yuyuchily commited on
Commit
fd8d96d
·
verified ·
1 Parent(s): 28ff9fc

Upload E-8_baseline_seq_e8

Browse files
.gitattributes CHANGED
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-444/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/Qwen3-4B-Instruct-2507
3
+ datasets:
4
+ - u-10bei/structured_data_with_cot_dataset_512_v2
5
+ language:
6
+ - en
7
+ license: apache-2.0
8
+ library_name: peft
9
+ pipeline_tag: text-generation
10
+ tags:
11
+ - qlora
12
+ - lora
13
+ - structured-output
14
+ ---
15
+
16
+ <【課題】ここは自分で記入して下さい>
17
+
18
+ This repository provides a **LoRA adapter** fine-tuned from
19
+ **unsloth/Qwen3-4B-Instruct-2507** using **QLoRA (4-bit, Unsloth)**.
20
+
21
+ This repository contains **LoRA adapter weights only**.
22
+ The base model must be loaded separately.
23
+
24
+ ## Training Objective
25
+
26
+ This adapter is trained to improve **structured output accuracy**
27
+ (JSON / YAML / XML / TOML / CSV).
28
+
29
+ Loss is applied only to the final assistant output,
30
+ while intermediate reasoning (Chain-of-Thought) is masked.
31
+
32
+ ## Training Configuration
33
+
34
+ - Base model: unsloth/Qwen3-4B-Instruct-2507
35
+ - Method: QLoRA (4-bit)
36
+ - Max sequence length: 512
37
+ - Epochs: 2
38
+ - Learning rate: 2e-06
39
+ - LoRA: r=64, alpha=128
40
+ - NEFTune: 5.0
41
+ - Data Cleaning: enabled
42
+
43
+ ## Usage
44
+
45
+ ```python
46
+ from transformers import AutoModelForCausalLM, AutoTokenizer
47
+ from peft import PeftModel
48
+ import torch
49
+
50
+ base = "unsloth/Qwen3-4B-Instruct-2507"
51
+ adapter = "your_id/your-repo"
52
+
53
+ tokenizer = AutoTokenizer.from_pretrained(base)
54
+ model = AutoModelForCausalLM.from_pretrained(
55
+ base,
56
+ torch_dtype=torch.float16,
57
+ device_map="auto",
58
+ )
59
+ model = PeftModel.from_pretrained(model, adapter)
60
+ ```
61
+
62
+ ## Sources & Terms (IMPORTANT)
63
+
64
+ Training data: u-10bei/structured_data_with_cot_dataset_512_v2
65
+
66
+ Dataset License: MIT License. This dataset is used and distributed under the terms of the MIT License.
67
+ Compliance: Users must comply with the MIT license (including copyright notice) and the base model's original terms of use.
adapter_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "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": 128,
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": 64,
33
+ "rank_pattern": {},
34
+ "revision": null,
35
+ "target_modules": [
36
+ "up_proj",
37
+ "down_proj",
38
+ "v_proj",
39
+ "o_proj",
40
+ "k_proj",
41
+ "q_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
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27d1bb265cdf5845d7f9cdb0bca0e4a4ba44c68725fa30f9c197b818aaed535b
3
+ size 528550256
added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "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": 128,
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": 64,
33
+ "rank_pattern": {},
34
+ "revision": null,
35
+ "target_modules": [
36
+ "up_proj",
37
+ "down_proj",
38
+ "v_proj",
39
+ "o_proj",
40
+ "k_proj",
41
+ "q_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
+ }
checkpoint-400/added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
