Hugging Face's logo

EColi
/
sponsorblock-base-v1

Text2Text Generation
Transformers
PyTorch
t5
generated_from_trainer
Inference Endpoints
text-generation-inference
Model card Files Community
EColi commited on
Commit
7ca11af
•
1 Parent(s): 25e9a2c

Add files

Browse files
Files changed (11) hide show
  1. checkpoint-570000/added_tokens.json +1 -0
  2. checkpoint-570000/config.json +57 -0
  3. checkpoint-570000/pytorch_model.bin +3 -0
  4. checkpoint-570000/rng_state.pth +3 -0
  5. checkpoint-570000/scheduler.pt +3 -0
  6. checkpoint-570000/special_tokens_map.json +1 -0
  7. checkpoint-570000/spiece.model +3 -0
  8. checkpoint-570000/tokenizer.json +0 -0
  9. checkpoint-570000/tokenizer_config.json +1 -0
  10. checkpoint-570000/trainer_state.json +756 -0
  11. checkpoint-570000/training_args.bin +3 -0
checkpoint-570000/added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"PROFANITY_TOKEN": 32110, "NO_SEGMENT_TOKEN": 32111, "[Music]": 32107, "NUMBER_TOKEN": 32104, "URL_TOKEN": 32101, "HYPHENATED_URL_TOKEN": 32102, "BETWEEN_SEGMENTS_TOKEN": 32118, "NUMBER_PERCENTAGE_TOKEN": 32103, "SHORT_HYPHENATED_TOKEN": 32105, "[Laughter]": 32109, "START_INTERACTION_TOKEN": 32116, "END_INTERACTION_TOKEN": 32117, "[Applause]": 32108, "END_SPONSOR_TOKEN": 32113, "END_SELFPROMO_TOKEN": 32115, "LONG_WORD_TOKEN": 32106, "START_SELFPROMO_TOKEN": 32114, "EXTRACT_SEGMENTS: ": 32100, "START_SPONSOR_TOKEN": 32112}
checkpoint-570000/config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/1TB_SSD/SB_AI/out_orig2",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 3072,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dropout_rate": 0.1,
11
+ "eos_token_id": 1,
12
+ "feed_forward_proj": "relu",
13
+ "initializer_factor": 1.0,
14
+ "is_encoder_decoder": true,
15
+ "layer_norm_epsilon": 1e-06,
16
+ "model_type": "t5",
17
+ "n_positions": 512,
18
+ "num_decoder_layers": 12,
19
+ "num_heads": 12,
20
+ "num_layers": 12,
21
+ "output_past": true,
22
+ "pad_token_id": 0,
23
+ "relative_attention_num_buckets": 32,
24
+ "task_specific_params": {
25
+ "summarization": {
26
+ "early_stopping": true,
27
+ "length_penalty": 2.0,
28
+ "max_length": 200,
29
+ "min_length": 30,
30
+ "no_repeat_ngram_size": 3,
31
+ "num_beams": 4,
32
+ "prefix": "summarize: "
33
+ },
34
+ "translation_en_to_de": {
35
+ "early_stopping": true,
36
+ "max_length": 300,
37
+ "num_beams": 4,
38
+ "prefix": "translate English to German: "
39
+ },
40
+ "translation_en_to_fr": {
41
+ "early_stopping": true,
42
+ "max_length": 300,
43
+ "num_beams": 4,
44
+ "prefix": "translate English to French: "
45
+ },
46
+ "translation_en_to_ro": {
47
+ "early_stopping": true,
48
+ "max_length": 300,
49
+ "num_beams": 4,
50
+ "prefix": "translate English to Romanian: "
51
+ }
52
+ },
53
+ "torch_dtype": "float32",
54
+ "transformers_version": "4.15.0",
55
+ "use_cache": true,
56
