Hugging Face's logo

gowitheflowlab
/
2560-stage-3-1024

PyTorch
clip
Model card Files Community
gowitheflow1998 commited on
Commit
ddf3694
•
1 Parent(s): 8e81db1

upload checkpoint

Browse files
Files changed (16) hide show
  1. .gitattributes +5 -0
  2. 49e6dc219d1a1a1c9236acaf05a48b542002016a6dc877ee72baab085a84257b.3f28e7f4b38e1efe1b6da4a3732404c19d4c6a614ff32dce90a251e293d4ce58 +3 -0
  3. config.json +166 -0
  4. merges.txt +0 -0
  5. optimizer.pt +3 -0
  6. preprocessor_config.json +19 -0
  7. pytorch_model.bin +3 -0
  8. rng_state.pth +3 -0
  9. scheduler.pt +3 -0
  10. special_tokens_map.json +1 -0
  11. text_renderer_config.json +253 -0
  12. tokenizer.json +0 -0
  13. tokenizer_config.json +34 -0
  14. trainer_state.json +2416 -0
  15. training_args.bin +3 -0
  16. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,8 @@ 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
+ training_args.bin filter=lfs diff=lfs merge=lfs -text
37
+ optimizer.pt filter=lfs diff=lfs merge=lfs -text
38
+ scheduler.pt filter=lfs diff=lfs merge=lfs -text
39
+ 49e6dc219d1a1a1c9236acaf05a48b542002016a6dc877ee72baab085a84257b.3f28e7f4b38e1efe1b6da4a3732404c19d4c6a614ff32dce90a251e293d4ce58 filter=lfs diff=lfs merge=lfs -text
40
+ pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
49e6dc219d1a1a1c9236acaf05a48b542002016a6dc877ee72baab085a84257b.3f28e7f4b38e1efe1b6da4a3732404c19d4c6a614ff32dce90a251e293d4ce58 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83ab5c39e2b1c34a955136275ce0db068cb20d9643ead033d6b8124a73ab4f64
3
+ size 15645492
config.json ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./checkpoints/clip-stage2-2560/checkpoint-7700",
3
+ "architectures": [
4
+ "CLIPModel"
5
+ ],
6
+ "id2label": {},
7
+ "initializer_factor": 1.0,
8
+ "label2id": {
9
+ "Contradiction": 2,
10
+ "Entailment": 0,
11
+ "Neutral": 1
12
+ },
13
+ "logit_scale_init_value": 2.6592,
14
+ "model_type": "clip",
15
+ "projection_dim": 512,
16
+ "text_config": {
17
+ "_name_or_path": "",
18
+ "add_cross_attention": false,
19
+ "architectures": null,
20
+ "attention_dropout": 0.0,
21
+ "bad_words_ids": null,
22
+ "bos_token_id": 0,
23
+ "chunk_size_feed_forward": 0,
24
+ "cross_attention_hidden_size": null,
25
+ "decoder_start_token_id": null,
26
+ "diversity_penalty": 0.0,
27
+ "do_sample": false,
28
+ "dropout": 0.0,
29
+ "early_stopping": false,
30
+ "encoder_no_repeat_ngram_size": 0,
31
+ "eos_token_id": 2,
32
+ "finetuning_task": null,
33
+ "forced_bos_token_id": null,
34
+ "forced_eos_token_id": null,
35
+ "hidden_act": "quick_gelu",
36
+ "hidden_size": 512,
37
+ "id2label": {
38
+ "0": "LABEL_0",
39
+ "1": "LABEL_1"
40
+ },
41
+ "initializer_factor": 1.0,
42
+ "initializer_range": 0.02,
43
+ "intermediate_size": 2048,
44
+ "is_decoder": false,
45
+ "is_encoder_decoder": false,
46
+ "label2id": {
47
+ "LABEL_0": 0,
48
+ "LABEL_1": 1
49
+ },
50
+ "layer_norm_eps": 1e-05,
51
+ "length_penalty": 1.0,
52
+ "max_length": 20,
53
+ "max_position_embeddings": 77,
54
+ "min_length": 0,
55
+ "model_type": "clip_text_model",
56
+ "no_repeat_ngram_size": 0,
57
+ "num_attention_heads": 8,
58
+ "num_beam_groups": 1,
59
+ "num_beams": 1,
60
+ "num_hidden_layers": 12,
61
+ "num_return_sequences": 1,
62
+ "output_attentions": false,
63
+ "output_hidden_states": false,
64
+ "output_scores": false,
65
+ "pad_token_id": 1,
66
+ "prefix": null,
67
+ "problem_type": null,
68
+ "pruned_heads": {},
69
+ "remove_invalid_values": false,
70
+ "repetition_penalty": 1.0,
71
+ "return_dict": true,
72
+ "return_dict_in_generate": false,
73
+ "sep_token_id": null,
74
+ "task_specific_params": null,
75
+ "temperature": 1.0,
76
+ "tie_encoder_decoder": false,
77
+ "tie_word_embeddings": true,
78
+ "tokenizer_class": null,
79
+ "top_k": 50,
80
+ "top_p": 1.0,
81
+ "torch_dtype": null,
82
+ "torchscript": false,
83
+ "transformers_version": "4.17.0",
84
+ "typical_p": 1.0,
85
+ "use_bfloat16": false,
86
+ "vocab_size": 49408
87
+ },
88
+ "text_config_dict": null,
89
+ "torch_dtype": "float32",
90
+ "transformers_version": null,
91
+ "vision_config": {
92
+ "_name_or_path": "",
93
+ "add_cross_attention": false,
94
+ "architectures": null,
95
+ "attention_dropout": 0.0,
96
+ "bad_words_ids": null,
97
+ "bos_token_id": null,
98
+ "chunk_size_feed_forward": 0,
99
+ "cross_attention_hidden_size": null,
100
+ "decoder_start_token_id": null,
101
+ "diversity_penalty": 0.0,
102
+ "do_sample": false,
103
+ "dropout": 0.0,
104
+ "early_stopping": false,
105
+ "encoder_no_repeat_ngram_size": 0,
106
+ "eos_token_id": null,
107
+ "finetuning_task": null,
108
+ "forced_bos_token_id": null,
109
+ "forced_eos_token_id": null,
110
+ "hidden_act": "quick_gelu",
111
+ "hidden_size": 768,
112
+ "id2label": {
113
+ "0": "LABEL_0",
114
+ "1": "LABEL_1"
115
+ },
116
+ "image_size": 224,
117
+ "initializer_factor": 1.0,
118
+ "initializer_range": 0.02,
119
+ "intermediate_size": 3072,
120
+ "is_decoder": false,
121
+ "is_encoder_decoder": false,
122
+ "label2id": {
123
+ "LABEL_0": 0,
124
+ "LABEL_1": 1
125
+ },
126
+ "layer_norm_eps": 1e-05,
127
+ "length_penalty": 1.0,
128
+ "max_length": 20,
129
+ "min_length": 0,
130
+ "model_type": "clip_vision_model",
131
+ "no_repeat_ngram_size": 0,
132
+ "num_attention_heads": 12,
133
+ "num_beam_groups": 1,
134
+ "num_beams": 1,
135
+ "num_hidden_layers": 12,
136
+ "num_return_sequences": 1,
137
+ "output_attentions": false,
138
+ "output_hidden_states": false,
139
+ "output_scores": false,
140
+ "pad_token_id": null,
141
+ "patch_size": 16,
142
+ "prefix": null,
143
+ "problem_type": null,
144
+ "pruned_heads": {},
145
+ "remove_invalid_values": false,
146
+ "repetition_penalty": 1.0,
147
+ "return_dict": true,
148
+ "return_dict_in_generate": false,
149
+ "sep_token_id": null,
150
+ "task_specific_params": null,
151
+ "temperature": 1.0,
152
+ "tie_encoder_decoder": false,
153
+ "tie_word_embeddings": true,
154
+ "tokenizer_class": null,
155
+ "top_k": 50,
156
+ "top_p": 1.0,
157
+ "torch_dtype": null,
158
+ "torchscript": false,
159
+ "transformers_version": "4.17.0",
160
+ "typical_p": 1.0,
161
+ "use_bfloat16": false
162
+ },
163
+ "vision_config_dict": {
164
+ "patch_size": 16
165
+ }
166
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7356af47073e50a45939dab2262909e9c012e65387f244e0a9dcfe029846bd6
3
+ size 689659578
preprocessor_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": 224,
3
+ "do_center_crop": true,
4
+ "do_normalize": true,
5
+ "do_resize": true,
6
+ "feature_extractor_type": "CLIPFeatureExtractor",
7
+ "image_mean": [
8
+ 0.48145466,
9
+ 0.4578275,
10
+ 0.40821073
11
+ ],
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "resample": 3,
18
+ "size": 224
19
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:507b5b5de982a5ee387d3253306c161d113a7e4f75d54ad4d3d67613ae945d25
3
+ size 598642122
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d6f7afe2098f5b695378bbbcec45939bbee7150062f83101e5cd88d18eb00cc
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaab7edf07106ae0e2812d7a23f89807251902919e434d3ba825482ea70020ab
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": {"content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "<|endoftext|>"}
text_renderer_config.json ADDED
@@ -0,0 +1,253 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "background_color": "white",
3
+ "dpi": 120,
4
+ "font_color": "black",
5
+ "font_file": "49e6dc219d1a1a1c9236acaf05a48b542002016a6dc877ee72baab085a84257b.3f28e7f4b38e1efe1b6da4a3732404c19d4c6a614ff32dce90a251e293d4ce58",
6
+ "font_size": 8,
7
+ "fonts_list": [
8
+ "Apple Color Emoji",
9
+ "DejaVu Sans",
10
+ "DejaVu Sans Mono",
11
+ "DejaVu Serif",
12
+ "FontAwesome",
13
+ "GLYPHICONS Halflings",
14
+ "Go Noto Current",
15
+ "Inconsolata",
16
+ "Lato",
17
+ "MathJax_AMS",
18
+ "MathJax_Caligraphic",
19
+ "MathJax_Fraktur",
20
+ "MathJax_Main",
21
+ "MathJax_Math",
22
+ "MathJax_SansSerif",
23
+ "MathJax_Script",
24
+ "MathJax_Size1",
25
+ "MathJax_Size2",
26
+ "MathJax_Size3",
27
+ "MathJax_Size4",
28
+ "MathJax_Typewriter",
29
+ "MathJax_Vector",
30
+ "MathJax_Vector-Bold",
31
+ "MathJax_WinChrome",
32
+ "MathJax_WinIE6",
33
+ "Monospace",
34
+ "Noto Fangsong KSS Rotated",
35
+ "Noto Fangsong KSS Vertical",
36
+ "Noto Kufi Arabic",
37
+ "Noto Music",
38
+ "Noto Naskh Arabic UI",
39
+ "Noto Nastaliq Urdu",
40
+ "Noto Rashi Hebrew",