checkpoint-400/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|vision_pad|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
checkpoint-400/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
checkpoint-400/tokenizer_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 262144,
235
+ "pad_token": "<|vision_pad|>",
236
+ "padding_side": "right",
237
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2Tokenizer",
239
+ "unk_token": null
240
+ }
checkpoint-400/trainer_state.json ADDED
@@ -0,0 +1,378 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.8027057497181511,
6
+ "eval_steps": 50,
7
+ "global_step": 400,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.04509582863585118,
14
+ "grad_norm": 4.880373001098633,
15
+ "learning_rate": 4e-07,
16
+ "loss": 1.7893,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.09019165727170236,
21
+ "grad_norm": 4.680130958557129,
22
+ "learning_rate": 8.444444444444444e-07,
23
+ "loss": 1.7309,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.13528748590755355,
28
+ "grad_norm": 4.52065372467041,
29
+ "learning_rate": 1.2888888888888889e-06,
30
+ "loss": 1.7019,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.18038331454340473,
35
+ "grad_norm": 4.010641574859619,
36
+ "learning_rate": 1.7333333333333334e-06,
37
+ "loss": 1.5762,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.2254791431792559,
42
+ "grad_norm": 2.6717236042022705,
43
+ "learning_rate": 1.9995040840893383e-06,
44
+ "loss": 1.6333,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.2254791431792559,
49
+ "eval_loss": 1.5759482383728027,
50
+ "eval_runtime": 14.6699,
51
+ "eval_samples_per_second": 12.747,
52
+ "eval_steps_per_second": 6.408,
53
+ "step": 50
54
+ },
55
+ {
56
+ "epoch": 0.2705749718151071,
57
+ "grad_norm": 1.3333920240402222,
58
+ "learning_rate": 1.9939306773179494e-06,
59
+ "loss": 1.2989,
60
+ "step": 60
61
+ },
62
+ {
63
+ "epoch": 0.3156708004509583,
64
+ "grad_norm": 0.6459554433822632,
65
+ "learning_rate": 1.9821986184473754e-06,
66
+ "loss": 1.2498,
67
+ "step": 70
68
+ },
69
+ {
70
+ "epoch": 0.36076662908680945,
71
+ "grad_norm": 0.6363914608955383,
72
+ "learning_rate": 1.964380602355277e-06,
73
+ "loss": 1.157,
74
+ "step": 80
75
+ },
76
+ {
77
+ "epoch": 0.40586245772266066,
78
+ "grad_norm": 0.4646184742450714,
79
+ "learning_rate": 1.9405870340877135e-06,
80
+ "loss": 1.1613,
81
+ "step": 90
82
+ },
83
+ {
84
+ "epoch": 0.4509582863585118,
85
+ "grad_norm": 0.5635167956352234,
86
+ "learning_rate": 1.9109653447608605e-06,
87
+ "loss": 1.3009,
88
+ "step": 100
89
+ },
90
+ {
91
+ "epoch": 0.4509582863585118,
92
+ "eval_loss": 1.3309173583984375,
93
+ "eval_runtime": 14.1549,
94
+ "eval_samples_per_second": 13.211,
95
+ "eval_steps_per_second": 6.641,
96
+ "step": 100
97
+ },
98
+ {
99
+ "epoch": 0.496054114994363,
100
+ "grad_norm": 0.5266286134719849,
101
+ "learning_rate": 1.8756990780396006e-06,
102
+ "loss": 1.1237,
103
+ "step": 110
104
+ },
105
+ {
106
+ "epoch": 0.5411499436302142,
107
+ "grad_norm": 0.5904309153556824,
108
+ "learning_rate": 1.8350067528534024e-06,
109
+ "loss": 1.2938,
110
+ "step": 120
111
+ },
112
+ {
113
+ "epoch": 0.5862457722660653,
114