+ "vocab_size": 32119
57
+ }
checkpoint-570000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c69e28f8e8c8fc81a5d4d9da1b2a1a755898ba4dcffe3bd3c598590a58c252b3
3
+ size 891703231
checkpoint-570000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75b97654688e6af009f0131110f142ee5988ac633699dd3da27022a4c7633bde
3
+ size 14439
checkpoint-570000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c30acca761c37aaf364be734568e10a882d259c787f1b2b36b20820f1e39028f
3
+ size 623
checkpoint-570000/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}
checkpoint-570000/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
checkpoint-570000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-570000/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "/1TB_SSD/SB_AI/out_orig2", "tokenizer_class": "T5Tokenizer"}
checkpoint-570000/trainer_state.json ADDED
@@ -0,0 +1,756 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.5104809805533613,
5
+ "global_step": 570000,
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": 4.977610483309063e-05,
13
+ "loss": 0.0854,
14
+ "step": 5000
15
+ },
16
+ {
17
+ "epoch": 0.01,
18
+ "learning_rate": 4.955220966618126e-05,
19
+ "loss": 0.0801,
20
+ "step": 10000
21
+ },
22
+ {
23
+ "epoch": 0.01,
24
+ "learning_rate": 4.9328314499271894e-05,
25
+ "loss": 0.082,
26
+ "step": 15000
27
+ },
28
+ {
29
+ "epoch": 0.02,
30
+ "learning_rate": 4.910441933236253e-05,
31
+ "loss": 0.0851,
32
+ "step": 20000
33
+ },
34
+ {
35
+ "epoch": 0.02,
36
+ "learning_rate": 4.8880524165453154e-05,
37
+ "loss": 0.0858,
38
+ "step": 25000
39
+ },
40
+ {
41
+ "epoch": 0.03,
42
+ "learning_rate": 4.865662899854379e-05,
43
+ "loss": 0.0777,
44
+ "step": 30000
45
+ },
46
+ {
47
+ "epoch": 0.03,
48
+ "learning_rate": 4.843273383163442e-05,
49
+ "loss": 0.0853,
50
+ "step": 35000
51
+ },
52
+ {
53
+ "epoch": 0.04,
54
+ "learning_rate": 4.8208838664725045e-05,
55
+ "loss": 0.0838,
56
+ "step": 40000
57
+ },
58
+ {
59
+ "epoch": 0.04,
60
+ "learning_rate": 4.798494349781568e-05,
61
+ "loss": 0.084,
62
+ "step": 45000
63
+ },
64
+ {
65
+ "epoch": 0.04,
66
+ "learning_rate": 4.776104833090631e-05,
67
+ "loss": 0.0794,
68
+ "step": 50000
69
+ },
70
+ {
71
+ "epoch": 0.05,
72
+ "learning_rate": 4.753715316399694e-05,
73
+ "loss": 0.0805,
74
+ "step": 55000
75
+ },
76
+ {
77
+ "epoch": 0.05,
78
+ "learning_rate": 4.7313257997087574e-05,
79
+ "loss": 0.0876,
80
+ "step": 60000
81
+ },
82
+ {
83
+ "epoch": 0.06,
84
+ "learning_rate": 4.708936283017821e-05,
85
+ "loss": 0.0773,
86
+ "step": 65000
87
+ },
88
+ {
89
+ "epoch": 0.06,
90
+ "learning_rate": 4.6865467663268834e-05,
91
+ "loss": 0.0846,
92
+ "step": 70000
93
+ },
94
+ {
95
+ "epoch": 0.07,
96
+ "learning_rate": 4.6641572496359465e-05,
97
+ "loss": 0.0867,
98
+ "step": 75000
99
+ },
100
+ {
101
+ "epoch": 0.07,
102
+ "eval_loss": 0.07421331852674484,
103
