Martha-987 commited on
Commit
61e0233
1 Parent(s): e4c0683

End of training

Browse files
check1000/config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/whisper-small",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "architectures": [
6
+ "WhisperForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "begin_suppress_tokens": [
10
+ 220,
11
+ 50257
12
+ ],
13
+ "bos_token_id": 50257,
14
+ "d_model": 768,
15
+ "decoder_attention_heads": 12,
16
+ "decoder_ffn_dim": 3072,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 12,
19
+ "decoder_start_token_id": 50258,
20
+ "dropout": 0.0,
21
+ "encoder_attention_heads": 12,
22
+ "encoder_ffn_dim": 3072,
23
+ "encoder_layerdrop": 0.0,
24
+ "encoder_layers": 12,
25
+ "eos_token_id": 50257,
26
+ "forced_decoder_ids": null,
27
+ "init_std": 0.02,
28
+ "is_encoder_decoder": true,
29
+ "max_length": 448,
30
+ "max_source_positions": 1500,
31
+ "max_target_positions": 448,
32
+ "model_type": "whisper",
33
+ "num_hidden_layers": 12,
34
+ "num_mel_bins": 80,
35
+ "pad_token_id": 50257,
36
+ "scale_embedding": false,
37
+ "suppress_tokens": [],
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.26.0.dev0",
40
+ "use_cache": true,
41
+ "vocab_size": 51865
42
+ }
check1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6ae001d56fc22cf99b14d892a4bb166f1e30174e851cc3934d271753beb540c
3
+ size 1934161093
check1000/preprocessor_config.json ADDED
The diff for this file is too large to render. See raw diff
 
