Hugging Face's logo

EColi
/
SB_Classifier

Text Classification
PyTorch
generic
bert
Model card Files
xet
Community
1
EColi commited on
Commit
1d7009e
·
1 Parent(s): 01f5324

Add 325000

Browse files
Files changed (12) hide show
  1. checkpoint-325000/added_tokens.json +1 -0
  2. checkpoint-325000/config.json +39 -0
  3. checkpoint-325000/optimizer.pt +3 -0
  4. checkpoint-325000/pytorch_model.bin +3 -0
  5. checkpoint-325000/rng_state.pth +3 -0
  6. checkpoint-325000/scheduler.pt +3 -0
  7. checkpoint-325000/special_tokens_map.json +1 -0
  8. checkpoint-325000/tokenizer.json +0 -0
  9. checkpoint-325000/tokenizer_config.json +1 -0
  10. checkpoint-325000/trainer_state.json +523 -0
  11. checkpoint-325000/training_args.bin +3 -0
  12. checkpoint-325000/vocab.txt +0 -0
checkpoint-325000/added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"[Applause]": 30530, "START_SPONSOR_TOKEN": 30534, "PROFANITY_TOKEN": 30532, "START_INTERACTION_TOKEN": 30538, "END_INTERACTION_TOKEN": 30539, "START_SELFPROMO_TOKEN": 30536, "END_SELFPROMO_TOKEN": 30537, "EXTRACT_SEGMENTS: ": 30522, "[Music]": 30529, "SHORT_HYPHENATED_TOKEN": 30527, "LONG_WORD_TOKEN": 30528, "NUMBER_TOKEN": 30526, "BETWEEN_SEGMENTS_TOKEN": 30540, "END_SPONSOR_TOKEN": 30535, "NUMBER_PERCENTAGE_TOKEN": 30525, "HYPHENATED_URL_TOKEN": 30524, "NO_SEGMENT_TOKEN": 30533, "URL_TOKEN": 30523, "[Laughter]": 30531}
checkpoint-325000/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Xenova/sponsorblock-classifier-v2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "NONE",
14
+ "1": "SPONSOR",
15
+ "2": "SELFPROMO",
16
+ "3": "INTERACTION"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "INTERACTION": 3,
22
+ "NONE": 0,
23
+ "SELFPROMO": 2,
24
+ "SPONSOR": 1
25
+ },
26
+ "layer_norm_eps": 1e-12,
27
+ "max_position_embeddings": 512,
28
+ "model_type": "bert",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "pad_token_id": 0,
32
+ "position_embedding_type": "absolute",
33
+ "problem_type": "single_label_classification",
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.18.0",
36
+ "type_vocab_size": 2,
37
+ "use_cache": true,
38
+ "vocab_size": 30541
39
+ }
checkpoint-325000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96765e5aa06e0e6bb3828a8da9c276e30fefada85f8a18852f84b00ff074a1ff
3
+ size 876116189
checkpoint-325000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49ed402b8d31340cbb7f93cd95d0070dce4b9a00a877de6e847c40ba30f57d0b
3
+ size 438070637
checkpoint-325000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1063c59997675d69839e5792e5c5bf26eeadc9bf95d5173065887af4fee39f2c
3
+ size 14503
checkpoint-325000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73479d1e96156ca8f7007c0365f6889805ee13e6c750cdab2fe491b54c47d85f
3
+ size 623
checkpoint-325000/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
checkpoint-325000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-325000/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "Xenova/sponsorblock-classifier-v2", "tokenizer_class": "BertTokenizer"}
