ayberkuckun commited on
Commit
37374c0
1 Parent(s): 48134b9

End of training

Browse files
last-checkpoint/config.json DELETED
@@ -1,42 +0,0 @@
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
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1216601a7d69e85fbdaa9105ccc5fc9e979b085a826f71fd53fd12f20ae52597
3
- size 1934158597
 
 
 
 
last-checkpoint/preprocessor_config.json DELETED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2dac2ab7014b02d3566985d480efacfe39a0864b50134c62fe92ef6fa9c0347a
3
- size 967099139
 
 
 
 
last-checkpoint/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f74d698f32e458d5d382f8d5bc8f1669a0463312931256ef35a853b6f55a4e9
3
- size 14567
 
 
 
 
last-checkpoint/scaler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea6f5a26544d77b7a9117cf0f491edbac06fba0acbfff578e5ef1a9715ef1d5a
3
- size 559
 
 
 
 
last-checkpoint/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9413a57988e992fb22d66463bdb0c47cc99a7e29c85cfa84292ca81644f8a85c
3
- size 623
 
 
 
 
last-checkpoint/trainer_state.json DELETED
@@ -1,265 +0,0 @@
1
- {
2
- "best_metric": 20.60444731252185,
3
- "best_model_checkpoint": "./whisper-small-sv-SE/checkpoint-1000",
4
- "epoch": 1.2936610608020698,
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": 0.03,
12
- "learning_rate": 4.2000000000000006e-07,
13
- "loss": 4.1984,
14
- "step": 25
15
- },
16
- {
17
- "epoch": 0.06,
18
- "learning_rate": 9.200000000000001e-07,
19
- "loss": 3.3699,
20
- "step": 50
21
- },
22
- {
23
- "epoch": 0.1,
24
- "learning_rate": 1.42e-06,
25
- "loss": 2.4858,
26
- "step": 75
27
- },
28
- {
29
- "epoch": 0.13,
30
- "learning_rate": 1.9200000000000003e-06,
31
- "loss": 1.4969,
32
- "step": 100
33
- },
34
- {
35
- "epoch": 0.16,
36
- "learning_rate": 2.42e-06,
37
- "loss": 1.1419,
38
- "step": 125
39
- },
40
- {
41
- "epoch": 0.19,
42
- "learning_rate": 2.92e-06,
43
- "loss": 1.0148,
44
- "step": 150
45
- },
46
- {
47
- "epoch": 0.23,
48
- "learning_rate": 3.4200000000000007e-06,
49
- "loss": 0.9297,
50
- "step": 175
51
- },
52
- {
53
- "epoch": 0.26,
54
- "learning_rate": 3.920000000000001e-06,
55
- "loss": 0.8621,
56
- "step": 200
57
- },
58
- {
59
- "epoch": 0.29,
60
- "learning_rate": 4.42e-06,
61
- "loss": 0.712,
62
- "step": 225
63
- },
64
- {
65
- "epoch": 0.32,
66
- "learning_rate": 4.92e-06,
67
- "loss": 0.6186,
68
- "step": 250
69
- },
70
- {
71
- "epoch": 0.36,
72
- "learning_rate": 5.420000000000001e-06,
73
- "loss": 0.4717,
74
- "step": 275
75
- },
76
- {
77
- "epoch": 0.39,
78
- "learning_rate": 5.92e-06,
79
- "loss": 0.3114,
80
- "step": 300
81
- },
82
- {
83
- "epoch": 0.42,
84
- "learning_rate": 6.42e-06,
85
- "loss": 0.3384,
86
- "step": 325
87
- },
88
- {
89
- "epoch": 0.45,
90
- "learning_rate": 6.92e-06,
91
- "loss": 0.2962,
92
- "step": 350
93
- },
94
- {
95
- "epoch": 0.49,
96
- "learning_rate": 7.420000000000001e-06,
97
- "loss": 0.3173,
98
- "step": 375
99
- },
100
- {
101
- "epoch": 0.52,
102
- "learning_rate": 7.92e-06,
103
- "loss": 0.3202,
104
- "step": 400
105
- },
106
- {
107
- "epoch": 0.55,
108
- "learning_rate": 8.42e-06,
109
- "loss": 0.3133,
110
- "step": 425
111
- },
112
- {
113
- "epoch": 0.58,
114
- "learning_rate": 8.920000000000001e-06,
115
- "loss": 0.3045,
116
- "step": 450
117
- },
118
- {
119
- "epoch": 0.61,
120
- "learning_rate": 9.42e-06,
121
- "loss": 0.2761,
122