+ "eval_runtime": 1684.9579,
104
+ "eval_samples_per_second": 36.816,
105
+ "eval_steps_per_second": 36.816,
106
+ "step": 75000
107
+ },
108
+ {
109
+ "epoch": 0.07,
110
+ "learning_rate": 4.64176773294501e-05,
111
+ "loss": 0.0779,
112
+ "step": 80000
113
+ },
114
+ {
115
+ "epoch": 0.08,
116
+ "learning_rate": 4.6193782162540726e-05,
117
+ "loss": 0.0795,
118
+ "step": 85000
119
+ },
120
+ {
121
+ "epoch": 0.08,
122
+ "learning_rate": 4.596988699563136e-05,
123
+ "loss": 0.082,
124
+ "step": 90000
125
+ },
126
+ {
127
+ "epoch": 0.09,
128
+ "learning_rate": 4.574599182872199e-05,
129
+ "loss": 0.0821,
130
+ "step": 95000
131
+ },
132
+ {
133
+ "epoch": 0.09,
134
+ "learning_rate": 4.5522096661812623e-05,
135
+ "loss": 0.0787,
136
+ "step": 100000
137
+ },
138
+ {
139
+ "epoch": 0.09,
140
+ "learning_rate": 4.5298201494903254e-05,
141
+ "loss": 0.0803,
142
+ "step": 105000
143
+ },
144
+ {
145
+ "epoch": 0.1,
146
+ "learning_rate": 4.5074306327993884e-05,
147
+ "loss": 0.0788,
148
+ "step": 110000
149
+ },
150
+ {
151
+ "epoch": 0.1,
152
+ "learning_rate": 4.4850411161084515e-05,
153
+ "loss": 0.0822,
154
+ "step": 115000
155
+ },
156
+ {
157
+ "epoch": 0.11,
158
+ "learning_rate": 4.4626515994175145e-05,
159
+ "loss": 0.0782,
160
+ "step": 120000
161
+ },
162
+ {
163
+ "epoch": 0.11,
164
+ "learning_rate": 4.4402620827265775e-05,
165
+ "loss": 0.0804,
166
+ "step": 125000
167
+ },
168
+ {
169
+ "epoch": 0.12,
170
+ "learning_rate": 4.4178725660356406e-05,
171
+ "loss": 0.0778,
172
+ "step": 130000
173
+ },
174
+ {
175
+ "epoch": 0.12,
176
+ "learning_rate": 4.3954830493447036e-05,
177
+ "loss": 0.0772,
178
+ "step": 135000
179
+ },
180
+ {
181
+ "epoch": 0.13,
182
+ "learning_rate": 4.3730935326537667e-05,
183
+ "loss": 0.0819,
184
+ "step": 140000
185
+ },
186
+ {
187
+ "epoch": 0.13,
188
+ "learning_rate": 4.35070401596283e-05,
189
+ "loss": 0.0741,
190
+ "step": 145000
191
+ },
192
+ {
193
+ "epoch": 0.13,
194
+ "learning_rate": 4.3283144992718934e-05,
195
+ "loss": 0.0783,
196
+ "step": 150000
197
+ },
198
+ {
199
+ "epoch": 0.13,
200
+ "eval_loss": 0.06954144686460495,
201
+ "eval_runtime": 1688.3337,
202
+ "eval_samples_per_second": 36.742,
203
+ "eval_steps_per_second": 36.742,
204
+ "step": 150000
205
+ },
206
+ {
207
+ "epoch": 0.14,
208
+ "learning_rate": 4.3059249825809564e-05,
209
+ "loss": 0.072,
210
+ "step": 155000
211
+ },
212
+ {
213
+ "epoch": 0.14,
214
+ "learning_rate": 4.2835354658900195e-05,
215
+ "loss": 0.0824,
216
+ "step": 160000
217
+ },
218
+ {
219
+ "epoch": 0.15,
220
+ "learning_rate": 4.2611459491990825e-05,
221
+ "loss": 0.0779,
222
+ "step": 165000
223
+ },
224
+ {
225
+ "epoch": 0.15,
226
+ "learning_rate": 4.2387564325081456e-05,
227
+ "loss": 0.0733,
228
+ "step": 170000
229
+ },
230
+ {
231
+ "epoch": 0.16,
232
+ "learning_rate": 4.2163669158172086e-05,
233
+ "loss": 0.0784,