check1000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:325219cdd0a28326de2172bd3df6924b2f4b2e7a6a59e35fb2070a0fecf5e0a3
3
+ size 967102601
check1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93f0089eb47760f9be550d5a46ecb3cef5953026a997e1a02e6301f4086d5ec3
3
+ size 14511
check1000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e95b5e63a2de24f8c8c9db56d650764aad12cf45e225f186d23cfc18a4c7a34a
3
+ size 557
check1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b6adcde01329da1c49a2d134cbe54a6b362ab48eeb83973a53b8bbb28a1e83f
3
+ size 627
check1000/trainer_state.json ADDED
@@ -0,0 +1,265 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 51.185382425856204,
3
+ "best_model_checkpoint": "./whisper-small-Arabicc1/checkpoint-1000",
4
+ "epoch": 0.41562759767248547,
5
+ "global_step": 1000,
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": 4.2000000000000006e-07,
13
+ "loss": 3.262,
14
+ "step": 25
15
+ },
16
+ {
17
+ "epoch": 0.02,
18
+ "learning_rate": 9.200000000000001e-07,
19
+ "loss": 2.5218,
20
+ "step": 50
21
+ },
22
+ {
23
+ "epoch": 0.03,
24
+ "learning_rate": 1.42e-06,
25
+ "loss": 1.7958,
26
+ "step": 75
27
+ },
28
+ {
29
+ "epoch": 0.04,
30
+ "learning_rate": 1.9200000000000003e-06,
31
+ "loss": 1.2313,
32
+ "step": 100
33
+ },
34
+ {
35
+ "epoch": 0.05,
36
+ "learning_rate": 2.42e-06,
37
+ "loss": 1.0969,
38
+ "step": 125
39
+ },
40
+ {
41
+ "epoch": 0.06,
42
+ "learning_rate": 2.92e-06,
43
+ "loss": 0.9609,
44
+ "step": 150
45
+ },
46
+ {
47
+ "epoch": 0.07,
48
+ "learning_rate": 3.4200000000000007e-06,
49
+ "loss": 0.9173,
50
+ "step": 175
51
+ },
52
+ {
53
+ "epoch": 0.08,
54
+ "learning_rate": 3.920000000000001e-06,
55
+ "loss": 0.8191,
56
+ "step": 200
57
+ },
58
+ {
59
+ "epoch": 0.09,
60
+ "learning_rate": 4.42e-06,
61
+ "loss": 0.7742,
62
+ "step": 225
63
+ },
64
+ {
65
+ "epoch": 0.1,
66
+ "learning_rate": 4.92e-06,
67
+ "loss": 0.6781,
68
+ "step": 250
69
+ },
70
+ {
71
+ "epoch": 0.11,
72
+ "learning_rate": 5.420000000000001e-06,
73
+ "loss": 0.5776,
74
+ "step": 275
75
+ },
76
+ {
77
+ "epoch": 0.12,
78
+ "learning_rate": 5.92e-06,
79
+ "loss": 0.4557,
80
+ "step": 300
81
+ },
82
+ {
83
+ "epoch": 0.14,
84
+ "learning_rate": 6.42e-06,
85
+ "loss": 0.4113,
86
+ "step": 325
87
+ },
88
+ {
89
+ "epoch": 0.15,
90
+ "learning_rate": 6.92e-06,
91
+ "loss": 0.4198,
92
+ "step": 350
93
+ },
94
+ {
95
+ "epoch": 0.16,
96
+ "learning_rate": 7.420000000000001e-06,
97
+ "loss": 0.393,
98
+ "step": 375
99
+ },
100
+ {
101
+ "epoch": 0.17,
102
+ "learning_rate": 7.92e-06,
103
+ "loss": 0.4105,
104
+ "step": 400
105
+ },
106
+ {
107
+ "epoch": 0.18,
108
+ "learning_rate": 8.42e-06,
109
+ "loss": 0.4266,
110
+ "step": 425
111
+ },
112
+ {
113
+ "epoch": 0.19,
114
+ "learning_rate": 8.920000000000001e-06,
115
+ "loss": 0.4303,
116
+ "step": 450
117
+ },
118
+ {
119
+ "epoch": 0.2,
120
+ "learning_rate": 9.42e-06,
121
+ "loss": 0.3524,
122
+ "step": 475
123
+ },
124
+ {
125
+ "epoch": 0.21,
126
+ "learning_rate": 9.920000000000002e-06,
127
+ "loss": 0.3636,
128
+ "step": 500
129
+ },
130
+ {
131
+ "epoch": 0.22,
132
+ "learning_rate": 9.58e-06,
133
+ "loss": 0.3609,
134
+ "step": 525
135
+ },
136
+ {
137
+ "epoch": 0.23,
138
+ "learning_rate": 9.080000000000001e-06,
139
+ "loss": 0.3359,
140
+ "step": 550
141
+ },
142
+ {
143
+ "epoch": 0.24,
144
+ "learning_rate": 8.580000000000001e-06,
145
+ "loss": 0.3273,
146
+ "step": 575
147
+ },
148
+ {
149
+ "epoch": 0.25,
150
+ "learning_rate": 8.08e-06,
151
+ "loss": 0.3641,
152
+ "step": 600
153
+ },
154
+ {
155
+ "epoch": 0.26,
156
+ "learning_rate": 7.58e-06,
157
+ "loss": 0.3759,
158
+ "step": 625
159
+ },
160
+ {
161
+ "epoch": 0.27,
162
+ "learning_rate": 7.08e-06,
163
+ "loss": 0.3445,
164
+ "step": 650
165
+ },
166
+ {
167
+ "epoch": 0.28,
168
+ "learning_rate": 6.5800000000000005e-06,
169
+ "loss": 0.3277,
170
+ "step": 675
171
+ },
172
+ {
173
+ "epoch": 0.29,
174
+ "learning_rate": 6.08e-06,
175
+ "loss": 0.3411,
176
+ "step": 700
177
+ },
178
+ {
179
+ "epoch": 0.3,
180
+ "learning_rate": 5.580000000000001e-06,
181
+ "loss": 0.3377,
182
+ "step": 725
183
+ },
184
+ {
185
+ "epoch": 0.31,
186
+ "learning_rate": 5.0800000000000005e-06,
187
+ "loss": 0.3398,
188
+ "step": 750
189
+ },
190
+ {
191
+ "epoch": 0.32,
192
+ "learning_rate": 4.58e-06,
193
+ "loss": 0.3125,
194
+ "step": 775
195
+ },
196
+ {
197
+ "epoch": 0.33,
198
+ "learning_rate": 4.08e-06,
199
+ "loss": 0.3291,
200
+ "step": 800
201
+ },
202
+ {
203
+ "epoch": 0.34,
204
+ "learning_rate": 3.58e-06,
205
+ "loss": 0.3104,
206
+ "step": 825
207
+ },
208
+ {
209
+ "epoch": 0.35,
210
+ "learning_rate": 3.08e-06,
211
+ "loss": 0.299,
212
+ "step": 850
213
+ },
214
+ {
215
+ "epoch": 0.36,
216
+ "learning_rate": 2.5800000000000003e-06,
217
+ "loss": 0.2963,
218
+ "step": 875
219
+ },
220
+ {
221
+ "epoch": 0.37,
222
+ "learning_rate": 2.08e-06,
223
+ "loss": 0.3068,
224
+ "step": 900
225
+ },
226
+ {
227
+ "epoch": 0.38,
228
+ "learning_rate": 1.5800000000000001e-06,
229
+ "loss": 0.3393,
230
+ "step": 925
231
+ },
232
+ {
233
+ "epoch": 0.39,
234
+ "learning_rate": 1.08e-06,
235
+ "loss": 0.3138,
236
+ "step": 950
237
+ },
238
+ {
239
+ "epoch": 0.41,
240
+ "learning_rate": 5.800000000000001e-07,
241
+ "loss": 0.3214,
242
+ "step": 975
243
+ },
244
+ {
245
+ "epoch": 0.42,
246
+ "learning_rate": 8e-08,
247
+ "loss": 0.2726,
248
+ "step": 1000
249
+ },
250
+ {
251
+ "epoch": 0.42,
252
+ "eval_loss": 0.38373443484306335,
253
+ "eval_runtime": 4844.9923,
254
+ "eval_samples_per_second": 2.155,
255
+ "eval_steps_per_second": 0.269,
256
+ "eval_wer": 51.185382425856204,
257
+ "step": 1000
258
+ }
259
+ ],
260
+ "max_steps": 1000,
261
+ "num_train_epochs": 1,
262
+ "total_flos": 4.61736640512e+18,
263
+ "trial_name": null,
264
+ "trial_params": null
265
+ }
check1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:554771e2c89811c21892a38338011221c19fff7d10fb3b6aeeaa38f7349a930a
3
+ size 3643
runs/Dec22_10-09-50_4f2cb89e8dff/events.out.tfevents.1671704145.4f2cb89e8dff.731.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c68aefa82259483a42446baee78ff18a8e123cad8ca1221c1453cceb819b9528
3
- size 10934
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3dba126d92386ed2bfabf362329d78ea846b263ce14c73fe4b3e0351ebf0949
3
+ size 11288