- "step": 475
123
- },
124
- {
125
- "epoch": 0.65,
126
- "learning_rate": 9.920000000000002e-06,
127
- "loss": 0.3105,
128
- "step": 500
129
- },
130
- {
131
- "epoch": 0.68,
132
- "learning_rate": 9.58e-06,
133
- "loss": 0.2968,
134
- "step": 525
135
- },
136
- {
137
- "epoch": 0.71,
138
- "learning_rate": 9.080000000000001e-06,
139
- "loss": 0.2914,
140
- "step": 550
141
- },
142
- {
143
- "epoch": 0.74,
144
- "learning_rate": 8.580000000000001e-06,
145
- "loss": 0.3019,
146
- "step": 575
147
- },
148
- {
149
- "epoch": 0.78,
150
- "learning_rate": 8.08e-06,
151
- "loss": 0.3058,
152
- "step": 600
153
- },
154
- {
155
- "epoch": 0.81,
156
- "learning_rate": 7.58e-06,
157
- "loss": 0.2896,
158
- "step": 625
159
- },
160
- {
161
- "epoch": 0.84,
162
- "learning_rate": 7.08e-06,
163
- "loss": 0.3014,
164
- "step": 650
165
- },
166
- {
167
- "epoch": 0.87,
168
- "learning_rate": 6.5800000000000005e-06,
169
- "loss": 0.2666,
170
- "step": 675
171
- },
172
- {
173
- "epoch": 0.91,
174
- "learning_rate": 6.08e-06,
175
- "loss": 0.279,
176
- "step": 700
177
- },
178
- {
179
- "epoch": 0.94,
180
- "learning_rate": 5.580000000000001e-06,
181
- "loss": 0.2843,
182
- "step": 725
183
- },
184
- {
185
- "epoch": 0.97,
186
- "learning_rate": 5.0800000000000005e-06,
187
- "loss": 0.274,
188
- "step": 750
189
- },
190
- {
191
- "epoch": 1.0,
192
- "learning_rate": 4.58e-06,
193
- "loss": 0.2686,
194
- "step": 775
195
- },
196
- {
197
- "epoch": 1.03,
198
- "learning_rate": 4.08e-06,
199
- "loss": 0.1352,
200
- "step": 800
201
- },
202
- {
203
- "epoch": 1.07,
204
- "learning_rate": 3.58e-06,
205
- "loss": 0.1423,
206
- "step": 825
207
- },
208
- {
209
- "epoch": 1.1,
210
- "learning_rate": 3.08e-06,
211
- "loss": 0.1416,
212
- "step": 850
213
- },
214
- {
215
- "epoch": 1.13,
216
- "learning_rate": 2.5800000000000003e-06,
217
- "loss": 0.1209,
218
- "step": 875
219
- },
220
- {
221
- "epoch": 1.16,
222
- "learning_rate": 2.08e-06,
223
- "loss": 0.1383,
224
- "step": 900
225
- },
226
- {
227
- "epoch": 1.2,
228
- "learning_rate": 1.5800000000000001e-06,
229
- "loss": 0.1495,
230
- "step": 925
231
- },
232
- {
233
- "epoch": 1.23,
234
- "learning_rate": 1.08e-06,
235
- "loss": 0.1427,
236
- "step": 950
237
- },
238
- {
239
- "epoch": 1.26,
240
- "learning_rate": 5.800000000000001e-07,
241
- "loss": 0.1401,
242
- "step": 975
243
- },
244
- {
245
- "epoch": 1.29,
246
- "learning_rate": 8e-08,
247
- "loss": 0.1296,
248
- "step": 1000
249
- },
250
- {
251
- "epoch": 1.29,
252
- "eval_loss": 0.2802535593509674,
253
- "eval_runtime": 2000.692,
254
- "eval_samples_per_second": 2.534,
255
- "eval_steps_per_second": 0.317,
256
- "eval_wer": 20.60444731252185,
257
- "step": 1000
258
- }
259
- ],
260
- "max_steps": 1000,
261
- "num_train_epochs": 2,
262
- "total_flos": 4.61505772191744e+18,
263
- "trial_name": null,
264
- "trial_params": null
265
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:411d5b28552c2eb72c502413197f03fc9df344de3ce2fdf1f2d93bec71897b45
3
- size 3503
 
 
 
 
runs/Dec06_14-05-42_95124521ccff/events.out.tfevents.1670335557.95124521ccff.74.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a27ddafacc2d63cbd2c5a9833dd5e7e09eae521b399d6d27ec82e947d4825ce
3
- size 10834
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3baffb70722616b605afc197f74a60fe716c562c9d103e3227b810736b6b86af
3
+ size 11188