hr16 commited on
Commit
60b053d
1 Parent(s): bc7181b

Training in progress, epoch 1, checkpoint

Browse files
checkpoint-490/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-490/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d0d305fe7d18469c699f8af09c6de8da15fc09dd157923c393d45244eee618a
3
+ size 358419776
checkpoint-490/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e024c7520678d099db15655cafdb1a32b8075d7cec9982d084593288c14dee31
3
+ size 707744314
checkpoint-490/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-490/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e98eae4f9ae907154431d389ab6aacd1b74927fc40870899dd45e9190a76fa7c
3
+ size 14244
checkpoint-490/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cecb4841553cbca36671362c8184bc7ac16a241bbc226dd8692e56cbe168e94
3
+ size 1064
checkpoint-490/trainer_state.json ADDED
@@ -0,0 +1,728 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8470824949698189,
3
+ "best_model_checkpoint": "PhoWhisper-small-vispeech-classifier-v4/checkpoint-490",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 490,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01020408163265306,
13
+ "grad_norm": 56193.578125,
14
+ "learning_rate": 2.5510204081632652e-08,
15
+ "loss": 2.0798,
16
+ "step": 5
17
+ },
18
+ {
19
+ "epoch": 0.02040816326530612,
20
+ "grad_norm": 50520.33203125,
21
+ "learning_rate": 5.1020408163265303e-08,
22
+ "loss": 2.0772,
23
+ "step": 10
24
+ },
25
+ {
26
+ "epoch": 0.030612244897959183,
27
+ "grad_norm": 47583.30859375,
28
+ "learning_rate": 7.653061224489796e-08,
29
+ "loss": 2.0762,
30
+ "step": 15
31
+ },
32
+ {
33
+ "epoch": 0.04081632653061224,
34
+ "grad_norm": 53174.3828125,
35
+ "learning_rate": 1.0204081632653061e-07,
36
+ "loss": 2.0754,
37
+ "step": 20
38
+ },
39
+ {
40
+ "epoch": 0.05102040816326531,
41
+ "grad_norm": 65972.65625,
42
+ "learning_rate": 1.2755102040816328e-07,
43
+ "loss": 2.0755,
44
+ "step": 25
45
+ },
46
+ {
47
+ "epoch": 0.061224489795918366,
48
+ "grad_norm": 53920.14453125,
49
+ "learning_rate": 1.5306122448979592e-07,
50
+ "loss": 2.0745,
51
+ "step": 30
52
+ },
53
+ {
54
+ "epoch": 0.07142857142857142,
55
+ "grad_norm": 52966.375,
56
+ "learning_rate": 1.7857142857142858e-07,
57
+ "loss": 2.0734,
58
+ "step": 35
59
+ },
60
+ {
61
+ "epoch": 0.08163265306122448,
62
+ "grad_norm": 60549.94921875,
63
+ "learning_rate": 2.0408163265306121e-07,
64
+ "loss": 2.0778,
65
+ "step": 40
66
+ },
67
+ {
68
+ "epoch": 0.09183673469387756,
69
+ "grad_norm": 55827.60546875,
70
+ "learning_rate": 2.295918367346939e-07,
71
+ "loss": 2.0787,
72
+ "step": 45
73
+ },
74
+ {
75
+ "epoch": 0.10204081632653061,
76
+ "grad_norm": 51334.3359375,
77
+ "learning_rate": 2.5510204081632656e-07,
78
+ "loss": 2.0759,
79
+ "step": 50
80
+ },
81
+ {
82
+ "epoch": 0.11224489795918367,
83
+ "grad_norm": 70249.5078125,
84
+ "learning_rate": 2.806122448979592e-07,
85
+ "loss": 2.0698,
86
+ "step": 55
87
+ },
88
+ {
89
+ "epoch": 0.12244897959183673,
90
+ "grad_norm": 54763.26171875,
91
+ "learning_rate": 3.0612244897959183e-07,
92
+ "loss": 2.0762,
93
+ "step": 60
94
+ },
95
+ {
96