+ "grad_norm": 0.4533354938030243,
115
+ "learning_rate": 1.7891405093963937e-06,
116
+ "loss": 1.3771,
117
+ "step": 130
118
+ },
119
+ {
120
+ "epoch": 0.6313416009019166,
121
+ "grad_norm": 0.6127325892448425,
122
+ "learning_rate": 1.7383845468013654e-06,
123
+ "loss": 1.417,
124
+ "step": 140
125
+ },
126
+ {
127
+ "epoch": 0.6764374295377678,
128
+ "grad_norm": 0.5645148754119873,
129
+ "learning_rate": 1.683053362168282e-06,
130
+ "loss": 1.1581,
131
+ "step": 150
132
+ },
133
+ {
134
+ "epoch": 0.6764374295377678,
135
+ "eval_loss": 1.2584223747253418,
136
+ "eval_runtime": 14.0101,
137
+ "eval_samples_per_second": 13.347,
138
+ "eval_steps_per_second": 6.709,
139
+ "step": 150
140
+ },
141
+ {
142
+ "epoch": 0.7215332581736189,
143
+ "grad_norm": 0.5589331984519958,
144
+ "learning_rate": 1.6234898018587336e-06,
145
+ "loss": 1.1287,
146
+ "step": 160
147
+ },
148
+ {
149
+ "epoch": 0.7666290868094702,
150
+ "grad_norm": 0.5021057724952698,
151
+ "learning_rate": 1.5600629371310144e-06,
152
+ "loss": 1.105,
153
+ "step": 170
154
+ },
155
+ {
156
+ "epoch": 0.8117249154453213,
157
+ "grad_norm": 0.4609015882015228,
158
+ "learning_rate": 1.4931657772789457e-06,
159
+ "loss": 1.1352,
160
+ "step": 180
161
+ },
162
+ {
163
+ "epoch": 0.8568207440811725,
164
+ "grad_norm": 0.46195802092552185,
165
+ "learning_rate": 1.423212834444425e-06,
166
+ "loss": 1.0855,
167
+ "step": 190
168
+ },
169
+ {
170
+ "epoch": 0.9019165727170236,
171
+ "grad_norm": 0.527087926864624,
172
+ "learning_rate": 1.3506375551927544e-06,
173
+ "loss": 1.0202,
174
+ "step": 200
175
+ },
176
+ {
177
+ "epoch": 0.9019165727170236,
178
+ "eval_loss": 1.2102832794189453,
179
+ "eval_runtime": 14.1065,
180
+ "eval_samples_per_second": 13.256,
181
+ "eval_steps_per_second": 6.664,
182
+ "step": 200
183
+ },
184
+ {
185
+ "epoch": 0.9470124013528749,
186
+ "grad_norm": 1.0008864402770996,
187
+ "learning_rate": 1.2758896347653752e-06,
188
+ "loss": 1.2173,
189
+ "step": 210
190
+ },
191
+ {
192
+ "epoch": 0.992108229988726,
193
+ "grad_norm": 0.5077604651451111,
194
+ "learning_rate": 1.1994322306515925e-06,
195
+ "loss": 1.0537,
196
+ "step": 220
197
+ },
198
+ {
199
+ "epoch": 1.0360766629086808,
200
+ "grad_norm": 0.711245596408844,
201
+ "learning_rate": 1.1217390927447225e-06,
202
+ "loss": 1.1367,
203
+ "step": 230
204
+ },
205
+ {
206
+ "epoch": 1.0811724915445322,
207
+ "grad_norm": 0.510122537612915,
208
+ "learning_rate": 1.043291627864961e-06,
209
+ "loss": 1.1316,
210
+ "step": 240
211
+ },
212
+ {
213
+ "epoch": 1.1262683201803834,
214
+ "grad_norm": 0.5964261293411255,
215
+ "learning_rate": 9.645759168379461e-07,
216
+ "loss": 1.2521,
217
+ "step": 250
218
+ },
219
+ {
220
+ "epoch": 1.1262683201803834,
221
+ "eval_loss": 1.1702840328216553,
222
+ "eval_runtime": 14.1699,
223
+ "eval_samples_per_second": 13.197,
224
+ "eval_steps_per_second": 6.634,
225
+ "step": 250
226
+ },
227
+ {
228
+ "epoch": 1.1713641488162345,
229
+ "grad_norm": 0.39409753680229187,
230
+ "learning_rate": 8.860797026119721e-07,
231
+ "loss": 0.915,
232
+ "step": 260
233
+ },
234
+ {
235
+ "epoch": 1.2164599774520857,
236
+ "grad_norm": 0.4673859179019928,
237
+ "learning_rate": 8.082893680762618e-07,