41
+ "Noto Sans",
42
+ "Noto Sans Adlam",
43
+ "Noto Sans Adlam Unjoined",
44
+ "Noto Sans Anatolian Hieroglyphs",
45
+ "Noto Sans Arabic",
46
+ "Noto Sans Armenian",
47
+ "Noto Sans Avestan",
48
+ "Noto Sans Balinese",
49
+ "Noto Sans Bamum",
50
+ "Noto Sans Bassa Vah",
51
+ "Noto Sans Batak",
52
+ "Noto Sans Bhaiksuki",
53
+ "Noto Sans Brahmi",
54
+ "Noto Sans Buginese",
55
+ "Noto Sans Buhid",
56
+ "Noto Sans CJK HK",
57
+ "Noto Sans CJK JP",
58
+ "Noto Sans CJK KR",
59
+ "Noto Sans CJK SC",
60
+ "Noto Sans CJK TC",
61
+ "Noto Sans Canadian Aboriginal",
62
+ "Noto Sans Carian",
63
+ "Noto Sans Caucasian Albanian",
64
+ "Noto Sans Chakma",
65
+ "Noto Sans Cham",
66
+ "Noto Sans Cherokee",
67
+ "Noto Sans Chorasmian",
68
+ "Noto Sans Coptic",
69
+ "Noto Sans Cuneiform",
70
+ "Noto Sans Cypriot",
71
+ "Noto Sans Cypro Minoan",
72
+ "Noto Sans Deseret",
73
+ "Noto Sans Devanagari",
74
+ "Noto Sans Devanagari UI",
75
+ "Noto Sans Duployan",
76
+ "Noto Sans Egyptian Hieroglyphs",
77
+ "Noto Sans Elbasan",
78
+ "Noto Sans Elymaic",
79
+ "Noto Sans Ethiopic",
80
+ "Noto Sans Georgian",
81
+ "Noto Sans Glagolitic",
82
+ "Noto Sans Gothic",
83
+ "Noto Sans Grantha",
84
+ "Noto Sans Gujarati",
85
+ "Noto Sans Gujarati UI",
86
+ "Noto Sans Gunjala Gondi",
87
+ "Noto Sans Gurmukhi",
88
+ "Noto Sans Gurmukhi UI",
89
+ "Noto Sans Hanifi Rohingya",
90
+ "Noto Sans Hanunoo",
91
+ "Noto Sans Hatran",
92
+ "Noto Sans Hebrew",
93
+ "Noto Sans Hebrew Droid",
94
+ "Noto Sans Imperial Aramaic",
95
+ "Noto Sans Indic Siyaq Numbers",
96
+ "Noto Sans Inscriptional Pahlavi",
97
+ "Noto Sans Inscriptional Parthian",
98
+ "Noto Sans Javanese",
99
+ "Noto Sans Kaithi",
100
+ "Noto Sans Kannada",
101
+ "Noto Sans Kannada UI",
102
+ "Noto Sans Kawi",
103
+ "Noto Sans Kayah Li",
104
+ "Noto Sans Kharoshthi",
105
+ "Noto Sans Khmer",
106
+ "Noto Sans Khmer UI",
107
+ "Noto Sans Khojki",
108
+ "Noto Sans Khudawadi",
109
+ "Noto Sans Lao",
110
+ "Noto Sans Lao Looped",
111
+ "Noto Sans Lao Looped UI",
112
+ "Noto Sans Lao UI",
113
+ "Noto Sans Lepcha",
114
+ "Noto Sans Limbu",
115
+ "Noto Sans Linear A",
116
+ "Noto Sans Linear B",
117
+ "Noto Sans Lisu",
118
+ "Noto Sans Lycian",
119
+ "Noto Sans Lydian",
120
+ "Noto Sans Mahajani",
121
+ "Noto Sans Malayalam",
122
+ "Noto Sans Malayalam UI",
123
+ "Noto Sans Mandaic",
124
+ "Noto Sans Manichaean",
125
+ "Noto Sans Marchen",
126
+ "Noto Sans Masaram Gondi",
127
+ "Noto Sans Math",
128
+ "Noto Sans Mayan Numerals",
129
+ "Noto Sans Medefaidrin",
130
+ "Noto Sans Meetei Mayek",
131
+ "Noto Sans Mende Kikakui",
132
+ "Noto Sans Meroitic",
133
+ "Noto Sans Miao",
134
+ "Noto Sans Modi",
135
+ "Noto Sans Mongolian",
136
+ "Noto Sans Mono",
137
+ "Noto Sans Mro",
138
+ "Noto Sans Multani",
139
+ "Noto Sans Myanmar",
140
+ "Noto Sans Myanmar UI",
141
+ "Noto Sans NKo",
142
+ "Noto Sans NKo Unjoined",
143
+ "Noto Sans Nabataean",
144
+ "Noto Sans Nag Mundari",
145
+ "Noto Sans Nandinagari",
146
+ "Noto Sans New Tai Lue",
147
+ "Noto Sans Newa",
148
+ "Noto Sans Nushu",
149
+ "Noto Sans Ogham",
150
+ "Noto Sans Ol Chiki",
151
+ "Noto Sans Old Hungarian",
152
+ "Noto Sans Old Italic",
153
+ "Noto Sans Old North Arabian",
154
+ "Noto Sans Old Permic",
155
+ "Noto Sans Old Persian",
156
+ "Noto Sans Old Sogdian",
157
+ "Noto Sans Old South Arabian",
158
+ "Noto Sans Old Turkic",
159
+ "Noto Sans Oriya",
160
+ "Noto Sans Osage",
161
+ "Noto Sans Osmanya",
162
+ "Noto Sans Pahawh Hmong",
163
+ "Noto Sans Palmyrene",
164
+ "Noto Sans Pau Cin Hau",
165
+ "Noto Sans PhagsPa",
166
+ "Noto Sans Phoenician",
167
+ "Noto Sans Psalter Pahlavi",
168
+ "Noto Sans Rejang",
169
+ "Noto Sans Runic",
170
+ "Noto Sans Samaritan",
171
+ "Noto Sans Saurashtra",
172
+ "Noto Sans Sharada",
173
+ "Noto Sans Shavian",
174
+ "Noto Sans Siddham",
175
+ "Noto Sans SignWriting",
176
+ "Noto Sans Sinhala",
177
+ "Noto Sans Sinhala UI",
178
+ "Noto Sans Sogdian",
179
+ "Noto Sans Sora Sompeng",
180
+ "Noto Sans Soyombo",
181
+ "Noto Sans Sundanese",
182
+ "Noto Sans Syloti Nagri",
183
+ "Noto Sans Symbols",
184
+ "Noto Sans Symbols 2",
185
+ "Noto Sans Syriac",
186
+ "Noto Sans Syriac Eastern",
187
+ "Noto Sans Syriac Western",
188
+ "Noto Sans Tagalog",
189
+ "Noto Sans Tagbanwa",
190
+ "Noto Sans Tai Le",
191
+ "Noto Sans Tai Tham",
192
+ "Noto Sans Tai Viet",
193
+ "Noto Sans Takri",
194
+ "Noto Sans Tamil",
195
+ "Noto Sans Tamil Supplement",
196
+ "Noto Sans Tamil UI",
197
+ "Noto Sans Tangsa",
198
+ "Noto Sans Telugu",
199
+ "Noto Sans Telugu UI",
200
+ "Noto Sans Test",
201
+ "Noto Sans Thaana",
202
+ "Noto Sans Thai",
203
+ "Noto Sans Thai Looped",
204
+ "Noto Sans Thai Looped UI",
205
+ "Noto Sans Thai UI",
206
+ "Noto Sans Tifinagh",
207
+ "Noto Sans Tifinagh APT",
208
+ "Noto Sans Tifinagh Adrar",
209
+ "Noto Sans Tifinagh Agraw Imazighen",
210
+ "Noto Sans Tifinagh Ahaggar",
211
+ "Noto Sans Tifinagh Air",
212
+ "Noto Sans Tifinagh Azawagh",
213
+ "Noto Sans Tifinagh Ghat",
214
+ "Noto Sans Tifinagh Hawad",
215
+ "Noto Sans Tifinagh Rhissa Ixa",
216
+ "Noto Sans Tifinagh SIL",
217
+ "Noto Sans Tifinagh Tawellemmet",
218
+ "Noto Sans Tirhuta",
219
+ "Noto Sans Ugaritic",
220
+ "Noto Sans Vai",
221
+ "Noto Sans Vithkuqi",
222
+ "Noto Sans Wancho",
223
+ "Noto Sans Warang Citi",
224
+ "Noto Sans Yi",
225
+ "Noto Sans Zanabazar Square",
226
+ "Noto Traditional Nushu",
227
+ "NotoSansOldHungarianUI",
228
+ "Sans",
229
+ "Serif",
230
+ "Source Code Pro",
231
+ "System-ui",
232
+ "Ubuntu",
233
+ "Ubuntu Condensed",
234
+ "Ubuntu Mono",
235
+ "cmex10",
236
+ "cmmi10",
237
+ "cmr10",
238
+ "cmsy10",
239
+ "dsrom10",
240
+ "esint10",
241
+ "eufm10",
242
+ "msam10",
243
+ "msbm10",
244
+ "rsfs10",
245
+ "stmary10",
246
+ "wasy10"
247
+ ],
248
+ "max_seq_length": 196,
249
+ "pad_size": 3,
250
+ "pixels_per_patch": 16,
251
+ "rgb": false,
252
+ "text_renderer_type": "PangoCairoTextRenderer"
253
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "unk_token": {
3
+ "content": "<|endoftext|>",
4
+ "single_word": false,
5
+ "lstrip": false,
6
+ "rstrip": false,
7
+ "normalized": true,
8
+ "__type": "AddedToken"
9
+ },
10
+ "bos_token": {
11
+ "content": "<|startoftext|>",
12
+ "single_word": false,
13
+ "lstrip": false,
14
+ "rstrip": false,
15
+ "normalized": true,
16
+ "__type": "AddedToken"
17
+ },
18
+ "eos_token": {
19
+ "content": "<|endoftext|>",
20
+ "single_word": false,
21
+ "lstrip": false,
22
+ "rstrip": false,
23
+ "normalized": true,
24
+ "__type": "AddedToken"
25
+ },
26
+ "pad_token": "<|endoftext|>",
27
+ "errors": "replace",
28
+ "add_prefix_space": false,
29
+ "do_lower_case": true,
30
+ "name_or_path": "openai/clip-vit-base-patch16",
31
+ "model_max_length": 77,
32
+ "special_tokens_map_file": "./special_tokens_map.json",
33
+ "tokenizer_class": "CLIPTokenizer"
34
+ }
trainer_state.json ADDED
@@ -0,0 +1,2416 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7822743590634694,
3
+ "best_model_checkpoint": "./checkpoints/clip-stage3pa-1024/checkpoint-3810",
4
+ "epoch": 0.7486430844095078,
5
+ "global_step": 4000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 1.5e-06,
13
+ "loss": 0.727,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.0,
18
+ "learning_rate": 3e-06,
19
+ "loss": 0.6697,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.01,
24
+ "learning_rate": 4.5e-06,
25
+ "loss": 0.6164,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.01,
30
+ "learning_rate": 6e-06,
31
+ "loss": 0.5883,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.01,
36
+ "learning_rate": 7.5e-06,
37
+ "loss": 0.5711,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.01,
42
+ "learning_rate": 9e-06,
43
+ "loss": 0.5863,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 0.01,
48
+ "learning_rate": 1.05e-05,
49
+ "loss": 0.5441,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.01,
54
+ "learning_rate": 1.2e-05,
55
+ "loss": 0.5303,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 0.02,
60
+ "learning_rate": 1.3500000000000001e-05,
61
+ "loss": 0.5436,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 0.02,
66
+ "learning_rate": 1.5e-05,
67
+ "loss": 0.5507,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 0.02,
72
+ "learning_rate": 1.65e-05,
73
+ "loss": 0.5534,
74
+ "step": 110
75
+ },
76
+ {
77
+ "epoch": 0.02,
78
+ "learning_rate": 1.8e-05,
79
