ShaoRun commited on
Commit
79ba0db
·
verified ·
1 Parent(s): b595125

Upload 22 files

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|point_placeholder|>": 151666,
18
+ "<|quad_end|>": 151651,
19
+ "<|quad_start|>": 151650,
20
+ "<|repo_name|>": 151663,
21
+ "<|video_pad|>": 151656,
22
+ "<|vision_end|>": 151653,
23
+ "<|vision_pad|>": 151654,
24
+ "<|vision_placeholder|>": 151665,
25
+ "<|vision_start|>": 151652
26
+ }
config.json ADDED
@@ -0,0 +1,224 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/g0001sr/code/allsparkv2_250120/model_zoo/rotation_point_stage1/allsparkv2_qwen25_7B_vision_stage1_stage1_5_stage2_point_reusetext_stage1",
3
+ "add_moe": true,
4
+ "architectures": [
5
+ "AllSparkForCausalLM"
6
+ ],
7
+ "hidden_size": 3584,
8
+ "ignore_index": -100,
9
+ "initializer_range": 0.02,
10
+ "llm_config": {
11
+ "_attn_implementation_autoset": true,
12
+ "_name_or_path": "./model_weights/Qwen2.5-7B-Instruct",
13
+ "add_cross_attention": false,
14
+ "architectures": [
15
+ "Qwen2ForCausalLM"
16
+ ],
17
+ "attention_dropout": 0.0,
18
+ "bad_words_ids": null,
19
+ "begin_suppress_tokens": null,
20
+ "bos_token_id": 151643,
21
+ "chunk_size_feed_forward": 0,
22
+ "cross_attention_hidden_size": null,
23
+ "decoder_start_token_id": null,
24
+ "diversity_penalty": 0.0,
25
+ "do_sample": false,
26
+ "early_stopping": false,
27
+ "encoder_no_repeat_ngram_size": 0,
28
+ "eos_token_id": 151645,
29
+ "exponential_decay_length_penalty": null,
30
+ "finetuning_task": null,
31
+ "forced_bos_token_id": null,
32
+ "forced_eos_token_id": null,
33
+ "hidden_act": "silu",
34
+ "hidden_size": 3584,
35
+ "id2label": {
36
+ "0": "LABEL_0",
37
+ "1": "LABEL_1"
38
+ },
39
+ "initializer_range": 0.02,
40
+ "intermediate_size": 18944,
41
+ "is_decoder": false,
42
+ "is_encoder_decoder": false,
43
+ "label2id": {
44
+ "LABEL_0": 0,
45
+ "LABEL_1": 1
46
+ },
47
+ "length_penalty": 1.0,
48
+ "max_length": 20,
49
+ "max_position_embeddings": 32768,
50
+ "max_window_layers": 28,
51
+ "min_length": 0,
52
+ "model_type": "qwen2",
53
+ "no_repeat_ngram_size": 0,
54
+ "num_attention_heads": 28,
55
+ "num_beam_groups": 1,
56
+ "num_beams": 1,
57
+ "num_hidden_layers": 28,
58
+ "num_key_value_heads": 4,
59
+ "num_return_sequences": 1,
60
+ "output_attentions": false,
61
+ "output_hidden_states": false,
62
+ "output_scores": false,
63
+ "pad_token_id": null,
64
+ "prefix": null,
65
+ "problem_type": null,
66
+ "pruned_heads": {},
67
+ "remove_invalid_values": false,
68
+ "repetition_penalty": 1.0,
69
+ "return_dict": true,
70
+ "return_dict_in_generate": false,
71
+ "rms_norm_eps": 1e-06,
72
+ "rope_scaling": null,
73
+ "rope_theta": 1000000.0,
74
+ "sep_token_id": null,
75
+ "sliding_window": null,
76
+ "suppress_tokens": null,
77
+ "task_specific_params": null,
78
+ "temperature": 1.0,
79
+ "tf_legacy_loss": false,
80
+ "tie_encoder_decoder": false,
81
+ "tie_word_embeddings": false,
82
+ "tokenizer_class": null,
83
+ "top_k": 50,
84
+ "top_p": 1.0,
85
+ "torch_dtype": "bfloat16",
86
+ "torchscript": false,
87
+ "typical_p": 1.0,
88
+ "use_bfloat16": false,
89
+ "use_cache": true,
90
+ "use_sliding_window": false,
91
+ "vocab_size": 151667
92
+ },
93
+ "llm_name_or_path": "./model_weights/Qwen2.5-7B-Instruct",
94
+ "modal_configs": [
95
+ {
96
+ "encoder_cfg": {
97
+ "_attn_implementation_autoset": true,
98
+ "_name_or_path": "./model_weights/siglip-so400m-patch14-384",
99
+ "add_cross_attention": false,
100
+ "architectures": null,
101
+ "attention_dropout": 0.0,
102
+ "bad_words_ids": null,
103
+ "begin_suppress_tokens": null,
104
+ "bos_token_id": null,
105
+ "chunk_size_feed_forward": 0,
106
+ "cross_attention_hidden_size": null,
107
+ "decoder_start_token_id": null,
108
+ "diversity_penalty": 0.0,
109
+ "do_sample": false,
110
+ "early_stopping": false,
111
+ "encoder_no_repeat_ngram_size": 0,
112
+ "eos_token_id": null,
113
+ "exponential_decay_length_penalty": null,
114
