jlondonobo commited on
Commit
327e455
β€’
1 Parent(s): 406c446

🌟 upload best model

Browse files
README.md ADDED
@@ -0,0 +1 @@
 
 
1
+ # Whisper Large-v2 Portuguese V2
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3231994f9250f0e0c574771075bb0e120ae61e2f3c437a69622017591bf38506
3
  size 3086784957
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:672d9494d92f5ea066029da9c95a3d912e4001953ef346d41e16415f907eb702
3
  size 3086784957
runs/Dec17_13-18-49_193-122-153-4/events.out.tfevents.1671283207.193-122-153-4.129410.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:efa2510a03f3a59d2bdffc22f3fe3ef588c35b7a15d0ec8adfe51fd525ab3d02
3
- size 17462
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7319e8dbc6feb9f3b437e112f8e45e34cd1b250c192a2cc2200424d4d5e3665
3
+ size 17619
trainer_state.json ADDED
@@ -0,0 +1,265 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 4.878868882500295,
3
+ "best_model_checkpoint": "./checkpoint-1000",
4
+ "epoch": 1.1523333333333334,
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": 1.6013176087541454e-06,
13
+ "loss": 0.8269,
14
+ "step": 25
15
+ },
16
+ {
17
+ "epoch": 0.02,
18
+ "learning_rate": 2.0137381186086706e-06,
19
+ "loss": 0.3045,
20
+ "step": 50
21
+ },
22
+ {
23
+ "epoch": 0.03,
24
+ "learning_rate": 2.2420279328577924e-06,
25
+ "loss": 0.2313,
26
+ "step": 75
27
+ },
28
+ {
29
+ "epoch": 0.03,
30
+ "learning_rate": 2.40069543942923e-06,
31
+ "loss": 0.1914,
32
+ "step": 100
33
+ },
34
+ {
35
+ "epoch": 0.04,
36
+ "learning_rate": 2.522426425046553e-06,
37
+ "loss": 0.1792,
38
+ "step": 125
39
+ },
40
+ {
41
+ "epoch": 0.05,
42
+ "learning_rate": 2.61759653240662e-06,
43
+ "loss": 0.1751,
44
+ "step": 150
45
+ },
46
+ {
47
+ "epoch": 0.06,
48
+ "learning_rate": 2.701259274807719e-06,
49
+ "loss": 0.1753,
50
+ "step": 175
51
+ },
52
+ {
53
+ "epoch": 0.07,
54
+ "learning_rate": 2.773422504448636e-06,
55
+ "loss": 0.1429,
56
+ "step": 200
57
+ },
58
+ {
59
+ "epoch": 0.07,
60
+ "learning_rate": 2.836868816606194e-06,
61
+ "loss": 0.1708,
62
+ "step": 225
63
+ },
64
+ {
65
+ "epoch": 0.08,
66
+ "learning_rate": 2.893478968555679e-06,
67
+ "loss": 0.156,
68
+ "step": 250
69
+ },
70
+ {
71
+ "epoch": 0.09,
72
+ "learning_rate": 2.944583870724746e-06,
73
+ "loss": 0.1573,
74
+ "step": 275
75
+ },
76
+ {
77
+ "epoch": 0.1,
78
+ "learning_rate": 2.991160014398659e-06,
79
+ "loss": 0.157,
80
+ "step": 300
81
+ },
82
+ {
83
+ "epoch": 0.11,
84
+ "learning_rate": 2.978888888888889e-06,
85
+ "loss": 0.1659,
86
+ "step": 325
87
+ },
88
+ {
89
+ "epoch": 0.12,
90
+ "learning_rate": 2.9511111111111114e-06,
91
+ "loss": 0.1362,
92
+ "step": 350
93
+ },
94
+ {
95
+ "epoch": 0.12,
96
+ "learning_rate": 2.9233333333333334e-06,
97
+ "loss": 0.1465,
98
+ "step": 375
99
+ },
100
+ {
101
+ "epoch": 0.13,
102
+ "learning_rate": 2.8955555555555555e-06,
103
+ "loss": 0.1432,
104
+ "step": 400
105
+ },
106
+ {
107
+ "epoch": 0.14,
108
+ "learning_rate": 2.867777777777778e-06,
109
+ "loss": 0.1306,
110
+ "step": 425
111
+ },
112
+ {
113
+ "epoch": 0.15,
114
+ "learning_rate": 2.84e-06,
115
+ "loss": 0.1388,
116
+ "step": 450
117
+ },