+ "loss": 0.5384,
80
+ "step": 120
81
+ },
82
+ {
83
+ "epoch": 0.02,
84
+ "learning_rate": 1.95e-05,
85
+ "loss": 0.5533,
86
+ "step": 130
87
+ },
88
+ {
89
+ "epoch": 0.03,
90
+ "learning_rate": 2.1e-05,
91
+ "loss": 0.5475,
92
+ "step": 140
93
+ },
94
+ {
95
+ "epoch": 0.03,
96
+ "learning_rate": 2.25e-05,
97
+ "loss": 0.5482,
98
+ "step": 150
99
+ },
100
+ {
101
+ "epoch": 0.03,
102
+ "learning_rate": 2.4e-05,
103
+ "loss": 0.5099,
104
+ "step": 160
105
+ },
106
+ {
107
+ "epoch": 0.03,
108
+ "learning_rate": 2.55e-05,
109
+ "loss": 0.539,
110
+ "step": 170
111
+ },
112
+ {
113
+ "epoch": 0.03,
114
+ "learning_rate": 2.7000000000000002e-05,
115
+ "loss": 0.5176,
116
+ "step": 180
117
+ },
118
+ {
119
+ "epoch": 0.04,
120
+ "learning_rate": 2.8499999999999998e-05,
121
+ "loss": 0.526,
122
+ "step": 190
123
+ },
124
+ {
125
+ "epoch": 0.04,
126
+ "learning_rate": 3e-05,
127
+ "loss": 0.5276,
128
+ "step": 200
129
+ },
130
+ {
131
+ "epoch": 0.04,
132
+ "learning_rate": 2.992105263157895e-05,
133
+ "loss": 0.5077,
134
+ "step": 210
135
+ },
136
+ {
137
+ "epoch": 0.04,
138
+ "learning_rate": 2.9842105263157894e-05,
139
+ "loss": 0.5375,
140
+ "step": 220
141
+ },
142
+ {
143
+ "epoch": 0.04,
144
+ "learning_rate": 2.9763157894736842e-05,
145
+ "loss": 0.5411,
146
+ "step": 230
147
+ },
148
+ {
149
+ "epoch": 0.04,
150
+ "learning_rate": 2.968421052631579e-05,
151
+ "loss": 0.4877,
152
+ "step": 240
153
+ },
154
+ {
155
+ "epoch": 0.05,
156
+ "learning_rate": 2.9605263157894735e-05,
157
+ "loss": 0.5347,
158
+ "step": 250
159
+ },
160
+ {
161
+ "epoch": 0.05,
162
+ "learning_rate": 2.9526315789473684e-05,
163
+ "loss": 0.4839,
164
+ "step": 260
165
+ },
166
+ {
167
+ "epoch": 0.05,
168
+ "learning_rate": 2.9447368421052635e-05,
169
+ "loss": 0.4936,
170
+ "step": 270
171
+ },
172
+ {
173
+ "epoch": 0.05,
174
+ "learning_rate": 2.936842105263158e-05,
175
+ "loss": 0.4849,
176
+ "step": 280
177
+ },
178
+ {
179
+ "epoch": 0.05,
180
+ "learning_rate": 2.928947368421053e-05,
181
+ "loss": 0.4696,
182
+ "step": 290
183
+ },
184
+ {
185
+ "epoch": 0.06,
186
+ "learning_rate": 2.9210526315789474e-05,
187
+ "loss": 0.4872,
188
+ "step": 300
189
+ },
190
+ {
191
+ "epoch": 0.06,
192
+ "learning_rate": 2.9131578947368422e-05,
193
+ "loss": 0.4636,
194
+ "step": 310
195
+ },
196
+ {
197
+ "epoch": 0.06,
198
+ "learning_rate": 2.905263157894737e-05,
199
+ "loss": 0.4728,
200
+ "step": 320
201
+ },
202
+ {
203
+ "epoch": 0.06,
204
+ "learning_rate": 2.8973684210526315e-05,
205
+ "loss": 0.4743,
206
+ "step": 330
207
+ },
208
+ {
209
+ "epoch": 0.06,
210
+ "learning_rate": 2.8894736842105263e-05,
211
+ "loss": 0.4774,
212
+ "step": 340
213
+ },
214
+ {
215
+ "epoch": 0.07,
216
+ "learning_rate": 2.8815789473684212e-05,
217
+ "loss": 0.4372,
218
+ "step": 350
219
+ },
220
+ {
221
+ "epoch": 0.07,
222
+ "learning_rate": 2.8736842105263157e-05,
223
+ "loss": 0.4515,
224
+ "step": 360
225
+ },
226
+ {
227
+ "epoch": 0.07,
228
+ "learning_rate": 2.8657894736842105e-05,
229
+ "loss": 0.422,
230
+ "step": 370
231
+ },
232
+ {
233
+ "epoch": 0.07,
234
+ "learning_rate": 2.8578947368421053e-05,
235
+ "loss": 0.4505,
236
+ "step": 380
237
+ },
238
+ {
239
+ "epoch": 0.07,
240
+ "learning_rate": 2.8499999999999998e-05,
241
+ "loss": 0.4383,
242
+ "step": 390
243
+ },
244
+ {
245
+ "epoch": 0.07,
246
+ "learning_rate": 2.8421052631578946e-05,
247
+ "loss": 0.4601,
248
+ "step": 400
249
+ },
250
+ {
251
+ "epoch": 0.08,
252
+ "learning_rate": 2.8342105263157898e-05,
253
+ "loss": 0.4327,
254
+ "step": 410
255
+ },
256
+ {
257
+ "epoch": 0.08,
258
+ "learning_rate": 2.8263157894736843e-05,
259
+ "loss": 0.4182,
260
+ "step": 420
261
+ },
262
+ {
263
+ "epoch": 0.08,
264
+ "learning_rate": 2.818421052631579e-05,
265
+ "loss": 0.4421,
266
+ "step": 430
267
+ },
268
+ {
269
+ "epoch": 0.08,
270
+ "learning_rate": 2.810526315789474e-05,
271
+ "loss": 0.427,
272
+ "step": 440
273
+ },
274
+ {
275
+ "epoch": 0.08,
276
+ "learning_rate": 2.8026315789473685e-05,
277
+ "loss": 0.4397,
278
+ "step": 450
279
+ },
280
+ {
281
+ "epoch": 0.09,
282
+ "learning_rate": 2.7947368421052633e-05,
283
+ "loss": 0.4249,
284
+ "step": 460
285
+ },
286
+ {
287
+ "epoch": 0.09,
288
+ "learning_rate": 2.786842105263158e-05,
289
+ "loss": 0.432,
290
+ "step": 470
291
+ },
292
+ {
293
+ "epoch": 0.09,
294
+ "learning_rate": 2.7789473684210526e-05,
295
+ "loss": 0.4264,
296
+ "step": 480
297
+ },
298
+ {
299
+ "epoch": 0.09,
300
+ "learning_rate": 2.7710526315789474e-05,
301
+ "loss": 0.4325,
302
+ "step": 490
303
+ },
304
+ {
305
+ "epoch": 0.09,
306
+ "learning_rate": 2.7631578947368423e-05,
307
+ "loss": 0.4204,
308
+ "step": 500
309
+ },
310
+ {
311
+ "epoch": 0.1,
312
+ "learning_rate": 2.7552631578947368e-05,
313
+ "loss": 0.4246,
314
+ "step": 510
315
+ },
316
+ {
317
+ "epoch": 0.1,
318
+ "learning_rate": 2.7473684210526316e-05,
319
+ "loss": 0.429,
320
+ "step": 520
321
+ },
322
+ {
323
+ "epoch": 0.1,
324
+ "learning_rate": 2.739473684210526e-05,
325
+ "loss": 0.4003,
326
+ "step": 530
327
+ },
328
+ {
329
+ "epoch": 0.1,
330
+ "learning_rate": 2.7315789473684213e-05,
331
+ "loss": 0.3946,
332
+ "step": 540
333
+ },
334
+ {
335
+ "epoch": 0.1,
336
+ "learning_rate": 2.723684210526316e-05,
337
+ "loss": 0.4035,
338
+ "step": 550
339
+ },
340
+ {
341
+ "epoch": 0.1,
342
+ "learning_rate": 2.7157894736842106e-05,
343
+ "loss": 0.384,
344
+ "step": 560
345
+ },
346
+ {
347
+ "epoch": 0.11,
348
+ "learning_rate": 2.7078947368421054e-05,
349
+ "loss": 0.4095,
350
+ "step": 570
351
+ },
352
+ {
353
+ "epoch": 0.11,
354
+ "learning_rate": 2.7000000000000002e-05,
355
+ "loss": 0.386,
356
+ "step": 580
357
+ },
358
+ {
359
+ "epoch": 0.11,
360
+ "learning_rate": 2.6921052631578947e-05,
361
+ "loss": 0.374,
362
+ "step": 590
363
+ },
364
+ {
365
+ "epoch": 0.11,
366
+ "learning_rate": 2.6842105263157896e-05,
367
+ "loss": 0.4155,
368
+ "step": 600
369
+ },
370
+ {
371
+ "epoch": 0.11,
372
+ "learning_rate": 2.6763157894736844e-05,
373
+ "loss": 0.403,
374
+ "step": 610
375
+ },
376
+ {
377
+ "epoch": 0.12,
378
+ "learning_rate": 2.668421052631579e-05,
379
+ "loss": 0.3722,
380
+ "step": 620
381
+ },
382
+ {
383
+ "epoch": 0.12,
384
+ "learning_rate": 2.6605263157894737e-05,
385
+ "loss": 0.39,
386
+ "step": 630
387
+ },
388
+ {
389
+ "epoch": 0.12,
390
+ "learning_rate": 2.6526315789473685e-05,
391
+ "loss": 0.4041,
392
+ "step": 640
393
+ },
394
+ {
395
+ "epoch": 0.12,
396
+ "learning_rate": 2.644736842105263e-05,
397
+ "loss": 0.4011,
398
+ "step": 650
399
+ },
400
+ {
401
+ "epoch": 0.12,
402
+ "learning_rate": 2.636842105263158e-05,
403
+ "loss": 0.3887,
404
+ "step": 660
405
+ },
406
+ {
407
+ "epoch": 0.13,
408
+ "learning_rate": 2.6289473684210527e-05,
409
+ "loss": 0.3807,
410
+ "step": 670
411
+ },
412
+ {
413
+ "epoch": 0.13,
414
+ "learning_rate": 2.6210526315789475e-05,
415
+ "loss": 0.3762,
416
+ "step": 680
417
+ },
418
+ {
419
+ "epoch": 0.13,
420
+ "learning_rate": 2.6131578947368424e-05,
421
+ "loss": 0.3831,
422
+ "step": 690
423
+ },
424
+ {
425
+ "epoch": 0.13,
426
+ "learning_rate": 2.605263157894737e-05,
427
+ "loss": 0.3408,
428
+ "step": 700
429
+ },
430
+ {
431
+ "epoch": 0.13,
432
+ "learning_rate": 2.5973684210526317e-05,
433
+ "loss": 0.362,
434
+ "step": 710
435
+ },
436
+ {
437
+ "epoch": 0.13,
438
+ "learning_rate": 2.5894736842105265e-05,
439
+ "loss": 0.3606,
440
+ "step": 720
441
+ },
442
+ {
443
+ "epoch": 0.14,
444
+ "learning_rate": 2.581578947368421e-05,
445
+ "loss": 0.3475,
446
+ "step": 730
447
+ },
448
+ {
449
+ "epoch": 0.14,
450
+ "learning_rate": 2.5736842105263158e-05,
451
+ "loss": 0.3659,
452
+ "step": 740
453
+ },
454
+ {
455
+ "epoch": 0.14,
456
+ "learning_rate": 2.5657894736842107e-05,
457
+ "loss": 0.3391,
458
+ "step": 750
459
+ },
460
+ {
461
+ "epoch": 0.14,
462
+ "learning_rate": 2.557894736842105e-05,
463
+ "loss": 0.3744,
464
+ "step": 760
465
+ },
466
+ {
467
+ "epoch": 0.14,
468
+ "learning_rate": 2.55e-05,
469
+ "loss": 0.3609,
470
+ "step": 770
471
+ },
472
+ {
473
+ "epoch": 0.15,
474
+ "learning_rate": 2.5421052631578948e-05,
475
+ "loss": 0.3525,
476
+ "step": 780
477
+ },
478
+ {
479
+ "epoch": 0.15,
480
+ "learning_rate": 2.5342105263157893e-05,
481
+ "loss": 0.3527,
482
+ "step": 790
483
+ },
484
+ {
485
+ "epoch": 0.15,
486
+ "learning_rate": 2.526315789473684e-05,
487
