hr16 commited on
Commit
3cd304c
·
verified ·
1 Parent(s): 7b0aa8c

Training in progress, epoch 1, checkpoint

Browse files
checkpoint-392/config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "vinai/PhoWhisper-small",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "apply_spec_augment": false,
6
+ "architectures": [
7
+ "ViSpeechClassification"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "begin_suppress_tokens": [
11
+ 220,
12
+ 50257
13
+ ],
14
+ "bos_token_id": 50257,
15
+ "classifier_proj_size": 256,
16
+ "d_model": 768,
17
+ "decoder_attention_heads": 12,
18
+ "decoder_ffn_dim": 3072,
19
+ "decoder_layerdrop": 0.0,
20
+ "decoder_layers": 12,
21
+ "decoder_start_token_id": 50258,
22
+ "dropout": 0.0,
23
+ "encoder_attention_heads": 12,
24
+ "encoder_ffn_dim": 3072,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 12,
27
+ "eos_token_id": 50257,
28
+ "forced_decoder_ids": null,
29
+ "id2label": {
30
+ "0": "male, northern dialect",
31
+ "1": "male, central dialect",
32
+ "2": "male, highland central dialect",
33
+ "3": "male, southern dialect",
34
+ "4": "female, northern dialect",
35
+ "5": "female, central dialect",
36
+ "6": "female, highland central dialect",
37
+ "7": "female, southern dialect"
38
+ },
39
+ "init_std": 0.02,
40
+ "is_encoder_decoder": true,
41
+ "label2id": {
42
+ "female, central dialect": "5",
43
+ "female, highland central dialect": "6",
44
+ "female, northern dialect": "4",
45
+ "female, southern dialect": "7",
46
+ "male, central dialect": "1",
47
+ "male, highland central dialect": "2",
48
+ "male, northern dialect": "0",
49
+ "male, southern dialect": "3"
50
+ },
51
+ "mask_feature_length": 10,
52
+ "mask_feature_min_masks": 0,
53
+ "mask_feature_prob": 0.0,
54
+ "mask_time_length": 10,
55
+ "mask_time_min_masks": 2,
56
+ "mask_time_prob": 0.05,
57
+ "max_length": 448,
58
+ "max_source_positions": 1500,
59
+ "max_target_positions": 448,
60
+ "median_filter_width": 7,
61
+ "model_type": "whisper",
62
+ "num_hidden_layers": 12,
63
+ "num_mel_bins": 80,
64
+ "pad_token_id": 50257,
65
+ "scale_embedding": false,
66
+ "torch_dtype": "float32",
67
+ "transformers_version": "4.41.2",
68
+ "use_cache": true,
69
+ "use_weighted_layer_sum": false,
70
+ "vocab_size": 51865
71
+ }
checkpoint-392/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb59ab58bb5ff3eafa91c958ea9b8f42f1fa8b72ed927daddf1923795ef1d594
3
+ size 358419776
checkpoint-392/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89b0a204171bf2a714b715d9823a351f76897f2b2a388ea04d12e5451646dce2
3
+ size 11572486
checkpoint-392/preprocessor_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 30,
3
+ "feature_extractor_type": "WhisperFeatureExtractor",
4
+ "feature_size": 80,
5
+ "hop_length": 160,
6
+ "n_fft": 400,
7
+ "n_samples": 480000,
8
+ "nb_max_frames": 3000,
9
+ "padding_side": "right",
10
+ "padding_value": 0.0,
11
+ "processor_class": "WhisperProcessor",
12
+ "return_attention_mask": false,
13
