Joshua Lochner commited on
Commit
d1c8305
1 Parent(s): 9663e05

Add model files (2.43m) - finetuned from https://huggingface.co/EColi/sponsorblock-base-v1

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"START_INTERACTION_TOKEN": 32116, "EXTRACT_SEGMENTS: ": 32100, "START_SELFPROMO_TOKEN": 32114, "PROFANITY_TOKEN": 32110, "END_SELFPROMO_TOKEN": 32115, "[Music]": 32107, "END_SPONSOR_TOKEN": 32113, "NUMBER_PERCENTAGE_TOKEN": 32103, "HYPHENATED_URL_TOKEN": 32102, "[Applause]": 32108, "[Laughter]": 32109, "END_INTERACTION_TOKEN": 32117, "BETWEEN_SEGMENTS_TOKEN": 32118, "LONG_WORD_TOKEN": 32106, "URL_TOKEN": 32101, "NUMBER_TOKEN": 32104, "SHORT_HYPHENATED_TOKEN": 32105, "START_SPONSOR_TOKEN": 32112, "NO_SEGMENT_TOKEN": 32111}
config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EColi/sponsorblock-base-v1",
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
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f73edbd433a522246e28e3335a1e66fb839f6f470632e4455c38ad39d2ffea58
3
+ size 891703231
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa2f33287398fca8deeed195495504ad565fd9a6ff416b3b341afbf8facdeca6
3
+ size 14503
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:764855c1fd49439e1ca3e8d2ff382456d8c6aa45ad71142cbff0d9ff375234e6
3
+ size 623
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>"]}
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
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": "EColi/sponsorblock-base-v1", "max_length": 768, "tokenizer_class": "T5Tokenizer"}
trainer_state.json ADDED
@@ -0,0 +1,362 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.5748183573990618,
5
+ "global_step": 200000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.01,
12
+ "learning_rate": 4.992814770532512e-05,
13
+ "loss": 0.0668,
14
+ "step": 5000
15
+ },
16
+ {
17
+ "epoch": 0.03,
18
+ "learning_rate": 4.985629541065024e-05,
19
+ "loss": 0.0693,
20
+ "step": 10000
21
+ },
22
+ {
23
+ "epoch": 0.03,
24
+ "eval_loss": 0.0688803568482399,
25
+ "eval_runtime": 645.0212,
26
+ "eval_samples_per_second": 29.968,
27
+ "eval_steps_per_second": 29.968,
28
+ "step": 10000
29
+ },
30
+ {
31
+ "epoch": 0.04,
32
+ "learning_rate": 4.978444311597535e-05,
33
+ "loss": 0.0634,
34
+ "step": 15000
35
+ },
36
+ {
37
+ "epoch": 0.06,
38
+ "learning_rate": 4.971259082130047e-05,
39
+ "loss": 0.0637,
40
+ "step": 20000
41
+ },
42
+ {
43
+ "epoch": 0.06,
44
+ "eval_loss": 0.05873561650514603,
45
+ "eval_runtime": 644.2466,
46
+ "eval_samples_per_second": 30.004,
47
+ "eval_steps_per_second": 30.004,
48
+ "step": 20000
49
+ },
50
+ {
51
+ "epoch": 0.07,
52
+ "learning_rate": 4.964073852662559e-05,
53
+ "loss": 0.0605,
54
+ "step": 25000
55
+ },
56
+ {
57
+ "epoch": 0.09,
58
+ "learning_rate": 4.9568886231950703e-05,
59
+ "loss": 0.0633,
60
+ "step": 30000
61
+ },
62
+ {
63
+ "epoch": 0.09,
64
+ "eval_loss": 0.05583559721708298,
65
+ "eval_runtime": 644.4128,
66
+ "eval_samples_per_second": 29.996,
67
+ "eval_steps_per_second": 29.996,
68
+ "step": 30000
69
+ },
70
+ {
71
+ "epoch": 0.1,
72
+ "learning_rate": 4.9497033937275825e-05,
73
+ "loss": 0.0635,
74
+ "step": 35000
75
+ },
76
+ {
77
+ "epoch": 0.11,
78
+ "learning_rate": 4.9425181642600946e-05,
79
+ "loss": 0.0584,
80
+ "step": 40000
81
+ },
82
+ {
83
+ "epoch": 0.11,
84
