here4code commited on
Commit
763d34f
·
verified ·
1 Parent(s): 2e91df9

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</box>": 151673,
3
+ "</img>": 151666,
4
+ "</quad>": 151669,
5
+ "</ref>": 151671,
6
+ "</tool_call>": 151658,
7
+ "<IMG_CONTEXT>": 151667,
8
+ "<box>": 151672,
9
+ "<img>": 151665,
10
+ "<quad>": 151668,
11
+ "<ref>": 151670,
12
+ "<tool_call>": 151657,
13
+ "<|box_end|>": 151649,
14
+ "<|box_start|>": 151648,
15
+ "<|endoftext|>": 151643,
16
+ "<|file_sep|>": 151664,
17
+ "<|fim_middle|>": 151660,
18
+ "<|fim_pad|>": 151662,
19
+ "<|fim_prefix|>": 151659,
20
+ "<|fim_suffix|>": 151661,
21
+ "<|im_end|>": 151645,
22
+ "<|im_start|>": 151644,
23
+ "<|image_pad|>": 151655,
24
+ "<|object_ref_end|>": 151647,
25
+ "<|object_ref_start|>": 151646,
26
+ "<|quad_end|>": 151651,
27
+ "<|quad_start|>": 151650,
28
+ "<|repo_name|>": 151663,
29
+ "<|video_pad|>": 151656,
30
+ "<|vision_end|>": 151653,
31
+ "<|vision_pad|>": 151654,
32
+ "<|vision_start|>": 151652
33
+ }
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9696969696969697,
3
+ "total_flos": 2.622912379643075e+19,
4
+ "train_loss": 0.0,
5
+ "train_runtime": 1207.2389,
6
+ "train_samples": 198,
7
+ "train_samples_per_second": 0.164,
8
+ "train_steps_per_second": 0.02
9
+ }
config.json ADDED
@@ -0,0 +1,225 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "24dc81a234a6e1901f3314eeadaa2813f2b78038",
3
+ "_name_or_path": "OpenGVLab/InternVL3-8B",
4
+ "architectures": [
5
+ "InternVLChatModel"
6
+ ],
7
+ "auto_map": {
8
+ "AutoConfig": "OpenGVLab/InternVL3-8B--configuration_internvl_chat.InternVLChatConfig",
9
+ "AutoModel": "OpenGVLab/InternVL3-8B--modeling_internvl_chat.InternVLChatModel",
10
+ "AutoModelForCausalLM": "OpenGVLab/InternVL3-8B--modeling_internvl_chat.InternVLChatModel"
11
+ },
12
+ "downsample_ratio": 0.5,
13
+ "dynamic_image_size": true,
14
+ "force_image_size": 448,
15
+ "hidden_size": 3584,
16
+ "image_fold": null,
17
+ "llm_config": {
18
+ "_attn_implementation_autoset": true,
19
+ "_name_or_path": "./pretrained/Qwen2.5-32B-Instruct",
20
+ "add_cross_attention": false,
21
+ "architectures": [
22
+ "Qwen2ForCausalLM"
23
+ ],
24
+ "attention_dropout": 0.0,
25
+ "attn_implementation": "flash_attention_2",
26
+ "bad_words_ids": null,
27
+ "begin_suppress_tokens": null,
28
+ "bos_token_id": 151643,
29
+ "chunk_size_feed_forward": 0,
30
+ "cross_attention_hidden_size": null,
31
+ "decoder_start_token_id": null,
32
+ "diversity_penalty": 0.0,
33
+ "do_sample": false,
34
+ "early_stopping": false,
35
+ "encoder_no_repeat_ngram_size": 0,
36
+ "eos_token_id": 151643,
37
+ "exponential_decay_length_penalty": null,
38
+ "finetuning_task": null,
39
+ "forced_bos_token_id": null,
40
+ "forced_eos_token_id": null,
41
+ "hidden_act": "silu",
42
+ "hidden_size": 3584,
43
+ "id2label": {
44
+ "0": "LABEL_0",
45
+ "1": "LABEL_1"
46
+ },
47
+ "initializer_range": 0.02,
48
+ "intermediate_size": 18944,
49
+ "is_decoder": false,
50
+ "is_encoder_decoder": false,
51
+ "label2id": {
52
+ "LABEL_0": 0,
53
+ "LABEL_1": 1
54
+ },
55
+ "length_penalty": 1.0,
56
+ "max_length": 20,
57
+ "max_position_embeddings": 32768,
58
+ "max_window_layers": 70,
59
+ "min_length": 0,
60
+ "model_type": "qwen2",
61
+ "moe_config": null,
62
+ "no_repeat_ngram_size": 0,
63
+ "num_attention_heads": 28,
64
+ "num_beam_groups": 1,
65
+ "num_beams": 1,
66
+ "num_hidden_layers": 28,
67
+ "num_key_value_heads": 4,
68
+ "num_return_sequences": 1,
69
+ "output_attentions": false,
70
+ "output_hidden_states": false,
71
+ "output_scores": false,
72
+ "pad_token_id": null,
73
+ "prefix": null,
74
+ "problem_type": null,
75
+ "pruned_heads": {},
76
+ "remove_invalid_values": false,
77
+ "repetition_penalty": 1.0,
78
+ "return_dict": true,
79
+ "return_dict_in_generate": false,
80
+ "rms_norm_eps": 1e-06,
