lighteternal commited on
Commit
c9229a1
1 Parent(s): cbf7f13

First commit

Browse files
wav2vec2-large-xlsr-greek/checkpoint-8800/config.json DELETED
@@ -1,76 +0,0 @@
1
- {
2
- "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
3
- "activation_dropout": 0.0,
4
- "apply_spec_augment": true,
5
- "architectures": [
6
- "Wav2Vec2ForCTC"
7
- ],
8
- "attention_dropout": 0.1,
9
- "bos_token_id": 1,
10
- "conv_bias": true,
11
- "conv_dim": [
12
- 512,
13
- 512,
14
- 512,
15
- 512,
16
- 512,
17
- 512,
18
- 512
19
- ],
20
- "conv_kernel": [
21
- 10,
22
- 3,
23
- 3,
24
- 3,
25
- 3,
26
- 2,
27
- 2
28
- ],
29
- "conv_stride": [
30
- 5,
31
- 2,
32
- 2,
33
- 2,
34
- 2,
35
- 2,
36
- 2
37
- ],
38
- "ctc_loss_reduction": "mean",
39
- "ctc_zero_infinity": false,
40
- "do_stable_layer_norm": true,
41
- "eos_token_id": 2,
42
- "feat_extract_activation": "gelu",
43
- "feat_extract_dropout": 0.0,
44
- "feat_extract_norm": "layer",
45
- "feat_proj_dropout": 0.0,
46
- "final_dropout": 0.0,
47
- "gradient_checkpointing": true,
48
- "hidden_act": "gelu",
49
- "hidden_dropout": 0.1,
50
- "hidden_size": 1024,
51
- "initializer_range": 0.02,
52
- "intermediate_size": 4096,
53
- "layer_norm_eps": 1e-05,
54
- "layerdrop": 0.1,
55
- "mask_channel_length": 10,
56
- "mask_channel_min_space": 1,
57
- "mask_channel_other": 0.0,
58
- "mask_channel_prob": 0.0,
59
- "mask_channel_selection": "static",
60
- "mask_feature_length": 10,
61
- "mask_feature_prob": 0.0,
62
- "mask_time_length": 10,
63
- "mask_time_min_space": 1,
64
- "mask_time_other": 0.0,
65
- "mask_time_prob": 0.05,
66
- "mask_time_selection": "static",
67
- "model_type": "wav2vec2",
68
- "num_attention_heads": 16,
69
- "num_conv_pos_embedding_groups": 16,
70
- "num_conv_pos_embeddings": 128,
71
- "num_feat_extract_layers": 7,
72
- "num_hidden_layers": 24,
73
- "pad_token_id": 52,
74
- "transformers_version": "4.4.0.dev0",
75
- "vocab_size": 53
76
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
wav2vec2-large-xlsr-greek/checkpoint-8800/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2521a9aceb81bcefcb8ca0e31b977861537b4d68662ad9c6d651c175b2cb41f3
3
- size 2524210623
 
 
 
 
wav2vec2-large-xlsr-greek/checkpoint-8800/preprocessor_config.json DELETED
@@ -1,8 +0,0 @@
1
- {
2
- "do_normalize": true,
3
- "feature_size": 1,
4
- "padding_side": "right",
5
- "padding_value": 0.0,
6
- "return_attention_mask": true,
7
- "sampling_rate": 16000
8
- }
 
 
 
 
 
 
 
 
 
wav2vec2-large-xlsr-greek/checkpoint-8800/pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:860d1192dee4efb741ad1d1806659170db014950f512314dc78506bbbe55d50f
3
- size 1262151127
 
 
 
 
wav2vec2-large-xlsr-greek/checkpoint-8800/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7435667b66a7cfb014c2cc86ae2e0765c90a0272fc552b25568f8ee435ef24ff
3
- size 623
 
 
 