238
+ "loss": 1.2371,
239
+ "step": 270
240
+ },
241
+ {
242
+ "epoch": 1.2615558060879368,
243
+ "grad_norm": 0.5883477926254272,
244
+ "learning_rate": 7.316869223065155e-07,
245
+ "loss": 1.1097,
246
+ "step": 280
247
+ },
248
+ {
249
+ "epoch": 1.306651634723788,
250
+ "grad_norm": 0.5270853638648987,
251
+ "learning_rate": 6.567470139117447e-07,
252
+ "loss": 1.0892,
253
+ "step": 290
254
+ },
255
+ {
256
+ "epoch": 1.3517474633596391,
257
+ "grad_norm": 0.5741926431655884,
258
+ "learning_rate": 5.839339899884628e-07,
259
+ "loss": 0.9821,
260
+ "step": 300
261
+ },
262
+ {
263
+ "epoch": 1.3517474633596391,
264
+ "eval_loss": 1.1472760438919067,
265
+ "eval_runtime": 14.092,
266
+ "eval_samples_per_second": 13.27,
267
+ "eval_steps_per_second": 6.67,
268
+ "step": 300
269
+ },
270
+ {
271
+ "epoch": 1.3968432919954905,
272
+ "grad_norm": 0.426485151052475,
273
+ "learning_rate": 5.136990189057187e-07,
274
+ "loss": 1.1382,
275
+ "step": 310
276
+ },
277
+ {
278
+ "epoch": 1.4419391206313417,
279
+ "grad_norm": 0.45604461431503296,
280
+ "learning_rate": 4.4647729474894123e-07,
281
+ "loss": 1.0356,
282
+ "step": 320
283
+ },
284
+ {
285
+ "epoch": 1.4870349492671928,
286
+ "grad_norm": 0.3508279621601105,
287
+ "learning_rate": 3.826853407445848e-07,
288
+ "loss": 1.0695,
289
+ "step": 330
290
+ },
291
+ {
292
+ "epoch": 1.532130777903044,
293
+ "grad_norm": 0.4223732352256775,
294
+ "learning_rate": 3.227184283742591e-07,
295
+ "loss": 0.9751,
296
+ "step": 340
297
+ },
298
+ {
299
+ "epoch": 1.5772266065388951,
300
+ "grad_norm": 0.6314070224761963,
301
+ "learning_rate": 2.6694812817017387e-07,
302
+ "loss": 1.0793,
303
+ "step": 350
304
+ },
305
+ {
306
+ "epoch": 1.5772266065388951,
307
+ "eval_loss": 1.136489748954773,
308
+ "eval_runtime": 14.3065,
309
+ "eval_samples_per_second": 13.071,
310
+ "eval_steps_per_second": 6.57,
311
+ "step": 350
312
+ },
313
+ {
314
+ "epoch": 1.6223224351747465,
315
+ "grad_norm": 0.5215230584144592,
316
+ "learning_rate": 2.157200073678137e-07,
317
+ "loss": 0.973,
318
+ "step": 360
319
+ },
320
+ {
321
+ "epoch": 1.6674182638105974,
322
+ "grad_norm": 0.5581642985343933,
323
+ "learning_rate": 1.6935148868177718e-07,
324
+ "loss": 0.9685,
325
+ "step": 370
326
+ },
327
+ {
328
+ "epoch": 1.7125140924464488,
329
+ "grad_norm": 0.5601069331169128,
330
+ "learning_rate": 1.2812988347236166e-07,
331
+ "loss": 1.0191,
332
+ "step": 380
333
+ },
334
+ {
335
+ "epoch": 1.7576099210822997,
336
+ "grad_norm": 0.4990064203739166,
337
+ "learning_rate": 9.231061148990648e-08,
338
+ "loss": 0.9674,
339
+ "step": 390
340
+ },
341
+ {
342
+ "epoch": 1.8027057497181511,
343
+ "grad_norm": 0.6436290144920349,
344
+ "learning_rate": 6.211561822781474e-08,
345
+ "loss": 0.826,
346
+ "step": 400
347
+ },
348
+ {
349
+ "epoch": 1.8027057497181511,
350
+ "eval_loss": 1.1320565938949585,
351
+ "eval_runtime": 14.0805,
352
+ "eval_samples_per_second": 13.281,
353
+ "eval_steps_per_second": 6.676,
354
+ "step": 400
355
+ }
356
+ ],
357
+ "logging_steps": 10,
358
+ "max_steps": 444,
359
+ "num_input_tokens_seen": 0,
360
+ "num_train_epochs": 2,
361
+ "save_steps": 100,
362
+ "stateful_callbacks": {
363
