steja commited on
Commit
e392a22
1 Parent(s): 8761e92

End of training

Browse files
Files changed (4) hide show
  1. all_results.json +12 -0
  2. eval_results.json +8 -0
  3. train_results.json +7 -0
  4. trainer_state.json +283 -0
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 76.89,
3
+ "eval_loss": 0.63818359375,
4
+ "eval_runtime": 604.2847,
5
+ "eval_samples_per_second": 1.622,
6
+ "eval_steps_per_second": 0.026,
7
+ "eval_wer": 27.692698197817073,
8
+ "train_loss": 0.1158139866143465,
9
+ "train_runtime": 9638.6666,
10
+ "train_samples_per_second": 6.64,
11
+ "train_steps_per_second": 0.104
12
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 76.89,
3
+ "eval_loss": 0.63818359375,
4
+ "eval_runtime": 604.2847,
5
+ "eval_samples_per_second": 1.622,
6
+ "eval_steps_per_second": 0.026,
7
+ "eval_wer": 27.692698197817073
8
+ }
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 76.89,
3
+ "train_loss": 0.1158139866143465,
4
+ "train_runtime": 9638.6666,
5
+ "train_samples_per_second": 6.64,
6
+ "train_steps_per_second": 0.104
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,283 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 27.692698197817073,
3
+ "best_model_checkpoint": "./whisper-large-sindhi/checkpoint-500",
4
+ "epoch": 76.88888888888889,
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": 1.89,
12
+ "learning_rate": 6.505149978319905e-06,
13
+ "loss": 3.6387,
14
+ "step": 25
15
+ },
16
+ {
17
+ "epoch": 3.81,
18
+ "learning_rate": 8.31378915840787e-06,
19
+ "loss": 0.5812,
20
+ "step": 50
21
+ },
22
+ {
23
+ "epoch": 5.74,
24
+ "learning_rate": 9.28666248215634e-06,
25
+ "loss": 0.2363,
26
+ "step": 75
27
+ },
28
+ {
29
+ "epoch": 7.67,
30
+ "learning_rate": 9.956130378462474e-06,
31
+ "loss": 0.0927,
32
+ "step": 100
33
+ },
34
+ {
35
+ "epoch": 9.59,
36
+ "learning_rate": 9.755555555555556e-06,
37
+ "loss": 0.0352,
38
+ "step": 125
39
+ },
40
+ {
41
+ "epoch": 11.52,
42
+ "learning_rate": 9.466666666666667e-06,
43
+ "loss": 0.0142,
44
+ "step": 150
45
+ },
46
+ {
47
+ "epoch": 13.44,
48
+ "learning_rate": 9.17777777777778e-06,
49
+ "loss": 0.0081,
50
+ "step": 175
51
+ },
52
+ {
53
+ "epoch": 15.37,
54
+ "learning_rate": 8.888888888888888e-06,
55
+ "loss": 0.0046,
56
+ "step": 200
57
+ },
58
+ {
59
+ "epoch": 17.3,
60
+ "learning_rate": 8.6e-06,
61
+ "loss": 0.0037,
62
+ "step": 225
63
+ },
64
+ {
65
+ "epoch": 19.22,
66
+ "learning_rate": 8.311111111111111e-06,
67
+ "loss": 0.0028,
68
+ "step": 250
69
+ },
70
+ {
71
+ "epoch": 21.15,
72
+ "learning_rate": 8.022222222222222e-06,
73
+ "loss": 0.0023,
74
+ "step": 275
75
+ },
76
+ {
77
+ "epoch": 23.07,
78
+ "learning_rate": 7.733333333333334e-06,
79
+ "loss": 0.0011,
80
+ "step": 300
81
+ },
82
+ {
83
+ "epoch": 24.96,
84
+ "learning_rate": 7.444444444444445e-06,
85
+ "loss": 0.0009,
86
+ "step": 325
87
+ },
88
+ {
89
+ "epoch": 26.89,
90
+ "learning_rate": 7.155555555555556e-06,
91
+ "loss": 0.0008,
92
+ "step": 350
93
+ },
94
+ {
95
+ "epoch": 28.81,
96
+ "learning_rate": 6.866666666666667e-06,
97
+ "loss": 0.0007,
98
+ "step": 375
99
+ },
100
+ {
101
+ "epoch": 30.74,
102
+ "learning_rate": 6.577777777777779e-06,
103
+ "loss": 0.0006,
104
+ "step": 400
105
+ },
106
+ {
107
+ "epoch": 32.67,
108
+ "learning_rate": 6.28888888888889e-06,
109
+ "loss": 0.0006,
110
+ "step": 425
111
+ },
112
+ {
113
+ "epoch": 34.59,
114
+ "learning_rate": 6e-06,
115
+ "loss": 0.0005,
116
+ "step": 450
117
+ },
118
+ {
119
+ "epoch": 36.52,
120
+ "learning_rate": 5.711111111111112e-06,
