drmeeseeks commited on
Commit
b03240e
1 Parent(s): a50ca49

Training in progress, step 1000

Browse files
.ipynb_checkpoints/README-checkpoint.md ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - fleurs
7
+ model-index:
8
+ - name: whisper-small-amet
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # whisper-small-amet
16
+
17
+ This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the fleurs dataset.
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 1e-05
37
+ - train_batch_size: 64
38
+ - eval_batch_size: 32
39
+ - seed: 42
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - lr_scheduler_warmup_steps: 500
43
+ - training_steps: 1000
44
+ - mixed_precision_training: Native AMP
45
+
46
+ ### Training results
47
+
48
+
49
+
50
+ ### Framework versions
51
+
52
+ - Transformers 4.26.0.dev0
53
+ - Pytorch 1.13.1+cu117
54
+ - Datasets 2.7.1.dev0
55
+ - Tokenizers 0.13.2
all_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 142.86,
3
+ "train_loss": 0.4370949484743178,
4
+ "train_runtime": 4327.5129,
5
+ "train_samples_per_second": 14.789,
6
+ "train_steps_per_second": 0.231
7
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5356644913b5f96b8261e2ce0904dd4c82f6839afb1d7f06b31f4501b6923f6d
3
  size 967102601
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1487280f1b4aa9561431f3d915653ee3a1ac337258830bf6925a4577b6406f0
3
  size 967102601
runs/Dec19_01-39-25_129-213-131-86/1671413978.0873578/events.out.tfevents.1671413978.129-213-131-86.78497.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:864c91abf926a39dccba92947099d1fa524b07c04a3016b12d6f0b67e562e2a1
3
+ size 5925
runs/Dec19_01-39-25_129-213-131-86/events.out.tfevents.1671413978.129-213-131-86.78497.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4365b812021cad83b4bdc90c78c3090c2f10934f5703b54de1e1e4d8dac8e702
3
+ size 10589
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 142.86,
3
+ "train_loss": 0.4370949484743178,
4
+ "train_runtime": 4327.5129,
5
+ "train_samples_per_second": 14.789,
6
+ "train_steps_per_second": 0.231
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,265 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 142.85714285714286,
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": 3.57,
12
+ "learning_rate": 4.2000000000000006e-07,
13
+ "loss": 3.0968,
14
+ "step": 25
15
+ },
16
+ {
17
+ "epoch": 7.14,
18
+ "learning_rate": 9.200000000000001e-07,
19
+ "loss": 2.4565,
20
+ "step": 50
21
+ },
22
+ {
23
+ "epoch": 10.71,
24
+ "learning_rate": 1.42e-06,
25
+ "loss": 1.9962,
26
+ "step": 75
27
+ },
28
+ {
29
+ "epoch": 14.29,
30
+ "learning_rate": 1.9200000000000003e-06,
31
+ "loss": 1.7133,
32
+ "step": 100
33
+ },
34
+ {
35
+ "epoch": 17.86,
36
+ "learning_rate": 2.42e-06,
37
+ "loss": 1.5526,
38
+ "step": 125
39
+ },
40
+ {
41
+ "epoch": 21.43,
42
+ "learning_rate": 2.92e-06,
43
+ "loss": 1.4427,
44
+ "step": 150
45
+ },
46
+ {
47
+ "epoch": 25.0,
48
+ "learning_rate": 3.4200000000000007e-06,
49
+ "loss": 1.3382,
50
+ "step": 175
51
+ },
52
+ {
53
+ "epoch": 28.57,
54
+ "learning_rate": 3.920000000000001e-06,
55
+ "loss": 1.178,
56
+ "step": 200
57
+ },
58
+ {
59
+ "epoch": 32.14,
60
+ "learning_rate": 4.42e-06,
61
+ "loss": 0.9536,
62
+ "step": 225
63
+ },
64
+ {
65
+ "epoch": 35.71,
66
+ "learning_rate": 4.92e-06,
67
+ "loss": 0.7107,
68
+ "step": 250
69
+ },
70
+ {
71
+ "epoch": 39.29,
72
+ "learning_rate": 5.420000000000001e-06,
73
+ "loss": 0.4791,
74
+ "step": 275
75
+ },
76
+ {
77
+ "epoch": 42.86,
78
+ "learning_rate": 5.92e-06,
79
+ "loss": 0.2683,
80
+ "step": 300
81
+ },
82
+ {
83
+ "epoch": 46.43,
84
+ "learning_rate": 6.42e-06,
85
+ "loss": 0.1293,
86
+ "step": 325
87
+ },
88
+ {
89
+ "epoch": 50.0,
90
+ "learning_rate": 6.92e-06,
91
+ "loss": 0.0561,
92