+ "TrainerControl": {
364
+ "args": {
365
+ "should_epoch_stop": false,
366
+ "should_evaluate": false,
367
+ "should_log": false,
368
+ "should_save": true,
369
+ "should_training_stop": false
370
+ },
371
+ "attributes": {}
372
+ }
373
+ },
374
+ "total_flos": 6.339717225125376e+16,
375
+ "train_batch_size": 2,
376
+ "trial_name": null,
377
+ "trial_params": null
378
+ }
checkpoint-400/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-444/adapter_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "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": 128,
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": 64,
33
+ "rank_pattern": {},
34
+ "revision": null,
35
+ "target_modules": [
36
+ "up_proj",
37
+ "down_proj",
38
+ "v_proj",
39
+ "o_proj",
40
+ "k_proj",
41
+ "q_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
+ }
checkpoint-444/added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
checkpoint-444/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|vision_pad|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
checkpoint-444/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
checkpoint-444/tokenizer_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 262144,
235
+ "pad_token": "<|vision_pad|>",
236
+ "padding_side": "right",
237
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2Tokenizer",
239
+ "unk_token": null
240
+ }
checkpoint-444/trainer_state.json ADDED
@@ -0,0 +1,406 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.0,
6
+ "eval_steps": 50,
7
+ "global_step": 444,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.04509582863585118,
14
+ "grad_norm": 4.880373001098633,
15
+ "learning_rate": 4e-07,
16
+ "loss": 1.7893,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.09019165727170236,
21
+ "grad_norm": 4.680130958557129,
22
+ "learning_rate": 8.444444444444444e-07,
23
+ "loss": 1.7309,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.13528748590755355,
28
+ "grad_norm": 4.52065372467041,
29
+ "learning_rate": 1.2888888888888889e-06,
30
+ "loss": 1.7019,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.18038331454340473,
35
+ "grad_norm": 4.010641574859619,
36
+ "learning_rate": 1.7333333333333334e-06,
37
+ "loss": 1.5762,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.2254791431792559,
42
+ "grad_norm": 2.6717236042022705,
43
+ "learning_rate": 1.9995040840893383e-06,
44
+ "loss": 1.6333,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.2254791431792559,
49
+ "eval_loss": 1.5759482383728027,
50
+ "eval_runtime": 14.6699,
51
+ "eval_samples_per_second": 12.747,
52
+ "eval_steps_per_second": 6.408,
53
+ "step": 50
54
+ },
55
+ {
56
+ "epoch": 0.2705749718151071,
57
+ "grad_norm": 1.3333920240402222,
58
+ "learning_rate": 1.9939306773179494e-06,
59
+ "loss": 1.2989,
60
+ "step": 60
61
+ },
62
+ {
63
+ "epoch": 0.3156708004509583,
64
+ "grad_norm": 0.6459554433822632,
65
+ "learning_rate": 1.9821986184473754e-06,
66
+ "loss": 1.2498,
67
+ "step": 70
68
+ },
69
+ {
70
+ "epoch": 0.36076662908680945,
71
+ "grad_norm": 0.6363914608955383,
72
+ "learning_rate": 1.964380602355277e-06,
73
+ "loss": 1.157,
74
+ "step": 80
75
+ },
76
+ {
77
+ "epoch": 0.40586245772266066,
78