+ "loss": 0.3566,
488
+ "step": 800
489
+ },
490
+ {
491
+ "epoch": 0.15,
492
+ "learning_rate": 2.518421052631579e-05,
493
+ "loss": 0.3327,
494
+ "step": 810
495
+ },
496
+ {
497
+ "epoch": 0.15,
498
+ "learning_rate": 2.5105263157894738e-05,
499
+ "loss": 0.3789,
500
+ "step": 820
501
+ },
502
+ {
503
+ "epoch": 0.16,
504
+ "learning_rate": 2.5026315789473686e-05,
505
+ "loss": 0.3415,
506
+ "step": 830
507
+ },
508
+ {
509
+ "epoch": 0.16,
510
+ "learning_rate": 2.4947368421052635e-05,
511
+ "loss": 0.3342,
512
+ "step": 840
513
+ },
514
+ {
515
+ "epoch": 0.16,
516
+ "learning_rate": 2.486842105263158e-05,
517
+ "loss": 0.3415,
518
+ "step": 850
519
+ },
520
+ {
521
+ "epoch": 0.16,
522
+ "learning_rate": 2.4789473684210528e-05,
523
+ "loss": 0.3562,
524
+ "step": 860
525
+ },
526
+ {
527
+ "epoch": 0.16,
528
+ "learning_rate": 2.4710526315789476e-05,
529
+ "loss": 0.3405,
530
+ "step": 870
531
+ },
532
+ {
533
+ "epoch": 0.16,
534
+ "learning_rate": 2.463157894736842e-05,
535
+ "loss": 0.368,
536
+ "step": 880
537
+ },
538
+ {
539
+ "epoch": 0.17,
540
+ "learning_rate": 2.455263157894737e-05,
541
+ "loss": 0.3547,
542
+ "step": 890
543
+ },
544
+ {
545
+ "epoch": 0.17,
546
+ "learning_rate": 2.4473684210526318e-05,
547
+ "loss": 0.3508,
548
+ "step": 900
549
+ },
550
+ {
551
+ "epoch": 0.17,
552
+ "learning_rate": 2.4394736842105262e-05,
553
+ "loss": 0.34,
554
+ "step": 910
555
+ },
556
+ {
557
+ "epoch": 0.17,
558
+ "learning_rate": 2.431578947368421e-05,
559
+ "loss": 0.3256,
560
+ "step": 920
561
+ },
562
+ {
563
+ "epoch": 0.17,
564
+ "learning_rate": 2.4236842105263156e-05,
565
+ "loss": 0.3515,
566
+ "step": 930
567
+ },
568
+ {
569
+ "epoch": 0.18,
570
+ "learning_rate": 2.4157894736842104e-05,
571
+ "loss": 0.316,
572
+ "step": 940
573
+ },
574
+ {
575
+ "epoch": 0.18,
576
+ "learning_rate": 2.4078947368421056e-05,
577
+ "loss": 0.3382,
578
+ "step": 950
579
+ },
580
+ {
581
+ "epoch": 0.18,
582
+ "learning_rate": 2.4e-05,
583
+ "loss": 0.3314,
584
+ "step": 960
585
+ },
586
+ {
587
+ "epoch": 0.18,
588
+ "learning_rate": 2.392105263157895e-05,
589
+ "loss": 0.3285,
590
+ "step": 970
591
+ },
592
+ {
593
+ "epoch": 0.18,
594
+ "learning_rate": 2.3842105263157897e-05,
595
+ "loss": 0.3472,
596
+ "step": 980
597
+ },
598
+ {
599
+ "epoch": 0.19,
600
+ "learning_rate": 2.3763157894736842e-05,
601
+ "loss": 0.3183,
602
+ "step": 990
603
+ },
604
+ {
605
+ "epoch": 0.19,
606
+ "learning_rate": 2.368421052631579e-05,
607
+ "loss": 0.332,
608
+ "step": 1000
609
+ },
610
+ {
611
+ "epoch": 0.19,
612
+ "learning_rate": 2.360526315789474e-05,
613
+ "loss": 0.314,
614
+ "step": 1010
615
+ },
616
+ {
617
+ "epoch": 0.19,
618
+ "learning_rate": 2.3526315789473684e-05,
619
+ "loss": 0.3127,
620
+ "step": 1020
621
+ },
622
+ {
623
+ "epoch": 0.19,
624
+ "learning_rate": 2.3447368421052632e-05,
625
+ "loss": 0.3483,
626
+ "step": 1030
627
+ },
628
+ {
629
+ "epoch": 0.19,
630
+ "learning_rate": 2.336842105263158e-05,
631
+ "loss": 0.3408,
632
+ "step": 1040
633
+ },
634
+ {
635
+ "epoch": 0.2,
636
+ "learning_rate": 2.3289473684210525e-05,
637
+ "loss": 0.3406,
638
+ "step": 1050
639
+ },
640
+ {
641
+ "epoch": 0.2,
642
+ "learning_rate": 2.3210526315789473e-05,
643
+ "loss": 0.3205,
644
+ "step": 1060
645
+ },
646
+ {
647
+ "epoch": 0.2,
648
+ "learning_rate": 2.3131578947368422e-05,
649
+ "loss": 0.3135,
650
+ "step": 1070
651
+ },
652
+ {
653
+ "epoch": 0.2,
654
+ "learning_rate": 2.3052631578947367e-05,
655
+ "loss": 0.3107,
656
+ "step": 1080
657
+ },
658
+ {
659
+ "epoch": 0.2,
660
+ "learning_rate": 2.297368421052632e-05,
661
+ "loss": 0.3079,
662
+ "step": 1090
663
+ },
664
+ {
665
+ "epoch": 0.21,
666
+ "learning_rate": 2.2894736842105263e-05,
667
+ "loss": 0.3141,
668
+ "step": 1100
669
+ },
670
+ {
671
+ "epoch": 0.21,
672
+ "learning_rate": 2.281578947368421e-05,
673
+ "loss": 0.3186,
674
+ "step": 1110
675
+ },
676
+ {
677
+ "epoch": 0.21,
678
+ "learning_rate": 2.273684210526316e-05,
679
+ "loss": 0.3254,
680
+ "step": 1120
681
+ },
682
+ {
683
+ "epoch": 0.21,
684
+ "learning_rate": 2.2657894736842105e-05,
685
+ "loss": 0.3219,
686
+ "step": 1130
687
+ },
688
+ {
689
+ "epoch": 0.21,
690
+ "learning_rate": 2.2578947368421053e-05,
691
+ "loss": 0.3106,
692
+ "step": 1140
693
+ },
694
+ {
695
+ "epoch": 0.22,
696
+ "learning_rate": 2.25e-05,
697
+ "loss": 0.3042,
698
+ "step": 1150
699
+ },
700
+ {
701
+ "epoch": 0.22,
702
+ "learning_rate": 2.2421052631578946e-05,
703
+ "loss": 0.3154,
704
+ "step": 1160
705
+ },
706
+ {
707
+ "epoch": 0.22,
708
+ "learning_rate": 2.2342105263157895e-05,
709
+ "loss": 0.3147,
710
+ "step": 1170
711
+ },
712
+ {
713
+ "epoch": 0.22,
714
+ "learning_rate": 2.2263157894736843e-05,
715
+ "loss": 0.2916,
716
+ "step": 1180
717
+ },
718
+ {
719
+ "epoch": 0.22,
720
+ "learning_rate": 2.2184210526315788e-05,
721
+ "loss": 0.3159,
722
+ "step": 1190
723
+ },
724
+ {
725
+ "epoch": 0.22,
726
+ "learning_rate": 2.2105263157894736e-05,
727
+ "loss": 0.3084,
728
+ "step": 1200
729
+ },
730
+ {
731
+ "epoch": 0.23,
732
+ "learning_rate": 2.2026315789473684e-05,
733
+ "loss": 0.3071,
734
+ "step": 1210
735
+ },
736
+ {
737
+ "epoch": 0.23,
738
+ "learning_rate": 2.1947368421052633e-05,
739
+ "loss": 0.312,
740
+ "step": 1220
741
+ },
742
+ {
743
+ "epoch": 0.23,
744
+ "learning_rate": 2.186842105263158e-05,
745
+ "loss": 0.3018,
746
+ "step": 1230
747
+ },
748
+ {
749
+ "epoch": 0.23,
750
+ "learning_rate": 2.178947368421053e-05,
751
+ "loss": 0.3195,
752
+ "step": 1240
753
+ },
754
+ {
755
+ "epoch": 0.23,
756
+ "learning_rate": 2.1710526315789474e-05,
757
+ "loss": 0.3115,
758
+ "step": 1250
759
+ },
760
+ {
761
+ "epoch": 0.24,
762
+ "learning_rate": 2.1631578947368423e-05,
763
+ "loss": 0.2827,
764
+ "step": 1260
765
+ },
766
+ {
767
+ "epoch": 0.24,
768
+ "learning_rate": 2.155263157894737e-05,
769
+ "loss": 0.3168,
770
+ "step": 1270
771
+ },
772
+ {
773
+ "epoch": 0.24,
774
+ "learning_rate": 2.1473684210526316e-05,
775
+ "loss": 0.3004,
776
+ "step": 1280
777
+ },
778
+ {
779
+ "epoch": 0.24,
780
+ "learning_rate": 2.1394736842105264e-05,
781
+ "loss": 0.3084,
782
+ "step": 1290
783
+ },
784
+ {
785
+ "epoch": 0.24,
786
+ "learning_rate": 2.1315789473684212e-05,
787
+ "loss": 0.3065,
788
+ "step": 1300
789
+ },
790
+ {
791
+ "epoch": 0.25,
792
+ "learning_rate": 2.1236842105263157e-05,
793
+ "loss": 0.318,
794
+ "step": 1310
795
+ },
796
+ {
797
+ "epoch": 0.25,
798
+ "learning_rate": 2.1157894736842106e-05,
799
+ "loss": 0.3035,
800
+ "step": 1320
801
+ },
802
+ {
803
+ "epoch": 0.25,
804
+ "learning_rate": 2.107894736842105e-05,
805
+ "loss": 0.2849,
806
+ "step": 1330
807
+ },
808
+ {
809
+ "epoch": 0.25,
810
+ "learning_rate": 2.1e-05,
811
+ "loss": 0.2861,
812
+ "step": 1340
813
+ },
814
+ {
815
+ "epoch": 0.25,
816
+ "learning_rate": 2.0921052631578947e-05,
817
+ "loss": 0.2852,
818
+ "step": 1350
819
+ },
820
+ {
821
+ "epoch": 0.25,
822
+ "learning_rate": 2.0842105263157895e-05,
823
+ "loss": 0.3204,
824
+ "step": 1360
825
+ },
826
+ {
827
+ "epoch": 0.26,
828
+ "learning_rate": 2.0763157894736844e-05,
829
+ "loss": 0.31,
830
+ "step": 1370
831
+ },
832
+ {
833
+ "epoch": 0.26,
834
+ "learning_rate": 2.0684210526315792e-05,
835
+ "loss": 0.2854,
836
+ "step": 1380
837
+ },
838
+ {
839
+ "epoch": 0.26,
840
+ "learning_rate": 2.0605263157894737e-05,
841
+ "loss": 0.2855,
842
+ "step": 1390
843
+ },
844
+ {
845
+ "epoch": 0.26,
846
+ "learning_rate": 2.0526315789473685e-05,
847
+ "loss": 0.3003,
848
+ "step": 1400
849
+ },
850
+ {
851
+ "epoch": 0.26,
852
+ "learning_rate": 2.0447368421052634e-05,
853
+ "loss": 0.2889,
854
+ "step": 1410
855
+ },
856
+ {
857
+ "epoch": 0.27,
858
+ "learning_rate": 2.036842105263158e-05,
859
+ "loss": 0.2834,
860
+ "step": 1420
861
+ },
862
+ {
863
+ "epoch": 0.27,
864
+ "learning_rate": 2.0289473684210527e-05,
865
+ "loss": 0.2696,
866
+ "step": 1430
867
+ },
868
+ {
869
+ "epoch": 0.27,
870
+ "learning_rate": 2.0210526315789475e-05,
871
+ "loss": 0.289,
872
+ "step": 1440
873
+ },
874
+ {
875
+ "epoch": 0.27,
876
+ "learning_rate": 2.013157894736842e-05,
877
+ "loss": 0.2851,
878
+ "step": 1450
879
+ },
880
+ {
881
+ "epoch": 0.27,
882
+ "learning_rate": 2.0052631578947368e-05,
883
+ "loss": 0.2903,
884
+ "step": 1460
885
+ },
886
+ {
887
+ "epoch": 0.28,
888
+ "learning_rate": 1.9973684210526317e-05,
889
+ "loss": 0.2742,
890
+ "step": 1470
891
+ },
892
+ {
893
+ "epoch": 0.28,
894
+ "learning_rate": 1.989473684210526e-05,
895
+ "loss": 0.2775,
896
+ "step": 1480
897
+ },
898
+ {
899
+ "epoch": 0.28,
900
+ "learning_rate": 1.9815789473684213e-05,
901
+ "loss": 0.2783,
902
+ "step": 1490
903
+ },
904
+ {
905
+ "epoch": 0.28,
906
+ "learning_rate": 1.9736842105263158e-05,
907
+ "loss": 0.2814,
908
+ "step": 1500
909
+ },
910
+ {
911
+ "epoch": 0.28,
912
+ "learning_rate": 1.9657894736842106e-05,
913
+ "loss": 0.2931,
914
+ "step": 1510
915
+ },
916
+ {
917
+ "epoch": 0.28,
918
+ "learning_rate": 1.9578947368421055e-05,
919
+ "loss": 0.2811,
920
+ "step": 1520
921
+ },
922
+ {
923
+ "epoch": 0.29,
924
+ "learning_rate": 1.95e-05,
925
+ "loss": 0.29,
926
+ "step": 1530
927
+ },
928
+ {
929
+ "epoch": 0.29,
930
+ "learning_rate": 1.9421052631578948e-05,
931
+ "loss": 0.2925,
932
+ "step": 1540
933
+ },
934
+ {
935
+ "epoch": 0.29,
936
+ "learning_rate": 1.9342105263157896e-05,
937
+ "loss": 0.2658,
938
+ "step": 1550
939
+ },
940
+ {
941
+ "epoch": 0.29,
942
+ "learning_rate": 1.926315789473684e-05,
943
+ "loss": 0.2959,
944
+ "step": 1560
945
+ },
946
+ {
947
+ "epoch": 0.29,
948
+ "learning_rate": 1.918421052631579e-05,
949
+ "loss": 0.2695,
950
+ "step": 1570
951
+ },
952
+ {
953
+ "epoch": 0.3,
954
+ "learning_rate": 1.9105263157894738e-05,
955
+ "loss": 0.2902,
956
+ "step": 1580
957
+ },
958
+ {
959
+ "epoch": 0.3,
960
+ "learning_rate": 1.9026315789473683e-05,
961
+ "loss": 0.2597,
962
+ "step": 1590
963
+ },
964
+ {
965
+ "epoch": 0.3,
966
+ "learning_rate": 1.894736842105263e-05,
967
+ "loss": 0.2745,
968
+ "step": 1600
969
+ },
970
+ {
971
+ "epoch": 0.3,
972
+ "learning_rate": 1.886842105263158e-05,
973
+ "loss": 0.2775,
974
+ "step": 1610
975
+ },
976
+ {
977
+ "epoch": 0.3,
978
+ "learning_rate": 1.8789473684210524e-05,
979
+ "loss": 0.2707,
980
+ "step": 1620
981
+ },
982
+ {
983
+ "epoch": 0.31,
984
+ "learning_rate": 1.8710526315789476e-05,
985
+ "loss": 0.2699,
986
+ "step": 1630
987
+ },
988
+ {
989
+ "epoch": 0.31,
990
+ "learning_rate": 1.8631578947368424e-05,
991
+ "loss": 0.2762,
992
+ "step": 1640
993
+ },
994
+ {
995
+ "epoch": 0.31,
996
+ "learning_rate": 1.855263157894737e-05,
997
+ "loss": 0.2539,
998
+ "step": 1650
999
+ },
1000
+ {
1001
+ "epoch": 0.31,
1002
+ "learning_rate": 1.8473684210526317e-05,
1003
+ "loss": 0.273,
1004
+ "step": 1660
1005
+ },
1006
+ {
1007
+ "epoch": 0.31,
1008
+ "learning_rate": 1.8394736842105266e-05,
1009
+ "loss": 0.244,
1010
+ "step": 1670
1011
+ },
1012
+ {
1013
+ "epoch": 0.31,
1014
+ "learning_rate": 1.831578947368421e-05,
1015
+ "loss": 0.2632,
1016
+ "step": 1680
1017
+ },
1018
+ {
1019
+ "epoch": 0.32,
1020
+ "learning_rate": 1.823684210526316e-05,
1021
+ "loss": 0.2756,
1022
+ "step": 1690
1023
+ },
1024
+ {
1025
+ "epoch": 0.32,
1026
+ "learning_rate": 1.8157894736842107e-05,
1027
+ "loss": 0.2555,
1028
+ "step": 1700
1029
+ },
1030
+ {
1031
+ "epoch": 0.32,
1032
+ "learning_rate": 1.8078947368421052e-05,
1033
+ "loss": 0.2863,
1034
+ "step": 1710
1035
+ },
1036
+ {
1037
+ "epoch": 0.32,
1038
+ "learning_rate": 1.8e-05,
1039
+ "loss": 0.2516,
1040
+ "step": 1720
1041
+ },
1042
+ {
1043
+ "epoch": 0.32,
1044
+ "learning_rate": 1.7921052631578945e-05,
1045
+ "loss": 0.2467,
1046
+ "step": 1730
1047
+ },
1048
+ {
1049
+ "epoch": 0.33,
1050
+ "learning_rate": 1.7842105263157894e-05,
1051
+ "loss": 0.2591,
1052
+ "step": 1740
1053
+ },
1054
+ {
1055
+ "epoch": 0.33,
1056
+ "learning_rate": 1.7763157894736842e-05,
1057
+ "loss": 0.2641,
1058
+ "step": 1750
1059
+ },
1060
+ {
1061
+ "epoch": 0.33,
1062
+ "learning_rate": 1.7684210526315787e-05,
1063
+ "loss": 0.2658,
1064
+ "step": 1760
1065
+ },
1066
+ {
1067
+ "epoch": 0.33,
1068
+ "learning_rate": 1.760526315789474e-05,
1069
+ "loss": 0.252,
1070
+ "step": 1770
1071
+ },
1072
+ {
1073
+ "epoch": 0.33,
1074
+ "learning_rate": 1.7526315789473687e-05,
1075
+ "loss": 0.2654,
1076
+ "step": 1780
1077
+ },
1078
+ {
1079
+ "epoch": 0.34,
1080
+ "learning_rate": 1.7447368421052632e-05,
1081
+ "loss": 0.2723,
1082
+ "step": 1790
1083
+ },
1084
+ {
1085
+ "epoch": 0.34,
1086
+ "learning_rate": 1.736842105263158e-05,
1087
+ "loss": 0.2716,
1088
+ "step": 1800
1089
+ },
1090
+ {
1091
+ "epoch": 0.34,
1092
+ "learning_rate": 1.728947368421053e-05,
1093
+ "loss": 0.2741,
1094
+ "step": 1810
1095
+ },
1096
+ {
1097
+ "epoch": 0.34,
1098
+ "learning_rate": 1.7210526315789473e-05,
1099
+ "loss": 0.2708,
1100
+ "step": 1820
1101
+ },
1102
+ {
1103
+ "epoch": 0.34,
1104
+ "learning_rate": 1.713157894736842e-05,
1105
+ "loss": 0.2484,
1106
+ "step": 1830
1107
+ },
1108
+ {
1109
+ "epoch": 0.34,
1110
+ "learning_rate": 1.705263157894737e-05,
1111
+ "loss": 0.2615,
1112
+ "step": 1840
1113
+ },
1114
+ {
1115
+ "epoch": 0.35,
1116
+ "learning_rate": 1.6973684210526315e-05,
1117
+ "loss": 0.2547,
1118
+ "step": 1850
1119
+ },
1120
+ {
1121
+ "epoch": 0.35,
1122
+ "learning_rate": 1.6894736842105263e-05,
1123
+ "loss": 0.264,
1124
+ "step": 1860
1125
+ },
1126
+ {
1127
+ "epoch": 0.35,
1128
+ "learning_rate": 1.681578947368421e-05,
1129
+ "loss": 0.2514,
1130
+ "step": 1870
1131
+ },
1132
+ {
1133
+ "epoch": 0.35,
1134
+ "learning_rate": 1.6736842105263156e-05,
1135
+ "loss": 0.2385,
1136
+ "step": 1880
1137
+ },
1138
+ {
1139
+ "epoch": 0.35,
1140
+ "learning_rate": 1.6657894736842105e-05,
1141
+ "loss": 0.2539,
1142
+ "step": 1890
1143
+ },
1144
+ {
1145
+ "epoch": 0.36,
1146
+ "learning_rate": 1.6578947368421053e-05,
1147
+ "loss": 0.24,
1148
+ "step": 1900
1149
+ },
1150
+ {
1151
+ "epoch": 0.36,
1152
+ "learning_rate": 1.65e-05,
1153
+ "loss": 0.2509,
1154
+ "step": 1910
1155
+ },
1156
+ {
1157
+ "epoch": 0.36,
1158
+ "learning_rate": 1.642105263157895e-05,
1159
+ "loss": 0.2573,
1160
+ "step": 1920
1161
+ },
1162
+ {
1163
+ "epoch": 0.36,
1164
+ "learning_rate": 1.6342105263157894e-05,
1165
+ "loss": 0.2427,
1166
+ "step": 1930
1167
+ },
1168
+ {
1169
+ "epoch": 0.36,
1170
+ "learning_rate": 1.6263157894736843e-05,
1171
+ "loss": 0.2572,
1172
+ "step": 1940
1173
+ },
1174
+ {
1175
+ "epoch": 0.36,
1176
+ "learning_rate": 1.618421052631579e-05,
1177
+ "loss": 0.2522,
1178
+ "step": 1950
1179
+ },
1180
+ {
1181
+ "epoch": 0.37,
1182
+ "learning_rate": 1.6105263157894736e-05,
1183
+ "loss": 0.2553,
1184
+ "step": 1960
1185
+ },
1186
+ {
1187
+ "epoch": 0.37,
1188
+ "learning_rate": 1.6026315789473684e-05,
1189
+ "loss": 0.2436,
1190
+ "step": 1970
1191
+ },
1192
+ {
1193
+ "epoch": 0.37,
1194
+ "learning_rate": 1.5947368421052633e-05,
1195
+ "loss": 0.2572,
1196
+ "step": 1980
1197
+ },
1198
+ {
1199
+ "epoch": 0.37,
1200
+ "learning_rate": 1.5868421052631578e-05,
1201
+ "loss": 0.2541,
1202
+ "step": 1990
1203
+ },
1204
+ {
1205
+ "epoch": 0.37,
1206
+ "learning_rate": 1.5789473684210526e-05,
1207
+ "loss": 0.2417,
1208
+ "step": 2000
1209
+ },
1210
+ {
1211
+ "epoch": 0.38,
1212
+ "learning_rate": 1.5710526315789474e-05,
1213
+ "loss": 0.2586,
1214
+ "step": 2010
1215
+ },
1216
+ {
1217
+ "epoch": 0.38,
1218
+ "learning_rate": 1.563157894736842e-05,
1219
+ "loss": 0.2383,
1220
+ "step": 2020
1221
+ },
1222
+ {
1223
+ "epoch": 0.38,
1224
+ "learning_rate": 1.5552631578947367e-05,
1225
+ "loss": 0.2497,
1226
+ "step": 2030
1227
+ },
1228
+ {
1229
+ "epoch": 0.38,
1230
+ "learning_rate": 1.547368421052632e-05,
1231
+ "loss": 0.2357,
1232
+ "step": 2040
1233
+ },
1234
+ {
1235
+ "epoch": 0.38,
1236
+ "learning_rate": 1.5394736842105264e-05,
1237
+ "loss": 0.26,
1238
+ "step": 2050
1239
+ },
1240
+ {
1241
+ "epoch": 0.39,
1242
+ "learning_rate": 1.5315789473684212e-05,
1243
+ "loss": 0.2442,
1244
+ "step": 2060
1245
+ },
1246
+ {
1247
+ "epoch": 0.39,
1248
+ "learning_rate": 1.5236842105263159e-05,
1249
+ "loss": 0.2269,
1250
+ "step": 2070
1251
+ },
1252
+ {
1253
+ "epoch": 0.39,
1254
+ "learning_rate": 1.5157894736842105e-05,
1255
+ "loss": 0.2419,
1256
+ "step": 2080
1257
+ },
1258
+ {
1259
+ "epoch": 0.39,
1260
+ "learning_rate": 1.5078947368421054e-05,
1261
+ "loss": 0.2442,
1262
+ "step": 2090
1263
+ },
1264
+ {
1265
+ "epoch": 0.39,
1266
+ "learning_rate": 1.5e-05,
1267
+ "loss": 0.2331,
1268
+ "step": 2100
1269
+ },
1270
+ {
1271
+ "epoch": 0.39,
1272
+ "learning_rate": 1.4921052631578947e-05,
1273
+ "loss": 0.2311,
1274
+ "step": 2110
1275
+ },
1276
+ {
1277
+ "epoch": 0.4,
1278
+ "learning_rate": 1.4842105263157895e-05,
1279
+ "loss": 0.2444,
1280
+ "step": 2120
1281
+ },
1282
+ {
1283
+ "epoch": 0.4,
1284
+ "learning_rate": 1.4763157894736842e-05,
1285
+ "loss": 0.2409,
1286
+ "step": 2130
1287
+ },
1288
+ {
1289
+ "epoch": 0.4,
1290
+ "learning_rate": 1.468421052631579e-05,
1291
+ "loss": 0.2365,
1292
+ "step": 2140
1293
+ },
1294
+ {
1295
+ "epoch": 0.4,
1296
+ "learning_rate": 1.4605263157894737e-05,
1297
+ "loss": 0.2517,
1298
+ "step": 2150
1299
+ },
1300
+ {
1301
+ "epoch": 0.4,
1302
+ "learning_rate": 1.4526315789473685e-05,
1303
+ "loss": 0.2562,
1304
+ "step": 2160
1305
+ },
1306
+ {
1307
+ "epoch": 0.41,
1308
+ "learning_rate": 1.4447368421052632e-05,
1309
+ "loss": 0.2233,
1310
+ "step": 2170
1311
+ },
1312
+ {
1313
+ "epoch": 0.41,
1314
+ "learning_rate": 1.4368421052631578e-05,
1315
+ "loss": 0.2496,
1316
+ "step": 2180
1317
+ },
1318
+ {
1319
+ "epoch": 0.41,
1320
+ "learning_rate": 1.4289473684210527e-05,
1321
+ "loss": 0.2452,
1322
+ "step": 2190
1323
+ },
1324
+ {
1325
+ "epoch": 0.41,
1326
+ "learning_rate": 1.4210526315789473e-05,
1327
+ "loss": 0.2374,
1328
+ "step": 2200
1329
+ },
1330
+ {
1331
+ "epoch": 0.41,
1332
+ "learning_rate": 1.4131578947368422e-05,
1333
+ "loss": 0.2233,
1334
+ "step": 2210
1335
+ },
1336
+ {
1337
+ "epoch": 0.42,
1338
+ "learning_rate": 1.405263157894737e-05,
1339
+ "loss": 0.2571,
1340
+ "step": 2220
1341
+ },
1342
+ {
1343
+ "epoch": 0.42,
1344
+ "learning_rate": 1.3973684210526316e-05,
1345
+ "loss": 0.2254,
1346
+ "step": 2230
1347
+ },
1348
+ {
1349
+ "epoch": 0.42,
1350
+ "learning_rate": 1.3894736842105263e-05,
1351
+ "loss": 0.2236,
1352
+ "step": 2240
1353
+ },
1354
+ {
1355
+ "epoch": 0.42,
1356
+ "learning_rate": 1.3815789473684211e-05,
1357
+ "loss": 0.2284,
1358
+ "step": 2250
1359
+ },
1360
+ {
1361
+ "epoch": 0.42,
1362
+ "learning_rate": 1.3736842105263158e-05,
1363
+ "loss": 0.232,
1364
+ "step": 2260
1365
+ },
1366
+ {
1367
+ "epoch": 0.42,
1368
+ "learning_rate": 1.3657894736842106e-05,
1369
+ "loss": 0.2415,
1370
+ "step": 2270
1371
+ },
1372
+ {
1373
+ "epoch": 0.43,
1374
+ "learning_rate": 1.3578947368421053e-05,
1375
+ "loss": 0.2244,
1376
+ "step": 2280
1377
+ },
1378
+ {
1379
+ "epoch": 0.43,
1380
+ "learning_rate": 1.3500000000000001e-05,
1381
+ "loss": 0.2338,
1382
+ "step": 2290
1383
+ },
1384
+ {
1385
+ "epoch": 0.43,
1386
+ "learning_rate": 1.3421052631578948e-05,
1387
+ "loss": 0.2382,
1388
+ "step": 2300
1389
+ },
1390
+ {
1391
+ "epoch": 0.43,
1392
+ "learning_rate": 1.3342105263157894e-05,
1393
+ "loss": 0.2349,
1394
+ "step": 2310
1395
+ },
1396
+ {
1397
+ "epoch": 0.43,
1398
+ "learning_rate": 1.3263157894736843e-05,
1399
+ "loss": 0.2267,
1400
+ "step": 2320
1401
+ },
1402
+ {
1403
+ "epoch": 0.44,
1404
+ "learning_rate": 1.318421052631579e-05,
1405
+ "loss": 0.2426,
1406
+ "step": 2330
1407
+ },
1408
+ {
1409
+ "epoch": 0.44,
1410
+ "learning_rate": 1.3105263157894738e-05,
1411
+ "loss": 0.238,
1412
+ "step": 2340
1413
+ },
1414
+ {
1415
+ "epoch": 0.44,
1416
+ "learning_rate": 1.3026315789473684e-05,
1417
+ "loss": 0.2332,
1418
+ "step": 2350
1419
+ },
1420
+ {
1421
+ "epoch": 0.44,
1422
+ "learning_rate": 1.2947368421052633e-05,
1423
+ "loss": 0.2332,
1424
+ "step": 2360
1425
+ },
1426
+ {
1427
+ "epoch": 0.44,
1428
+ "learning_rate": 1.2868421052631579e-05,
1429
+ "loss": 0.2477,
1430
+ "step": 2370
1431
+ },
1432
+ {
1433
+ "epoch": 0.45,
1434
+ "learning_rate": 1.2789473684210526e-05,
1435
+ "loss": 0.2176,
1436
+ "step": 2380
1437
+ },
1438
+ {
1439
+ "epoch": 0.45,
1440
+ "learning_rate": 1.2710526315789474e-05,
1441
+ "loss": 0.2177,
1442
+ "step": 2390
1443
+ },
1444
+ {
1445
+ "epoch": 0.45,
1446
+ "learning_rate": 1.263157894736842e-05,
1447
+ "loss": 0.2278,
1448
+ "step": 2400
1449
+ },
1450
+ {
1451
+ "epoch": 0.45,
1452
+ "learning_rate": 1.2552631578947369e-05,
1453
+ "loss": 0.2221,
1454
+ "step": 2410
1455
+ },
1456
+ {
1457
+ "epoch": 0.45,
1458
+ "learning_rate": 1.2473684210526317e-05,
1459
+ "loss": 0.2173,
1460
+ "step": 2420
1461
+ },
1462
+ {
1463
+ "epoch": 0.45,
1464
+ "learning_rate": 1.2394736842105264e-05,
1465
+ "loss": 0.2131,
1466
+ "step": 2430
1467
+ },
1468
+ {
1469
+ "epoch": 0.46,
1470
+ "learning_rate": 1.231578947368421e-05,
1471
+ "loss": 0.2346,
1472
+ "step": 2440
1473
+ },
1474
+ {
1475
+ "epoch": 0.46,
1476
+ "learning_rate": 1.2236842105263159e-05,
1477
+ "loss": 0.2301,
1478
+ "step": 2450
1479
+ },
1480
+ {
1481
+ "epoch": 0.46,
1482
+ "learning_rate": 1.2157894736842105e-05,
1483
+ "loss": 0.2173,
1484
+ "step": 2460
1485
+ },
1486
+ {
1487
+ "epoch": 0.46,
1488
+ "learning_rate": 1.2078947368421052e-05,
1489
+ "loss": 0.2297,
1490
+ "step": 2470
1491
+ },
1492
+ {
1493
+ "epoch": 0.46,
1494
+ "learning_rate": 1.2e-05,
1495
+ "loss": 0.2255,
1496
+ "step": 2480
1497
+ },
1498
+ {
1499
+ "epoch": 0.47,
1500
+ "learning_rate": 1.1921052631578949e-05,
1501
+ "loss": 0.2307,
1502
+ "step": 2490
1503
+ },
1504
+ {
1505
+ "epoch": 0.47,
1506
+ "learning_rate": 1.1842105263157895e-05,
1507
+ "loss": 0.222,
1508
+ "step": 2500
1509
+ },
1510
+ {
1511
+ "epoch": 0.47,
1512
+ "learning_rate": 1.1763157894736842e-05,
1513
+ "loss": 0.2319,
1514
+ "step": 2510
1515
+ },
1516
+ {
1517
+ "epoch": 0.47,
1518
+ "learning_rate": 1.168421052631579e-05,
1519
+ "loss": 0.228,
1520
+ "step": 2520
1521
+ },
1522
+ {
1523
+ "epoch": 0.47,
1524
+ "learning_rate": 1.1605263157894737e-05,
1525
+ "loss": 0.2267,
1526
+ "step": 2530
1527
+ },
1528
+ {
1529
+ "epoch": 0.48,
1530
+ "learning_rate": 1.1526315789473683e-05,
1531
+ "loss": 0.2163,
1532
+ "step": 2540
1533
+ },
1534
+ {
1535
+ "epoch": 0.48,
1536
+ "learning_rate": 1.1447368421052632e-05,
1537
+ "loss": 0.2167,
1538
+ "step": 2550
1539
+ },
1540
+ {
1541
+ "epoch": 0.48,
1542
+ "learning_rate": 1.136842105263158e-05,
1543
+ "loss": 0.1991,
1544
+ "step": 2560
1545
+ },
1546
+ {
1547
+ "epoch": 0.48,
1548
+ "learning_rate": 1.1289473684210527e-05,
1549
+ "loss": 0.2165,
1550
+ "step": 2570
1551
+ },
1552
+ {
1553
+ "epoch": 0.48,
1554
+ "learning_rate": 1.1210526315789473e-05,
1555
+ "loss": 0.2147,
1556
+ "step": 2580
1557
+ },
1558
+ {
1559
+ "epoch": 0.48,
1560
+ "learning_rate": 1.1131578947368421e-05,
1561
+ "loss": 0.2203,
1562
+ "step": 2590
1563
+ },
1564
+ {
1565
+ "epoch": 0.49,
1566
+ "learning_rate": 1.1052631578947368e-05,
1567
+ "loss": 0.2253,
1568
+ "step": 2600
1569
+ },
1570
+ {
1571
+ "epoch": 0.49,
1572
+ "learning_rate": 1.0973684210526316e-05,
1573
+ "loss": 0.2326,
1574
+ "step": 2610
1575
+ },
1576
+ {
1577
+ "epoch": 0.49,
1578
+ "learning_rate": 1.0894736842105265e-05,
1579
+ "loss": 0.221,
1580
+ "step": 2620
1581
+ },
1582
+ {
1583
+ "epoch": 0.49,
1584
+ "learning_rate": 1.0815789473684211e-05,
1585
+ "loss": 0.2233,
1586
+ "step": 2630
1587
+ },
1588
+ {
1589
+ "epoch": 0.49,
1590
+ "learning_rate": 1.0736842105263158e-05,
1591
+ "loss": 0.2199,
1592
+ "step": 2640
1593
+ },
1594
+ {
1595
+ "epoch": 0.5,
1596
+ "learning_rate": 1.0657894736842106e-05,
1597
+ "loss": 0.2077,
1598
+ "step": 2650
1599
+ },
1600
+ {
1601
+ "epoch": 0.5,
1602
+ "learning_rate": 1.0578947368421053e-05,
1603
+ "loss": 0.2108,
1604
+ "step": 2660
1605
+ },
1606
+ {
1607
+ "epoch": 0.5,
1608
+ "learning_rate": 1.05e-05,
1609
+ "loss": 0.2217,
1610
+ "step": 2670
1611
+ },
1612
+ {
1613
+ "epoch": 0.5,
1614
+ "learning_rate": 1.0421052631578948e-05,
1615
+ "loss": 0.2067,
1616
+ "step": 2680
1617
+ },
1618
+ {
1619
+ "epoch": 0.5,
1620
+ "learning_rate": 1.0342105263157896e-05,
1621
+ "loss": 0.2351,
1622
+ "step": 2690
1623
+ },
1624
+ {
1625
+ "epoch": 0.51,
1626
+ "learning_rate": 1.0263157894736843e-05,
1627
+ "loss": 0.1952,
1628
+ "step": 2700
1629
+ },
1630
+ {
1631
+ "epoch": 0.51,
1632
+ "learning_rate": 1.018421052631579e-05,
1633
+ "loss": 0.2259,
1634
+ "step": 2710
1635
+ },
1636
+ {
1637
+ "epoch": 0.51,
1638
+ "learning_rate": 1.0105263157894738e-05,
1639
+ "loss": 0.2074,
1640
+ "step": 2720
1641
+ },
1642
+ {
1643
+ "epoch": 0.51,
1644
+ "learning_rate": 1.0026315789473684e-05,
1645
+ "loss": 0.1963,
1646
+ "step": 2730
1647
+ },
1648
+ {
1649
+ "epoch": 0.51,
1650
+ "learning_rate": 9.94736842105263e-06,
1651
+ "loss": 0.2193,
1652
+ "step": 2740
1653
+ },
1654
+ {
1655
+ "epoch": 0.51,
1656
+ "learning_rate": 9.868421052631579e-06,
1657
+ "loss": 0.2172,
1658
+ "step": 2750
1659
+ },
1660
+ {
1661
+ "epoch": 0.52,
1662
+ "learning_rate": 9.789473684210527e-06,
1663
+ "loss": 0.2278,
1664
+ "step": 2760
1665
+ },
1666
+ {
1667
+ "epoch": 0.52,
1668
+ "learning_rate": 9.710526315789474e-06,
1669
+ "loss": 0.1933,
1670
+ "step": 2770
1671
+ },
1672
+ {
1673
+ "epoch": 0.52,
1674
+ "learning_rate": 9.63157894736842e-06,
1675
+ "loss": 0.2177,
1676
+ "step": 2780
1677
+ },
1678
+ {
1679
+ "epoch": 0.52,
1680
+ "learning_rate": 9.552631578947369e-06,
1681
+ "loss": 0.204,
1682
+ "step": 2790
1683
+ },
1684
+ {
1685
+ "epoch": 0.52,
1686
+ "learning_rate": 9.473684210526315e-06,
1687
+ "loss": 0.2178,
1688
+ "step": 2800
1689
+ },
1690
+ {
1691
+ "epoch": 0.53,
1692
+ "learning_rate": 9.394736842105262e-06,
1693
+ "loss": 0.2012,
1694
+ "step": 2810
1695
+ },
1696
+ {
1697
+ "epoch": 0.53,
1698
+ "learning_rate": 9.315789473684212e-06,
1699
+ "loss": 0.2054,
1700
+ "step": 2820
1701
+ },
1702
+ {
1703
+ "epoch": 0.53,
1704
+ "learning_rate": 9.236842105263159e-06,
1705
+ "loss": 0.2067,
1706
+ "step": 2830
1707
+ },
1708
+ {
1709
+ "epoch": 0.53,
1710
+ "learning_rate": 9.157894736842105e-06,
1711
+ "loss": 0.2132,
1712
+ "step": 2840
1713
+ },
1714
+ {
1715
+ "epoch": 0.53,
1716
+ "learning_rate": 9.078947368421054e-06,
1717
+ "loss": 0.2081,
1718
+ "step": 2850
1719
+ },
1720
+ {
1721
+ "epoch": 0.54,
1722
+ "learning_rate": 9e-06,
1723
+ "loss": 0.2033,
1724
+ "step": 2860
1725
+ },
1726
+ {
1727
+ "epoch": 0.54,
1728
+ "learning_rate": 8.921052631578947e-06,
1729
+ "loss": 0.2158,
1730
+ "step": 2870
1731
+ },
1732
+ {
1733
+ "epoch": 0.54,
1734
+ "learning_rate": 8.842105263157893e-06,
1735
+ "loss": 0.2043,
1736
+ "step": 2880
1737
+ },
1738
+ {
1739
+ "epoch": 0.54,
1740
+ "learning_rate": 8.763157894736843e-06,
1741
+ "loss": 0.1979,
1742
+ "step": 2890
1743
+ },
1744
+ {
1745
+ "epoch": 0.54,
1746
+ "learning_rate": 8.68421052631579e-06,
1747
+ "loss": 0.213,
1748
+ "step": 2900
1749
+ },
1750
+ {
1751
+ "epoch": 0.54,
1752
+ "learning_rate": 8.605263157894737e-06,
1753
+ "loss": 0.2042,
1754
+ "step": 2910
1755
+ },
1756
+ {
1757
+ "epoch": 0.55,
1758
+ "learning_rate": 8.526315789473685e-06,
1759
+ "loss": 0.2067,
1760
+ "step": 2920
1761
+ },
1762
+ {
1763
+ "epoch": 0.55,
1764
+ "learning_rate": 8.447368421052632e-06,
1765
+ "loss": 0.2052,
1766
+ "step": 2930
1767
+ },
1768
+ {
1769
+ "epoch": 0.55,
1770
+ "learning_rate": 8.368421052631578e-06,
1771
+ "loss": 0.2036,
1772
+ "step": 2940
1773
+ },
1774
+ {
1775
+ "epoch": 0.55,
1776
+ "learning_rate": 8.289473684210526e-06,
1777
+ "loss": 0.2224,
1778
+ "step": 2950
1779
+ },
1780
+ {
1781
+ "epoch": 0.55,
1782
+ "learning_rate": 8.210526315789475e-06,
1783
+ "loss": 0.2106,
1784
+ "step": 2960
1785
+ },
1786
+ {
1787
+ "epoch": 0.56,
1788
+ "learning_rate": 8.131578947368421e-06,
1789
+ "loss": 0.1956,
1790
+ "step": 2970
1791
+ },
1792
+ {
1793
+ "epoch": 0.56,
1794
+ "learning_rate": 8.052631578947368e-06,
1795
+ "loss": 0.1973,
1796
+ "step": 2980
1797
+ },
1798
+ {
1799
+ "epoch": 0.56,
1800
+ "learning_rate": 7.973684210526316e-06,
1801
+ "loss": 0.2103,
1802
+ "step": 2990
1803
+ },
1804
+ {
1805
+ "epoch": 0.56,
1806
+ "learning_rate": 7.894736842105263e-06,
1807
+ "loss": 0.2011,
1808
+ "step": 3000
1809
+ },
1810
+ {
1811
+ "epoch": 0.56,
1812
+ "learning_rate": 7.81578947368421e-06,
1813
+ "loss": 0.2085,
1814
+ "step": 3010
1815
+ },
1816
+ {
1817
+ "epoch": 0.57,
1818
+ "learning_rate": 7.73684210526316e-06,
1819
+ "loss": 0.2042,
1820
+ "step": 3020
1821
+ },
1822
+ {
1823
+ "epoch": 0.57,
1824
+ "learning_rate": 7.657894736842106e-06,
1825
+ "loss": 0.2123,
1826
+ "step": 3030
1827
+ },
1828
+ {
1829
+ "epoch": 0.57,
1830
+ "learning_rate": 7.578947368421053e-06,
1831
+ "loss": 0.1853,
1832
+ "step": 3040
1833
+ },
1834
+ {
1835
+ "epoch": 0.57,
1836
+ "learning_rate": 7.5e-06,
1837
+ "loss": 0.1943,
1838
+ "step": 3050
1839
+ },
1840
+ {
1841
+ "epoch": 0.57,
1842
+ "learning_rate": 7.421052631578948e-06,
1843
+ "loss": 0.2049,
1844
+ "step": 3060
1845
+ },
1846
+ {
1847
+ "epoch": 0.57,
1848
+ "learning_rate": 7.342105263157895e-06,
1849
+ "loss": 0.1986,
1850
+ "step": 3070
1851
+ },
1852
+ {
1853
+ "epoch": 0.58,
1854
+ "learning_rate": 7.2631578947368426e-06,
1855
+ "loss": 0.1912,
1856
+ "step": 3080
1857
+ },
1858
+ {
1859
+ "epoch": 0.58,
1860
+ "learning_rate": 7.184210526315789e-06,
1861
+ "loss": 0.2061,
1862
+ "step": 3090
1863
+ },
1864
+ {
1865
+ "epoch": 0.58,
1866
+ "learning_rate": 7.105263157894737e-06,
1867
+ "loss": 0.1968,
1868
+ "step": 3100
1869
+ },
1870
+ {
1871
+ "epoch": 0.58,
1872
+ "learning_rate": 7.026315789473685e-06,
1873
+ "loss": 0.1827,
1874
+ "step": 3110
1875
+ },
1876
+ {
1877
+ "epoch": 0.58,
1878
+ "learning_rate": 6.9473684210526315e-06,
1879
+ "loss": 0.2016,
1880
+ "step": 3120
1881
+ },
1882
+ {
1883
+ "epoch": 0.59,
1884
+ "learning_rate": 6.868421052631579e-06,
1885
+ "loss": 0.2212,
1886
+ "step": 3130
1887
+ },
1888
+ {
1889
+ "epoch": 0.59,
1890
+ "learning_rate": 6.7894736842105264e-06,
1891
+ "loss": 0.2108,
1892
+ "step": 3140
1893
+ },
1894
+ {
1895
+ "epoch": 0.59,
1896
+ "learning_rate": 6.710526315789474e-06,
1897
+ "loss": 0.2121,
1898
+ "step": 3150
1899
+ },
1900
+ {
1901
+ "epoch": 0.59,
1902
+ "learning_rate": 6.631578947368421e-06,
1903
+ "loss": 0.1888,
1904
+ "step": 3160
1905
+ },
1906
+ {
1907
+ "epoch": 0.59,
1908
+ "learning_rate": 6.552631578947369e-06,
1909
+ "loss": 0.2018,
1910
+ "step": 3170
1911
+ },
1912
+ {
1913
+ "epoch": 0.6,
1914
+ "learning_rate": 6.473684210526316e-06,
1915
+ "loss": 0.2049,
1916
+ "step": 3180
1917
+ },
1918
+ {
1919
+ "epoch": 0.6,
1920
+ "learning_rate": 6.394736842105263e-06,
1921
+ "loss": 0.2084,
1922
+ "step": 3190
1923
+ },
1924
+ {
1925
+ "epoch": 0.6,
1926
+ "learning_rate": 6.31578947368421e-06,
1927
+ "loss": 0.188,
1928
+ "step": 3200
1929
+ },
1930
+ {
1931
+ "epoch": 0.6,
1932
+ "learning_rate": 6.236842105263159e-06,
1933
+ "loss": 0.1863,
1934
+ "step": 3210
1935
+ },
1936
+ {
1937
+ "epoch": 0.6,
1938
+ "learning_rate": 6.157894736842105e-06,
1939
+ "loss": 0.2082,
1940
+ "step": 3220
1941
+ },
1942
+ {
1943
+ "epoch": 0.6,
1944
+ "learning_rate": 6.078947368421053e-06,
1945
+ "loss": 0.2047,
1946
+ "step": 3230
1947
+ },
1948
+ {
1949
+ "epoch": 0.61,
1950
+ "learning_rate": 6e-06,
1951
+ "loss": 0.208,
1952
+ "step": 3240
1953
+ },
1954
+ {
1955
+ "epoch": 0.61,
1956
+ "learning_rate": 5.921052631578948e-06,
1957
+ "loss": 0.2067,
1958
+ "step": 3250
1959
+ },
1960
+ {
1961
+ "epoch": 0.61,
1962
+ "learning_rate": 5.842105263157895e-06,
1963
+ "loss": 0.2032,
1964
+ "step": 3260
1965
+ },
1966
+ {
1967
+ "epoch": 0.61,
1968
+ "learning_rate": 5.763157894736842e-06,
1969
+ "loss": 0.1891,
1970
+ "step": 3270
1971
+ },
1972
+ {
1973
+ "epoch": 0.61,
1974
+ "learning_rate": 5.68421052631579e-06,
1975
+ "loss": 0.176,
1976
+ "step": 3280
1977
+ },
1978
+ {
1979
+ "epoch": 0.62,
1980
+ "learning_rate": 5.605263157894737e-06,
1981
+ "loss": 0.2063,
1982
+ "step": 3290
1983
+ },
1984
+ {
1985
+ "epoch": 0.62,
1986
+ "learning_rate": 5.526315789473684e-06,
1987
+ "loss": 0.2006,
1988
+ "step": 3300
1989
+ },
1990
+ {
1991
+ "epoch": 0.62,
1992
+ "learning_rate": 5.447368421052632e-06,
1993
+ "loss": 0.2016,
1994
+ "step": 3310
1995
+ },
1996
+ {
1997
+ "epoch": 0.62,
1998
+ "learning_rate": 5.368421052631579e-06,
1999
+ "loss": 0.1875,
2000
+ "step": 3320
2001
+ },
2002
+ {
2003
+ "epoch": 0.62,
2004
+ "learning_rate": 5.289473684210526e-06,
2005
+ "loss": 0.1951,
2006
+ "step": 3330
2007
+ },
2008
+ {
2009
+ "epoch": 0.63,
2010
+ "learning_rate": 5.210526315789474e-06,
2011
+ "loss": 0.2017,
2012
+ "step": 3340
2013
+ },
2014
+ {
2015
+ "epoch": 0.63,
2016
+ "learning_rate": 5.131578947368421e-06,
2017
+ "loss": 0.2072,
2018
+ "step": 3350
2019
+ },
2020
+ {
2021
+ "epoch": 0.63,
2022
+ "learning_rate": 5.052631578947369e-06,
2023
+ "loss": 0.1919,
2024
+ "step": 3360
2025
+ },
2026
+ {
2027
+ "epoch": 0.63,
2028
+ "learning_rate": 4.973684210526315e-06,
2029
+ "loss": 0.2072,
2030
+ "step": 3370
2031
+ },
2032
+ {
2033
+ "epoch": 0.63,
2034
+ "learning_rate": 4.894736842105264e-06,
2035
+ "loss": 0.1955,
2036
+ "step": 3380
2037
+ },
2038
+ {
2039
+ "epoch": 0.63,
2040
+ "learning_rate": 4.81578947368421e-06,
2041
+ "loss": 0.2037,
2042
+ "step": 3390
2043
+ },
2044
+ {
2045
+ "epoch": 0.64,
2046
+ "learning_rate": 4.736842105263158e-06,
2047
+ "loss": 0.1891,
2048
+ "step": 3400
2049
+ },
2050
+ {
2051
+ "epoch": 0.64,
2052
+ "learning_rate": 4.657894736842106e-06,
2053
+ "loss": 0.1814,
2054
+ "step": 3410
2055
+ },
2056
+ {
2057
+ "epoch": 0.64,
2058
+ "learning_rate": 4.578947368421053e-06,
2059
+ "loss": 0.1737,
2060
+ "step": 3420
2061
+ },
2062
+ {
2063
+ "epoch": 0.64,
2064
+ "learning_rate": 4.5e-06,
2065
+ "loss": 0.2123,
2066
+ "step": 3430
2067
+ },
2068
+ {
2069
+ "epoch": 0.64,
2070
+ "learning_rate": 4.421052631578947e-06,
2071
+ "loss": 0.1984,
2072
+ "step": 3440
2073
+ },
2074
+ {
2075
+ "epoch": 0.65,
2076
+ "learning_rate": 4.342105263157895e-06,
2077
+ "loss": 0.1857,
2078
+ "step": 3450
2079
+ },
2080
+ {
2081
+ "epoch": 0.65,
2082
+ "learning_rate": 4.2631578947368425e-06,
2083
+ "loss": 0.1855,
2084
+ "step": 3460
2085
+ },
2086
+ {
2087
+ "epoch": 0.65,
2088
+ "learning_rate": 4.184210526315789e-06,
2089
+ "loss": 0.1993,
2090
+ "step": 3470
2091
+ },
2092
+ {
2093
+ "epoch": 0.65,
2094
+ "learning_rate": 4.105263157894737e-06,
2095
+ "loss": 0.1951,
2096
+ "step": 3480
2097
+ },
2098
+ {
2099
+ "epoch": 0.65,
2100
+ "learning_rate": 4.026315789473684e-06,
2101
+ "loss": 0.1976,
2102
+ "step": 3490
2103
+ },
2104
+ {
2105
+ "epoch": 0.66,
2106
+ "learning_rate": 3.9473684210526315e-06,
2107
+ "loss": 0.1848,
2108
+ "step": 3500
2109
+ },
2110
+ {
2111
+ "epoch": 0.66,
2112
+ "learning_rate": 3.86842105263158e-06,
2113
+ "loss": 0.2031,
2114
+ "step": 3510
2115
+ },
2116
+ {
2117
+ "epoch": 0.66,
2118
+ "learning_rate": 3.7894736842105264e-06,
2119
+ "loss": 0.1773,
2120
+ "step": 3520
2121
+ },
2122
+ {
2123
+ "epoch": 0.66,
2124
+ "learning_rate": 3.710526315789474e-06,
2125
+ "loss": 0.1955,
2126
+ "step": 3530
2127
+ },
2128
+ {
2129
+ "epoch": 0.66,
2130
+ "learning_rate": 3.6315789473684213e-06,
2131
+ "loss": 0.1836,
2132
+ "step": 3540
2133
+ },
2134
+ {
2135
+ "epoch": 0.66,
2136
+ "learning_rate": 3.5526315789473683e-06,
2137
+ "loss": 0.199,
2138
+ "step": 3550
2139
+ },
2140
+ {
2141
+ "epoch": 0.67,
2142
+ "learning_rate": 3.4736842105263158e-06,
2143
+ "loss": 0.1827,
2144
+ "step": 3560
2145
+ },
2146
+ {
2147
+ "epoch": 0.67,
2148
+ "learning_rate": 3.3947368421052632e-06,
2149
+ "loss": 0.1917,
2150
+ "step": 3570
2151
+ },
2152
+ {
2153
+ "epoch": 0.67,
2154
+ "learning_rate": 3.3157894736842107e-06,
2155
+ "loss": 0.1849,
2156
+ "step": 3580
2157
+ },
2158
+ {
2159
+ "epoch": 0.67,
2160
+ "learning_rate": 3.236842105263158e-06,
2161
+ "loss": 0.1913,
2162
+ "step": 3590
2163
+ },
2164
+ {
2165
+ "epoch": 0.67,
2166
+ "learning_rate": 3.157894736842105e-06,
2167
+ "loss": 0.1822,
2168
+ "step": 3600
2169
+ },
2170
+ {
2171
+ "epoch": 0.68,
2172
+ "learning_rate": 3.0789473684210526e-06,
2173
+ "loss": 0.2005,
2174
+ "step": 3610
2175
+ },
2176
+ {
2177
+ "epoch": 0.68,
2178
+ "learning_rate": 3e-06,
2179
+ "loss": 0.1969,
2180
+ "step": 3620
2181
+ },
2182
+ {
2183
+ "epoch": 0.68,
2184
+ "learning_rate": 2.9210526315789475e-06,
2185
+ "loss": 0.184,
2186
+ "step": 3630
2187
+ },
2188
+ {
2189
+ "epoch": 0.68,
2190
+ "learning_rate": 2.842105263157895e-06,
2191
+ "loss": 0.1829,
2192
+ "step": 3640
2193
+ },
2194
+ {
2195
+ "epoch": 0.68,
2196
+ "learning_rate": 2.763157894736842e-06,
2197
+ "loss": 0.1856,
2198
+ "step": 3650
2199
+ },
2200
+ {
2201
+ "epoch": 0.69,
2202
+ "learning_rate": 2.6842105263157895e-06,
2203
+ "loss": 0.18,
2204
+ "step": 3660
2205
+ },
2206
+ {
2207
+ "epoch": 0.69,
2208
+ "learning_rate": 2.605263157894737e-06,
2209
+ "loss": 0.1794,
2210
+ "step": 3670
2211
+ },
2212
+ {
2213
+ "epoch": 0.69,
2214
+ "learning_rate": 2.5263157894736844e-06,
2215
+ "loss": 0.1892,
2216
+ "step": 3680
2217
+ },
2218
+ {
2219
+ "epoch": 0.69,
2220
+ "learning_rate": 2.447368421052632e-06,
2221
+ "loss": 0.1953,
2222
+ "step": 3690
2223
+ },
2224
+ {
2225
+ "epoch": 0.69,
2226
+ "learning_rate": 2.368421052631579e-06,
2227
+ "loss": 0.1996,
2228
+ "step": 3700
2229
+ },
2230
+ {
2231
+ "epoch": 0.69,
2232
+ "learning_rate": 2.2894736842105263e-06,
2233
+ "loss": 0.1781,
2234
+ "step": 3710
2235
+ },
2236
+ {
2237
+ "epoch": 0.7,
2238
+ "learning_rate": 2.2105263157894734e-06,
2239
+ "loss": 0.1884,
2240
+ "step": 3720
2241
+ },
2242
+ {
2243
+ "epoch": 0.7,
2244
+ "learning_rate": 2.1315789473684212e-06,
2245
+ "loss": 0.1829,
2246
+ "step": 3730
2247
+ },
2248
+ {
2249
+ "epoch": 0.7,
2250
+ "learning_rate": 2.0526315789473687e-06,
2251
+ "loss": 0.1853,
2252
+ "step": 3740
2253
+ },
2254
+ {
2255
+ "epoch": 0.7,
2256
+ "learning_rate": 1.9736842105263157e-06,
2257
+ "loss": 0.1999,
2258
+ "step": 3750
2259
+ },
2260
+ {
2261
+ "epoch": 0.7,
2262
+ "learning_rate": 1.8947368421052632e-06,
2263
+ "loss": 0.181,
2264
+ "step": 3760
2265
+ },
2266
+ {
2267
+ "epoch": 0.71,
2268
+ "learning_rate": 1.8157894736842106e-06,
2269
+ "loss": 0.1769,
2270
+ "step": 3770
2271
+ },
2272
+ {
2273
+ "epoch": 0.71,
2274
+ "learning_rate": 1.7368421052631579e-06,
2275
+ "loss": 0.1965,
2276
+ "step": 3780
2277
+ },
2278
+ {
2279
+ "epoch": 0.71,
2280
+ "learning_rate": 1.6578947368421053e-06,
2281
+ "loss": 0.1866,
2282
+ "step": 3790
2283
+ },
2284
+ {
2285
+ "epoch": 0.71,
2286
+ "learning_rate": 1.5789473684210526e-06,
2287
+ "loss": 0.1848,
2288
+ "step": 3800
2289
+ },
2290
+ {
2291
+ "epoch": 0.71,
2292
+ "learning_rate": 1.5e-06,
2293
+ "loss": 0.204,
2294
+ "step": 3810
2295
+ },
2296
+ {
2297
+ "epoch": 0.71,
2298
+ "learning_rate": 1.4210526315789475e-06,
2299
+ "loss": 0.1807,
2300
+ "step": 3820
2301
+ },
2302
+ {
2303
+ "epoch": 0.72,
2304
+ "learning_rate": 1.3421052631578947e-06,
2305
+ "loss": 0.1858,
2306
+ "step": 3830
2307
+ },
2308
+ {
2309
+ "epoch": 0.72,
2310
+ "learning_rate": 1.2631578947368422e-06,
2311
+ "loss": 0.1953,
2312
+ "step": 3840
2313
+ },
2314
+ {
2315
+ "epoch": 0.72,
2316
+ "learning_rate": 1.1842105263157894e-06,
2317
+ "loss": 0.1793,
2318
+ "step": 3850
2319
+ },
2320
+ {
2321
+ "epoch": 0.72,
2322
+ "learning_rate": 1.1052631578947367e-06,
2323
+ "loss": 0.1987,
2324
+ "step": 3860
2325
+ },
2326
+ {
2327
+ "epoch": 0.72,
2328
+ "learning_rate": 1.0263157894736843e-06,
2329
+ "loss": 0.1857,
2330
+ "step": 3870
2331
+ },
2332
+ {
2333
+ "epoch": 0.73,
2334
+ "learning_rate": 9.473684210526316e-07,
2335
+ "loss": 0.1767,
2336
+ "step": 3880
2337
+ },
2338
+ {
2339
+ "epoch": 0.73,
2340
+ "learning_rate": 8.684210526315789e-07,
2341
+ "loss": 0.1784,
2342
+ "step": 3890
2343
+ },
2344
+ {
2345
+ "epoch": 0.73,
2346
+ "learning_rate": 7.894736842105263e-07,
2347
+ "loss": 0.1657,
2348
+ "step": 3900
2349
+ },
2350
+ {
2351
+ "epoch": 0.73,
2352
+ "learning_rate": 7.105263157894737e-07,
2353
+ "loss": 0.1801,
2354
+ "step": 3910
2355
+ },
2356
+ {
2357
+ "epoch": 0.73,
2358
+ "learning_rate": 6.315789473684211e-07,
2359
+ "loss": 0.1853,
2360
+ "step": 3920
2361
+ },
2362
+ {
2363
+ "epoch": 0.74,
2364
+ "learning_rate": 5.526315789473683e-07,
2365
+ "loss": 0.1843,
2366
+ "step": 3930
2367
+ },
2368
+ {
2369
+ "epoch": 0.74,
2370
+ "learning_rate": 4.736842105263158e-07,
2371
+ "loss": 0.2039,
2372
+ "step": 3940
2373
+ },
2374
+ {
2375
+ "epoch": 0.74,
2376
+ "learning_rate": 3.9473684210526315e-07,
2377
+ "loss": 0.2031,
2378
+ "step": 3950
2379
+ },
2380
+ {
2381
+ "epoch": 0.74,
2382
+ "learning_rate": 3.1578947368421055e-07,
2383
+ "loss": 0.1851,
2384
+ "step": 3960
2385
+ },
2386
+ {
2387
+ "epoch": 0.74,
2388
+ "learning_rate": 2.368421052631579e-07,
2389
+ "loss": 0.1765,
2390
+ "step": 3970
2391
+ },
2392
+ {
2393
+ "epoch": 0.74,
2394
+ "learning_rate": 1.5789473684210527e-07,
2395
+ "loss": 0.1724,
2396
+ "step": 3980
2397
+ },
2398
+ {
2399
+ "epoch": 0.75,
2400
+ "learning_rate": 7.894736842105264e-08,
2401
+ "loss": 0.1824,
2402
+ "step": 3990
2403
+ },
2404
+ {
2405
+ "epoch": 0.75,
2406
+ "learning_rate": 0.0,
2407
+ "loss": 0.1716,
2408
+ "step": 4000
2409
+ }
2410
+ ],
2411
+ "max_steps": 4000,
2412
+ "num_train_epochs": 1,
2413
+ "total_flos": 0.0,
2414
+ "trial_name": null,
2415
+ "trial_params": null
2416
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:394c966a3916c2084bb3f658dc58658542e223e154512e859f162ceeb743539a
3
+ size 3640
vocab.json ADDED
The diff for this file is too large to render. See raw diff