+ "finetuning_task": null,
115
+ "forced_bos_token_id": null,
116
+ "forced_eos_token_id": null,
117
+ "hidden_act": "gelu_pytorch_tanh",
118
+ "hidden_size": 1152,
119
+ "id2label": {
120
+ "0": "LABEL_0",
121
+ "1": "LABEL_1"
122
+ },
123
+ "image_size": 384,
124
+ "intermediate_size": 4304,
125
+ "is_decoder": false,
126
+ "is_encoder_decoder": false,
127
+ "label2id": {
128
+ "LABEL_0": 0,
129
+ "LABEL_1": 1
130
+ },
131
+ "layer_norm_eps": 1e-06,
132
+ "length_penalty": 1.0,
133
+ "max_length": 20,
134
+ "min_length": 0,
135
+ "model_type": "siglip_vision_model",
136
+ "no_repeat_ngram_size": 0,
137
+ "num_attention_heads": 16,
138
+ "num_beam_groups": 1,
139
+ "num_beams": 1,
140
+ "num_channels": 3,
141
+ "num_hidden_layers": 27,
142
+ "num_return_sequences": 1,
143
+ "output_attentions": false,
144
+ "output_hidden_states": false,
145
+ "output_scores": false,
146
+ "pad_token_id": null,
147
+ "patch_size": 14,
148
+ "prefix": null,
149
+ "problem_type": null,
150
+ "pruned_heads": {},
151
+ "remove_invalid_values": false,
152
+ "repetition_penalty": 1.0,
153
+ "return_dict": true,
154
+ "return_dict_in_generate": false,
155
+ "sep_token_id": null,
156
+ "suppress_tokens": null,
157
+ "task_specific_params": null,
158
+ "temperature": 1.0,
159
+ "tf_legacy_loss": false,
160
+ "tie_encoder_decoder": false,
161
+ "tie_word_embeddings": true,
162
+ "tokenizer_class": null,
163
+ "top_k": 50,
164
+ "top_p": 1.0,
165
+ "torch_dtype": null,
166
+ "torchscript": false,
167
+ "transformers_version": "4.47.0",
168
+ "typical_p": 1.0,
169
+ "use_bfloat16": false
170
+ },
171
+ "modal_placeholder_token": "<|vision_placeholder|>",
172
+ "modal_placeholder_token_id": 151665,
173
+ "modal_tag": "vision",
174
+ "model_name_or_path": "./model_weights/siglip-so400m-patch14-384",
175
+ "multi_grid": false,
176
+ "proj_input_dim": 1152,
177
+ "proj_num_layers": 2,
178
+ "proj_output_dim": 3584
179
+ },
180
+ {
181
+ "depth": 24,
182
+ "drop_path_rate": 0.1,
183
+ "embed_dim": 1024,
184
+ "encoder_cfg": {
185
+ "depth": 24,
186
+ "drop_path_rate": 0.1,
187
+ "embed_dim": 1024,
188
+ "group_size": 32,
189
+ "img_queries": 13,
190
+ "large_embedding": false,
191
+ "mask_type": "rand",
192
+ "modal_placeholder_token": "<|point_placeholder|>",
193
+ "modal_tag": "point",
194
+ "model_path": "/g0001sr/code/allsparkv2_250120/model_weights/pointencoder/recon2_converted.pth",
195
+ "num_group": 512,
196
+ "num_heads": 16,
197
+ "output_dim": 3584,
198
+ "pretrained_model_name": "eva_large_patch14_336.in22k_ft_in22k_in1k",
199
+ "stop_grad": false,
200
+ "text_queries": 3,
201
+ "with_color": true
202
+ },
203
+ "group_size": 32,
204
+ "img_queries": 13,
205
+ "large_embedding": false,
206
+ "mask_type": "rand",
207
+ "modal_placeholder_token": "<|point_placeholder|>",
208
+ "modal_placeholder_token_id": 151666,
209
+ "modal_tag": "point",
210
+ "model_path": "/g0001sr/code/allsparkv2_250120/model_weights/pointencoder/recon2_converted.pth",
211
+ "num_group": 512,
212
+ "num_heads": 16,
213
+ "output_dim": 3584,
214
+ "pretrained_model_name": "eva_large_patch14_336.in22k_ft_in22k_in1k",
215
+ "stop_grad": false,
216
+ "text_queries": 3,
217
+ "with_color": true
218
+ }
219
+ ],
220
+ "model_type": "allspark",
221
+ "tokenizer_padding_side": "right",
222
+ "torch_dtype": "bfloat16",
223
+ "transformers_version": "4.47.0"
224
+ }
generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.47.0"
4
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5826805e3b1d75407d67e6ad096b07ea4e0975b917db9149c4fd9dcca581c671
3
+ size 4896281328
model-00002-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ef127995c0061506e640b82d0037ad863fe0f6bd87855deec096080861039e5
3
+ size 4987654672
model-00003-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c99767b312e82e63b114ecbf9eb965ea33595101b93d4810531b5700611889f6
3
+ size 4928924360