+ "sampling_rate": 16000
14
+ }
checkpoint-392/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac4f2223ae20a15f214a3351b5b55f85f2c47207d3b172dfffc1d6e3c643d1ed
3
+ size 14244
checkpoint-392/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d88888ca2b44ec47bab12de6ac3870d08ad1350b6518691df634bee808eee7a1
3
+ size 1064
checkpoint-392/trainer_state.json ADDED
@@ -0,0 +1,588 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0857774206508638,
3
+ "best_model_checkpoint": "PhoWhisper-small-vispeech-classifier-v3/checkpoint-392",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 392,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.012755102040816327,
13
+ "grad_norm": 48589.94921875,
14
+ "learning_rate": 6.377551020408164e-08,
15
+ "loss": 2.0884,
16
+ "step": 5
17
+ },
18
+ {
19
+ "epoch": 0.025510204081632654,
20
+ "grad_norm": 50532.125,
21
+ "learning_rate": 1.2755102040816328e-07,
22
+ "loss": 2.0887,
23
+ "step": 10
24
+ },
25
+ {
26
+ "epoch": 0.03826530612244898,
27
+ "grad_norm": 50246.4296875,
28
+ "learning_rate": 1.913265306122449e-07,
29
+ "loss": 2.0885,
30
+ "step": 15
31
+ },
32
+ {
33
+ "epoch": 0.05102040816326531,
34
+ "grad_norm": 57370.44140625,
35
+ "learning_rate": 2.5510204081632656e-07,
36
+ "loss": 2.0908,
37
+ "step": 20
38
+ },
39
+ {
40
+ "epoch": 0.06377551020408163,
41
+ "grad_norm": 40133.53125,
42
+ "learning_rate": 3.188775510204082e-07,
43
+ "loss": 2.0889,
44
+ "step": 25
45
+ },
46
+ {
47
+ "epoch": 0.07653061224489796,
48
+ "grad_norm": 58377.3671875,
49
+ "learning_rate": 3.826530612244898e-07,
50
+ "loss": 2.0874,
51
+ "step": 30
52
+ },
53
+ {
54
+ "epoch": 0.08928571428571429,
55
+ "grad_norm": 50888.7421875,
56
+ "learning_rate": 4.4642857142857147e-07,
57
+ "loss": 2.088,
58
+ "step": 35
59
+ },
60
+ {
61
+ "epoch": 0.10204081632653061,
62
+ "grad_norm": 44107.75390625,
63
+ "learning_rate": 5.102040816326531e-07,
64
+ "loss": 2.0872,
65
+ "step": 40
66
+ },
67
+ {
68
+ "epoch": 0.11479591836734694,
69
+ "grad_norm": 62939.18359375,
70
+ "learning_rate": 5.739795918367347e-07,
71
+ "loss": 2.0873,
72
+ "step": 45
73
+ },
74
+ {
75
+ "epoch": 0.12755102040816327,
76
+ "grad_norm": 42077.53515625,
77
+ "learning_rate": 6.377551020408164e-07,
78
+ "loss": 2.0852,
79
+ "step": 50
80
+ },
81
+ {
82
+ "epoch": 0.14030612244897958,
83
+ "grad_norm": 50233.00390625,
84
+ "learning_rate": 7.015306122448979e-07,
85
+ "loss": 2.0861,
86
+ "step": 55
87
+ },
88
+ {
89
+ "epoch": 0.15306122448979592,
90
+ "grad_norm": 60839.4765625,
91
+ "learning_rate": 7.653061224489796e-07,
92
+ "loss": 2.0856,
93
+ "step": 60
94
+ },
95
+ {
96
+ "epoch": 0.16581632653061223,
97
+ "grad_norm": 57499.3515625,
98
+ "learning_rate": 8.290816326530612e-07,
99
+ "loss": 2.0838,
100
+ "step": 65
101
+ },
102
+ {
103
+ "epoch": 0.17857142857142858,
104
+ "grad_norm": 65030.765625,
105
+ "learning_rate": 8.928571428571429e-07,
106
+ "loss": 2.083,
107
+ "step": 70
108
+ },
109
+ {
110
+ "epoch": 0.1913265306122449,