+ "eval_loss": 0.06174061447381973,
85
+ "eval_runtime": 644.7843,
86
+ "eval_samples_per_second": 29.979,
87
+ "eval_steps_per_second": 29.979,
88
+ "step": 40000
89
+ },
90
+ {
91
+ "epoch": 0.13,
92
+ "learning_rate": 4.935332934792606e-05,
93
+ "loss": 0.0592,
94
+ "step": 45000
95
+ },
96
+ {
97
+ "epoch": 0.14,
98
+ "learning_rate": 4.9281477053251175e-05,
99
+ "loss": 0.061,
100
+ "step": 50000
101
+ },
102
+ {
103
+ "epoch": 0.14,
104
+ "eval_loss": 0.05651352182030678,
105
+ "eval_runtime": 642.7605,
106
+ "eval_samples_per_second": 30.073,
107
+ "eval_steps_per_second": 30.073,
108
+ "step": 50000
109
+ },
110
+ {
111
+ "epoch": 0.16,
112
+ "learning_rate": 4.92096247585763e-05,
113
+ "loss": 0.0693,
114
+ "step": 55000
115
+ },
116
+ {
117
+ "epoch": 0.17,
118
+ "learning_rate": 4.913777246390141e-05,
119
+ "loss": 0.0652,
120
+ "step": 60000
121
+ },
122
+ {
123
+ "epoch": 0.17,
124
+ "eval_loss": 0.055016856640577316,
125
+ "eval_runtime": 641.3853,
126
+ "eval_samples_per_second": 30.138,
127
+ "eval_steps_per_second": 30.138,
128
+ "step": 60000
129
+ },
130
+ {
131
+ "epoch": 0.19,
132
+ "learning_rate": 4.9065920169226526e-05,
133
+ "loss": 0.0665,
134
+ "step": 65000
135
+ },
136
+ {
137
+ "epoch": 0.2,
138
+ "learning_rate": 4.899406787455164e-05,
139
+ "loss": 0.0646,
140
+ "step": 70000
141
+ },
142
+ {
143
+ "epoch": 0.2,
144
+ "eval_loss": 0.05567777901887894,
145
+ "eval_runtime": 642.5363,
146
+ "eval_samples_per_second": 30.084,
147
+ "eval_steps_per_second": 30.084,
148
+ "step": 70000
149
+ },
150
+ {
151
+ "epoch": 0.22,
152
+ "learning_rate": 4.892221557987676e-05,
153
+ "loss": 0.0617,
154
+ "step": 75000
155
+ },
156
+ {
157
+ "epoch": 0.23,
158
+ "learning_rate": 4.8850363285201876e-05,
159
+ "loss": 0.0648,
160
+ "step": 80000
161
+ },
162
+ {
163
+ "epoch": 0.23,
164
+ "eval_loss": 0.05431482940912247,
165
+ "eval_runtime": 641.7629,
166
+ "eval_samples_per_second": 30.12,
167
+ "eval_steps_per_second": 30.12,
168
+ "step": 80000
169
+ },
170
+ {
171
+ "epoch": 0.24,
172
+ "learning_rate": 4.877851099052699e-05,
173
+ "loss": 0.0654,
174
+ "step": 85000
175
+ },
176
+ {
177
+ "epoch": 0.26,
178
+ "learning_rate": 4.870665869585211e-05,
179
+ "loss": 0.0664,
180
+ "step": 90000
181
+ },
182
+ {
183
+ "epoch": 0.26,
184
+ "eval_loss": 0.05483051761984825,
185
+ "eval_runtime": 643.1769,
186
+ "eval_samples_per_second": 30.054,
187
+ "eval_steps_per_second": 30.054,
188
+ "step": 90000
189
+ },
190
+ {
191
+ "epoch": 0.27,
192
+ "learning_rate": 4.863480640117723e-05,
193
+ "loss": 0.0649,
194
+ "step": 95000
195
+ },
196
+ {
197
+ "epoch": 0.29,
198
+ "learning_rate": 4.856295410650235e-05,
199
+ "loss": 0.0615,
200
+ "step": 100000
201
+ },
202
+ {
203
+ "epoch": 0.29,
204
+ "eval_loss": 0.061954181641340256,
205
+ "eval_runtime": 641.5389,
206
+ "eval_samples_per_second": 30.131,
207
+ "eval_steps_per_second": 30.131,
208
+ "step": 100000
209
+ },
210
+ {
211
+ "epoch": 0.3,
212
+ "learning_rate": 4.849110181182747e-05,
213
+ "loss": 0.0596,
214
+ "step": 105000
215
+ },
216
+ {
217
+ "epoch": 0.32,
218
+ "learning_rate": 4.8419249517152584e-05,
219
+ "loss": 0.0629,
220
+ "step": 110000
221
+ },
222
+ {
223
+ "epoch": 0.32,
224
+ "eval_loss": 0.06062796711921692,
225
+ "eval_runtime": 642.0211,
226