121
+ "loss": 0.0005,
122
+ "step": 475
123
+ },
124
+ {
125
+ "epoch": 38.44,
126
+ "learning_rate": 5.422222222222223e-06,
127
+ "loss": 0.0005,
128
+ "step": 500
129
+ },
130
+ {
131
+ "epoch": 38.44,
132
+ "eval_loss": 0.63818359375,
133
+ "eval_runtime": 605.6018,
134
+ "eval_samples_per_second": 1.618,
135
+ "eval_steps_per_second": 0.026,
136
+ "eval_wer": 27.692698197817073,
137
+ "step": 500
138
+ },
139
+ {
140
+ "epoch": 40.37,
141
+ "learning_rate": 5.133333333333334e-06,
142
+ "loss": 0.0004,
143
+ "step": 525
144
+ },
145
+ {
146
+ "epoch": 42.3,
147
+ "learning_rate": 4.8444444444444446e-06,
148
+ "loss": 0.0004,
149
+ "step": 550
150
+ },
151
+ {
152
+ "epoch": 44.22,
153
+ "learning_rate": 4.555555555555556e-06,
154
+ "loss": 0.0004,
155
+ "step": 575
156
+ },
157
+ {
158
+ "epoch": 46.15,
159
+ "learning_rate": 4.266666666666668e-06,
160
+ "loss": 0.0004,
161
+ "step": 600
162
+ },
163
+ {
164
+ "epoch": 48.07,
165
+ "learning_rate": 3.977777777777778e-06,
166
+ "loss": 0.0004,
167
+ "step": 625
168
+ },
169
+ {
170
+ "epoch": 49.96,
171
+ "learning_rate": 3.7e-06,
172
+ "loss": 0.0003,
173
+ "step": 650
174
+ },
175
+ {
176
+ "epoch": 51.89,
177
+ "learning_rate": 3.4111111111111113e-06,
178
+ "loss": 0.0003,
179
+ "step": 675
180
+ },
181
+ {
182
+ "epoch": 53.81,
183
+ "learning_rate": 3.1222222222222228e-06,
184
+ "loss": 0.0003,
185
+ "step": 700
186
+ },
187
+ {
188
+ "epoch": 55.74,
189
+ "learning_rate": 2.8333333333333335e-06,
190
+ "loss": 0.0003,
191
+ "step": 725
192
+ },
193
+ {
194
+ "epoch": 57.67,
195
+ "learning_rate": 2.5444444444444446e-06,
196
+ "loss": 0.0003,
197
+ "step": 750
198
+ },
199
+ {
200
+ "epoch": 59.59,
201
+ "learning_rate": 2.2555555555555557e-06,
202
+ "loss": 0.0003,
203
+ "step": 775
204
+ },
205
+ {
206
+ "epoch": 61.52,
207
+ "learning_rate": 1.9666666666666668e-06,
208
+ "loss": 0.0003,
209
+ "step": 800
210
+ },
211
+ {
212
+ "epoch": 63.44,
213
+ "learning_rate": 1.6777777777777779e-06,
214
+ "loss": 0.0003,
215
+ "step": 825
216
+ },
217
+ {
218
+ "epoch": 65.37,
219
+ "learning_rate": 1.3888888888888892e-06,
220
+ "loss": 0.0003,
221
+ "step": 850
222
+ },
223
+ {
224
+ "epoch": 67.3,
225
+ "learning_rate": 1.1e-06,
226
+ "loss": 0.0003,
227
+ "step": 875
228
+ },
229
+ {
230
+ "epoch": 69.22,
231
+ "learning_rate": 8.111111111111112e-07,
232
+ "loss": 0.0003,
233
+ "step": 900
234
+ },
235
+ {
236
+ "epoch": 71.15,
237
+ "learning_rate": 5.222222222222223e-07,
238
+ "loss": 0.0003,
239
+ "step": 925
240
+ },
241
+ {
242
+ "epoch": 73.07,
243
+ "learning_rate": 2.3333333333333336e-07,
244
+ "loss": 0.0003,
245
+ "step": 950
246
+ },
247
+ {
248
+ "epoch": 74.96,
249
+ "learning_rate": 0.0,
250
+ "loss": 0.0003,
251
+ "step": 975
252
+ },
253
+ {
254
+ "epoch": 76.89,
255
+ "learning_rate": 0.0,
256
+ "loss": 0.0003,
257
+ "step": 1000
258
+ },
259
+ {
260
+ "epoch": 76.89,
261
+ "eval_loss": 0.67138671875,
262
+ "eval_runtime": 605.19,
263
+ "eval_samples_per_second": 1.619,
264
+ "eval_steps_per_second": 0.026,
265
+ "eval_wer": 27.832303917421104,
266
+ "step": 1000
267
+ },
268
+ {
269
+ "epoch": 76.89,
270
+ "step": 1000,
271
+ "total_flos": 1.384647263524592e+20,
272
+ "train_loss": 0.1158139866143465,
273
+ "train_runtime": 9638.6666,
274
+ "train_samples_per_second": 6.64,
275
+ "train_steps_per_second": 0.104
276
+ }
277
+ ],
278
+ "max_steps": 1000,
279
+ "num_train_epochs": 77,
280
+ "total_flos": 1.384647263524592e+20,
281
+ "trial_name": null,
282
+ "trial_params": null
283
+ }