checkpoint-325000/trainer_state.json ADDED
@@ -0,0 +1,523 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.2465230735200596,
5
+ "global_step": 325000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.03,
12
+ "learning_rate": 1.993087621312246e-06,
13
+ "loss": 0.2839,
14
+ "step": 5000
15
+ },
16
+ {
17
+ "epoch": 0.07,
18
+ "learning_rate": 1.986175242624492e-06,
19
+ "loss": 0.2584,
20
+ "step": 10000
21
+ },
22
+ {
23
+ "epoch": 0.1,
24
+ "learning_rate": 1.979262863936738e-06,
25
+ "loss": 0.2684,
26
+ "step": 15000
27
+ },
28
+ {
29
+ "epoch": 0.14,
30
+ "learning_rate": 1.972350485248984e-06,
31
+ "loss": 0.2725,
32
+ "step": 20000
33
+ },
34
+ {
35
+ "epoch": 0.17,
36
+ "learning_rate": 1.96543810656123e-06,
37
+ "loss": 0.2631,
38
+ "step": 25000
39
+ },
40
+ {
41
+ "epoch": 0.17,
42
+ "eval_accuracy": 0.9506088495254517,
43
+ "eval_loss": 0.2637203335762024,
44
+ "eval_runtime": 690.6403,
45
+ "eval_samples_per_second": 46.495,
46
+ "eval_steps_per_second": 11.624,
47
+ "step": 25000
48
+ },
49
+ {
50
+ "epoch": 0.21,
51
+ "learning_rate": 1.958525727873476e-06,
52
+ "loss": 0.2808,
53
+ "step": 30000
54
+ },
55
+ {
56
+ "epoch": 0.24,
57
+ "learning_rate": 1.951613349185722e-06,
58
+ "loss": 0.2601,
59
+ "step": 35000
60
+ },
61
+ {
62
+ "epoch": 0.28,
63
+ "learning_rate": 1.944700970497968e-06,
64
+ "loss": 0.2746,
65
+ "step": 40000
66
+ },
67
+ {
68
+ "epoch": 0.31,
69
+ "learning_rate": 1.937788591810214e-06,
70
+ "loss": 0.2688,
71
+ "step": 45000
72
+ },
73
+ {
74
+ "epoch": 0.35,
75
+ "learning_rate": 1.93087621312246e-06,
76
+ "loss": 0.2619,
77
+ "step": 50000
78
+ },
79
+ {
80
+ "epoch": 0.35,
81
+ "eval_accuracy": 0.9507022500038147,
82
+ "eval_loss": 0.2595760226249695,
83
+ "eval_runtime": 690.7368,
84
+ "eval_samples_per_second": 46.488,
85
+ "eval_steps_per_second": 11.622,
86
+ "step": 50000
87
+ },
88
+ {
89
+ "epoch": 0.38,
90
+ "learning_rate": 1.9239638344347054e-06,
91
+ "loss": 0.2765,
92
+ "step": 55000
93
+ },
94
+ {
95
+ "epoch": 0.41,
96
+ "learning_rate": 1.9170514557469514e-06,
97
+ "loss": 0.2736,
98
+ "step": 60000
99
+ },
100
+ {
101
+ "epoch": 0.45,
102
+ "learning_rate": 1.9101390770591978e-06,
103
+ "loss": 0.2616,
104
+ "step": 65000
105
+ },
106
+ {
107
+ "epoch": 0.48,
108
+ "learning_rate": 1.9032266983714436e-06,
109
+ "loss": 0.2558,
110
+ "step": 70000
111
+ },
112
+ {
113
+ "epoch": 0.52,
114
+ "learning_rate": 1.8963143196836895e-06,
115
+ "loss": 0.2653,
116
+ "step": 75000
117
+ },
118
+ {
119
+ "epoch": 0.52,
120
+ "eval_accuracy": 0.9514496326446533,
121
+ "eval_loss": 0.2495056539773941,
122
+ "eval_runtime": 689.7436,
123
+ "eval_samples_per_second": 46.555,
124
+ "eval_steps_per_second": 11.639,
125
+ "step": 75000
126
+ },
127
+ {
128
+ "epoch": 0.55,
129
+ "learning_rate": 1.8894019409959353e-06,
130
+ "loss": 0.2594,
131
+ "step": 80000
132
+ },
133
+ {
134
+ "epoch": 0.59,
135
+ "learning_rate": 1.8824895623081813e-06,
136
+ "loss": 0.2678,
137
+ "step": 85000
138
+ },