+ "eval_samples_per_second": 30.108,
227
+ "eval_steps_per_second": 30.108,
228
+ "step": 110000
229
+ },
230
+ {
231
+ "epoch": 0.33,
232
+ "learning_rate": 4.83473972224777e-05,
233
+ "loss": 0.0613,
234
+ "step": 115000
235
+ },
236
+ {
237
+ "epoch": 0.34,
238
+ "learning_rate": 4.827554492780282e-05,
239
+ "loss": 0.0683,
240
+ "step": 120000
241
+ },
242
+ {
243
+ "epoch": 0.34,
244
+ "eval_loss": 0.055720094591379166,
245
+ "eval_runtime": 642.5633,
246
+ "eval_samples_per_second": 30.083,
247
+ "eval_steps_per_second": 30.083,
248
+ "step": 120000
249
+ },
250
+ {
251
+ "epoch": 0.36,
252
+ "learning_rate": 4.8203692633127935e-05,
253
+ "loss": 0.0631,
254
+ "step": 125000
255
+ },
256
+ {
257
+ "epoch": 0.37,
258
+ "learning_rate": 4.813184033845305e-05,
259
+ "loss": 0.0649,
260
+ "step": 130000
261
+ },
262
+ {
263
+ "epoch": 0.37,
264
+ "eval_loss": 0.06274710595607758,
265
+ "eval_runtime": 642.0067,
266
+ "eval_samples_per_second": 30.109,
267
+ "eval_steps_per_second": 30.109,
268
+ "step": 130000
269
+ },
270
+ {
271
+ "epoch": 0.39,
272
+ "learning_rate": 4.805998804377817e-05,
273
+ "loss": 0.0642,
274
+ "step": 135000
275
+ },
276
+ {
277
+ "epoch": 0.4,
278
+ "learning_rate": 4.7988135749103285e-05,
279
+ "loss": 0.064,
280
+ "step": 140000
281
+ },
282
+ {
283
+ "epoch": 0.4,
284
+ "eval_loss": 0.05436055734753609,
285
+ "eval_runtime": 642.9629,
286
+ "eval_samples_per_second": 30.064,
287
+ "eval_steps_per_second": 30.064,
288
+ "step": 140000
289
+ },
290
+ {
291
+ "epoch": 0.42,
292
+ "learning_rate": 4.79162834544284e-05,
293
+ "loss": 0.0592,
294
+ "step": 145000
295
+ },
296
+ {
297
+ "epoch": 0.43,
298
+ "learning_rate": 4.784443115975352e-05,
299
+ "loss": 0.0574,
300
+ "step": 150000
301
+ },
302
+ {
303
+ "epoch": 0.43,
304
+ "eval_loss": 0.059992264956235886,
305
+ "eval_runtime": 642.342,
306
+ "eval_samples_per_second": 30.093,
307
+ "eval_steps_per_second": 30.093,
308
+ "step": 150000
309
+ },
310
+ {
311
+ "epoch": 0.45,
312
+ "learning_rate": 4.7772578865078636e-05,
313
+ "loss": 0.0637,
314
+ "step": 155000
315
+ },
316
+ {
317
+ "epoch": 0.46,
318
+ "learning_rate": 4.770072657040375e-05,
319
+ "loss": 0.0599,
320
+ "step": 160000
321
+ },
322
+ {
323
+ "epoch": 0.46,
324
+ "eval_loss": 0.05961042642593384,
325
+ "eval_runtime": 642.0137,
326
+ "eval_samples_per_second": 30.108,
327
+ "eval_steps_per_second": 30.108,
328
+ "step": 160000
329
+ },
330
+ {
331
+ "epoch": 0.47,
332
+ "learning_rate": 4.762887427572887e-05,
333
+ "loss": 0.0618,
334
+ "step": 165000
335
+ },
336
+ {
337
+ "epoch": 0.5,
338
+ "learning_rate": 4.748516968637911e-05,
339
+ "loss": 0.0619,
340
+ "step": 175000
341
+ },
342
+ {
343
+ "epoch": 0.57,
344
+ "learning_rate": 4.7125908213004694e-05,
345
+ "loss": 0.0558,
346
+ "step": 200000
347
+ },
348
+ {
349
+ "epoch": 0.57,
350
+ "eval_loss": 0.061555784195661545,
351
+ "eval_runtime": 654.4106,
352
+ "eval_samples_per_second": 29.538,
353
+ "eval_steps_per_second": 29.538,
354
+ "step": 200000
355
+ }
356
+ ],
357
+ "max_steps": 3479360,
358
+ "num_train_epochs": 10,
359
+ "total_flos": 6.998757674752512e+16,
360
+ "trial_name": null,
361
+ "trial_params": null
362
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff45ae7a4c7d70aca065fada9ae931b0ce50044f40c72cead39c54826e164fb2
3
+ size 3119