model-00004-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6686fa68e751abaa7d3cfa98c2e2cf6544caa8dbea557d37d915f5d7e8ee42a0
3
+ size 4987654712
model-00005-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a82561e925f91af1941d72d215e093081d2fdf05817956eec79740475476b8a
3
+ size 4987654736
model-00006-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4c2858316686cc1dcc13155b75253aa7ccf84b429b6aa6b8da455464822f992
3
+ size 4987654736
model-00007-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0215c7bbca3e2fb2d35dcb3119523d268d99334090a19da1a2cf0ebd0c696204
3
+ size 4987654736
model-00008-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5520bc80d6cd9e7d5fe52def3180c7cf49cdfdb80557692bc33bce6bab5a7e0
3
+ size 4521544984
model-00009-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:062578ba94d997c28b697a1700ce2e458a288ae87c17c2a98d9a126b3ad8535c
3
+ size 1087178048
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.5,
8
+ 0.5,
9
+ 0.5
10
+ ],
11
+ "image_processor_type": "SiglipImageProcessor",
12
+ "image_std": [
13
+ 0.5,
14
+ 0.5,
15
+ 0.5
16
+ ],
17
+ "processor_class": "SiglipProcessor",
18
+ "resample": 3,
19
+ "rescale_factor": 0.00392156862745098,
20
+ "size": {
21
+ "height": 384,
22
+ "width": 384
23
+ }
24
+ }
runs/Feb27_11-49-49_pytorch-f7e2cb9f-jqm28/events.out.tfevents.1740628401.pytorch-f7e2cb9f-jqm28.223.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5d88df915f5d264c8fafa27bf64c1aed6dab40de859619f8233d18f42ab9b29
3
+ size 36200
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48e7a0fe20cfac1091a6b008096ee61236548817eee5dc662f85fe9a55aaeb97
3
+ size 11422293
tokenizer_config.json ADDED
@@ -0,0 +1,224 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|vision_placeholder|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "151666": {
190
+ "content": "<|point_placeholder|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ }
197
+ },
198
+ "additional_special_tokens": [
199
+ "<|im_start|>",
200
+ "<|im_end|>",
201
+ "<|object_ref_start|>",
202
+ "<|object_ref_end|>",
203
+ "<|box_start|>",
204
+ "<|box_end|>",
205
+ "<|quad_start|>",
206
+ "<|quad_end|>",
207
+ "<|vision_start|>",
208
+ "<|vision_end|>",
209
+ "<|vision_pad|>",
210
+ "<|image_pad|>",
211
+ "<|video_pad|>"
212
+ ],
213
+ "bos_token": null,
214
+ "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",
215
+ "clean_up_tokenization_spaces": false,
216
+ "eos_token": "<|im_end|>",
217
+ "errors": "replace",
218
+ "extra_special_tokens": {},
219
+ "model_max_length": 4096,
220
+ "pad_token": "<|endoftext|>",
221
+ "split_special_tokens": false,
222
+ "tokenizer_class": "Qwen2Tokenizer",
223
+ "unk_token": null
224
+ }
trainer_state.json ADDED
@@ -0,0 +1,819 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.999775734469612,
5
+ "eval_steps": 500,
6
+ "global_step": 2229,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.008970621215519175,
13
+ "grad_norm": 0.9008947014808655,
14
+ "learning_rate": 5.970149253731343e-06,
15
+ "loss": 3.6325,
16
+ "step": 20
17
+ },
18
+ {
19
+ "epoch": 0.01794124243103835,
20
+ "grad_norm": 0.5066778063774109,
21
+ "learning_rate": 1.1940298507462686e-05,
22
+ "loss": 2.6461,
23
+ "step": 40
24
+ },
25
+ {
26
+ "epoch": 0.026911863646557524,
27
+ "grad_norm": 0.5029802322387695,
28
+ "learning_rate": 1.791044776119403e-05,
29
+ "loss": 2.6127,
30
+ "step": 60
31
+ },
32
+ {
33
+ "epoch": 0.0358824848620767,
34
+ "grad_norm": 0.3778040111064911,
35
+ "learning_rate": 1.999821584672887e-05,
36
+ "loss": 2.5859,
37
+ "step": 80
38
+ },
39
+ {
40
+ "epoch": 0.04485310607759587,
41
+ "grad_norm": 0.3385876715183258,
42
+ "learning_rate": 1.998850515736159e-05,
43
+ "loss": 2.6276,
44
+ "step": 100
45
+ },
46
+ {
47
+ "epoch": 0.05382372729311505,
48
+ "grad_norm": 0.2863208055496216,
49
+ "learning_rate": 1.9970358823117534e-05,
50
+ "loss": 2.6081,
51
+ "step": 120
52
+ },
53
+ {
54
+ "epoch": 0.06279434850863422,
55
+ "grad_norm": 0.31687623262405396,
56