234
+ "step": 175000
235
+ },
236
+ {
237
+ "epoch": 0.16,
238
+ "learning_rate": 4.1939773991262716e-05,
239
+ "loss": 0.0745,
240
+ "step": 180000
241
+ },
242
+ {
243
+ "epoch": 0.17,
244
+ "learning_rate": 4.171587882435335e-05,
245
+ "loss": 0.0778,
246
+ "step": 185000
247
+ },
248
+ {
249
+ "epoch": 0.17,
250
+ "learning_rate": 4.149198365744398e-05,
251
+ "loss": 0.0753,
252
+ "step": 190000
253
+ },
254
+ {
255
+ "epoch": 0.17,
256
+ "learning_rate": 4.1268088490534614e-05,
257
+ "loss": 0.0735,
258
+ "step": 195000
259
+ },
260
+ {
261
+ "epoch": 0.18,
262
+ "learning_rate": 4.104419332362524e-05,
263
+ "loss": 0.072,
264
+ "step": 200000
265
+ },
266
+ {
267
+ "epoch": 0.18,
268
+ "learning_rate": 4.082029815671587e-05,
269
+ "loss": 0.0752,
270
+ "step": 205000
271
+ },
272
+ {
273
+ "epoch": 0.19,
274
+ "learning_rate": 4.0596402989806505e-05,
275
+ "loss": 0.0759,
276
+ "step": 210000
277
+ },
278
+ {
279
+ "epoch": 0.19,
280
+ "learning_rate": 4.037250782289713e-05,
281
+ "loss": 0.0715,
282
+ "step": 215000
283
+ },
284
+ {
285
+ "epoch": 0.2,
286
+ "learning_rate": 4.0148612655987766e-05,
287
+ "loss": 0.0734,
288
+ "step": 220000
289
+ },
290
+ {
291
+ "epoch": 0.2,
292
+ "learning_rate": 3.9924717489078396e-05,
293
+ "loss": 0.0719,
294
+ "step": 225000
295
+ },
296
+ {
297
+ "epoch": 0.2,
298
+ "eval_loss": 0.07320380210876465,
299
+ "eval_runtime": 1689.2398,
300
+ "eval_samples_per_second": 36.722,
301
+ "eval_steps_per_second": 36.722,
302
+ "step": 225000
303
+ },
304
+ {
305
+ "epoch": 0.21,
306
+ "learning_rate": 3.970082232216903e-05,
307
+ "loss": 0.0782,
308
+ "step": 230000
309
+ },
310
+ {
311
+ "epoch": 0.21,
312
+ "learning_rate": 3.947692715525966e-05,
313
+ "loss": 0.0689,
314
+ "step": 235000
315
+ },
316
+ {
317
+ "epoch": 0.21,
318
+ "learning_rate": 3.925303198835029e-05,
319
+ "loss": 0.0721,
320
+ "step": 240000
321
+ },
322
+ {
323
+ "epoch": 0.22,
324
+ "learning_rate": 3.902913682144092e-05,
325
+ "loss": 0.0717,
326
+ "step": 245000
327
+ },
328
+ {
329
+ "epoch": 0.22,
330
+ "learning_rate": 3.880524165453155e-05,
331
+ "loss": 0.0751,
332
+ "step": 250000
333
+ },
334
+ {
335
+ "epoch": 0.23,
336
+ "learning_rate": 3.8581346487622186e-05,
337
+ "loss": 0.075,
338
+ "step": 255000
339
+ },
340
+ {
341
+ "epoch": 0.23,
342
+ "learning_rate": 3.835745132071281e-05,
343
+ "loss": 0.0774,
344
+ "step": 260000
345
+ },
346
+ {
347
+ "epoch": 0.24,
348
+ "learning_rate": 3.8133556153803446e-05,
349
+ "loss": 0.0729,
350
+ "step": 265000
351
+ },
352
+ {
353
+ "epoch": 0.24,
354
+ "learning_rate": 3.790966098689408e-05,
355
+ "loss": 0.0666,
356
+ "step": 270000
357
+ },
358
+ {
359
+ "epoch": 0.25,
360
+ "learning_rate": 3.76857658199847e-05,
361
+ "loss": 0.0668,
362
+ "step": 275000
363
+ },
364
+ {
365
+ "epoch": 0.25,
366
+ "learning_rate": 3.746187065307534e-05,