+ "epoch": 0.1326530612244898,
97
+ "grad_norm": 58244.69921875,
98
+ "learning_rate": 3.3163265306122455e-07,
99
+ "loss": 2.0696,
100
+ "step": 65
101
+ },
102
+ {
103
+ "epoch": 0.14285714285714285,
104
+ "grad_norm": 51894.46484375,
105
+ "learning_rate": 3.5714285714285716e-07,
106
+ "loss": 2.0702,
107
+ "step": 70
108
+ },
109
+ {
110
+ "epoch": 0.15306122448979592,
111
+ "grad_norm": 72845.734375,
112
+ "learning_rate": 3.826530612244898e-07,
113
+ "loss": 2.0676,
114
+ "step": 75
115
+ },
116
+ {
117
+ "epoch": 0.16326530612244897,
118
+ "grad_norm": 56673.85546875,
119
+ "learning_rate": 4.0816326530612243e-07,
120
+ "loss": 2.0693,
121
+ "step": 80
122
+ },
123
+ {
124
+ "epoch": 0.17346938775510204,
125
+ "grad_norm": 61739.0546875,
126
+ "learning_rate": 4.3367346938775514e-07,
127
+ "loss": 2.0668,
128
+ "step": 85
129
+ },
130
+ {
131
+ "epoch": 0.1836734693877551,
132
+ "grad_norm": 68551.390625,
133
+ "learning_rate": 4.591836734693878e-07,
134
+ "loss": 2.0651,
135
+ "step": 90
136
+ },
137
+ {
138
+ "epoch": 0.19387755102040816,
139
+ "grad_norm": 55835.78125,
140
+ "learning_rate": 4.846938775510205e-07,
141
+ "loss": 2.0701,
142
+ "step": 95
143
+ },
144
+ {
145
+ "epoch": 0.20408163265306123,
146
+ "grad_norm": 60520.2734375,
147
+ "learning_rate": 5.102040816326531e-07,
148
+ "loss": 2.0654,
149
+ "step": 100
150
+ },
151
+ {
152
+ "epoch": 0.21428571428571427,
153
+ "grad_norm": 45642.94921875,
154
+ "learning_rate": 5.357142857142857e-07,
155
+ "loss": 2.0672,
156
+ "step": 105
157
+ },
158
+ {
159
+ "epoch": 0.22448979591836735,
160
+ "grad_norm": 67603.8515625,
161
+ "learning_rate": 5.612244897959184e-07,
162
+ "loss": 2.0673,
163
+ "step": 110
164
+ },
165
+ {
166
+ "epoch": 0.23469387755102042,
167
+ "grad_norm": 54359.4375,
168
+ "learning_rate": 5.867346938775511e-07,
169
+ "loss": 2.0604,
170
+ "step": 115
171
+ },
172
+ {
173
+ "epoch": 0.24489795918367346,
174
+ "grad_norm": 81289.5390625,
175
+ "learning_rate": 6.122448979591837e-07,
176
+ "loss": 2.061,
177
+ "step": 120
178
+ },
179
+ {
180
+ "epoch": 0.25510204081632654,
181
+ "grad_norm": 70781.5703125,
182
+ "learning_rate": 6.377551020408164e-07,
183
+ "loss": 2.0573,
184
+ "step": 125
185
+ },
186
+ {
187
+ "epoch": 0.2653061224489796,
188
+ "grad_norm": 73178.1875,
189
+ "learning_rate": 6.632653061224491e-07,
190
+ "loss": 2.0541,
191
+ "step": 130
192
+ },
193
+ {
194
+ "epoch": 0.2755102040816326,
195
+ "grad_norm": 69632.25,
196
+ "learning_rate": 6.887755102040817e-07,
197
+ "loss": 2.0603,
198
+ "step": 135
199
+ },
200
+ {
201
+ "epoch": 0.2857142857142857,
202
+ "grad_norm": 54642.47265625,
203
+ "learning_rate": 7.142857142857143e-07,
204
+ "loss": 2.0587,
205
+ "step": 140
206
+ },
207
+ {
208
+ "epoch": 0.29591836734693877,
209
+ "grad_norm": 64884.2890625,
210
+ "learning_rate": 7.39795918367347e-07,
211
+ "loss": 2.0574,
212
+ "step": 145
213
+ },
214
+ {
215
+ "epoch": 0.30612244897959184,
216
+ "grad_norm": 74709.9609375,
217
+ "learning_rate": 7.653061224489796e-07,
218
+ "loss": 2.0466,
219
+ "step": 150
220
+ },
221
+ {
222
+ "epoch": 0.3163265306122449,
223