139
+ {
140
+ "epoch": 0.62,
141
+ "learning_rate": 1.8755771836204273e-06,
142
+ "loss": 0.2648,
143
+ "step": 90000
144
+ },
145
+ {
146
+ "epoch": 0.66,
147
+ "learning_rate": 1.8686648049326735e-06,
148
+ "loss": 0.2671,
149
+ "step": 95000
150
+ },
151
+ {
152
+ "epoch": 0.69,
153
+ "learning_rate": 1.8617524262449193e-06,
154
+ "loss": 0.262,
155
+ "step": 100000
156
+ },
157
+ {
158
+ "epoch": 0.69,
159
+ "eval_accuracy": 0.9511382579803467,
160
+ "eval_loss": 0.25494277477264404,
161
+ "eval_runtime": 689.2307,
162
+ "eval_samples_per_second": 46.59,
163
+ "eval_steps_per_second": 11.648,
164
+ "step": 100000
165
+ },
166
+ {
167
+ "epoch": 0.73,
168
+ "learning_rate": 1.8548400475571653e-06,
169
+ "loss": 0.273,
170
+ "step": 105000
171
+ },
172
+ {
173
+ "epoch": 0.76,
174
+ "learning_rate": 1.8479276688694113e-06,
175
+ "loss": 0.265,
176
+ "step": 110000
177
+ },
178
+ {
179
+ "epoch": 0.79,
180
+ "learning_rate": 1.841015290181657e-06,
181
+ "loss": 0.2677,
182
+ "step": 115000
183
+ },
184
+ {
185
+ "epoch": 0.83,
186
+ "learning_rate": 1.8341029114939032e-06,
187
+ "loss": 0.2644,
188
+ "step": 120000
189
+ },
190
+ {
191
+ "epoch": 0.86,
192
+ "learning_rate": 1.8271905328061492e-06,
193
+ "loss": 0.2667,
194
+ "step": 125000
195
+ },
196
+ {
197
+ "epoch": 0.86,
198
+ "eval_accuracy": 0.9517922401428223,
199
+ "eval_loss": 0.2526009976863861,
200
+ "eval_runtime": 689.2471,
201
+ "eval_samples_per_second": 46.589,
202
+ "eval_steps_per_second": 11.647,
203
+ "step": 125000
204
+ },
205
+ {
206
+ "epoch": 0.9,
207
+ "learning_rate": 1.8202781541183952e-06,
208
+ "loss": 0.262,
209
+ "step": 130000
210
+ },
211
+ {
212
+ "epoch": 0.93,
213
+ "learning_rate": 1.813365775430641e-06,
214
+ "loss": 0.2689,
215
+ "step": 135000
216
+ },
217
+ {
218
+ "epoch": 0.97,
219
+ "learning_rate": 1.806453396742887e-06,
220
+ "loss": 0.2713,
221
+ "step": 140000
222
+ },
223
+ {
224
+ "epoch": 1.0,
225
+ "learning_rate": 1.7995410180551332e-06,
226
+ "loss": 0.2522,
227
+ "step": 145000
228
+ },
229
+ {
230
+ "epoch": 1.04,
231
+ "learning_rate": 1.7926286393673792e-06,
232
+ "loss": 0.2425,
233
+ "step": 150000
234
+ },
235
+ {
236
+ "epoch": 1.04,
237
+ "eval_accuracy": 0.9516676664352417,
238
+ "eval_loss": 0.2566453516483307,
239
+ "eval_runtime": 689.1693,
240
+ "eval_samples_per_second": 46.594,
241
+ "eval_steps_per_second": 11.649,
242
+ "step": 150000
243
+ },
244
+ {
245
+ "epoch": 1.07,
246
+ "learning_rate": 1.785716260679625e-06,
247
+ "loss": 0.2445,
248
+ "step": 155000
249
+ },
250
+ {
251
+ "epoch": 1.11,
252
+ "learning_rate": 1.778803881991871e-06,
253
+ "loss": 0.2353,
254
+ "step": 160000
255
+ },
256
+ {
257
+ "epoch": 1.14,
258
+ "learning_rate": 1.771891503304117e-06,
259
+ "loss": 0.2478,
260
+ "step": 165000
261
+ },
262
+ {
263
+ "epoch": 1.18,
264
+ "learning_rate": 1.764979124616363e-06,
265
+ "loss": 0.2461,
266
+ "step": 170000
267
+ },
268
+ {
269
+ "epoch": 1.21,
270
+ "learning_rate": 1.758066745928609e-06,
271
+ "loss": 0.2506,