81
+ "rope_scaling": {
82
+ "factor": 2.0,
83
+ "rope_type": "dynamic",
84
+ "type": "dynamic"
85
+ },
86
+ "rope_theta": 1000000.0,
87
+ "sep_token_id": null,
88
+ "sliding_window": null,
89
+ "suppress_tokens": null,
90
+ "task_specific_params": null,
91
+ "temperature": 1.0,
92
+ "tf_legacy_loss": false,
93
+ "tie_encoder_decoder": false,
94
+ "tie_word_embeddings": false,
95
+ "tokenizer_class": null,
96
+ "top_k": 50,
97
+ "top_p": 1.0,
98
+ "torch_dtype": "bfloat16",
99
+ "torchscript": false,
100
+ "transformers_version": "4.41.2",
101
+ "typical_p": 1.0,
102
+ "use_bfloat16": true,
103
+ "use_cache": false,
104
+ "use_sliding_window": false,
105
+ "vocab_size": 151674
106
+ },
107
+ "max_dynamic_patch": 6,
108
+ "min_dynamic_patch": 1,
109
+ "model_type": "internvl_chat",
110
+ "pad2square": false,
111
+ "ps_version": "v2",
112
+ "select_layer": -1,
113
+ "system_message": null,
114
+ "template": "internvl2_5",
115
+ "tie_word_embeddings": false,
116
+ "torch_dtype": "bfloat16",
117
+ "transformers_version": null,
118
+ "use_backbone_lora": 0,
119
+ "use_llm_lora": 128,
120
+ "use_thumbnail": true,
121
+ "vision_config": {
122
+ "_attn_implementation_autoset": true,
123
+ "_name_or_path": "OpenGVLab/InternViT-6B-448px-V1-5",
124
+ "add_cross_attention": false,
125
+ "architectures": [
126
+ "InternVisionModel"
127
+ ],
128
+ "attention_dropout": 0.0,
129
+ "auto_map": {
130
+ "AutoConfig": "configuration_intern_vit.InternVisionConfig",
131
+ "AutoModel": "modeling_intern_vit.InternVisionModel"
132
+ },
133
+ "bad_words_ids": null,
134
+ "begin_suppress_tokens": null,
135
+ "bos_token_id": null,
136
+ "capacity_factor": 1.2,
137
+ "chunk_size_feed_forward": 0,
138
+ "cross_attention_hidden_size": null,
139
+ "decoder_start_token_id": null,
140
+ "diversity_penalty": 0.0,
141
+ "do_sample": false,
142
+ "drop_path_rate": 0.0,
143
+ "dropout": 0.0,
144
+ "early_stopping": false,
145
+ "encoder_no_repeat_ngram_size": 0,
146
+ "eos_token_id": null,
147
+ "eval_capacity_factor": 1.4,
148
+ "exponential_decay_length_penalty": null,
149
+ "finetuning_task": null,
150
+ "forced_bos_token_id": null,
151
+ "forced_eos_token_id": null,
152
+ "hidden_act": "gelu",
153
+ "hidden_size": 1024,
154
+ "id2label": {
155
+ "0": "LABEL_0",
156
+ "1": "LABEL_1"
157
+ },
158
+ "image_size": 448,
159
+ "initializer_factor": 0.1,
160
+ "initializer_range": 1e-10,
161
+ "intermediate_size": 4096,
162
+ "is_decoder": false,
163
+ "is_encoder_decoder": false,
164
+ "label2id": {
165
+ "LABEL_0": 0,
166
+ "LABEL_1": 1
167
+ },
168
+ "laux_allreduce": "all_nodes",
169
+ "layer_norm_eps": 1e-06,
170
+ "length_penalty": 1.0,
171
+ "max_length": 20,
172
+ "min_length": 0,
173
+ "model_type": "intern_vit_6b",
174
+ "moe_coeff_ratio": 0.5,
175
+ "moe_intermediate_size": 768,
176
+ "moe_output_scale": 4.0,
177
+ "no_repeat_ngram_size": 0,
178
+ "noisy_gate_policy": "RSample_before",
179
+ "norm_type": "layer_norm",
180
+ "num_attention_heads": 16,
181
+ "num_beam_groups": 1,
182
+ "num_beams": 1,
183
+ "num_channels": 3,
184
+ "num_experts": 8,
185
+ "num_hidden_layers": 24,
186
+ "num_return_sequences": 1,
187
+ "num_routed_experts": 4,
188
+ "num_shared_experts": 4,
189
+ "output_attentions": false,
190
+ "output_hidden_states": false,
191
+ "output_scores": false,
192
+ "pad_token_id": null,
193
+ "patch_size": 14,
194
+ "prefix": null,
195
+ "problem_type": null,
196
+ "pruned_heads": {},
197
+ "qk_normalization": false,
198
+ "qkv_bias": true,
199
+ "remove_invalid_values": false,
200
+ "repetition_penalty": 1.0,
201
+ "return_dict": true,
202
+ "return_dict_in_generate": false,
203
+ "sep_token_id": null,
204
+ "shared_expert_intermediate_size": 3072,
205
+ "suppress_tokens": null,
206
+ "task_specific_params": null,
207
+ "temperature": 1.0,
208
+ "tf_legacy_loss": false,
209
+ "tie_encoder_decoder": false,
210
+ "tie_word_embeddings": true,
211
+ "tokenizer_class": null,
212
+ "top_k": 50,
213
+ "top_p": 1.0,
214
+ "torch_dtype": "bfloat16",
215
+ "torchscript": false,
216
+ "transformers_version": "4.41.2",
217
+ "typical_p": 1.0,
218
+ "use_bfloat16": true,
219
+ "use_flash_attn": true,
220
+ "use_moe": false,
221
+ "use_residual": true,
222
+ "use_rts": false,
223
+ "use_weighted_residual": false
224
+ }
225
+ }
generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.41.2"
4
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9047778631012976ea736f1e7a896155b7db7fcd3a778678c7bc86f913882e4d
3
+ size 4978009712
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17426b229d1f758c46341dda2a07bb5ee230b87dad8b8c141d4c43218a29f12e
3
+ size 4891883888
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:027f2783ea736c2fb1f45fba7e72703bd33cc9b7de8209a6d1e738daba5a8cf2
3
+ size 4891884000
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe94b544da01ba1d103deac79b526ae9b3ac0ba5c5c25341f93e638089ecf73b
3
+ size 1773049448
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
runs/Jul31_07-38-54_cfb9aa843d58/events.out.tfevents.1753947576.cfb9aa843d58.18698.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86a73e6a6c2461c737bb30c0c12d283ecd7a268a3cab37b567e8d2c4f7000d94
3
+ size 10582
runs/Jul31_07-41-44_cfb9aa843d58/events.out.tfevents.1753947748.cfb9aa843d58.19852.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5475a9cef9f993bad5477f3bdfba29ed0103778397dec4aa87c327ee82256f7
3
+ size 15898
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,281 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "151643": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "151644": {
15
+ "content": "<|im_start|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "151645": {
23
+ "content": "<|im_end|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "151646": {
31
+ "content": "<|object_ref_start|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "151647": {
39
+ "content": "<|object_ref_end|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "151648": {
47
+ "content": "<|box_start|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "151649": {
55
+ "content": "<|box_end|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "151650": {
63
+ "content": "<|quad_start|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "151651": {
71
+ "content": "<|quad_end|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "151652": {
79
+ "content": "<|vision_start|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "151653": {
87
+ "content": "<|vision_end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "151654": {
95
+ "content": "<|vision_pad|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "151655": {
103
+ "content": "<|image_pad|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "151656": {
111
+ "content": "<|video_pad|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "151657": {
119
+ "content": "<tool_call>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "151658": {
127
+ "content": "</tool_call>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "151659": {
135
+ "content": "<|fim_prefix|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "151660": {
143
+ "content": "<|fim_middle|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "151661": {
151
+ "content": "<|fim_suffix|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "151662": {
159
+ "content": "<|fim_pad|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "151663": {
167
+ "content": "<|repo_name|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "151664": {
175
+ "content": "<|file_sep|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "151665": {
183
+ "content": "<img>",
184
+ "lstrip": false,
185
+ "normalized": false,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": true
189
+ },
190
+ "151666": {
191
+ "content": "</img>",
192
+ "lstrip": false,
193
+ "normalized": false,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": true
197
+ },
198
+ "151667": {
199
+ "content": "<IMG_CONTEXT>",
200
+ "lstrip": false,
201
+ "normalized": false,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": true
205
+ },
206
+ "151668": {
207
+ "content": "<quad>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": true
213
+ },
214
+ "151669": {
215
+ "content": "</quad>",
216
+ "lstrip": false,
217
+ "normalized": false,
218
+ "rstrip": false,
219
+ "single_word": false,
220
+ "special": true
221
+ },
222
+ "151670": {
223
+ "content": "<ref>",
224
+ "lstrip": false,
225
+ "normalized": false,
226
+ "rstrip": false,
227
+ "single_word": false,
228
+ "special": true
229
+ },
230
+ "151671": {
231
+ "content": "</ref>",
232
+ "lstrip": false,
233
+ "normalized": false,
234
+ "rstrip": false,
235
+ "single_word": false,
236
+ "special": true
237
+ },
238
+ "151672": {
239
+ "content": "<box>",
240
+ "lstrip": false,
241
+ "normalized": false,
242
+ "rstrip": false,
243
+ "single_word": false,
244
+ "special": true
245
+ },
246
+ "151673": {
247
+ "content": "</box>",
248
+ "lstrip": false,
249
+ "normalized": false,
250
+ "rstrip": false,
251
+ "single_word": false,
252
+ "special": true
253
+ }
254
+ },
255
+ "additional_special_tokens": [
256
+ "<|im_start|>",
257
+ "<|im_end|>",
258
+ "<|object_ref_start|>",
259
+ "<|object_ref_end|>",
260
+ "<|box_start|>",
261
+ "<|box_end|>",
262
+ "<|quad_start|>",
263
+ "<|quad_end|>",
264
+ "<|vision_start|>",
265
+ "<|vision_end|>",
266
+ "<|vision_pad|>",
267
+ "<|image_pad|>",
268
+ "<|video_pad|>"
269
+ ],
270
+ "bos_token": null,
271
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\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\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
272
+ "clean_up_tokenization_spaces": false,
273
+ "eos_token": "<|im_end|>",
274
+ "errors": "replace",
275
+ "extra_special_tokens": {},
276
+ "model_max_length": 8191,
277
+ "pad_token": "<|endoftext|>",
278
+ "split_special_tokens": false,
279
+ "tokenizer_class": "Qwen2Tokenizer",
280
+ "unk_token": null
281
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9696969696969697,
3
+ "total_flos": 2.622912379643075e+19,
4
+ "train_loss": 0.0,
5
+ "train_runtime": 1207.2389,
6
+ "train_samples": 198,
7
+ "train_samples_per_second": 0.164,
8
+ "train_steps_per_second": 0.02
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,210 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9696969696969697,
5
+ "eval_steps": 500,
6
+ "global_step": 24,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.04040404040404041,
13
+ "grad_norm": 0.0,
14
+ "learning_rate": 2e-05,
15
+ "loss": 0.0,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.08080808080808081,
20
+ "grad_norm": 0.0,
21
+ "learning_rate": 1.9906859460363307e-05,
22
+ "loss": 0.0,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.12121212121212122,
27
+ "grad_norm": 0.0,
28
+ "learning_rate": 1.9629172873477995e-05,
29
+ "loss": 0.0,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.16161616161616163,
34
+ "grad_norm": 0.0,
35
+ "learning_rate": 1.917211301505453e-05,
36
+ "loss": 0.0,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.20202020202020202,
41
+ "grad_norm": 0.0,
42
+ "learning_rate": 1.8544194045464888e-05,
43
+ "loss": 0.0,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.24242424242424243,
48
+ "grad_norm": 0.0,
49
+ "learning_rate": 1.77571129070442e-05,
50
+ "loss": 0.0,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.2828282828282828,
55
+ "grad_norm": 0.0,
56
+ "learning_rate": 1.6825531432186545e-05,
57
+ "loss": 0.0,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.32323232323232326,
62
+ "grad_norm": 0.0,
63
+ "learning_rate": 1.5766803221148676e-05,
64
+ "loss": 0.0,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.36363636363636365,
69
+ "grad_norm": 0.0,
70
+ "learning_rate": 1.4600650377311523e-05,
71
+ "loss": 0.0,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.40404040404040403,
76
+ "grad_norm": 0.0,
77
+ "learning_rate": 1.3348796121709862e-05,
78
+ "loss": 0.0,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.4444444444444444,
83
+ "grad_norm": 0.0,
84
+ "learning_rate": 1.2034560130526341e-05,
85
+ "loss": 0.0,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.48484848484848486,
90
+ "grad_norm": 0.0,
91
+ "learning_rate": 1.0682424133646712e-05,
92
+ "loss": 0.0,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.5252525252525253,
97
+ "grad_norm": 0.0,
98
+ "learning_rate": 9.317575866353293e-06,
99
+ "loss": 0.0,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.5656565656565656,
104
+ "grad_norm": 0.0,
105
+ "learning_rate": 7.965439869473664e-06,
106
+ "loss": 0.0,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.6060606060606061,
111
+ "grad_norm": 0.0,
112
+ "learning_rate": 6.651203878290139e-06,
113
+ "loss": 0.0,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.6464646464646465,
118
+ "grad_norm": 0.0,
119
+ "learning_rate": 5.399349622688479e-06,
120
+ "loss": 0.0,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.6868686868686869,
125
+ "grad_norm": 0.0,
126
+ "learning_rate": 4.2331967788513295e-06,
127
+ "loss": 0.0,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.7272727272727273,
132
+ "grad_norm": 0.0,
133
+ "learning_rate": 3.174468567813461e-06,
134
+ "loss": 0.0,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.7676767676767676,
139
+ "grad_norm": 0.0,
140
+ "learning_rate": 2.2428870929558012e-06,
141
+ "loss": 0.0,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.8080808080808081,
146
+ "grad_norm": 0.0,
147
+ "learning_rate": 1.4558059545351144e-06,
148
+ "loss": 0.0,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.8484848484848485,
153
+ "grad_norm": 0.0,
154
+ "learning_rate": 8.278869849454718e-07,
155
+ "loss": 0.0,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.8888888888888888,
160
+ "grad_norm": 0.0,
161
+ "learning_rate": 3.708271265220087e-07,
162
+ "loss": 0.0,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.9292929292929293,
167
+ "grad_norm": 0.0,
168
+ "learning_rate": 9.314053963669245e-08,
169
+ "loss": 0.0,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.9696969696969697,
174
+ "grad_norm": 0.0,
175
+ "learning_rate": 0.0,
176
+ "loss": 0.0,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.9696969696969697,
181
+ "step": 24,
182
+ "total_flos": 2.622912379643075e+19,
183
+ "train_loss": 0.0,
184
+ "train_runtime": 1207.2389,
185
+ "train_samples_per_second": 0.164,
186
+ "train_steps_per_second": 0.02
187
+ }
188
+ ],
189
+ "logging_steps": 1.0,
190
+ "max_steps": 24,
191
+ "num_input_tokens_seen": 0,
192
+ "num_train_epochs": 1,
193
+ "save_steps": 200,
194
+ "stateful_callbacks": {
195
+ "TrainerControl": {
196
+ "args": {
197
+ "should_epoch_stop": false,
198
+ "should_evaluate": false,
199
+ "should_log": false,
200
+ "should_save": false,
201
+ "should_training_stop": false
202
+ },
203
+ "attributes": {}
204
+ }
205
+ },
206
+ "total_flos": 2.622912379643075e+19,
207
+ "train_batch_size": 1,
208
+ "trial_name": null,
209
+ "trial_params": null
210
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5ae787d60f782731ee46900780a369287ff6c553e7fe200237aee1b69e8de39
3
+ size 5176
training_log.txt ADDED
The diff for this file is too large to render. See raw diff
 
vocab.json ADDED
The diff for this file is too large to render. See raw diff