+ "grad_norm": 59361.31640625,
224
+ "learning_rate": 7.908163265306124e-07,
225
+ "loss": 2.0473,
226
+ "step": 155
227
+ },
228
+ {
229
+ "epoch": 0.32653061224489793,
230
+ "grad_norm": 76060.171875,
231
+ "learning_rate": 8.163265306122449e-07,
232
+ "loss": 2.0413,
233
+ "step": 160
234
+ },
235
+ {
236
+ "epoch": 0.336734693877551,
237
+ "grad_norm": 52821.26953125,
238
+ "learning_rate": 8.418367346938776e-07,
239
+ "loss": 2.0495,
240
+ "step": 165
241
+ },
242
+ {
243
+ "epoch": 0.3469387755102041,
244
+ "grad_norm": 55647.62109375,
245
+ "learning_rate": 8.673469387755103e-07,
246
+ "loss": 2.0361,
247
+ "step": 170
248
+ },
249
+ {
250
+ "epoch": 0.35714285714285715,
251
+ "grad_norm": 49648.828125,
252
+ "learning_rate": 8.928571428571429e-07,
253
+ "loss": 2.0395,
254
+ "step": 175
255
+ },
256
+ {
257
+ "epoch": 0.3673469387755102,
258
+ "grad_norm": 63527.9140625,
259
+ "learning_rate": 9.183673469387756e-07,
260
+ "loss": 2.0334,
261
+ "step": 180
262
+ },
263
+ {
264
+ "epoch": 0.37755102040816324,
265
+ "grad_norm": 80417.828125,
266
+ "learning_rate": 9.438775510204082e-07,
267
+ "loss": 2.0331,
268
+ "step": 185
269
+ },
270
+ {
271
+ "epoch": 0.3877551020408163,
272
+ "grad_norm": 82782.7265625,
273
+ "learning_rate": 9.69387755102041e-07,
274
+ "loss": 2.0251,
275
+ "step": 190
276
+ },
277
+ {
278
+ "epoch": 0.3979591836734694,
279
+ "grad_norm": 66964.8125,
280
+ "learning_rate": 9.948979591836735e-07,
281
+ "loss": 2.0289,
282
+ "step": 195
283
+ },
284
+ {
285
+ "epoch": 0.40816326530612246,
286
+ "grad_norm": 73848.046875,
287
+ "learning_rate": 1.0204081632653063e-06,
288
+ "loss": 2.0259,
289
+ "step": 200
290
+ },
291
+ {
292
+ "epoch": 0.41836734693877553,
293
+ "grad_norm": 70241.171875,
294
+ "learning_rate": 1.0459183673469388e-06,
295
+ "loss": 2.0082,
296
+ "step": 205
297
+ },
298
+ {
299
+ "epoch": 0.42857142857142855,
300
+ "grad_norm": 63360.8125,
301
+ "learning_rate": 1.0714285714285714e-06,
302
+ "loss": 2.0091,
303
+ "step": 210
304
+ },
305
+ {
306
+ "epoch": 0.4387755102040816,
307
+ "grad_norm": 82052.796875,
308
+ "learning_rate": 1.0969387755102041e-06,
309
+ "loss": 2.0008,
310
+ "step": 215
311
+ },
312
+ {
313
+ "epoch": 0.4489795918367347,
314
+ "grad_norm": 63768.30078125,
315
+ "learning_rate": 1.122448979591837e-06,
316
+ "loss": 1.9958,
317
+ "step": 220
318
+ },
319
+ {
320
+ "epoch": 0.45918367346938777,
321
+ "grad_norm": 90230.640625,
322
+ "learning_rate": 1.1479591836734695e-06,
323
+ "loss": 1.9816,
324
+ "step": 225
325
+ },
326
+ {
327
+ "epoch": 0.46938775510204084,
328
+ "grad_norm": 48253.55078125,
329
+ "learning_rate": 1.1734693877551022e-06,
330
+ "loss": 2.0064,
331
+ "step": 230
332
+ },
333
+ {
334
+ "epoch": 0.47959183673469385,
335
+ "grad_norm": 73846.0859375,
336
+ "learning_rate": 1.1989795918367348e-06,
337
+ "loss": 1.996,
338
+ "step": 235
339
+ },
340
+ {
341
+ "epoch": 0.4897959183673469,
342
+ "grad_norm": 86008.8046875,
343
+ "learning_rate": 1.2244897959183673e-06,
344
+ "loss": 1.9858,
345
+ "step": 240
346
+ },
347
+ {
348
+ "epoch": 0.5,
349
+ "grad_norm": 86437.734375,
350
+ "learning_rate": 1.25e-06,