272
+ "step": 175000
273
+ },
274
+ {
275
+ "epoch": 1.21,
276
+ "eval_accuracy": 0.9521347880363464,
277
+ "eval_loss": 0.25962916016578674,
278
+ "eval_runtime": 689.0728,
279
+ "eval_samples_per_second": 46.6,
280
+ "eval_steps_per_second": 11.65,
281
+ "step": 175000
282
+ },
283
+ {
284
+ "epoch": 1.24,
285
+ "learning_rate": 1.751154367240855e-06,
286
+ "loss": 0.245,
287
+ "step": 180000
288
+ },
289
+ {
290
+ "epoch": 1.28,
291
+ "learning_rate": 1.7442419885531009e-06,
292
+ "loss": 0.2516,
293
+ "step": 185000
294
+ },
295
+ {
296
+ "epoch": 1.31,
297
+ "learning_rate": 1.7373296098653467e-06,
298
+ "loss": 0.2392,
299
+ "step": 190000
300
+ },
301
+ {
302
+ "epoch": 1.35,
303
+ "learning_rate": 1.7304172311775929e-06,
304
+ "loss": 0.2495,
305
+ "step": 195000
306
+ },
307
+ {
308
+ "epoch": 1.38,
309
+ "learning_rate": 1.7235048524898389e-06,
310
+ "loss": 0.2485,
311
+ "step": 200000
312
+ },
313
+ {
314
+ "epoch": 1.38,
315
+ "eval_accuracy": 0.9533492922782898,
316
+ "eval_loss": 0.2515329122543335,
317
+ "eval_runtime": 689.5664,
318
+ "eval_samples_per_second": 46.567,
319
+ "eval_steps_per_second": 11.642,
320
+ "step": 200000
321
+ },
322
+ {
323
+ "epoch": 1.42,
324
+ "learning_rate": 1.7165924738020846e-06,
325
+ "loss": 0.2311,
326
+ "step": 205000
327
+ },
328
+ {
329
+ "epoch": 1.45,
330
+ "learning_rate": 1.7096800951143306e-06,
331
+ "loss": 0.2335,
332
+ "step": 210000
333
+ },
334
+ {
335
+ "epoch": 1.49,
336
+ "learning_rate": 1.7027677164265766e-06,
337
+ "loss": 0.2568,
338
+ "step": 215000
339
+ },
340
+ {
341
+ "epoch": 1.52,
342
+ "learning_rate": 1.6958553377388226e-06,
343
+ "loss": 0.2392,
344
+ "step": 220000
345
+ },
346
+ {
347
+ "epoch": 1.56,
348
+ "learning_rate": 1.6889429590510686e-06,
349
+ "loss": 0.2411,
350
+ "step": 225000
351
+ },
352
+ {
353
+ "epoch": 1.56,
354
+ "eval_accuracy": 0.9527575969696045,
355
+ "eval_loss": 0.25586625933647156,
356
+ "eval_runtime": 688.9498,
357
+ "eval_samples_per_second": 46.609,
358
+ "eval_steps_per_second": 11.653,
359
+ "step": 225000
360
+ },
361
+ {
362
+ "epoch": 1.59,
363
+ "learning_rate": 1.6820305803633146e-06,
364
+ "loss": 0.2474,
365
+ "step": 230000
366
+ },
367
+ {
368
+ "epoch": 1.62,
369
+ "learning_rate": 1.6751182016755606e-06,
370
+ "loss": 0.2511,
371
+ "step": 235000
372
+ },
373
+ {
374
+ "epoch": 1.66,
375
+ "learning_rate": 1.6682058229878063e-06,
376
+ "loss": 0.2435,
377
+ "step": 240000
378
+ },
379
+ {
380
+ "epoch": 1.69,
381
+ "learning_rate": 1.6612934443000523e-06,
382
+ "loss": 0.2485,
383
+ "step": 245000
384
+ },
385
+ {
386
+ "epoch": 1.73,
387
+ "learning_rate": 1.6543810656122985e-06,
388
+ "loss": 0.234,
389
+ "step": 250000
390
+ },
391
+ {
392
+ "epoch": 1.73,
393
+ "eval_accuracy": 0.9526330828666687,
394
+ "eval_loss": 0.2587934136390686,
395
+ "eval_runtime": 688.8864,
396
+ "eval_samples_per_second": 46.613,
397
+ "eval_steps_per_second": 11.654,
398
+ "step": 250000
399
+ },
400
+ {
401
+ "epoch": 1.76,
402
+ "learning_rate": 1.6474686869245445e-06,