367
+ "loss": 0.0688,
368
+ "step": 280000
369
+ },
370
+ {
371
+ "epoch": 0.26,
372
+ "learning_rate": 3.723797548616597e-05,
373
+ "loss": 0.0732,
374
+ "step": 285000
375
+ },
376
+ {
377
+ "epoch": 0.26,
378
+ "learning_rate": 3.70140803192566e-05,
379
+ "loss": 0.0729,
380
+ "step": 290000
381
+ },
382
+ {
383
+ "epoch": 0.26,
384
+ "learning_rate": 3.679018515234723e-05,
385
+ "loss": 0.0746,
386
+ "step": 295000
387
+ },
388
+ {
389
+ "epoch": 0.27,
390
+ "learning_rate": 3.6566289985437866e-05,
391
+ "loss": 0.0743,
392
+ "step": 300000
393
+ },
394
+ {
395
+ "epoch": 0.27,
396
+ "eval_loss": 0.06632131338119507,
397
+ "eval_runtime": 1749.4291,
398
+ "eval_samples_per_second": 35.459,
399
+ "eval_steps_per_second": 35.459,
400
+ "step": 300000
401
+ },
402
+ {
403
+ "epoch": 0.27,
404
+ "learning_rate": 3.634239481852849e-05,
405
+ "loss": 0.0689,
406
+ "step": 305000
407
+ },
408
+ {
409
+ "epoch": 0.28,
410
+ "learning_rate": 3.611849965161912e-05,
411
+ "loss": 0.0705,
412
+ "step": 310000
413
+ },
414
+ {
415
+ "epoch": 0.28,
416
+ "learning_rate": 3.589460448470976e-05,
417
+ "loss": 0.0691,
418
+ "step": 315000
419
+ },
420
+ {
421
+ "epoch": 0.29,
422
+ "learning_rate": 3.567070931780038e-05,
423
+ "loss": 0.0673,
424
+ "step": 320000
425
+ },
426
+ {
427
+ "epoch": 0.29,
428
+ "learning_rate": 3.544681415089102e-05,
429
+ "loss": 0.0713,
430
+ "step": 325000
431
+ },
432
+ {
433
+ "epoch": 0.3,
434
+ "learning_rate": 3.522291898398165e-05,
435
+ "loss": 0.0704,
436
+ "step": 330000
437
+ },
438
+ {
439
+ "epoch": 0.3,
440
+ "learning_rate": 3.499902381707228e-05,
441
+ "loss": 0.0734,
442
+ "step": 335000
443
+ },
444
+ {
445
+ "epoch": 0.3,
446
+ "learning_rate": 3.477512865016291e-05,
447
+ "loss": 0.0731,
448
+ "step": 340000
449
+ },
450
+ {
451
+ "epoch": 0.31,
452
+ "learning_rate": 3.455123348325354e-05,
453
+ "loss": 0.0682,
454
+ "step": 345000
455
+ },
456
+ {
457
+ "epoch": 0.31,
458
+ "learning_rate": 3.432733831634417e-05,
459
+ "loss": 0.0719,
460
+ "step": 350000
461
+ },
462
+ {
463
+ "epoch": 0.32,
464
+ "learning_rate": 3.41034431494348e-05,
465
+ "loss": 0.0724,
466
+ "step": 355000
467
+ },
468
+ {
469
+ "epoch": 0.32,
470
+ "learning_rate": 3.387954798252544e-05,
471
+ "loss": 0.0677,
472
+ "step": 360000
473
+ },
474
+ {
475
+ "epoch": 0.33,
476
+ "learning_rate": 3.365565281561606e-05,
477
+ "loss": 0.0697,
478
+ "step": 365000
479
+ },
480
+ {
481
+ "epoch": 0.33,
482
+ "learning_rate": 3.343175764870669e-05,
483
+ "loss": 0.0759,
484
+ "step": 370000
485
+ },
486
+ {
487
+ "epoch": 0.34,
488
+ "learning_rate": 3.320786248179733e-05,
489
+ "loss": 0.0659,
490
+ "step": 375000
491
+ },
492
+ {
493
+ "epoch": 0.34,
494
+ "eval_loss": 0.06863044947385788,
495
+ "eval_runtime": 1687.8956,
496
+ "eval_samples_per_second": 36.752,
497
+ "eval_steps_per_second": 36.752,
498
+ "step": 375000
499
+ },
500
+ {
501
+ "epoch": 0.34,
502
+ "learning_rate": 3.298396731488795e-05,
503
+ "loss": 0.0704,
504
+ "step": 380000
505
+ },
506
+ {
507
+ "epoch": 0.34,
508
+ "learning_rate": 3.276007214797859e-05,
509
+ "loss": 0.0711,
510
+ "step": 385000
511
+ },
512
+ {
513
+ "epoch": 0.35,
514
+ "learning_rate": 3.253617698106922e-05,
515
+ "loss": 0.0689,
516
+ "step": 390000
517
+ },
518
+ {
519
+ "epoch": 0.35,
520
+ "learning_rate": 3.231228181415985e-05,
521
+ "loss": 0.0689,
522
+ "step": 395000
523
+ },
524
+ {
525
+ "epoch": 0.36,
526
+ "learning_rate": 3.208838664725048e-05,
527
+ "loss": 0.0657,
528
+ "step": 400000
529
+ },
530
+ {
531
+ "epoch": 0.36,
532
+ "learning_rate": 3.186449148034111e-05,
533
+ "loss": 0.0695,
534
+ "step": 405000
535
+ },
536
+ {
537
+ "epoch": 0.37,
538
+ "learning_rate": 3.164059631343174e-05,
539
+ "loss": 0.07,
540
+ "step": 410000
541
+ },
542
+ {
543
+ "epoch": 0.37,
544
+ "learning_rate": 3.141670114652237e-05,
545
+ "loss": 0.0654,
546
+ "step": 415000
547
+ },
548
+ {
549
+ "epoch": 0.38,
550
+ "learning_rate": 3.1192805979613e-05,
551
+ "loss": 0.0668,
552
+ "step": 420000
553
+ },
554
+ {
555
+ "epoch": 0.38,
556
+ "learning_rate": 3.096891081270363e-05,
557
+ "loss": 0.0692,
558
+ "step": 425000
559
+ },
560
+ {
561
+ "epoch": 0.39,
562
+ "learning_rate": 3.074501564579427e-05,
563
+ "loss": 0.0692,
564
+ "step": 430000
565
+ },
566
+ {
567
+ "epoch": 0.39,
568
+ "learning_rate": 3.052112047888489e-05,
569
+ "loss": 0.0707,
570
+ "step": 435000
571
+ },
572
+ {
573
+ "epoch": 0.39,
574
+ "learning_rate": 3.0297225311975523e-05,
575
+ "loss": 0.0677,
576
+ "step": 440000
577
+ },
578
+ {
579
+ "epoch": 0.4,
580
+ "learning_rate": 3.007333014506616e-05,
581
+ "loss": 0.0721,
582
+ "step": 445000
583
+ },
584
+ {
585
+ "epoch": 0.4,
586
+ "learning_rate": 2.9849434978156787e-05,
587
+ "loss": 0.0664,
588
+ "step": 450000
589
+ },
590
+ {
591
+ "epoch": 0.4,
592
+ "eval_loss": 0.06826464831829071,
593
+ "eval_runtime": 1692.5106,
594
+ "eval_samples_per_second": 36.651,
595
+ "eval_steps_per_second": 36.651,
596
+ "step": 450000
597
+ },
598
+ {
599
+ "epoch": 0.41,
600
+ "learning_rate": 2.962553981124742e-05,
601
+ "loss": 0.0647,
602
+ "step": 455000
603
+ },
604
+ {
605
+ "epoch": 0.41,
606
+ "learning_rate": 2.940164464433805e-05,
607
+ "loss": 0.0683,
608
+ "step": 460000
609
+ },
610
+ {
611
+ "epoch": 0.42,
612
+ "learning_rate": 2.9177749477428685e-05,
613
+ "loss": 0.0693,
614
+ "step": 465000
615
+ },
616
+ {
617
+ "epoch": 0.42,
618
+ "learning_rate": 2.8953854310519312e-05,
619
+ "loss": 0.0677,
620
+ "step": 470000
621
+ },
622
+ {
623
+ "epoch": 0.43,
624
+ "learning_rate": 2.8729959143609942e-05,
625
+ "loss": 0.0674,
626
+ "step": 475000
627
+ },
628
+ {
629
+ "epoch": 0.43,
630
+ "learning_rate": 2.8506063976700576e-05,
631