351
+ "loss": 1.9696,
352
+ "step": 245
353
+ },
354
+ {
355
+ "epoch": 0.5102040816326531,
356
+ "grad_norm": 82227.921875,
357
+ "learning_rate": 1.2755102040816329e-06,
358
+ "loss": 1.9803,
359
+ "step": 250
360
+ },
361
+ {
362
+ "epoch": 0.5204081632653061,
363
+ "grad_norm": 96575.4765625,
364
+ "learning_rate": 1.3010204081632654e-06,
365
+ "loss": 1.9375,
366
+ "step": 255
367
+ },
368
+ {
369
+ "epoch": 0.5306122448979592,
370
+ "grad_norm": 89167.7265625,
371
+ "learning_rate": 1.3265306122448982e-06,
372
+ "loss": 1.9585,
373
+ "step": 260
374
+ },
375
+ {
376
+ "epoch": 0.5408163265306123,
377
+ "grad_norm": 101032.5,
378
+ "learning_rate": 1.3520408163265307e-06,
379
+ "loss": 1.947,
380
+ "step": 265
381
+ },
382
+ {
383
+ "epoch": 0.5510204081632653,
384
+ "grad_norm": 105424.25,
385
+ "learning_rate": 1.3775510204081633e-06,
386
+ "loss": 1.9482,
387
+ "step": 270
388
+ },
389
+ {
390
+ "epoch": 0.5612244897959183,
391
+ "grad_norm": 84136.484375,
392
+ "learning_rate": 1.4030612244897959e-06,
393
+ "loss": 1.9386,
394
+ "step": 275
395
+ },
396
+ {
397
+ "epoch": 0.5714285714285714,
398
+ "grad_norm": 83034.078125,
399
+ "learning_rate": 1.4285714285714286e-06,
400
+ "loss": 1.9245,
401
+ "step": 280
402
+ },
403
+ {
404
+ "epoch": 0.5816326530612245,
405
+ "grad_norm": 89200.4609375,
406
+ "learning_rate": 1.4540816326530614e-06,
407
+ "loss": 1.9138,
408
+ "step": 285
409
+ },
410
+ {
411
+ "epoch": 0.5918367346938775,
412
+ "grad_norm": 103667.9609375,
413
+ "learning_rate": 1.479591836734694e-06,
414
+ "loss": 1.9283,
415
+ "step": 290
416
+ },
417
+ {
418
+ "epoch": 0.6020408163265306,
419
+ "grad_norm": 98443.2734375,
420
+ "learning_rate": 1.5051020408163267e-06,
421
+ "loss": 1.9025,
422
+ "step": 295
423
+ },
424
+ {
425
+ "epoch": 0.6122448979591837,
426
+ "grad_norm": 99525.0,
427
+ "learning_rate": 1.5306122448979593e-06,
428
+ "loss": 1.8933,
429
+ "step": 300
430
+ },
431
+ {
432
+ "epoch": 0.6224489795918368,
433
+ "grad_norm": 145139.5625,
434
+ "learning_rate": 1.556122448979592e-06,
435
+ "loss": 1.8563,
436
+ "step": 305
437
+ },
438
+ {
439
+ "epoch": 0.6326530612244898,
440
+ "grad_norm": 116158.859375,
441
+ "learning_rate": 1.5816326530612248e-06,
442
+ "loss": 1.8931,
443
+ "step": 310
444
+ },
445
+ {
446
+ "epoch": 0.6428571428571429,
447
+ "grad_norm": 131590.09375,
448
+ "learning_rate": 1.6071428571428574e-06,
449
+ "loss": 1.8599,
450
+ "step": 315
451
+ },
452
+ {
453
+ "epoch": 0.6530612244897959,
454
+ "grad_norm": 112483.40625,
455
+ "learning_rate": 1.6326530612244897e-06,
456
+ "loss": 1.8596,
457
+ "step": 320
458
+ },
459
+ {
460
+ "epoch": 0.6632653061224489,
461
+ "grad_norm": 82979.0859375,
462
+ "learning_rate": 1.6581632653061225e-06,
463
+ "loss": 1.883,
464
+ "step": 325
465
+ },
466
+ {
467
+ "epoch": 0.673469387755102,
468
+ "grad_norm": 96548.5703125,
469
+ "learning_rate": 1.6836734693877552e-06,
470
+ "loss": 1.8586,
471
+ "step": 330
472
+ },
473
+ {
474
+ "epoch": 0.6836734693877551,
475
+ "grad_norm": 113625.171875,
476
+ "learning_rate": 1.7091836734693878e-06,
477
+ "loss": 1.8375,
478