403
+ "loss": 0.2534,
404
+ "step": 255000
405
+ },
406
+ {
407
+ "epoch": 1.8,
408
+ "learning_rate": 1.6405563082367903e-06,
409
+ "loss": 0.2432,
410
+ "step": 260000
411
+ },
412
+ {
413
+ "epoch": 1.83,
414
+ "learning_rate": 1.6336439295490363e-06,
415
+ "loss": 0.2466,
416
+ "step": 265000
417
+ },
418
+ {
419
+ "epoch": 1.87,
420
+ "learning_rate": 1.6267315508612823e-06,
421
+ "loss": 0.2393,
422
+ "step": 270000
423
+ },
424
+ {
425
+ "epoch": 1.9,
426
+ "learning_rate": 1.6198191721735283e-06,
427
+ "loss": 0.242,
428
+ "step": 275000
429
+ },
430
+ {
431
+ "epoch": 1.9,
432
+ "eval_accuracy": 0.9526330828666687,
433
+ "eval_loss": 0.2543439269065857,
434
+ "eval_runtime": 688.3982,
435
+ "eval_samples_per_second": 46.646,
436
+ "eval_steps_per_second": 11.662,
437
+ "step": 275000
438
+ },
439
+ {
440
+ "epoch": 1.94,
441
+ "learning_rate": 1.6129067934857743e-06,
442
+ "loss": 0.2455,
443
+ "step": 280000
444
+ },
445
+ {
446
+ "epoch": 1.97,
447
+ "learning_rate": 1.6059944147980203e-06,
448
+ "loss": 0.2413,
449
+ "step": 285000
450
+ },
451
+ {
452
+ "epoch": 2.0,
453
+ "learning_rate": 1.5990820361102662e-06,
454
+ "loss": 0.241,
455
+ "step": 290000
456
+ },
457
+ {
458
+ "epoch": 2.04,
459
+ "learning_rate": 1.592169657422512e-06,
460
+ "loss": 0.2401,
461
+ "step": 295000
462
+ },
463
+ {
464
+ "epoch": 2.07,
465
+ "learning_rate": 1.5852572787347582e-06,
466
+ "loss": 0.217,
467
+ "step": 300000
468
+ },
469
+ {
470
+ "epoch": 2.07,
471
+ "eval_accuracy": 0.9530379176139832,
472
+ "eval_loss": 0.26496848464012146,
473
+ "eval_runtime": 688.7791,
474
+ "eval_samples_per_second": 46.62,
475
+ "eval_steps_per_second": 11.655,
476
+ "step": 300000
477
+ },
478
+ {
479
+ "epoch": 2.11,
480
+ "learning_rate": 1.5783449000470042e-06,
481
+ "loss": 0.2281,
482
+ "step": 305000
483
+ },
484
+ {
485
+ "epoch": 2.14,
486
+ "learning_rate": 1.57143252135925e-06,
487
+ "loss": 0.2203,
488
+ "step": 310000
489
+ },
490
+ {
491
+ "epoch": 2.18,
492
+ "learning_rate": 1.564520142671496e-06,
493
+ "loss": 0.219,
494
+ "step": 315000
495
+ },
496
+ {
497
+ "epoch": 2.21,
498
+ "learning_rate": 1.557607763983742e-06,
499
+ "loss": 0.2287,
500
+ "step": 320000
501
+ },
502
+ {
503
+ "epoch": 2.25,
504
+ "learning_rate": 1.5506953852959882e-06,
505
+ "loss": 0.2272,
506
+ "step": 325000
507
+ },
508
+ {
509
+ "epoch": 2.25,
510
+ "eval_accuracy": 0.9527264833450317,
511
+ "eval_loss": 0.2502051889896393,
512
+ "eval_runtime": 688.3338,
513
+ "eval_samples_per_second": 46.65,
514
+ "eval_steps_per_second": 11.663,
515
+ "step": 325000
516
+ }
517
+ ],
518
+ "max_steps": 1446680,
519
+ "num_train_epochs": 10,
520
+ "total_flos": 3.420489354301194e+17,
521
+ "trial_name": null,
522
+ "trial_params": null
523
+ }
checkpoint-325000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c5389b3797c627e56dcae336bd0d6e414e54c3e515ab3c97a7ff3f16301ece2
3
+ size 3183
checkpoint-325000/vocab.txt ADDED
The diff for this file is too large to render. See raw diff