+ "loss": 0.0675,
632
+ "step": 480000
633
+ },
634
+ {
635
+ "epoch": 0.43,
636
+ "learning_rate": 2.8282168809791203e-05,
637
+ "loss": 0.0676,
638
+ "step": 485000
639
+ },
640
+ {
641
+ "epoch": 0.44,
642
+ "learning_rate": 2.8058273642881837e-05,
643
+ "loss": 0.066,
644
+ "step": 490000
645
+ },
646
+ {
647
+ "epoch": 0.44,
648
+ "learning_rate": 2.7834378475972467e-05,
649
+ "loss": 0.0692,
650
+ "step": 495000
651
+ },
652
+ {
653
+ "epoch": 0.45,
654
+ "learning_rate": 2.76104833090631e-05,
655
+ "loss": 0.0709,
656
+ "step": 500000
657
+ },
658
+ {
659
+ "epoch": 0.45,
660
+ "learning_rate": 2.7386588142153728e-05,
661
+ "loss": 0.0651,
662
+ "step": 505000
663
+ },
664
+ {
665
+ "epoch": 0.46,
666
+ "learning_rate": 2.716269297524436e-05,
667
+ "loss": 0.0684,
668
+ "step": 510000
669
+ },
670
+ {
671
+ "epoch": 0.46,
672
+ "learning_rate": 2.6938797808334992e-05,
673
+ "loss": 0.067,
674
+ "step": 515000
675
+ },
676
+ {
677
+ "epoch": 0.47,
678
+ "learning_rate": 2.6714902641425623e-05,
679
+ "loss": 0.0631,
680
+ "step": 520000
681
+ },
682
+ {
683
+ "epoch": 0.47,
684
+ "learning_rate": 2.6491007474516256e-05,
685
+ "loss": 0.0637,
686
+ "step": 525000
687
+ },
688
+ {
689
+ "epoch": 0.47,
690
+ "eval_loss": 0.06799625605344772,
691
+ "eval_runtime": 1690.2201,
692
+ "eval_samples_per_second": 36.701,
693
+ "eval_steps_per_second": 36.701,
694
+ "step": 525000
695
+ },
696
+ {
697
+ "epoch": 0.47,
698
+ "learning_rate": 2.6267112307606883e-05,
699
+ "loss": 0.0691,
700
+ "step": 530000
701
+ },
702
+ {
703
+ "epoch": 0.48,
704
+ "learning_rate": 2.6043217140697517e-05,
705
+ "loss": 0.0707,
706
+ "step": 535000
707
+ },
708
+ {
709
+ "epoch": 0.48,
710
+ "learning_rate": 2.5819321973788147e-05,
711
+ "loss": 0.0692,
712
+ "step": 540000
713
+ },
714
+ {
715
+ "epoch": 0.49,
716
+ "learning_rate": 2.5595426806878774e-05,
717
+ "loss": 0.067,
718
+ "step": 545000
719
+ },
720
+ {
721
+ "epoch": 0.49,
722
+ "learning_rate": 2.5371531639969408e-05,
723
+ "loss": 0.067,
724
+ "step": 550000
725
+ },
726
+ {
727
+ "epoch": 0.5,
728
+ "learning_rate": 2.514763647306004e-05,
729
+ "loss": 0.0734,
730
+ "step": 555000
731
+ },
732
+ {
733
+ "epoch": 0.5,
734
+ "learning_rate": 2.492374130615067e-05,
735
+ "loss": 0.0663,
736
+ "step": 560000
737
+ },
738
+ {
739
+ "epoch": 0.51,
740
+ "learning_rate": 2.46998461392413e-05,
741
+ "loss": 0.0689,
742
+ "step": 565000
743
+ },
744
+ {
745
+ "epoch": 0.51,
746
+ "learning_rate": 2.4475950972331933e-05,
747
+ "loss": 0.0642,
748
+ "step": 570000
749
+ }
750
+ ],
751
+ "max_steps": 1116594,
752
+ "num_train_epochs": 1,
753
+ "total_flos": 1.7128824397599744e+17,
754
+ "trial_name": null,
755
+ "trial_params": null
756
+ }
checkpoint-570000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:626bad985fb1862f6b32ba4ebd7449b96bad7c0595dcabc271cd02a0adcc193d
3
+ size 3119