anuragshas commited on
Commit
d145dd0
1 Parent(s): 4aecb25

End of training

Browse files
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 9.0,
3
+ "eval_loss": 0.361572265625,
4
+ "eval_runtime": 552.4778,
5
+ "eval_samples_per_second": 2.968,
6
+ "eval_steps_per_second": 0.186,
7
+ "eval_wer": 18.464443960194668,
8
+ "train_loss": 0.13070509910583497,
9
+ "train_runtime": 8375.5647,
10
+ "train_samples_per_second": 3.821,
11
+ "train_steps_per_second": 0.119
12
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 9.0,
3
+ "eval_loss": 0.361572265625,
4
+ "eval_runtime": 552.4778,
5
+ "eval_samples_per_second": 2.968,
6
+ "eval_steps_per_second": 0.186,
7
+ "eval_wer": 18.464443960194668
8
+ }
runs/Dec19_19-51-33_129-146-105-103/events.out.tfevents.1671488607.129-146-105-103.2974729.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cd8f75a0f86aa00c13af1dadb6440da7725e237748e8988c807f50282d827cc
3
+ size 358
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 9.0,
3
+ "train_loss": 0.13070509910583497,
4
+ "train_runtime": 8375.5647,
5
+ "train_samples_per_second": 3.821,
6
+ "train_steps_per_second": 0.119
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,274 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 9.001,
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": 6.505149978319905e-06,
13
+ "loss": 1.4407,
14
+ "step": 25
15
+ },
16
+ {
17
+ "epoch": 0.05,
18
+ "learning_rate": 8.266062568876717e-06,
19
+ "loss": 0.7384,
20
+ "step": 50
21
+ },
22
+ {
23
+ "epoch": 0.07,
24
+ "learning_rate": 9.225490200071284e-06,
25
+ "loss": 0.5419,
26
+ "step": 75
27
+ },
28
+ {
29
+ "epoch": 0.1,
30
+ "learning_rate": 9.888618026444238e-06,
31
+ "loss": 0.4384,
32
+ "step": 100
33
+ },
34
+ {
35
+ "epoch": 1.01,
36
+ "learning_rate": 9.78888888888889e-06,
37
+ "loss": 0.3515,
38
+ "step": 125
39
+ },
40
+ {
41
+ "epoch": 1.04,
42
+ "learning_rate": 9.511111111111112e-06,
43
+ "loss": 0.2833,
44
+ "step": 150
45
+ },
46
+ {
47
+ "epoch": 1.06,
48
+ "learning_rate": 9.233333333333334e-06,
49
+ "loss": 0.2293,
50
+ "step": 175
51
+ },
52
+ {
53
+ "epoch": 1.09,
54
+ "learning_rate": 8.955555555555555e-06,
55
+ "loss": 0.188,
56
+ "step": 200
57
+ },
58
+ {
59
+ "epoch": 2.0,
60
+ "learning_rate": 8.677777777777779e-06,
61
+ "loss": 0.1587,
62
+ "step": 225
63
+ },
64
+ {
65
+ "epoch": 2.03,
66
+ "learning_rate": 8.400000000000001e-06,
67
+ "loss": 0.1237,
68
+ "step": 250
69
+ },
70
+ {
71
+ "epoch": 2.05,
72
+ "learning_rate": 8.122222222222223e-06,
73
+ "loss": 0.1073,
74
+ "step": 275
75
+ },
76
+ {
77
+ "epoch": 2.08,
78
+ "learning_rate": 7.844444444444446e-06,
79
+ "loss": 0.0877,
80
+ "step": 300
81
+ },
82
+ {
83
+ "epoch": 2.1,
84
+ "learning_rate": 7.566666666666667e-06,
85
+ "loss": 0.0767,
86
+ "step": 325
87
+ },
88
+ {
89
+ "epoch": 3.02,
90
+ "learning_rate": 7.28888888888889e-06,
91
+ "loss": 0.0653,
92
+ "step": 350
93
+ },
94
+ {
95
+ "epoch": 3.04,
96
+ "learning_rate": 7.011111111111112e-06,
97
+ "loss": 0.0546,
98
+ "step": 375
99
+ },
100
+ {
101
+ "epoch": 3.07,
102
+ "learning_rate": 6.733333333333334e-06,
103
+ "loss": 0.0479,
104
+ "step": 400
105
+ },
106
+ {
107
+ "epoch": 3.09,
108
+ "learning_rate": 6.455555555555556e-06,
109
+ "loss": 0.0397,
110
+ "step": 425
111
+ },
112
+ {
113
+ "epoch": 4.01,
114
+ "learning_rate": 6.177777777777778e-06,
115
+ "loss": 0.0371,
116
+ "step": 450
117