+ "step": 350
93
+ },
94
+ {
95
+ "epoch": 53.57,
96
+ "learning_rate": 7.420000000000001e-06,
97
+ "loss": 0.03,
98
+ "step": 375
99
+ },
100
+ {
101
+ "epoch": 57.14,
102
+ "learning_rate": 7.92e-06,
103
+ "loss": 0.0178,
104
+ "step": 400
105
+ },
106
+ {
107
+ "epoch": 60.71,
108
+ "learning_rate": 8.42e-06,
109
+ "loss": 0.0134,
110
+ "step": 425
111
+ },
112
+ {
113
+ "epoch": 64.29,
114
+ "learning_rate": 8.920000000000001e-06,
115
+ "loss": 0.0087,
116
+ "step": 450
117
+ },
118
+ {
119
+ "epoch": 67.86,
120
+ "learning_rate": 9.42e-06,
121
+ "loss": 0.008,
122
+ "step": 475
123
+ },
124
+ {
125
+ "epoch": 71.43,
126
+ "learning_rate": 9.920000000000002e-06,
127
+ "loss": 0.0064,
128
+ "step": 500
129
+ },
130
+ {
131
+ "epoch": 75.0,
132
+ "learning_rate": 9.58e-06,
133
+ "loss": 0.0068,
134
+ "step": 525
135
+ },
136
+ {
137
+ "epoch": 78.57,
138
+ "learning_rate": 9.080000000000001e-06,
139
+ "loss": 0.0049,
140
+ "step": 550
141
+ },
142
+ {
143
+ "epoch": 82.14,
144
+ "learning_rate": 8.580000000000001e-06,
145
+ "loss": 0.0035,
146
+ "step": 575
147
+ },
148
+ {
149
+ "epoch": 85.71,
150
+ "learning_rate": 8.08e-06,
151
+ "loss": 0.0022,
152
+ "step": 600
153
+ },
154
+ {
155
+ "epoch": 89.29,
156
+ "learning_rate": 7.58e-06,
157
+ "loss": 0.0015,
158
+ "step": 625
159
+ },
160
+ {
161
+ "epoch": 92.86,
162
+ "learning_rate": 7.08e-06,
163
+ "loss": 0.0017,
164
+ "step": 650
165
+ },
166
+ {
167
+ "epoch": 96.43,
168
+ "learning_rate": 6.5800000000000005e-06,
169
+ "loss": 0.0014,
170
+ "step": 675
171
+ },
172
+ {
173
+ "epoch": 100.0,
174
+ "learning_rate": 6.08e-06,
175
+ "loss": 0.0013,
176
+ "step": 700
177
+ },
178
+ {
179
+ "epoch": 103.57,
180
+ "learning_rate": 5.580000000000001e-06,
181
+ "loss": 0.0006,
182
+ "step": 725
183
+ },
184
+ {
185
+ "epoch": 107.14,
186
+ "learning_rate": 5.0800000000000005e-06,
187
+ "loss": 0.0004,
188
+ "step": 750
189
+ },
190
+ {
191
+ "epoch": 110.71,
192
+ "learning_rate": 4.58e-06,
193
+ "loss": 0.0004,
194
+ "step": 775
195
+ },
196
+ {
197
+ "epoch": 114.29,
198
+ "learning_rate": 4.08e-06,
199
+ "loss": 0.0004,
200
+ "step": 800
201
+ },
202
+ {
203
+ "epoch": 117.86,
204
+ "learning_rate": 3.58e-06,
205
+ "loss": 0.0004,
206
+ "step": 825
207
+ },
208
+ {
209
+ "epoch": 121.43,
210
+ "learning_rate": 3.08e-06,
211
+ "loss": 0.0004,
212
+ "step": 850
213
+ },
214
+ {
215
+ "epoch": 125.0,
216
+ "learning_rate": 2.5800000000000003e-06,
217
+ "loss": 0.0004,
218
+ "step": 875
219
+ },
220
+ {
221
+ "epoch": 128.57,
222
+ "learning_rate": 2.08e-06,
223
+ "loss": 0.0004,
224
+ "step": 900
225
+ },
226
+ {
227
+ "epoch": 132.14,
228
+ "learning_rate": 1.5800000000000001e-06,
229
+ "loss": 0.0004,
230
+ "step": 925
231
+ },
232
+ {
233
+ "epoch": 135.71,
234
+ "learning_rate": 1.08e-06,
235
+ "loss": 0.0004,
236
+ "step": 950
237
+ },
238
+ {
239
+ "epoch": 139.29,
240
+ "learning_rate": 5.800000000000001e-07,
241
+ "loss": 0.0004,
242
+ "step": 975
243
+ },
244
+ {
245
+ "epoch": 142.86,
246
+ "learning_rate": 8e-08,
247
+ "loss": 0.0004,
248
+ "step": 1000
249
+ },
250
+ {
251
+ "epoch": 142.86,
252
+ "step": 1000,
253
+ "total_flos": 1.838750736678912e+19,
254
+ "train_loss": 0.4370949484743178,
255
+ "train_runtime": 4327.5129,
256
+ "train_samples_per_second": 14.789,
257
+ "train_steps_per_second": 0.231
258
+ }
259
+ ],
260
+ "max_steps": 1000,
261
+ "num_train_epochs": 143,
262
+ "total_flos": 1.838750736678912e+19,
263
+ "trial_name": null,
264
+ "trial_params": null
265
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b90fe34fba8b85448fc7538e6fcf5babf9fb0e25546a7893086c92629a885c8
3
  size 3643
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e17bb139a6f45054fbc879a51adc6088586288345db0acb365937b9051b4aa89
3
  size 3643