+ "grad_norm": 0.4646184742450714,
79
+ "learning_rate": 1.9405870340877135e-06,
80
+ "loss": 1.1613,
81
+ "step": 90
82
+ },
83
+ {
84
+ "epoch": 0.4509582863585118,
85
+ "grad_norm": 0.5635167956352234,
86
+ "learning_rate": 1.9109653447608605e-06,
87
+ "loss": 1.3009,
88
+ "step": 100
89
+ },
90
+ {
91
+ "epoch": 0.4509582863585118,
92
+ "eval_loss": 1.3309173583984375,
93
+ "eval_runtime": 14.1549,
94
+ "eval_samples_per_second": 13.211,
95
+ "eval_steps_per_second": 6.641,
96
+ "step": 100
97
+ },
98
+ {
99
+ "epoch": 0.496054114994363,
100
+ "grad_norm": 0.5266286134719849,
101
+ "learning_rate": 1.8756990780396006e-06,
102
+ "loss": 1.1237,
103
+ "step": 110
104
+ },
105
+ {
106
+ "epoch": 0.5411499436302142,
107
+ "grad_norm": 0.5904309153556824,
108
+ "learning_rate": 1.8350067528534024e-06,
109
+ "loss": 1.2938,
110
+ "step": 120
111
+ },
112
+ {
113
+ "epoch": 0.5862457722660653,
114
+ "grad_norm": 0.4533354938030243,
115
+ "learning_rate": 1.7891405093963937e-06,
116
+ "loss": 1.3771,
117
+ "step": 130
118
+ },
119
+ {
120
+ "epoch": 0.6313416009019166,
121
+ "grad_norm": 0.6127325892448425,
122
+ "learning_rate": 1.7383845468013654e-06,
123
+ "loss": 1.417,
124
+ "step": 140
125
+ },
126
+ {
127
+ "epoch": 0.6764374295377678,
128
+ "grad_norm": 0.5645148754119873,
129
+ "learning_rate": 1.683053362168282e-06,
130
+ "loss": 1.1581,
131
+ "step": 150
132
+ },
133
+ {
134
+ "epoch": 0.6764374295377678,
135
+ "eval_loss": 1.2584223747253418,
136
+ "eval_runtime": 14.0101,
137
+ "eval_samples_per_second": 13.347,
138
+ "eval_steps_per_second": 6.709,
139
+ "step": 150
140
+ },
141
+ {
142
+ "epoch": 0.7215332581736189,
143
+ "grad_norm": 0.5589331984519958,
144
+ "learning_rate": 1.6234898018587336e-06,
145
+ "loss": 1.1287,
146
+ "step": 160
147
+ },
148
+ {
149
+ "epoch": 0.7666290868094702,
150
+ "grad_norm": 0.5021057724952698,
151
+ "learning_rate": 1.5600629371310144e-06,
152
+ "loss": 1.105,
153
+ "step": 170
154
+ },
155
+ {
156
+ "epoch": 0.8117249154453213,
157
+ "grad_norm": 0.4609015882015228,
158
+ "learning_rate": 1.4931657772789457e-06,
159
+ "loss": 1.1352,
160
+ "step": 180
161
+ },
162
+ {
163
+ "epoch": 0.8568207440811725,
164
+ "grad_norm": 0.46195802092552185,
165
+ "learning_rate": 1.423212834444425e-06,
166
+ "loss": 1.0855,
167
+ "step": 190
168
+ },
169
+ {
170
+ "epoch": 0.9019165727170236,
171
+ "grad_norm": 0.527087926864624,
172
+ "learning_rate": 1.3506375551927544e-06,
173
+ "loss": 1.0202,
174
+ "step": 200
175
+ },
176
+ {
177
+ "epoch": 0.9019165727170236,
178
+ "eval_loss": 1.2102832794189453,
179
+ "eval_runtime": 14.1065,
180
+ "eval_samples_per_second": 13.256,
181
+ "eval_steps_per_second": 6.664,
182
+ "step": 200
183
+ },
184
+ {
185
+ "epoch": 0.9470124013528749,
186
+ "grad_norm": 1.0008864402770996,
187
+ "learning_rate": 1.2758896347653752e-06,
188
+ "loss": 1.2173,
189
+ "step": 210
190
+ },
191
+ {
192
+ "epoch": 0.992108229988726,
193
+ "grad_norm": 0.5077604651451111,
194
+ "learning_rate": 1.1994322306515925e-06,
195
+ "loss": 1.0537,
196
+ "step": 220
197
+ },
198
+ {
199
+ "epoch": 1.0360766629086808,
200
+ "grad_norm": 0.711245596408844,
201
+ "learning_rate": 1.1217390927447225e-06,
202