111
+ "grad_norm": 53192.35546875,
112
+ "learning_rate": 9.566326530612244e-07,
113
+ "loss": 2.0841,
114
+ "step": 75
115
+ },
116
+ {
117
+ "epoch": 0.20408163265306123,
118
+ "grad_norm": 52991.80078125,
119
+ "learning_rate": 1.0204081632653063e-06,
120
+ "loss": 2.0817,
121
+ "step": 80
122
+ },
123
+ {
124
+ "epoch": 0.21683673469387754,
125
+ "grad_norm": 48656.234375,
126
+ "learning_rate": 1.0841836734693879e-06,
127
+ "loss": 2.0813,
128
+ "step": 85
129
+ },
130
+ {
131
+ "epoch": 0.22959183673469388,
132
+ "grad_norm": 63459.2421875,
133
+ "learning_rate": 1.1479591836734695e-06,
134
+ "loss": 2.081,
135
+ "step": 90
136
+ },
137
+ {
138
+ "epoch": 0.2423469387755102,
139
+ "grad_norm": 47800.3515625,
140
+ "learning_rate": 1.211734693877551e-06,
141
+ "loss": 2.0775,
142
+ "step": 95
143
+ },
144
+ {
145
+ "epoch": 0.25510204081632654,
146
+ "grad_norm": 64353.37890625,
147
+ "learning_rate": 1.2755102040816329e-06,
148
+ "loss": 2.0772,
149
+ "step": 100
150
+ },
151
+ {
152
+ "epoch": 0.26785714285714285,
153
+ "grad_norm": 59652.29296875,
154
+ "learning_rate": 1.3392857142857143e-06,
155
+ "loss": 2.0779,
156
+ "step": 105
157
+ },
158
+ {
159
+ "epoch": 0.28061224489795916,
160
+ "grad_norm": 44752.69140625,
161
+ "learning_rate": 1.4030612244897959e-06,
162
+ "loss": 2.0764,
163
+ "step": 110
164
+ },
165
+ {
166
+ "epoch": 0.29336734693877553,
167
+ "grad_norm": 49883.0,
168
+ "learning_rate": 1.4668367346938777e-06,
169
+ "loss": 2.0763,
170
+ "step": 115
171
+ },
172
+ {
173
+ "epoch": 0.30612244897959184,
174
+ "grad_norm": 65950.28125,
175
+ "learning_rate": 1.5306122448979593e-06,
176
+ "loss": 2.0739,
177
+ "step": 120
178
+ },
179
+ {
180
+ "epoch": 0.31887755102040816,
181
+ "grad_norm": 61354.83203125,
182
+ "learning_rate": 1.5943877551020409e-06,
183
+ "loss": 2.0706,
184
+ "step": 125
185
+ },
186
+ {
187
+ "epoch": 0.33163265306122447,
188
+ "grad_norm": 53169.91796875,
189
+ "learning_rate": 1.6581632653061225e-06,
190
+ "loss": 2.0709,
191
+ "step": 130
192
+ },
193
+ {
194
+ "epoch": 0.34438775510204084,
195
+ "grad_norm": 55883.31640625,
196
+ "learning_rate": 1.7219387755102043e-06,
197
+ "loss": 2.0695,
198
+ "step": 135
199
+ },
200
+ {
201
+ "epoch": 0.35714285714285715,
202
+ "grad_norm": 38134.765625,
203
+ "learning_rate": 1.7857142857142859e-06,
204
+ "loss": 2.0675,
205
+ "step": 140
206
+ },
207
+ {
208
+ "epoch": 0.36989795918367346,
209
+ "grad_norm": 53920.7265625,
210
+ "learning_rate": 1.8494897959183675e-06,
211
+ "loss": 2.0659,
212
+ "step": 145
213
+ },
214
+ {
215
+ "epoch": 0.3826530612244898,
216
+ "grad_norm": 68777.28125,
217
+ "learning_rate": 1.913265306122449e-06,
218
+ "loss": 2.0638,
219
+ "step": 150
220
+ },
221
+ {
222
+ "epoch": 0.39540816326530615,
223
+ "grad_norm": 46247.8984375,
224
+ "learning_rate": 1.977040816326531e-06,
225
+ "loss": 2.0656,
226
+ "step": 155
227
+ },
228
+ {
229
+ "epoch": 0.40816326530612246,
230
+ "grad_norm": 49636.04296875,