+ "step": 335
479
+ },
480
+ {
481
+ "epoch": 0.6938775510204082,
482
+ "grad_norm": 115079.0078125,
483
+ "learning_rate": 1.7346938775510206e-06,
484
+ "loss": 1.838,
485
+ "step": 340
486
+ },
487
+ {
488
+ "epoch": 0.7040816326530612,
489
+ "grad_norm": 139868.21875,
490
+ "learning_rate": 1.7602040816326531e-06,
491
+ "loss": 1.8013,
492
+ "step": 345
493
+ },
494
+ {
495
+ "epoch": 0.7142857142857143,
496
+ "grad_norm": 126350.546875,
497
+ "learning_rate": 1.7857142857142859e-06,
498
+ "loss": 1.847,
499
+ "step": 350
500
+ },
501
+ {
502
+ "epoch": 0.7244897959183674,
503
+ "grad_norm": 149690.375,
504
+ "learning_rate": 1.8112244897959187e-06,
505
+ "loss": 1.8203,
506
+ "step": 355
507
+ },
508
+ {
509
+ "epoch": 0.7346938775510204,
510
+ "grad_norm": 132708.578125,
511
+ "learning_rate": 1.8367346938775512e-06,
512
+ "loss": 1.7931,
513
+ "step": 360
514
+ },
515
+ {
516
+ "epoch": 0.7448979591836735,
517
+ "grad_norm": 128203.3203125,
518
+ "learning_rate": 1.862244897959184e-06,
519
+ "loss": 1.7533,
520
+ "step": 365
521
+ },
522
+ {
523
+ "epoch": 0.7551020408163265,
524
+ "grad_norm": 118367.4765625,
525
+ "learning_rate": 1.8877551020408163e-06,
526
+ "loss": 1.7662,
527
+ "step": 370
528
+ },
529
+ {
530
+ "epoch": 0.7653061224489796,
531
+ "grad_norm": 162099.25,
532
+ "learning_rate": 1.913265306122449e-06,
533
+ "loss": 1.7775,
534
+ "step": 375
535
+ },
536
+ {
537
+ "epoch": 0.7755102040816326,
538
+ "grad_norm": 132369.234375,
539
+ "learning_rate": 1.938775510204082e-06,
540
+ "loss": 1.7908,
541
+ "step": 380
542
+ },
543
+ {
544
+ "epoch": 0.7857142857142857,
545
+ "grad_norm": 161412.09375,
546
+ "learning_rate": 1.9642857142857144e-06,
547
+ "loss": 1.7045,
548
+ "step": 385
549
+ },
550
+ {
551
+ "epoch": 0.7959183673469388,
552
+ "grad_norm": 117275.65625,
553
+ "learning_rate": 1.989795918367347e-06,
554
+ "loss": 1.74,
555
+ "step": 390
556
+ },
557
+ {
558
+ "epoch": 0.8061224489795918,
559
+ "grad_norm": 134175.890625,
560
+ "learning_rate": 2.01530612244898e-06,
561
+ "loss": 1.7041,
562
+ "step": 395
563
+ },
564
+ {
565
+ "epoch": 0.8163265306122449,
566
+ "grad_norm": 165093.34375,
567
+ "learning_rate": 2.0408163265306125e-06,
568
+ "loss": 1.7217,
569
+ "step": 400
570
+ },
571
+ {
572
+ "epoch": 0.826530612244898,
573
+ "grad_norm": 108558.96875,
574
+ "learning_rate": 2.066326530612245e-06,
575
+ "loss": 1.7211,
576
+ "step": 405
577
+ },
578
+ {
579
+ "epoch": 0.8367346938775511,
580
+ "grad_norm": 159761.328125,
581
+ "learning_rate": 2.0918367346938776e-06,
582
+ "loss": 1.7056,
583
+ "step": 410
584
+ },
585
+ {
586
+ "epoch": 0.8469387755102041,
587
+ "grad_norm": 131097.640625,
588
+ "learning_rate": 2.1173469387755106e-06,
589
+ "loss": 1.7289,
590
+ "step": 415
591
+ },
592
+ {
593
+ "epoch": 0.8571428571428571,
594
+ "grad_norm": 162492.6875,
595
+ "learning_rate": 2.1428571428571427e-06,
596
+ "loss": 1.7312,
597
+ "step": 420
598
+ },
599
+ {
600
+ "epoch": 0.8673469387755102,
601
+ "grad_norm": 122069.125,
602
+ "learning_rate": 2.1683673469387757e-06,
603
+ "loss": 1.6696,
604
+ "step": 425
605
+ },
606
+ {
607