118
+ {
119
+ "epoch": 0.16,
120
+ "learning_rate": 2.812222222222222e-06,
121
+ "loss": 0.1434,
122
+ "step": 475
123
+ },
124
+ {
125
+ "epoch": 0.17,
126
+ "learning_rate": 2.7844444444444444e-06,
127
+ "loss": 0.1425,
128
+ "step": 500
129
+ },
130
+ {
131
+ "epoch": 0.17,
132
+ "learning_rate": 2.756666666666667e-06,
133
+ "loss": 0.1411,
134
+ "step": 525
135
+ },
136
+ {
137
+ "epoch": 1.0,
138
+ "learning_rate": 2.7288888888888893e-06,
139
+ "loss": 0.1316,
140
+ "step": 550
141
+ },
142
+ {
143
+ "epoch": 1.01,
144
+ "learning_rate": 2.702222222222222e-06,
145
+ "loss": 0.1212,
146
+ "step": 575
147
+ },
148
+ {
149
+ "epoch": 1.02,
150
+ "learning_rate": 2.674444444444444e-06,
151
+ "loss": 0.1117,
152
+ "step": 600
153
+ },
154
+ {
155
+ "epoch": 1.03,
156
+ "learning_rate": 2.6466666666666666e-06,
157
+ "loss": 0.1,
158
+ "step": 625
159
+ },
160
+ {
161
+ "epoch": 1.04,
162
+ "learning_rate": 2.618888888888889e-06,
163
+ "loss": 0.0931,
164
+ "step": 650
165
+ },
166
+ {
167
+ "epoch": 1.04,
168
+ "learning_rate": 2.5911111111111115e-06,
169
+ "loss": 0.0876,
170
+ "step": 675
171
+ },
172
+ {
173
+ "epoch": 1.05,
174
+ "learning_rate": 2.5633333333333335e-06,
175
+ "loss": 0.0943,
176
+ "step": 700
177
+ },
178
+ {
179
+ "epoch": 1.06,
180
+ "learning_rate": 2.5355555555555555e-06,
181
+ "loss": 0.0866,
182
+ "step": 725
183
+ },
184
+ {
185
+ "epoch": 1.07,
186
+ "learning_rate": 2.507777777777778e-06,
187
+ "loss": 0.0817,
188
+ "step": 750
189
+ },
190
+ {
191
+ "epoch": 1.08,
192
+ "learning_rate": 2.48e-06,
193
+ "loss": 0.0977,
194
+ "step": 775
195
+ },
196
+ {
197
+ "epoch": 1.09,
198
+ "learning_rate": 2.452222222222222e-06,
199
+ "loss": 0.0878,
200
+ "step": 800
201
+ },
202
+ {
203
+ "epoch": 1.09,
204
+ "learning_rate": 2.4244444444444444e-06,
205
+ "loss": 0.0819,
206
+ "step": 825
207
+ },
208
+ {
209
+ "epoch": 1.1,
210
+ "learning_rate": 2.396666666666667e-06,
211
+ "loss": 0.0818,
212
+ "step": 850
213
+ },
214
+ {
215
+ "epoch": 1.11,
216
+ "learning_rate": 2.3688888888888893e-06,
217
+ "loss": 0.0829,
218
+ "step": 875
219
+ },
220
+ {
221
+ "epoch": 1.12,
222
+ "learning_rate": 2.3411111111111113e-06,
223
+ "loss": 0.0801,
224
+ "step": 900
225
+ },
226
+ {
227
+ "epoch": 1.13,
228
+ "learning_rate": 2.3133333333333333e-06,
229
+ "loss": 0.0743,
230
+ "step": 925
231
+ },
232
+ {
233
+ "epoch": 1.14,
234
+ "learning_rate": 2.285555555555556e-06,
235
+ "loss": 0.0758,
236
+ "step": 950
237
+ },
238
+ {
239
+ "epoch": 1.14,
240
+ "learning_rate": 2.257777777777778e-06,
241
+ "loss": 0.0771,
242
+ "step": 975
243
+ },
244
+ {
245
+ "epoch": 1.15,
246
+ "learning_rate": 2.23e-06,
247
+ "loss": 0.0774,
248
+ "step": 1000
249
+ },
250
+ {
251
+ "epoch": 1.15,
252
+ "eval_loss": 0.148193359375,
253
+ "eval_runtime": 2293.5239,
254
+ "eval_samples_per_second": 3.79,
255
+ "eval_steps_per_second": 0.237,
256
+ "eval_wer": 4.878868882500295,
257
+ "step": 1000
258
+ }
259
+ ],
260
+ "max_steps": 3000,
261
+ "num_train_epochs": 9223372036854775807,
262
+ "total_flos": 6.794147330330198e+19,
263
+ "trial_name": null,
264
+ "trial_params": null
265
+ }