231
+ "learning_rate": 2.0408163265306125e-06,
232
+ "loss": 2.0621,
233
+ "step": 160
234
+ },
235
+ {
236
+ "epoch": 0.42091836734693877,
237
+ "grad_norm": 51880.3515625,
238
+ "learning_rate": 2.104591836734694e-06,
239
+ "loss": 2.057,
240
+ "step": 165
241
+ },
242
+ {
243
+ "epoch": 0.4336734693877551,
244
+ "grad_norm": 52808.734375,
245
+ "learning_rate": 2.1683673469387757e-06,
246
+ "loss": 2.0585,
247
+ "step": 170
248
+ },
249
+ {
250
+ "epoch": 0.44642857142857145,
251
+ "grad_norm": 46398.125,
252
+ "learning_rate": 2.2321428571428573e-06,
253
+ "loss": 2.0505,
254
+ "step": 175
255
+ },
256
+ {
257
+ "epoch": 0.45918367346938777,
258
+ "grad_norm": 59347.2578125,
259
+ "learning_rate": 2.295918367346939e-06,
260
+ "loss": 2.0487,
261
+ "step": 180
262
+ },
263
+ {
264
+ "epoch": 0.4719387755102041,
265
+ "grad_norm": 58343.73828125,
266
+ "learning_rate": 2.3596938775510205e-06,
267
+ "loss": 2.0563,
268
+ "step": 185
269
+ },
270
+ {
271
+ "epoch": 0.4846938775510204,
272
+ "grad_norm": 43836.42578125,
273
+ "learning_rate": 2.423469387755102e-06,
274
+ "loss": 2.0486,
275
+ "step": 190
276
+ },
277
+ {
278
+ "epoch": 0.49744897959183676,
279
+ "grad_norm": 69661.5859375,
280
+ "learning_rate": 2.487244897959184e-06,
281
+ "loss": 2.0443,
282
+ "step": 195
283
+ },
284
+ {
285
+ "epoch": 0.5102040816326531,
286
+ "grad_norm": 53888.24609375,
287
+ "learning_rate": 2.5510204081632657e-06,
288
+ "loss": 2.0475,
289
+ "step": 200
290
+ },
291
+ {
292
+ "epoch": 0.5229591836734694,
293
+ "grad_norm": 50369.1640625,
294
+ "learning_rate": 2.6147959183673473e-06,
295
+ "loss": 2.035,
296
+ "step": 205
297
+ },
298
+ {
299
+ "epoch": 0.5357142857142857,
300
+ "grad_norm": 62733.9609375,
301
+ "learning_rate": 2.6785714285714285e-06,
302
+ "loss": 2.0354,
303
+ "step": 210
304
+ },
305
+ {
306
+ "epoch": 0.548469387755102,
307
+ "grad_norm": 48340.67578125,
308
+ "learning_rate": 2.74234693877551e-06,
309
+ "loss": 2.0373,
310
+ "step": 215
311
+ },
312
+ {
313
+ "epoch": 0.5612244897959183,
314
+ "grad_norm": 50353.734375,
315
+ "learning_rate": 2.8061224489795917e-06,
316
+ "loss": 2.0389,
317
+ "step": 220
318
+ },
319
+ {
320
+ "epoch": 0.5739795918367347,
321
+ "grad_norm": 62351.765625,
322
+ "learning_rate": 2.869897959183674e-06,
323
+ "loss": 2.0263,
324
+ "step": 225
325
+ },
326
+ {
327
+ "epoch": 0.5867346938775511,
328
+ "grad_norm": 73855.609375,
329
+ "learning_rate": 2.9336734693877553e-06,
330
+ "loss": 2.0269,
331
+ "step": 230
332
+ },
333
+ {
334
+ "epoch": 0.5994897959183674,
335
+ "grad_norm": 84417.859375,
336
+ "learning_rate": 2.997448979591837e-06,
337
+ "loss": 2.0311,
338
+ "step": 235
339
+ },
340
+ {
341
+ "epoch": 0.6122448979591837,
342
+ "grad_norm": 57347.55078125,
343
+ "learning_rate": 3.0612244897959185e-06,
344
+ "loss": 2.0239,
345
+ "step": 240
346
+ },
347
+ {
348
+ "epoch": 0.625,
349
+ "grad_norm": 65611.1875,
350
+ "learning_rate": 3.125e-06,
351