 
wav2vec2-large-xlsr-greek/checkpoint-8800/trainer_state.json DELETED
@@ -1,324 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 28.387096774193548,
5
- "global_step": 8800,
6
- "is_hyper_param_search": false,
7
- "is_local_process_zero": true,
8
- "is_world_process_zero": true,
9
- "log_history": [
10
- {
11
- "epoch": 1.29,
12
- "learning_rate": 0.00023999999999999998,
13
- "loss": 7.3425,
14
- "step": 400
15
- },
16
- {
17
- "epoch": 1.29,
18
- "eval_loss": 3.277569532394409,
19
- "eval_runtime": 138.4344,
20
- "eval_samples_per_second": 10.994,
21
- "eval_wer": 1.0,
22
- "step": 400
23
- },
24
- {
25
- "epoch": 2.58,
26
- "learning_rate": 0.0002897727272727273,
27
- "loss": 2.6649,
28
- "step": 800
29
- },
30
- {
31
- "epoch": 2.58,
32
- "eval_loss": 1.1241918802261353,
33
- "eval_runtime": 115.4749,
34
- "eval_samples_per_second": 13.18,
35
- "eval_wer": 0.8526294539214697,
36
- "step": 800
37
- },
38
- {
39
- "epoch": 3.87,
40
- "learning_rate": 0.0002761363636363636,
41
- "loss": 0.7589,
42
- "step": 1200
43
- },
44
- {
45
- "epoch": 3.87,
46
- "eval_loss": 0.69745272397995,
47
- "eval_runtime": 137.7134,
48
- "eval_samples_per_second": 11.052,
49
- "eval_wer": 0.6960734833955788,
50
- "step": 1200
51
- },
52
- {
53
- "epoch": 5.16,
54
- "learning_rate": 0.0002625,
55
- "loss": 0.476,
56
- "step": 1600
57
- },
58
- {
59
- "epoch": 5.16,
60
- "eval_loss": 0.6482455730438232,
61
- "eval_runtime": 115.5054,
62
- "eval_samples_per_second": 13.177,
63
- "eval_wer": 0.6553951751286968,
64
- "step": 1600
65
- },
66
- {
67
- "epoch": 6.45,
68
- "learning_rate": 0.00024886363636363637,
69
- "loss": 0.3479,
70
- "step": 2000
71
- },
72
- {
73
- "epoch": 6.45,
74
- "eval_loss": 0.6039410829544067,
75
- "eval_runtime": 115.7857,
76
- "eval_samples_per_second": 13.145,
77
- "eval_wer": 0.5894821843141214,
78
- "step": 2000
79
- },
80
- {
81
- "epoch": 7.74,
82
- "learning_rate": 0.0002352272727272727,
83
- "loss": 0.2783,
84
- "step": 2400
85
- },
86
- {
87
- "epoch": 7.74,
88
- "eval_loss": 0.6183858513832092,
89
- "eval_runtime": 115.9363,
90
- "eval_samples_per_second": 13.128,
91
- "eval_wer": 0.5855455738366812,
92
- "step": 2400
93
- },
94
- {
95
- "epoch": 9.03,
96
- "learning_rate": 0.00022159090909090908,
97
- "loss": 0.2204,
98
- "step": 2800
99
- },
100
- {
101
- "epoch": 9.03,
102
- "eval_loss": 0.5993764996528625,
103
- "eval_runtime": 137.9021,
104
- "eval_samples_per_second": 11.037,
105
- "eval_wer": 0.550721711920864,
106
- "step": 2800
107
- },
108
- {
109
- "epoch": 10.32,
110
- "learning_rate": 0.00020795454545454546,
111
- "loss": 0.1881,
112
- "step": 3200
113
- },
114
- {
115
- "epoch": 10.32,
116
- "eval_loss": 0.5736687779426575,
117
- "eval_runtime": 138.6384,
118
- "eval_samples_per_second": 10.978,
119
- "eval_wer": 0.537801554456445,
120
- "step": 3200
121
- },
122
- {
123
- "epoch": 11.61,
124
- "learning_rate": 0.00019431818181818179,
125
- "loss": 0.1639,
126
- "step": 3600
127
- },
128
- {
129
- "epoch": 11.61,
130
- "eval_loss": 0.5788838267326355,
131
- "eval_runtime": 139.0007,
132
- "eval_samples_per_second": 10.95,
133
- "eval_wer": 0.5217522963561119,
134
- "step": 3600
135
- },
136
- {
137
- "epoch": 12.9,
138
- "learning_rate": 0.00018068181818181817,
139
- "loss": 0.1464,
140
- "step": 4000
141
- },
142
- {
143
- "epoch": 12.9,
144
- "eval_loss": 0.5988554358482361,
145
- "eval_runtime": 116.0695,
146
- "eval_samples_per_second": 13.113,
147
- "eval_wer": 0.5138790754012315,
148
- "step": 4000
149
- },
150
- {
151
- "epoch": 14.19,
152
- "learning_rate": 0.00016704545454545452,
153
- "loss": 0.1222,
154
- "step": 4400
155
- },
156
- {
157
- "epoch": 14.19,
158
- "eval_loss": 0.6150318384170532,
159
- "eval_runtime": 140.7397,
160
- "eval_samples_per_second": 10.814,
161
- "eval_wer": 0.5012617341273847,
162
- "step": 4400
163
- },
164
- {
165
- "epoch": 15.48,
166
- "learning_rate": 0.0001534090909090909,
167
- "loss": 0.112,
168