+ "loss": 1.1367,
203
+ "step": 230
204
+ },
205
+ {
206
+ "epoch": 1.0811724915445322,
207
+ "grad_norm": 0.510122537612915,
208
+ "learning_rate": 1.043291627864961e-06,
209
+ "loss": 1.1316,
210
+ "step": 240
211
+ },
212
+ {
213
+ "epoch": 1.1262683201803834,
214
+ "grad_norm": 0.5964261293411255,
215
+ "learning_rate": 9.645759168379461e-07,
216
+ "loss": 1.2521,
217
+ "step": 250
218
+ },
219
+ {
220
+ "epoch": 1.1262683201803834,
221
+ "eval_loss": 1.1702840328216553,
222
+ "eval_runtime": 14.1699,
223
+ "eval_samples_per_second": 13.197,
224
+ "eval_steps_per_second": 6.634,
225
+ "step": 250
226
+ },
227
+ {
228
+ "epoch": 1.1713641488162345,
229
+ "grad_norm": 0.39409753680229187,
230
+ "learning_rate": 8.860797026119721e-07,
231
+ "loss": 0.915,
232
+ "step": 260
233
+ },
234
+ {
235
+ "epoch": 1.2164599774520857,
236
+ "grad_norm": 0.4673859179019928,
237
+ "learning_rate": 8.082893680762618e-07,
238
+ "loss": 1.2371,
239
+ "step": 270
240
+ },
241
+ {
242
+ "epoch": 1.2615558060879368,
243
+ "grad_norm": 0.5883477926254272,
244
+ "learning_rate": 7.316869223065155e-07,
245
+ "loss": 1.1097,
246
+ "step": 280
247
+ },
248
+ {
249
+ "epoch": 1.306651634723788,
250
+ "grad_norm": 0.5270853638648987,
251
+ "learning_rate": 6.567470139117447e-07,
252
+ "loss": 1.0892,
253
+ "step": 290
254
+ },
255
+ {
256
+ "epoch": 1.3517474633596391,
257
+ "grad_norm": 0.5741926431655884,
258
+ "learning_rate": 5.839339899884628e-07,
259
+ "loss": 0.9821,
260
+ "step": 300
261
+ },
262
+ {
263
+ "epoch": 1.3517474633596391,
264
+ "eval_loss": 1.1472760438919067,
265
+ "eval_runtime": 14.092,
266
+ "eval_samples_per_second": 13.27,
267
+ "eval_steps_per_second": 6.67,
268
+ "step": 300
269
+ },
270
+ {
271
+ "epoch": 1.3968432919954905,
272
+ "grad_norm": 0.426485151052475,
273
+ "learning_rate": 5.136990189057187e-07,
274
+ "loss": 1.1382,
275
+ "step": 310
276
+ },
277
+ {
278
+ "epoch": 1.4419391206313417,
279
+ "grad_norm": 0.45604461431503296,
280
+ "learning_rate": 4.4647729474894123e-07,
281
+ "loss": 1.0356,
282
+ "step": 320
283
+ },
284
+ {
285
+ "epoch": 1.4870349492671928,
286
+ "grad_norm": 0.3508279621601105,
287
+ "learning_rate": 3.826853407445848e-07,
288
+ "loss": 1.0695,
289
+ "step": 330
290
+ },
291
+ {
292
+ "epoch": 1.532130777903044,
293
+ "grad_norm": 0.4223732352256775,
294
+ "learning_rate": 3.227184283742591e-07,
295
+ "loss": 0.9751,
296
+ "step": 340
297
+ },
298
+ {
299
+ "epoch": 1.5772266065388951,
300
+ "grad_norm": 0.6314070224761963,
301
+ "learning_rate": 2.6694812817017387e-07,
302
+ "loss": 1.0793,
303
+ "step": 350
304
+ },
305
+ {
306
+ "epoch": 1.5772266065388951,
307
+ "eval_loss": 1.136489748954773,
308
+ "eval_runtime": 14.3065,
309
+ "eval_samples_per_second": 13.071,
310
+ "eval_steps_per_second": 6.57,
311
+ "step": 350
312
+ },
313
+ {
314
+ "epoch": 1.6223224351747465,
315
+ "grad_norm": 0.5215230584144592,
316
+ "learning_rate": 2.157200073678137e-07,
317
+ "loss": 0.973,
318
+ "step": 360
319
+ },
320
+ {
321
+ "epoch": 1.6674182638105974,
322
+ "grad_norm": 0.5581642985343933,
323
+ "learning_rate": 1.6935148868177718e-07,
324
+ "loss": 0.9685,
325
+ "step": 370
326
+ },
327
+ {
328
+ "epoch": 1.7125140924464488,