+ "epoch": 0.8775510204081632,
608
+ "grad_norm": 194332.5625,
609
+ "learning_rate": 2.1938775510204083e-06,
610
+ "loss": 1.6226,
611
+ "step": 430
612
+ },
613
+ {
614
+ "epoch": 0.8877551020408163,
615
+ "grad_norm": 132711.28125,
616
+ "learning_rate": 2.219387755102041e-06,
617
+ "loss": 1.663,
618
+ "step": 435
619
+ },
620
+ {
621
+ "epoch": 0.8979591836734694,
622
+ "grad_norm": 166239.375,
623
+ "learning_rate": 2.244897959183674e-06,
624
+ "loss": 1.6127,
625
+ "step": 440
626
+ },
627
+ {
628
+ "epoch": 0.9081632653061225,
629
+ "grad_norm": 132459.359375,
630
+ "learning_rate": 2.2704081632653064e-06,
631
+ "loss": 1.6042,
632
+ "step": 445
633
+ },
634
+ {
635
+ "epoch": 0.9183673469387755,
636
+ "grad_norm": 114693.3046875,
637
+ "learning_rate": 2.295918367346939e-06,
638
+ "loss": 1.6276,
639
+ "step": 450
640
+ },
641
+ {
642
+ "epoch": 0.9285714285714286,
643
+ "grad_norm": 184974.53125,
644
+ "learning_rate": 2.321428571428572e-06,
645
+ "loss": 1.6448,
646
+ "step": 455
647
+ },
648
+ {
649
+ "epoch": 0.9387755102040817,
650
+ "grad_norm": 134113.625,
651
+ "learning_rate": 2.3469387755102044e-06,
652
+ "loss": 1.6329,
653
+ "step": 460
654
+ },
655
+ {
656
+ "epoch": 0.9489795918367347,
657
+ "grad_norm": 137895.78125,
658
+ "learning_rate": 2.372448979591837e-06,
659
+ "loss": 1.5441,
660
+ "step": 465
661
+ },
662
+ {
663
+ "epoch": 0.9591836734693877,
664
+ "grad_norm": 158595.234375,
665
+ "learning_rate": 2.3979591836734696e-06,
666
+ "loss": 1.5524,
667
+ "step": 470
668
+ },
669
+ {
670
+ "epoch": 0.9693877551020408,
671
+ "grad_norm": 162135.703125,
672
+ "learning_rate": 2.423469387755102e-06,
673
+ "loss": 1.5796,
674
+ "step": 475
675
+ },
676
+ {
677
+ "epoch": 0.9795918367346939,
678
+ "grad_norm": 205519.296875,
679
+ "learning_rate": 2.4489795918367347e-06,
680
+ "loss": 1.5343,
681
+ "step": 480
682
+ },
683
+ {
684
+ "epoch": 0.9897959183673469,
685
+ "grad_norm": 193819.75,
686
+ "learning_rate": 2.4744897959183676e-06,
687
+ "loss": 1.5776,
688
+ "step": 485
689
+ },
690
+ {
691
+ "epoch": 1.0,
692
+ "grad_norm": 225175.609375,
693
+ "learning_rate": 2.5e-06,
694
+ "loss": 1.5384,
695
+ "step": 490
696
+ },
697
+ {
698
+ "epoch": 1.0,
699
+ "eval_accuracy": 0.8470824949698189,
700
+ "eval_loss": 1.4336239099502563,
701
+ "eval_runtime": 214.7827,
702
+ "eval_samples_per_second": 13.884,
703
+ "eval_steps_per_second": 0.582,
704
+ "step": 490
705
+ }
706
+ ],
707
+ "logging_steps": 5,
708
+ "max_steps": 4900,
709
+ "num_input_tokens_seen": 0,
710
+ "num_train_epochs": 10,
711
+ "save_steps": 500,
712
+ "stateful_callbacks": {
713
+ "TrainerControl": {
714
+ "args": {
715
+ "should_epoch_stop": false,
716
+ "should_evaluate": false,
717
+ "should_log": false,
718
+ "should_save": true,
719
+ "should_training_stop": false
720
+ },
721
+ "attributes": {}
722
+ }
723
+ },
724
+ "total_flos": 1.49679069336576e+18,
725
+ "train_batch_size": 24,
726
+ "trial_name": null,
727
+ "trial_params": null
728
+ }
checkpoint-490/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0feb04296f2d882ffa509dd7c6583732c9fea0f6c1d003c8bddb1fbd32ad29ca
3
+ size 5176