- "step": 4800
169
- },
170
- {
171
- "epoch": 15.48,
172
- "eval_loss": 0.6471191644668579,
173
- "eval_runtime": 138.3313,
174
- "eval_samples_per_second": 11.003,
175
- "eval_wer": 0.5148884627031391,
176
- "step": 4800
177
- },
178
- {
179
- "epoch": 16.77,
180
- "learning_rate": 0.00013977272727272726,
181
- "loss": 0.105,
182
- "step": 5200
183
- },
184
- {
185
- "epoch": 16.77,
186
- "eval_loss": 0.6167843341827393,
187
- "eval_runtime": 116.3058,
188
- "eval_samples_per_second": 13.086,
189
- "eval_wer": 0.49237912587059657,
190
- "step": 5200
191
- },
192
- {
193
- "epoch": 18.06,
194
- "learning_rate": 0.00012613636363636364,
195
- "loss": 0.0936,
196
- "step": 5600
197
- },
198
- {
199
- "epoch": 18.06,
200
- "eval_loss": 0.6400735378265381,
201
- "eval_runtime": 138.5841,
202
- "eval_samples_per_second": 10.983,
203
- "eval_wer": 0.4856162309478147,
204
- "step": 5600
205
- },
206
- {
207
- "epoch": 19.35,
208
- "learning_rate": 0.0001125,
209
- "loss": 0.0849,
210
- "step": 6000
211
- },
212
- {
213
- "epoch": 19.35,
214
- "eval_loss": 0.6149299740791321,
215
- "eval_runtime": 116.9081,
216
- "eval_samples_per_second": 13.019,
217
- "eval_wer": 0.47875239729484204,
218
- "step": 6000
219
- },
220
- {
221
- "epoch": 20.65,
222
- "learning_rate": 9.886363636363635e-05,
223
- "loss": 0.079,
224
- "step": 6400
225
- },
226
- {
227
- "epoch": 20.65,
228
- "eval_loss": 0.6410804986953735,
229
- "eval_runtime": 139.105,
230
- "eval_samples_per_second": 10.941,
231
- "eval_wer": 0.48067023316846674,
232
- "step": 6400
233
- },
234
- {
235
- "epoch": 21.94,
236
- "learning_rate": 8.522727272727273e-05,
237
- "loss": 0.0752,
238
- "step": 6800
239
- },
240
- {
241
- "epoch": 21.94,
242
- "eval_loss": 0.6123934388160706,
243
- "eval_runtime": 138.8056,
244
- "eval_samples_per_second": 10.965,
245
- "eval_wer": 0.4773392550721712,
246
- "step": 6800
247
- },
248
- {
249
- "epoch": 23.23,
250
- "learning_rate": 7.159090909090909e-05,
251
- "loss": 0.0688,
252
- "step": 7200
253
- },
254
- {
255
- "epoch": 23.23,
256
- "eval_loss": 0.6324551105499268,
257
- "eval_runtime": 137.9116,
258
- "eval_samples_per_second": 11.036,
259
- "eval_wer": 0.47198950237206017,
260
- "step": 7200
261
- },
262
- {
263
- "epoch": 24.52,
264
- "learning_rate": 5.795454545454545e-05,
265
- "loss": 0.0659,
266
- "step": 7600
267
- },
268
- {
269
- "epoch": 24.52,
270
- "eval_loss": 0.6281149387359619,
271
- "eval_runtime": 139.9793,
272
- "eval_samples_per_second": 10.873,
273
- "eval_wer": 0.464923791258706,
274
- "step": 7600
275
- },
276
- {
277
- "epoch": 25.81,
278
- "learning_rate": 4.431818181818182e-05,
279
- "loss": 0.0582,
280
- "step": 8000
281
- },
282
- {
283
- "epoch": 25.81,
284
- "eval_loss": 0.6326279640197754,
285
- "eval_runtime": 139.8038,
286
- "eval_samples_per_second": 10.887,
287
- "eval_wer": 0.4604824871303119,
288
- "step": 8000
289
- },
290
- {
291
- "epoch": 27.1,
292
- "learning_rate": 3.068181818181818e-05,
293
- "loss": 0.0551,
294
- "step": 8400
295
- },
296
- {
297
- "epoch": 27.1,
298
- "eval_loss": 0.6271815299987793,
299
- "eval_runtime": 139.3604,
300
- "eval_samples_per_second": 10.921,
301
- "eval_wer": 0.46300595538508127,
302
- "step": 8400
303
- },
304
- {
305
- "epoch": 28.39,
306
- "learning_rate": 1.7045454545454543e-05,
307
- "loss": 0.0508,
308
- "step": 8800
309
- },
310
- {
311
- "epoch": 28.39,
312
- "eval_loss": 0.6332981586456299,
313
- "eval_runtime": 139.0366,
314
- "eval_samples_per_second": 10.947,
315
- "eval_wer": 0.4594730998284042,
316
- "step": 8800
317
- }
318
- ],
319
- "max_steps": 9300,
320
- "num_train_epochs": 30,
321
- "total_flos": 1.3468833622888647e+19,
322
- "trial_name": null,
323
- "trial_params": null
324
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
wav2vec2-large-xlsr-greek/checkpoint-8800/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:19745f202d764bbd63c72bfc82b74cad7c731fae95861ba3eaa8aae2d3c48a33
3
- size 2287