+ "learning_rate": 1.994379216921594e-05,
57
+ "loss": 2.5151,
58
+ "step": 140
59
+ },
60
+ {
61
+ "epoch": 0.0717649697241534,
62
+ "grad_norm": 0.27848467230796814,
63
+ "learning_rate": 1.990882763213298e-05,
64
+ "loss": 2.5367,
65
+ "step": 160
66
+ },
67
+ {
68
+ "epoch": 0.08073559093967257,
69
+ "grad_norm": 0.2719942629337311,
70
+ "learning_rate": 1.986549474065333e-05,
71
+ "loss": 2.6009,
72
+ "step": 180
73
+ },
74
+ {
75
+ "epoch": 0.08970621215519174,
76
+ "grad_norm": 0.28745323419570923,
77
+ "learning_rate": 1.98138300909321e-05,
78
+ "loss": 2.6414,
79
+ "step": 200
80
+ },
81
+ {
82
+ "epoch": 0.09867683337071093,
83
+ "grad_norm": 0.27338650822639465,
84
+ "learning_rate": 1.9753877315588072e-05,
85
+ "loss": 2.3677,
86
+ "step": 220
87
+ },
88
+ {
89
+ "epoch": 0.1076474545862301,
90
+ "grad_norm": 0.3499230742454529,
91
+ "learning_rate": 1.9685687046854415e-05,
92
+ "loss": 2.4714,
93
+ "step": 240
94
+ },
95
+ {
96
+ "epoch": 0.11661807580174927,
97
+ "grad_norm": 0.2322498857975006,
98
+ "learning_rate": 1.9609316873817992e-05,
99
+ "loss": 2.5646,
100
+ "step": 260
101
+ },
102
+ {
103
+ "epoch": 0.12558869701726844,
104
+ "grad_norm": 0.26533788442611694,
105
+ "learning_rate": 1.952483129378333e-05,
106
+ "loss": 2.511,
107
+ "step": 280
108
+ },
109
+ {
110
+ "epoch": 0.13455931823278763,
111
+ "grad_norm": 0.2915363013744354,
112
+ "learning_rate": 1.9432301657802378e-05,
113
+ "loss": 2.5829,
114
+ "step": 300
115
+ },
116
+ {
117
+ "epoch": 0.1435299394483068,
118
+ "grad_norm": 0.23644109070301056,
119
+ "learning_rate": 1.9331806110416027e-05,
120
+ "loss": 2.5513,
121
+ "step": 320
122
+ },
123
+ {
124
+ "epoch": 0.15250056066382597,
125
+ "grad_norm": 0.23692189157009125,
126
+ "learning_rate": 1.922342952365829e-05,
127
+ "loss": 2.4833,
128
+ "step": 340
129
+ },
130
+ {
131
+ "epoch": 0.16147118187934514,
132
+ "grad_norm": 0.22117172181606293,
133
+ "learning_rate": 1.9107263425378873e-05,
134
+ "loss": 2.5499,
135
+ "step": 360
136
+ },
137
+ {
138
+ "epoch": 0.1704418030948643,
139
+ "grad_norm": 0.2725989818572998,
140
+ "learning_rate": 1.8983405921944686e-05,
141
+ "loss": 2.4439,
142
+ "step": 380
143
+ },
144
+ {
145
+ "epoch": 0.17941242431038348,
146
+ "grad_norm": 0.22964678704738617,
147
+ "learning_rate": 1.8851961615385542e-05,
148
+ "loss": 2.5341,
149
+ "step": 400
150
+ },
151
+ {
152
+ "epoch": 0.18838304552590268,
153
+ "grad_norm": 0.22048306465148926,
154
+ "learning_rate": 1.8713041515054065e-05,
155
+ "loss": 2.5151,
156
+ "step": 420
157
+ },
158
+ {
159
+ "epoch": 0.19735366674142185,
160
+ "grad_norm": 0.2410048246383667,
161
+ "learning_rate": 1.8566762943874376e-05,
162
+ "loss": 2.4619,
163
+ "step": 440
164
+ },
165
+ {
166
+ "epoch": 0.20632428795694102,
167
+ "grad_norm": 0.2247011512517929,
168
+ "learning_rate": 1.8413249439258743e-05,
169
+ "loss": 2.5112,
170
+ "step": 460
171
+ },
172
+ {
173
+ "epoch": 0.2152949091724602,
174
+ "grad_norm": 0.25305867195129395,
175
+ "learning_rate": 1.8252630648775874e-05,
176
+ "loss": 2.5259,
177
+ "step": 480
178
+ },
179
+ {
180
+ "epoch": 0.22426553038797936,
181
+ "grad_norm": 0.23119617998600006,
182
+ "learning_rate": 1.8085042220658993e-05,
183
+ "loss": 2.488,
184
+ "step": 500
185
+ },
186
+ {
187
+ "epoch": 0.23323615160349853,
188
+ "grad_norm": 0.2174287885427475,
189
+ "learning_rate": 1.791062568924609e-05,
190
+ "loss": 2.491,
191
+ "step": 520
192
+ },
193
+ {
194
+ "epoch": 0.24220677281901773,
195
+ "grad_norm": 0.22464613616466522,
196
+ "learning_rate": 1.7729528355449214e-05,
197
+ "loss": 2.4441,
198
+ "step": 540
199
+ },
200
+ {
201
+ "epoch": 0.25117739403453687,
202
+ "grad_norm": 0.2646411657333374,
203
+ "learning_rate": 1.7541903162353638e-05,
204
+ "loss": 2.4999,
205
+ "step": 560
206
+ },
207
+ {
208
+ "epoch": 0.26014801525005604,
209
+ "grad_norm": 0.24847449362277985,
210
+ "learning_rate": 1.734790856605204e-05,
211