+ "loss": 2.0064,
352
+ "step": 245
353
+ },
354
+ {
355
+ "epoch": 0.6377551020408163,
356
+ "grad_norm": 70810.75,
357
+ "learning_rate": 3.1887755102040818e-06,
358
+ "loss": 2.0224,
359
+ "step": 250
360
+ },
361
+ {
362
+ "epoch": 0.6505102040816326,
363
+ "grad_norm": 46479.8828125,
364
+ "learning_rate": 3.2525510204081634e-06,
365
+ "loss": 2.0057,
366
+ "step": 255
367
+ },
368
+ {
369
+ "epoch": 0.6632653061224489,
370
+ "grad_norm": 34124.89453125,
371
+ "learning_rate": 3.316326530612245e-06,
372
+ "loss": 2.0135,
373
+ "step": 260
374
+ },
375
+ {
376
+ "epoch": 0.6760204081632653,
377
+ "grad_norm": 53196.58203125,
378
+ "learning_rate": 3.3801020408163266e-06,
379
+ "loss": 2.0087,
380
+ "step": 265
381
+ },
382
+ {
383
+ "epoch": 0.6887755102040817,
384
+ "grad_norm": 64588.515625,
385
+ "learning_rate": 3.4438775510204086e-06,
386
+ "loss": 2.0006,
387
+ "step": 270
388
+ },
389
+ {
390
+ "epoch": 0.701530612244898,
391
+ "grad_norm": 73780.546875,
392
+ "learning_rate": 3.50765306122449e-06,
393
+ "loss": 1.9965,
394
+ "step": 275
395
+ },
396
+ {
397
+ "epoch": 0.7142857142857143,
398
+ "grad_norm": 63101.05859375,
399
+ "learning_rate": 3.5714285714285718e-06,
400
+ "loss": 2.0005,
401
+ "step": 280
402
+ },
403
+ {
404
+ "epoch": 0.7270408163265306,
405
+ "grad_norm": 78616.109375,
406
+ "learning_rate": 3.6352040816326534e-06,
407
+ "loss": 1.9904,
408
+ "step": 285
409
+ },
410
+ {
411
+ "epoch": 0.7397959183673469,
412
+ "grad_norm": 79120.6484375,
413
+ "learning_rate": 3.698979591836735e-06,
414
+ "loss": 1.9891,
415
+ "step": 290
416
+ },
417
+ {
418
+ "epoch": 0.7525510204081632,
419
+ "grad_norm": 92711.09375,
420
+ "learning_rate": 3.7627551020408166e-06,
421
+ "loss": 1.9611,
422
+ "step": 295
423
+ },
424
+ {
425
+ "epoch": 0.7653061224489796,
426
+ "grad_norm": 77935.4765625,
427
+ "learning_rate": 3.826530612244898e-06,
428
+ "loss": 1.9746,
429
+ "step": 300
430
+ },
431
+ {
432
+ "epoch": 0.7780612244897959,
433
+ "grad_norm": 85825.375,
434
+ "learning_rate": 3.89030612244898e-06,
435
+ "loss": 1.9753,
436
+ "step": 305
437
+ },
438
+ {
439
+ "epoch": 0.7908163265306123,
440
+ "grad_norm": 65178.671875,
441
+ "learning_rate": 3.954081632653062e-06,
442
+ "loss": 1.9534,
443
+ "step": 310
444
+ },
445
+ {
446
+ "epoch": 0.8035714285714286,
447
+ "grad_norm": 71973.671875,
448
+ "learning_rate": 4.017857142857143e-06,
449
+ "loss": 1.9474,
450
+ "step": 315
451
+ },
452
+ {
453
+ "epoch": 0.8163265306122449,
454
+ "grad_norm": 88983.125,
455
+ "learning_rate": 4.081632653061225e-06,
456
+ "loss": 1.9492,
457
+ "step": 320
458
+ },
459
+ {
460
+ "epoch": 0.8290816326530612,
461
+ "grad_norm": 76345.84375,
462
+ "learning_rate": 4.145408163265306e-06,
463
+ "loss": 1.9513,
464
+ "step": 325
465
+ },
466
+ {
467
+ "epoch": 0.8418367346938775,
468
+ "grad_norm": 64801.640625,
469
+ "learning_rate": 4.209183673469388e-06,
470
+ "loss": 1.9583,
471
+ "step": 330
472
+ },
473
+ {
474