+ },
118
+ {
119
+ "epoch": 4.03,
120
+ "learning_rate": 5.9e-06,
121
+ "loss": 0.0228,
122
+ "step": 475
123
+ },
124
+ {
125
+ "epoch": 4.06,
126
+ "learning_rate": 5.622222222222222e-06,
127
+ "loss": 0.0228,
128
+ "step": 500
129
+ },
130
+ {
131
+ "epoch": 4.08,
132
+ "learning_rate": 5.344444444444446e-06,
133
+ "loss": 0.0285,
134
+ "step": 525
135
+ },
136
+ {
137
+ "epoch": 4.11,
138
+ "learning_rate": 5.077777777777778e-06,
139
+ "loss": 0.0257,
140
+ "step": 550
141
+ },
142
+ {
143
+ "epoch": 5.02,
144
+ "learning_rate": 4.800000000000001e-06,
145
+ "loss": 0.0166,
146
+ "step": 575
147
+ },
148
+ {
149
+ "epoch": 5.04,
150
+ "learning_rate": 4.5222222222222225e-06,
151
+ "loss": 0.011,
152
+ "step": 600
153
+ },
154
+ {
155
+ "epoch": 5.07,
156
+ "learning_rate": 4.244444444444445e-06,
157
+ "loss": 0.0153,
158
+ "step": 625
159
+ },
160
+ {
161
+ "epoch": 5.09,
162
+ "learning_rate": 3.966666666666667e-06,
163
+ "loss": 0.014,
164
+ "step": 650
165
+ },
166
+ {
167
+ "epoch": 6.01,
168
+ "learning_rate": 3.688888888888889e-06,
169
+ "loss": 0.01,
170
+ "step": 675
171
+ },
172
+ {
173
+ "epoch": 6.03,
174
+ "learning_rate": 3.4111111111111113e-06,
175
+ "loss": 0.0071,
176
+ "step": 700
177
+ },
178
+ {
179
+ "epoch": 6.06,
180
+ "learning_rate": 3.133333333333334e-06,
181
+ "loss": 0.0064,
182
+ "step": 725
183
+ },
184
+ {
185
+ "epoch": 6.08,
186
+ "learning_rate": 2.855555555555556e-06,
187
+ "loss": 0.0058,
188
+ "step": 750
189
+ },
190
+ {
191
+ "epoch": 6.11,
192
+ "learning_rate": 2.577777777777778e-06,
193
+ "loss": 0.0059,
194
+ "step": 775
195
+ },
196
+ {
197
+ "epoch": 7.02,
198
+ "learning_rate": 2.3000000000000004e-06,
199
+ "loss": 0.0037,
200
+ "step": 800
201
+ },
202
+ {
203
+ "epoch": 7.05,
204
+ "learning_rate": 2.0222222222222223e-06,
205
+ "loss": 0.003,
206
+ "step": 825
207
+ },
208
+ {
209
+ "epoch": 7.07,
210
+ "learning_rate": 1.7444444444444448e-06,
211
+ "loss": 0.0034,
212
+ "step": 850
213
+ },
214
+ {
215
+ "epoch": 7.1,
216
+ "learning_rate": 1.4666666666666669e-06,
217
+ "loss": 0.0032,
218
+ "step": 875
219
+ },
220
+ {
221
+ "epoch": 8.01,
222
+ "learning_rate": 1.188888888888889e-06,
223
+ "loss": 0.0029,
224
+ "step": 900
225
+ },
226
+ {
227
+ "epoch": 8.04,
228
+ "learning_rate": 9.111111111111113e-07,
229
+ "loss": 0.0026,
230
+ "step": 925
231
+ },
232
+ {
233
+ "epoch": 8.06,
234
+ "learning_rate": 6.333333333333334e-07,
235
+ "loss": 0.0026,
236
+ "step": 950
237
+ },
238
+ {
239
+ "epoch": 8.09,
240
+ "learning_rate": 3.555555555555556e-07,
241
+ "loss": 0.0025,
242
+ "step": 975
243
+ },
244
+ {
245
+ "epoch": 9.0,
246
+ "learning_rate": 7.777777777777778e-08,
247
+ "loss": 0.0023,
248
+ "step": 1000
249
+ },
250
+ {
251
+ "epoch": 9.0,
252
+ "eval_loss": 0.361572265625,
253
+ "eval_runtime": 564.3144,
254
+ "eval_samples_per_second": 2.906,
255
+ "eval_steps_per_second": 0.183,
256
+ "eval_wer": 18.464443960194668,
257
+ "step": 1000
258
+ },
259
+ {
260
+ "epoch": 9.0,
261
+ "step": 1000,
262
+ "total_flos": 6.767395305329315e+19,
263
+ "train_loss": 0.13070509910583497,
264
+ "train_runtime": 8375.5647,
265
+ "train_samples_per_second": 3.821,
266
+ "train_steps_per_second": 0.119
267
+ }
268
+ ],
269
+ "max_steps": 1000,
270
+ "num_train_epochs": 9223372036854775807,
271
+ "total_flos": 6.767395305329315e+19,
272
+ "trial_name": null,
273
+ "trial_params": null
274
+ }