+ "loss": 2.4666,
212
+ "step": 580
213
+ },
214
+ {
215
+ "epoch": 0.26911863646557527,
216
+ "grad_norm": 0.20716962218284607,
217
+ "learning_rate": 1.714770840182273e-05,
218
+ "loss": 2.4222,
219
+ "step": 600
220
+ },
221
+ {
222
+ "epoch": 0.27808925768109444,
223
+ "grad_norm": 0.24155037105083466,
224
+ "learning_rate": 1.6941471745764996e-05,
225
+ "loss": 2.4417,
226
+ "step": 620
227
+ },
228
+ {
229
+ "epoch": 0.2870598788966136,
230
+ "grad_norm": 0.2298847883939743,
231
+ "learning_rate": 1.672937277200837e-05,
232
+ "loss": 2.5199,
233
+ "step": 640
234
+ },
235
+ {
236
+ "epoch": 0.2960305001121328,
237
+ "grad_norm": 0.22792883217334747,
238
+ "learning_rate": 1.6511590605616423e-05,
239
+ "loss": 2.4298,
240
+ "step": 660
241
+ },
242
+ {
243
+ "epoch": 0.30500112132765195,
244
+ "grad_norm": 0.2478325068950653,
245
+ "learning_rate": 1.628830917130935e-05,
246
+ "loss": 2.494,
247
+ "step": 680
248
+ },
249
+ {
250
+ "epoch": 0.3139717425431711,
251
+ "grad_norm": 0.22993171215057373,
252
+ "learning_rate": 1.6059717038133038e-05,
253
+ "loss": 2.5366,
254
+ "step": 700
255
+ },
256
+ {
257
+ "epoch": 0.3229423637586903,
258
+ "grad_norm": 0.23914852738380432,
259
+ "learning_rate": 1.5826007260205868e-05,
260
+ "loss": 2.4151,
261
+ "step": 720
262
+ },
263
+ {
264
+ "epoch": 0.33191298497420946,
265
+ "grad_norm": 0.2367142289876938,
266
+ "learning_rate": 1.5587377213677705e-05,
267
+ "loss": 2.3964,
268
+ "step": 740
269
+ },
270
+ {
271
+ "epoch": 0.3408836061897286,
272
+ "grad_norm": 0.25746768712997437,
273
+ "learning_rate": 1.5344028430038764e-05,
274
+ "loss": 2.4184,
275
+ "step": 760
276
+ },
277
+ {
278
+ "epoch": 0.3498542274052478,
279
+ "grad_norm": 0.23596778512001038,
280
+ "learning_rate": 1.5096166425919176e-05,
281
+ "loss": 2.4126,
282
+ "step": 780
283
+ },
284
+ {
285
+ "epoch": 0.35882484862076697,
286
+ "grad_norm": 0.22444961965084076,
287
+ "learning_rate": 1.4844000529522942e-05,
288
+ "loss": 2.4106,
289
+ "step": 800
290
+ },
291
+ {
292
+ "epoch": 0.36779546983628614,
293
+ "grad_norm": 0.2117769718170166,
294
+ "learning_rate": 1.458774370384287e-05,
295
+ "loss": 2.4786,
296
+ "step": 820
297
+ },
298
+ {
299
+ "epoch": 0.37676609105180536,
300
+ "grad_norm": 0.19232399761676788,
301
+ "learning_rate": 1.4327612366805832e-05,
302
+ "loss": 2.436,
303
+ "step": 840
304
+ },
305
+ {
306
+ "epoch": 0.38573671226732453,
307
+ "grad_norm": 0.2247142344713211,
308
+ "learning_rate": 1.4063826208500182e-05,
309
+ "loss": 2.5193,
310
+ "step": 860
311
+ },
312
+ {
313
+ "epoch": 0.3947073334828437,
314
+ "grad_norm": 0.24078157544136047,
315
+ "learning_rate": 1.3796608005639738e-05,
316
+ "loss": 2.5,
317
+ "step": 880
318
+ },
319
+ {
320
+ "epoch": 0.4036779546983629,
321
+ "grad_norm": 0.2095336616039276,
322
+ "learning_rate": 1.352618343342098e-05,
323
+ "loss": 2.4365,
324
+ "step": 900
325
+ },
326
+ {
327
+ "epoch": 0.41264857591388204,
328
+ "grad_norm": 0.2053331881761551,
329
+ "learning_rate": 1.3252780874932395e-05,
330
+ "loss": 2.4161,
331
+ "step": 920
332
+ },
333
+ {
334
+ "epoch": 0.4216191971294012,
335
+ "grad_norm": 0.20598524808883667,
336
+ "learning_rate": 1.2976631228276894e-05,
337
+ "loss": 2.4314,
338
+ "step": 940
339
+ },
340
+ {
341
+ "epoch": 0.4305898183449204,
342
+ "grad_norm": 0.2612752318382263,
343
+ "learning_rate": 1.2697967711570243e-05,
344
+ "loss": 2.3568,
345
+ "step": 960
346
+ },
347
+ {
348
+ "epoch": 0.43956043956043955,
349
+ "grad_norm": 0.18916811048984528,
350
+ "learning_rate": 1.2417025665980114e-05,
351
+ "loss": 2.4058,
352
+ "step": 980
353
+ },
354
+ {
355
+ "epoch": 0.4485310607759587,
356
+ "grad_norm": 0.23678423464298248,
357
+ "learning_rate": 1.2134042356972175e-05,
358
+ "loss": 2.4794,
359
+ "step": 1000
360
+ },
361
+ {
362
+ "epoch": 0.4575016819914779,
363
+ "grad_norm": 0.204436257481575,
364
+ "learning_rate": 1.1849256773931058e-05,
365
