8.75e-05,
149
- "loss": 0.2821,
150
- "step": 400
151
- },
152
- {
153
- "epoch": 1.819512195121951,
154
- "grad_norm": 0.37887388467788696,
155
- "learning_rate": 8.154761904761904e-05,
156
- "loss": 0.2803,
157
- "step": 420
158
- },
159
- {
160
- "epoch": 1.9062330623306232,
161
- "grad_norm": 0.4070832133293152,
162
- "learning_rate": 7.55952380952381e-05,
163
- "loss": 0.2789,
164
- "step": 440
165
- },
166
- {
167
- "epoch": 1.9929539295392953,
168
- "grad_norm": 0.4019191265106201,
169
- "learning_rate": 6.964285714285715e-05,
170
- "loss": 0.2803,
171
- "step": 460
172
- },
173
- {
174
- "epoch": 2.078048780487805,
175
- "grad_norm": 0.529030442237854,
176
- "learning_rate": 6.369047619047619e-05,
177
- "loss": 0.2263,
178
- "step": 480
179
- },
180
- {
181
- "epoch": 2.164769647696477,
182
- "grad_norm": 0.5251573920249939,
183
- "learning_rate": 5.773809523809524e-05,
184
- "loss": 0.2159,
185
- "step": 500
186
- },
187
- {
188
- "epoch": 2.251490514905149,
189
- "grad_norm": 0.5224559903144836,
190
- "learning_rate": 5.1785714285714296e-05,
191
- "loss": 0.2148,
192
- "step": 520
193
- },
194
- {
195
- "epoch": 2.3382113821138213,
196
- "grad_norm": 0.524760365486145,
197
- "learning_rate": 4.5833333333333334e-05,
198
- "loss": 0.2204,
199
- "step": 540
200
- },
201
- {
202
- "epoch": 2.4249322493224934,
203
- "grad_norm": 0.536670446395874,
204
- "learning_rate": 3.9880952380952386e-05,
205
- "loss": 0.2161,
206
- "step": 560
207
- },
208
- {
209
- "epoch": 2.511653116531165,
210
- "grad_norm": 0.5357058048248291,
211
- "learning_rate": 3.392857142857143e-05,
212
- "loss": 0.2166,
213
- "step": 580
214
- },
215
- {
216
- "epoch": 2.5983739837398376,
217
- "grad_norm": 0.4932177662849426,
218
- "learning_rate": 2.797619047619048e-05,
219
- "loss": 0.2171,
220
- "step": 600
221
- },
222
- {
223
- "epoch": 2.6850948509485093,
224
- "grad_norm": 0.5447421073913574,
225
- "learning_rate": 2.2023809523809524e-05,
226
- "loss": 0.2152,
227
- "step": 620
228
- },
229
- {
230
- "epoch": 2.7718157181571814,
231
- "grad_norm": 0.5578698515892029,
232
- "learning_rate": 1.6071428571428572e-05,
233
- "loss": 0.212,
234
- "step": 640
235
- },
236
- {
237
- "epoch": 2.8585365853658535,
238
- "grad_norm": 0.5826957821846008,
239
- "learning_rate": 1.011904761904762e-05,
240
- "loss": 0.2142,
241
- "step": 660
242
- },
243
- {
244
- "epoch": 2.9452574525745256,
245
- "grad_norm": 0.551535964012146,
246
- "learning_rate": 4.166666666666667e-06,
247
- "loss": 0.2104,
248
- "step": 680
249
- }
250
- ],
251
- "logging_steps": 20,
252
- "max_steps": 693,
253
- "num_input_tokens_seen": 0,
254
- "num_train_epochs": 3,
255
- "save_steps": 500,
256
- "stateful_callbacks": {
257
- "TrainerControl": {
258
- "args": {
259
- "should_epoch_stop": false,
260
- "should_evaluate": false,
261
- "should_log": false,
262
- "should_save": true,
263
- "should_training_stop": true
264
- },
265
- "attributes": {}
266
- }
267
- },
268
- "total_flos": 7.125494080439808e+16,
269
- "train_batch_size": 4,
270
- "trial_name": null,
271
- "trial_params": null
272
- }