329
+ "grad_norm": 0.5601069331169128,
330
+ "learning_rate": 1.2812988347236166e-07,
331
+ "loss": 1.0191,
332
+ "step": 380
333
+ },
334
+ {
335
+ "epoch": 1.7576099210822997,
336
+ "grad_norm": 0.4990064203739166,
337
+ "learning_rate": 9.231061148990648e-08,
338
+ "loss": 0.9674,
339
+ "step": 390
340
+ },
341
+ {
342
+ "epoch": 1.8027057497181511,
343
+ "grad_norm": 0.6436290144920349,
344
+ "learning_rate": 6.211561822781474e-08,
345
+ "loss": 0.826,
346
+ "step": 400
347
+ },
348
+ {
349
+ "epoch": 1.8027057497181511,
350
+ "eval_loss": 1.1320565938949585,
351
+ "eval_runtime": 14.0805,
352
+ "eval_samples_per_second": 13.281,
353
+ "eval_steps_per_second": 6.676,
354
+ "step": 400
355
+ },
356
+ {
357
+ "epoch": 1.8478015783540023,
358
+ "grad_norm": 0.4911165237426758,
359
+ "learning_rate": 3.7731999690749585e-08,
360
+ "loss": 0.9581,
361
+ "step": 410
362
+ },
363
+ {
364
+ "epoch": 1.8928974069898534,
365
+ "grad_norm": 0.46329793334007263,
366
+ "learning_rate": 1.9310843099295204e-08,
367
+ "loss": 1.0405,
368
+ "step": 420
369
+ },
370
+ {
371
+ "epoch": 1.9379932356257046,
372
+ "grad_norm": 0.634383499622345,
373
+ "learning_rate": 6.966290714375933e-09,
374
+ "loss": 1.076,
375
+ "step": 430
376
+ },
377
+ {
378
+ "epoch": 1.9830890642615557,
379
+ "grad_norm": 0.4782802164554596,
380
+ "learning_rate": 7.748325822234392e-10,
381
+ "loss": 1.1295,
382
+ "step": 440
383
+ }
384
+ ],
385
+ "logging_steps": 10,
386
+ "max_steps": 444,
387
+ "num_input_tokens_seen": 0,
388
+ "num_train_epochs": 2,
389
+ "save_steps": 100,
390
+ "stateful_callbacks": {
391
+ "TrainerControl": {
392
+ "args": {
393
+ "should_epoch_stop": false,
394
+ "should_evaluate": false,
395
+ "should_log": false,
396
+ "should_save": true,
397
+ "should_training_stop": true
398
+ },
399
+ "attributes": {}
400
+ }
401
+ },
402
+ "total_flos": 7.020122585580134e+16,
403
+ "train_batch_size": 2,
404
+ "trial_name": null,
405
+ "trial_params": null
406
+ }
checkpoint-444/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
sft_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "sft_experiment_id": "E-8",
3
+ "dataset_strategy_id": "baseline",
4
+ "base_model": "unsloth/Qwen3-4B-Instruct-2507",
5
+ "neftune_alpha": 5.0,
6
+ "data_cleaning": true,
7
+ "lora": {
8
+ "r": 64,
9
+ "alpha": 128,
10
+ "dropout": 0.0,
11
+ "target_modules": [
12
+ "q_proj",
13
+ "k_proj",
14
+ "v_proj",
15
+ "o_proj",
16
+ "gate_proj",
17
+ "up_proj",
18
+ "down_proj"
19
+ ]
20
+ },
21
+ "training": {
22
+ "max_seq_len": 512,
23
+ "epochs": 2,
24
+ "lr": 2e-06,
25
+ "per_device_train_bs": 2,
26
+ "grad_accum": 8,
27
+ "warmup_ratio": 0.1,
28
+ "weight_decay": 0.05
29
+ },
30
+ "special": {
31
+ "mask_cot": true,
32
+ "upsampling": false,
33
+ "curriculum": true
34
+ }
35
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|vision_pad|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
tokenizer_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 262144,
235
+ "pad_token": "<|vision_pad|>",
236
+ "padding_side": "right",
237
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2Tokenizer",
239
+ "unk_token": null
240
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff