sanchit-gandhi HF staff commited on
Commit
e1c3d80
1 Parent(s): d5da3eb

End of training

Browse files
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.33,
3
+ "eval_loss": 0.20645689964294434,
4
+ "eval_runtime": 2865.7931,
5
+ "eval_samples_per_second": 3.749,
6
+ "eval_steps_per_second": 0.234,
7
+ "eval_wer": 11.786082500535915,
8
+ "train_loss": 0.15881791234016418,
9
+ "train_runtime": 6379.5137,
10
+ "train_samples_per_second": 5.016,
11
+ "train_steps_per_second": 0.157
12
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.33,
3
+ "eval_loss": 0.20645689964294434,
4
+ "eval_runtime": 2865.7931,
5
+ "eval_samples_per_second": 3.749,
6
+ "eval_steps_per_second": 0.234,
7
+ "eval_wer": 11.786082500535915
8
+ }
runs/Dec12_05-46-55_150-136-46-204/events.out.tfevents.1670833314.150-136-46-204.133395.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e0c80d4ef8181073dc1115309bde58a303093534315dfc3a7a392709fe56caa
3
+ size 358
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.33,
3
+ "train_loss": 0.15881791234016418,
4
+ "train_runtime": 6379.5137,
5
+ "train_samples_per_second": 5.016,
6
+ "train_steps_per_second": 0.157
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,274 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.329,
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": 4.4e-06,
13
+ "loss": 0.8997,
14
+ "step": 25
15
+ },
16
+ {
17
+ "epoch": 0.05,
18
+ "learning_rate": 9.4e-06,
19
+ "loss": 0.2863,
20
+ "step": 50
21
+ },
22
+ {
23
+ "epoch": 0.07,
24
+ "learning_rate": 1e-05,
25
+ "loss": 0.2519,
26
+ "step": 75
27
+ },
28
+ {
29
+ "epoch": 0.1,
30
+ "learning_rate": 1e-05,
31
+ "loss": 0.3038,
32
+ "step": 100
33
+ },
34
+ {
35
+ "epoch": 0.12,
36
+ "learning_rate": 1e-05,
37
+ "loss": 0.2015,
38
+ "step": 125
39
+ },
40
+ {
41
+ "epoch": 0.15,
42
+ "learning_rate": 1e-05,
43
+ "loss": 0.1834,
44
+ "step": 150
45
+ },
46
+ {
47
+ "epoch": 0.17,
48
+ "learning_rate": 1e-05,
49
+ "loss": 0.2019,
50
+ "step": 175
51
+ },
52
+ {
53
+ "epoch": 0.2,
54
+ "learning_rate": 1e-05,
55
+ "loss": 0.197,
56
+ "step": 200
57
+ },
58
+ {
59
+ "epoch": 0.23,
60
+ "learning_rate": 1e-05,
61
+ "loss": 0.1499,
62
+ "step": 225
63
+ },
64
+ {
65
+ "epoch": 0.25,
66
+ "learning_rate": 1e-05,
67
+ "loss": 0.1695,
68
+ "step": 250
69
+ },
70
+ {
71
+ "epoch": 0.28,
72
+ "learning_rate": 1e-05,
73
+ "loss": 0.146,
74
+ "step": 275
75
+ },
76
+ {
77
+ "epoch": 0.3,
78
+ "learning_rate": 1e-05,
79
+ "loss": 0.1643,
80
+ "step": 300
81
+ },
82
+ {
83
+ "epoch": 0.33,
84
+ "learning_rate": 1e-05,
85
+ "loss": 0.1822,
86
+ "step": 325
87
+ },
88
+ {
89
+ "epoch": 0.35,
90
+ "learning_rate": 1e-05,
91
+ "loss": 0.1506,
92
+ "step": 350
93
+ },
94
+ {
95
+ "epoch": 0.38,
96
+ "learning_rate": 1e-05,
97
+ "loss": 0.1486,
98
+ "step": 375
99
+ },
100
+ {
101
+ "epoch": 0.4,
102
+ "learning_rate": 1e-05,
103
+ "loss": 0.1588,
104
+ "step": 400
105
+ },
106
+ {
107
+ "epoch": 0.42,
108
+ "learning_rate": 1e-05,
109
+ "loss": 0.152,
110
+ "step": 425
111
+ },
112
+ {
113
+ "epoch": 0.45,
114
+ "learning_rate": 1e-05,
115
+ "loss": 0.2014,
116
+ "step": 450
117
+ },
118
+ {
119
+ "epoch": 0.47,
120
+ "learning_rate": 1e-05,
121
+ "loss": 0.1674,
122
+ "step": 475
123
+ },
124
+ {
125
+ "epoch": 0.5,
126
+ "learning_rate": 1e-05,
127
+ "loss": 0.1711,
128
+ "step": 500
129
+ },
130
+ {
131
+ "epoch": 0.53,
132
+ "learning_rate": 1e-05,
133
+ "loss": 0.1271,
134
+ "step": 525
135
+ },
136
+ {
137
+ "epoch": 0.55,
138
+ "learning_rate": 1e-05,
139
+ "loss": 0.1157,
140
+ "step": 550
141
+ },
142
+ {
143
+ "epoch": 0.57,
144
+ "learning_rate": 1e-05,
145
+ "loss": 0.1077,
146
+ "step": 575
147
+ },
148
+ {
149
+ "epoch": 0.6,
150
+ "learning_rate": 1e-05,
151
+ "loss": 0.1195,
152
+ "step": 600
153
+ },
154
+ {
155
+ "epoch": 0.62,
156
+ "learning_rate": 1e-05,
157
+ "loss": 0.1502,
158
+ "step": 625
159
+ },
160
+ {
161
+ "epoch": 0.65,
162
+ "learning_rate": 1e-05,
163
+ "loss": 0.1706,
164
+ "step": 650
165
+ },
166
+ {
167
+ "epoch": 1.0,
168
+ "learning_rate": 1e-05,
169
+ "loss": 0.1524,
170
+ "step": 675
171
+ },
172
+ {
173
+ "epoch": 1.03,
174
+ "learning_rate": 1e-05,
175
+ "loss": 0.0954,
176
+ "step": 700
177
+ },
178
+ {
179
+ "epoch": 1.05,
180
+ "learning_rate": 1e-05,
181
+ "loss": 0.079,
182
+ "step": 725
183
+ },
184
+ {
185
+ "epoch": 1.08,
186
+ "learning_rate": 1e-05,
187
+ "loss": 0.0845,
188
+ "step": 750
189
+ },
190
+ {
191
+ "epoch": 1.1,
192
+ "learning_rate": 1e-05,
193
+ "loss": 0.1013,
194
+ "step": 775
195
+ },
196
+ {
197
+ "epoch": 1.13,
198
+ "learning_rate": 1e-05,
199
+ "loss": 0.0703,
200
+ "step": 800
201
+ },
202
+ {
203
+ "epoch": 1.15,
204
+ "learning_rate": 1e-05,
205
+ "loss": 0.0669,
206
+ "step": 825
207
+ },
208
+ {
209
+ "epoch": 1.18,
210
+ "learning_rate": 1e-05,
211
+ "loss": 0.0772,
212
+ "step": 850
213
+ },
214
+ {
215
+ "epoch": 1.2,
216
+ "learning_rate": 1e-05,
217
+ "loss": 0.057,
218
+ "step": 875
219
+ },
220
+ {
221
+ "epoch": 1.23,
222
+ "learning_rate": 1e-05,
223
+ "loss": 0.0546,
224
+ "step": 900
225
+ },
226
+ {
227
+ "epoch": 1.25,
228
+ "learning_rate": 1e-05,
229
+ "loss": 0.056,
230
+ "step": 925
231
+ },
232
+ {
233
+ "epoch": 1.28,
234
+ "learning_rate": 1e-05,
235
+ "loss": 0.0522,
236
+ "step": 950
237
+ },
238
+ {
239
+ "epoch": 1.3,
240
+ "learning_rate": 1e-05,
241
+ "loss": 0.0592,
242
+ "step": 975
243
+ },
244
+ {
245
+ "epoch": 1.33,
246
+ "learning_rate": 1e-05,
247
+ "loss": 0.0686,
248
+ "step": 1000
249
+ },
250
+ {
251
+ "epoch": 1.33,
252
+ "eval_loss": 0.20645689964294434,
253
+ "eval_runtime": 2856.486,
254
+ "eval_samples_per_second": 3.761,
255
+ "eval_steps_per_second": 0.235,
256
+ "eval_wer": 11.786082500535915,
257
+ "step": 1000
258
+ },
259
+ {
260
+ "epoch": 1.33,
261
+ "step": 1000,
262
+ "total_flos": 9.23473281024e+18,
263
+ "train_loss": 0.15881791234016418,
264
+ "train_runtime": 6379.5137,
265
+ "train_samples_per_second": 5.016,
266
+ "train_steps_per_second": 0.157
267
+ }
268
+ ],
269
+ "max_steps": 1000,
270
+ "num_train_epochs": 9223372036854775807,
271
+ "total_flos": 9.23473281024e+18,
272
+ "trial_name": null,
273
+ "trial_params": null
274
+ }