+ "loss": 2.3,
366
+ "step": 1020
367
+ },
368
+ {
369
+ "epoch": 0.46647230320699706,
370
+ "grad_norm": 0.20532362163066864,
371
+ "learning_rate": 1.156290942832536e-05,
372
+ "loss": 2.3845,
373
+ "step": 1040
374
+ },
375
+ {
376
+ "epoch": 0.47544292442251623,
377
+ "grad_norm": 0.2221594899892807,
378
+ "learning_rate": 1.1275242150587254e-05,
379
+ "loss": 2.4282,
380
+ "step": 1060
381
+ },
382
+ {
383
+ "epoch": 0.48441354563803546,
384
+ "grad_norm": 0.23072290420532227,
385
+ "learning_rate": 1.0986497885878145e-05,
386
+ "loss": 2.3869,
387
+ "step": 1080
388
+ },
389
+ {
390
+ "epoch": 0.49338416685355463,
391
+ "grad_norm": 0.20840080082416534,
392
+ "learning_rate": 1.0696920488912923e-05,
393
+ "loss": 2.4322,
394
+ "step": 1100
395
+ },
396
+ {
397
+ "epoch": 0.5023547880690737,
398
+ "grad_norm": 0.23384802043437958,
399
+ "learning_rate": 1.0406754518016047e-05,
400
+ "loss": 2.506,
401
+ "step": 1120
402
+ },
403
+ {
404
+ "epoch": 0.5113254092845929,
405
+ "grad_norm": 0.22102180123329163,
406
+ "learning_rate": 1.0116245028583418e-05,
407
+ "loss": 2.4869,
408
+ "step": 1140
409
+ },
410
+ {
411
+ "epoch": 0.5202960305001121,
412
+ "grad_norm": 0.18945130705833435,
413
+ "learning_rate": 9.825637366124458e-06,
414
+ "loss": 2.3671,
415
+ "step": 1160
416
+ },
417
+ {
418
+ "epoch": 0.5292666517156313,
419
+ "grad_norm": 0.22617211937904358,
420
+ "learning_rate": 9.535176959059171e-06,
421
+ "loss": 2.423,
422
+ "step": 1180
423
+ },
424
+ {
425
+ "epoch": 0.5382372729311505,
426
+ "grad_norm": 0.2126481682062149,
427
+ "learning_rate": 9.245109111445189e-06,
428
+ "loss": 2.3887,
429
+ "step": 1200
430
+ },
431
+ {
432
+ "epoch": 0.5472078941466697,
433
+ "grad_norm": 0.22861531376838684,
434
+ "learning_rate": 8.95567879580984e-06,
435
+ "loss": 2.36,
436
+ "step": 1220
437
+ },
438
+ {
439
+ "epoch": 0.5561785153621889,
440
+ "grad_norm": 0.2701588273048401,
441
+ "learning_rate": 8.667130446262214e-06,
442
+ "loss": 2.401,
443
+ "step": 1240
444
+ },
445
+ {
446
+ "epoch": 0.565149136577708,
447
+ "grad_norm": 0.2689853608608246,
448
+ "learning_rate": 8.379707752059932e-06,
449
+ "loss": 2.3753,
450
+ "step": 1260
451
+ },
452
+ {
453
+ "epoch": 0.5741197577932272,
454
+ "grad_norm": 0.22886186838150024,
455
+ "learning_rate": 8.093653451804987e-06,
456
+ "loss": 2.4807,
457
+ "step": 1280
458
+ },
459
+ {
460
+ "epoch": 0.5830903790087464,
461
+ "grad_norm": 0.24667732417583466,
462
+ "learning_rate": 7.809209128442408e-06,
463
+ "loss": 2.4269,
464
+ "step": 1300
465
+ },
466
+ {
467
+ "epoch": 0.5920610002242656,
468
+ "grad_norm": 0.22338470816612244,
469
+ "learning_rate": 7.52661500523497e-06,
470
+ "loss": 2.4133,
471
+ "step": 1320
472
+ },
473
+ {
474
+ "epoch": 0.6010316214397847,
475
+ "grad_norm": 0.21941307187080383,
476
+ "learning_rate": 7.246109742886156e-06,
477
+ "loss": 2.4606,
478
+ "step": 1340
479
+ },
480
+ {
481
+ "epoch": 0.6100022426553039,
482
+ "grad_norm": 0.22378675639629364,
483
+ "learning_rate": 6.967930237982793e-06,
484
+ "loss": 2.3498,
485
+ "step": 1360
486
+ },
487
+ {
488
+ "epoch": 0.6189728638708231,
489
+ "grad_norm": 0.23019564151763916,
490
+ "learning_rate": 6.692311422927515e-06,
491
+ "loss": 2.3927,
492
+ "step": 1380
493
+ },
494
+ {
495
+ "epoch": 0.6279434850863422,
496
+ "grad_norm": 0.22530066967010498,
497
+ "learning_rate": 6.4194860675300695e-06,
498
+ "loss": 2.4463,
499
+ "step": 1400
500
+ },
501
+ {
502
+ "epoch": 0.6369141063018614,
503
+ "grad_norm": 0.2268647849559784,
504
+ "learning_rate": 6.149684582425013e-06,
505
+ "loss": 2.4025,
506
+ "step": 1420
507
+ },
508
+ {
509
+ "epoch": 0.6458847275173806,
510
+ "grad_norm": 0.2626585066318512,
511
+ "learning_rate": 5.883134824481786e-06,
512
+ "loss": 2.3956,
513
+ "step": 1440
514
+ },
515
+ {
516
+ "epoch": 0.6548553487328997,
517
+ "grad_norm": 0.24002288281917572,
518
+ "learning_rate": 5.620061904371565e-06,
519