+ "epoch": 0.8545918367346939,
475
+ "grad_norm": 72903.8203125,
476
+ "learning_rate": 4.272959183673469e-06,
477
+ "loss": 1.9579,
478
+ "step": 335
479
+ },
480
+ {
481
+ "epoch": 0.8673469387755102,
482
+ "grad_norm": 65284.796875,
483
+ "learning_rate": 4.336734693877551e-06,
484
+ "loss": 1.9272,
485
+ "step": 340
486
+ },
487
+ {
488
+ "epoch": 0.8801020408163265,
489
+ "grad_norm": 65237.38671875,
490
+ "learning_rate": 4.400510204081633e-06,
491
+ "loss": 1.9065,
492
+ "step": 345
493
+ },
494
+ {
495
+ "epoch": 0.8928571428571429,
496
+ "grad_norm": 79606.9296875,
497
+ "learning_rate": 4.464285714285715e-06,
498
+ "loss": 1.9013,
499
+ "step": 350
500
+ },
501
+ {
502
+ "epoch": 0.9056122448979592,
503
+ "grad_norm": 76137.6328125,
504
+ "learning_rate": 4.528061224489797e-06,
505
+ "loss": 1.8892,
506
+ "step": 355
507
+ },
508
+ {
509
+ "epoch": 0.9183673469387755,
510
+ "grad_norm": 40717.60546875,
511
+ "learning_rate": 4.591836734693878e-06,
512
+ "loss": 1.9072,
513
+ "step": 360
514
+ },
515
+ {
516
+ "epoch": 0.9311224489795918,
517
+ "grad_norm": 110416.125,
518
+ "learning_rate": 4.65561224489796e-06,
519
+ "loss": 1.9024,
520
+ "step": 365
521
+ },
522
+ {
523
+ "epoch": 0.9438775510204082,
524
+ "grad_norm": 99101.6875,
525
+ "learning_rate": 4.719387755102041e-06,
526
+ "loss": 1.8979,
527
+ "step": 370
528
+ },
529
+ {
530
+ "epoch": 0.9566326530612245,
531
+ "grad_norm": 86707.7109375,
532
+ "learning_rate": 4.783163265306123e-06,
533
+ "loss": 1.878,
534
+ "step": 375
535
+ },
536
+ {
537
+ "epoch": 0.9693877551020408,
538
+ "grad_norm": 85074.75,
539
+ "learning_rate": 4.846938775510204e-06,
540
+ "loss": 1.871,
541
+ "step": 380
542
+ },
543
+ {
544
+ "epoch": 0.9821428571428571,
545
+ "grad_norm": 47668.7109375,
546
+ "learning_rate": 4.910714285714286e-06,
547
+ "loss": 1.8762,
548
+ "step": 385
549
+ },
550
+ {
551
+ "epoch": 0.9948979591836735,
552
+ "grad_norm": 133846.6875,
553
+ "learning_rate": 4.974489795918368e-06,
554
+ "loss": 1.8344,
555
+ "step": 390
556
+ },
557
+ {
558
+ "epoch": 1.0,
559
+ "eval_accuracy": 0.0857774206508638,
560
+ "eval_loss": 1.9574071168899536,
561
+ "eval_runtime": 313.0247,
562
+ "eval_samples_per_second": 15.903,
563
+ "eval_steps_per_second": 0.53,
564
+ "step": 392
565
+ }
566
+ ],
567
+ "logging_steps": 5,
568
+ "max_steps": 3920,
569
+ "num_input_tokens_seen": 0,
570
+ "num_train_epochs": 10,
571
+ "save_steps": 500,
572
+ "stateful_callbacks": {
573
+ "TrainerControl": {
574
+ "args": {
575
+ "should_epoch_stop": false,
576
+ "should_evaluate": false,
577
+ "should_log": false,
578
+ "should_save": true,
579
+ "should_training_stop": false
580
+ },
581
+ "attributes": {}
582
+ }
583
+ },
584
+ "total_flos": 1.49679069336576e+18,
585
+ "train_batch_size": 30,
586
+ "trial_name": null,
587
+ "trial_params": null
588
+ }
checkpoint-392/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62d4afa24b2e5344ef9e2ace3afc7237855a36ba40c6701cd39cbf7db81b4cdc
3
+ size 5176