+ "loss": 2.3784,
520
+ "step": 1460
521
+ },
522
+ {
523
+ "epoch": 0.6638259699484189,
524
+ "grad_norm": 0.2304755002260208,
525
+ "learning_rate": 5.360687996453348e-06,
526
+ "loss": 2.4067,
527
+ "step": 1480
528
+ },
529
+ {
530
+ "epoch": 0.6727965911639381,
531
+ "grad_norm": 0.22266767919063568,
532
+ "learning_rate": 5.105232151139895e-06,
533
+ "loss": 2.4311,
534
+ "step": 1500
535
+ },
536
+ {
537
+ "epoch": 0.6817672123794573,
538
+ "grad_norm": 0.25173887610435486,
539
+ "learning_rate": 4.853910109901901e-06,
540
+ "loss": 2.3631,
541
+ "step": 1520
542
+ },
543
+ {
544
+ "epoch": 0.6907378335949764,
545
+ "grad_norm": 0.2748667299747467,
546
+ "learning_rate": 4.606934123066739e-06,
547
+ "loss": 2.3062,
548
+ "step": 1540
549
+ },
550
+ {
551
+ "epoch": 0.6997084548104956,
552
+ "grad_norm": 0.3214375972747803,
553
+ "learning_rate": 4.3645127705655654e-06,
554
+ "loss": 2.4436,
555
+ "step": 1560
556
+ },
557
+ {
558
+ "epoch": 0.7086790760260148,
559
+ "grad_norm": 0.25126707553863525,
560
+ "learning_rate": 4.126850785780199e-06,
561
+ "loss": 2.5224,
562
+ "step": 1580
563
+ },
564
+ {
565
+ "epoch": 0.7176496972415339,
566
+ "grad_norm": 0.24009720981121063,
567
+ "learning_rate": 3.8941488826385855e-06,
568
+ "loss": 2.3984,
569
+ "step": 1600
570
+ },
571
+ {
572
+ "epoch": 0.7266203184570531,
573
+ "grad_norm": 0.269382506608963,
574
+ "learning_rate": 3.6666035861047744e-06,
575
+ "loss": 2.4344,
576
+ "step": 1620
577
+ },
578
+ {
579
+ "epoch": 0.7355909396725723,
580
+ "grad_norm": 0.2938186526298523,
581
+ "learning_rate": 3.444407066206692e-06,
582
+ "loss": 2.3371,
583
+ "step": 1640
584
+ },
585
+ {
586
+ "epoch": 0.7445615608880914,
587
+ "grad_norm": 0.23332324624061584,
588
+ "learning_rate": 3.2277469757417403e-06,
589
+ "loss": 2.3741,
590
+ "step": 1660
591
+ },
592
+ {
593
+ "epoch": 0.7535321821036107,
594
+ "grad_norm": 0.24623927474021912,
595
+ "learning_rate": 3.0168062917974173e-06,
596
+ "loss": 2.3467,
597
+ "step": 1680
598
+ },
599
+ {
600
+ "epoch": 0.7625028033191299,
601
+ "grad_norm": 0.2714971601963043,
602
+ "learning_rate": 2.8117631612207084e-06,
603
+ "loss": 2.3712,
604
+ "step": 1700
605
+ },
606
+ {
607
+ "epoch": 0.7714734245346491,
608
+ "grad_norm": 0.24978309869766235,
609
+ "learning_rate": 2.6127907501667726e-06,
610
+ "loss": 2.4389,
611
+ "step": 1720
612
+ },
613
+ {
614
+ "epoch": 0.7804440457501682,
615
+ "grad_norm": 0.25042879581451416,
616
+ "learning_rate": 2.420057097854046e-06,
617
+ "loss": 2.3793,
618
+ "step": 1740
619
+ },
620
+ {
621
+ "epoch": 0.7894146669656874,
622
+ "grad_norm": 0.2673550248146057,
623
+ "learning_rate": 2.2337249746491695e-06,
624
+ "loss": 2.3452,
625
+ "step": 1760
626
+ },
627
+ {
628
+ "epoch": 0.7983852881812066,
629
+ "grad_norm": 0.2639400362968445,
630
+ "learning_rate": 2.0539517446016975e-06,
631
+ "loss": 2.3364,
632
+ "step": 1780
633
+ },
634
+ {
635
+ "epoch": 0.8073559093967257,
636
+ "grad_norm": 0.2685152590274811,
637
+ "learning_rate": 1.880889232544585e-06,
638
+ "loss": 2.3915,
639
+ "step": 1800
640
+ },
641
+ {
642
+ "epoch": 0.8163265306122449,
643
+ "grad_norm": 0.2522066533565521,
644
+ "learning_rate": 1.714683595872777e-06,
645
+ "loss": 2.3616,
646
+ "step": 1820
647
+ },
648
+ {
649
+ "epoch": 0.8252971518277641,
650
+ "grad_norm": 0.25205305218696594,
651
+ "learning_rate": 1.5554752011081332e-06,
652
+ "loss": 2.3692,
653
+ "step": 1840
654
+ },
655
+ {
656
+ "epoch": 0.8342677730432833,
657
+ "grad_norm": 0.30145809054374695,
658
+ "learning_rate": 1.4033985053549425e-06,
659
+ "loss": 2.3174,
660
+ "step": 1860
661
+ },
662
+ {
663
+ "epoch": 0.8432383942588024,
664
+ "grad_norm": 0.2629565894603729,
665
+ "learning_rate": 1.2585819427461564e-06,
666
+ "loss": 2.3526,
667
+ "step": 1880
668
+ },
669
+ {
670
+ "epoch": 0.8522090154743216,
671
+ "grad_norm": 0.2707832455635071,
672
+ "learning_rate": 1.121147815976248e-06,
673
+ "loss": 2.3042,
674
+ "step": 1900
675
+ },
676
+ {
677
+ "epoch": 0.8611796366898408,
678
+ "grad_norm": 0.23665176331996918,
679
+ "learning_rate": 9.912121930122542e-07,
680
+ "loss": 2.3199,
681
+ "step": 1920
682
+ },
683
+ {
684
+ "epoch": 0.8701502579053599,
685
+ "grad_norm": 0.2816649377346039,
686
+ "learning_rate": 8.688848090702928e-07,
687
+ "loss": 2.331,
688
+ "step": 1940
689
+ },
690
+ {
691
+ "epoch": 0.8791208791208791,
692
+ "grad_norm": 0.27171188592910767,
693
+ "learning_rate": 7.542689739403097e-07,
694
+ "loss": 2.3775,
695
+ "step": 1960
696
+ },
697
+ {
698
+ "epoch": 0.8880915003363983,
699
+ "grad_norm": 0.250848650932312,
700
+ "learning_rate": 6.474614847373051e-07,
701
+ "loss": 2.3671,
702
+ "step": 1980
703
+ },
704
+ {
705
+ "epoch": 0.8970621215519174,
706
+ "grad_norm": 0.2723957598209381,
707
+ "learning_rate": 5.485525441527651e-07,
708
+ "loss": 2.2999,
709
+ "step": 2000
710
+ },
711
+ {
712
+ "epoch": 0.9060327427674366,
713
+ "grad_norm": 0.2722890079021454,
714
+ "learning_rate": 4.5762568427529795e-07,
715
+ "loss": 2.3807,
716
+ "step": 2020
717
+ },
718
+ {
719
+ "epoch": 0.9150033639829558,
720
+ "grad_norm": 0.2557665705680847,
721
+ "learning_rate": 3.747576960448551e-07,
722
+ "loss": 2.3589,
723
+ "step": 2040
724
+ },
725
+ {
726
+ "epoch": 0.923973985198475,
727
+ "grad_norm": 0.3588675856590271,
728
+ "learning_rate": 3.0001856440005307e-07,
729
+ "loss": 2.3025,
730
+ "step": 2060
731
+ },
732
+ {
733
+ "epoch": 0.9329446064139941,
734
+ "grad_norm": 0.2574796676635742,
735
+ "learning_rate": 2.3347140917344579e-07,
736
+ "loss": 2.4445,
737
+ "step": 2080
738
+ },
739
+ {
740
+ "epoch": 0.9419152276295133,
741
+ "grad_norm": 0.2603015899658203,
742
+ "learning_rate": 1.7517243178458486e-07,
743
+ "loss": 2.3884,
744
+ "step": 2100
745
+ },
746
+ {
747
+ "epoch": 0.9508858488450325,
748
+ "grad_norm": 0.2759827673435211,
749
+ "learning_rate": 1.2517086777594112e-07,
750
+ "loss": 2.3706,
751
+ "step": 2120
752
+ },
753
+ {
754
+ "epoch": 0.9598564700605517,
755
+ "grad_norm": 0.2819114327430725,
756
+ "learning_rate": 8.35089452317639e-08,
757
+ "loss": 2.2965,
758
+ "step": 2140
759
+ },
760
+ {
761
+ "epoch": 0.9688270912760709,
762
+ "grad_norm": 0.2688797414302826,
763
+ "learning_rate": 5.022184911495864e-08,
764
+ "loss": 2.3142,
765
+ "step": 2160
766
+ },
767
+ {
768
+ "epoch": 0.9777977124915901,
769
+ "grad_norm": 0.2871028780937195,
770
+ "learning_rate": 2.5337691552156372e-08,
771
+ "loss": 2.3665,
772
+ "step": 2180
773
+ },
774
+ {
775
+ "epoch": 0.9867683337071093,
776
+ "grad_norm": 0.25957873463630676,
777
+ "learning_rate": 8.877488092022823e-09,
778
+ "loss": 2.3602,
779
+ "step": 2200
780
+ },
781
+ {
782
+ "epoch": 0.9957389549226284,
783
+ "grad_norm": 0.2717770040035248,
784
+ "learning_rate": 8.551399568945684e-10,
785
+ "loss": 2.3519,
786
+ "step": 2220
787
+ },
788
+ {
789
+ "epoch": 0.999775734469612,
790
+ "step": 2229,
791
+ "total_flos": 3.1724140856564777e+18,
792
+ "train_loss": 2.4421788879230237,
793
+ "train_runtime": 8917.1095,
794
+ "train_samples_per_second": 15.998,
795
+ "train_steps_per_second": 0.25
796
+ }
797
+ ],
798
+ "logging_steps": 20,
799
+ "max_steps": 2229,
800
+ "num_input_tokens_seen": 0,
801
+ "num_train_epochs": 1,
802
+ "save_steps": 5000,
803
+ "stateful_callbacks": {
804
+ "TrainerControl": {
805
+ "args": {
806
+ "should_epoch_stop": false,
807
+ "should_evaluate": false,
808
+ "should_log": false,
809
+ "should_save": true,
810
+ "should_training_stop": true
811
+ },
812
+ "attributes": {}
813
+ }
814
+ },
815
+ "total_flos": 3.1724140856564777e+18,
816
+ "train_batch_size": 4,
817
+ "trial_name": null,
818
+ "trial_params": null
819
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a10f4490c03e79d1b69c6be2dcbaa1baf82d77b75e6ee314eabb97033b494c5
3
+ size 12216
vocab.json ADDED
The diff for this file is too large to render. See raw diff