Hugging Face's logo

DrishtiSharma
/
wav2vec2-xls-r-300m-rm-vallader-d1

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
mozilla-foundation/common_voice_8_0
Generated from Trainer
rm-vallader
robust-speech-event
model_for_talk
hf-asr-leaderboard
Eval Results (legacy)
Model card Files
xet
 Community
1
DrishtiSharma commited on
Commit
c32f5d8
·
1 Parent(s): 8b54074

End of training

Browse files
Files changed (4) hide show
  1. all_results.json +14 -0
  2. eval_results.json +9 -0
  3. train_results.json +8 -0
  4. trainer_state.json +277 -0
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 100.0,
3
+ "eval_loss": 0.2753646671772003,
4
+ "eval_runtime": 19.8089,
5
+ "eval_samples": 427,
6
+ "eval_samples_per_second": 21.556,
7
+ "eval_steps_per_second": 1.363,
8
+ "eval_wer": 0.28305984555984554,
9
+ "train_loss": 1.620846695177483,
10
+ "train_runtime": 7377.7284,
11
+ "train_samples": 1025,
12
+ "train_samples_per_second": 13.893,
13
+ "train_steps_per_second": 0.447
14
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 100.0,
3
+ "eval_loss": 0.2753646671772003,
4
+ "eval_runtime": 19.8089,
5
+ "eval_samples": 427,
6
+ "eval_samples_per_second": 21.556,
7
+ "eval_steps_per_second": 1.363,
8
+ "eval_wer": 0.28305984555984554
9
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 100.0,
3
+ "train_loss": 1.620846695177483,
4
+ "train_runtime": 7377.7284,
5
+ "train_samples": 1025,
6
+ "train_samples_per_second": 13.893,
7
+ "train_steps_per_second": 0.447
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,277 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 100.0,
5
+ "global_step": 3300,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 3.03,
12
+ "learning_rate": 1.455e-05,
13
+ "loss": 13.8145,
14
+ "step": 100
15
+ },
16
+ {
17
+ "epoch": 6.06,
18
+ "learning_rate": 2.955e-05,
19
+ "loss": 4.8042,
20
+ "step": 200
21
+ },
22
+ {
23
+ "epoch": 9.09,
24
+ "learning_rate": 4.454999999999999e-05,
25
+ "loss": 3.4947,
26
+ "step": 300
27
+ },
28
+ {
29
+ "epoch": 12.12,
30
+ "learning_rate": 5.955e-05,
31
+ "loss": 3.0225,
32
+ "step": 400
33
+ },
34
+ {
35
+ "epoch": 15.15,
36
+ "learning_rate": 7.455e-05,
37
+ "loss": 2.927,
38
+ "step": 500
39
+ },
40
+ {
41
+ "epoch": 15.15,
42
+ "eval_loss": 2.919621706008911,
43
+ "eval_runtime": 20.0515,
44
+ "eval_samples_per_second": 21.295,
45
+ "eval_steps_per_second": 1.347,
46
+ "eval_wer": 1.0,
47
+ "step": 500
48
+ },
49
+ {
50
+ "epoch": 18.18,
51
+ "learning_rate": 7.240178571428571e-05,
52
+ "loss": 2.8838,
53
+ "step": 600
54
+ },
55
+ {
56
+ "epoch": 21.21,
57
+ "learning_rate": 6.972321428571428e-05,
58
+ "loss": 2.8617,
59
+ "step": 700
60
+ },
61
+ {
62
+ "epoch": 24.24,
63
+ "learning_rate": 6.704464285714285e-05,
64
+ "loss": 2.8313,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 27.27,
69
+ "learning_rate": 6.436607142857142e-05,
70
+ "loss": 2.0706,
71
+ "step": 900
72
+ },
73
+ {
74
+ "epoch": 30.3,
75
+ "learning_rate": 6.16875e-05,
76
+ "loss": 1.3835,
77
+ "step": 1000
78
+ },
79
+ {
80
+ "epoch": 30.3,
81
+ "eval_loss": 0.5878978967666626,
82
+ "eval_runtime": 20.2624,
83
+ "eval_samples_per_second": 21.073,
84
+ "eval_steps_per_second": 1.333,
85
+ "eval_wer": 0.5866312741312741,
86
+ "step": 1000
87
+ },
88
+ {
89
+ "epoch": 33.33,
90
+ "learning_rate": 5.9008928571428565e-05,
91
+ "loss": 1.1555,
92
+ "step": 1100
93
+ },
94
+ {
95
+ "epoch": 36.36,
96
+ "learning_rate": 5.633035714285714e-05,
97
+ "loss": 0.9935,
98
+ "step": 1200
99
+ },
100
+ {
101
+ "epoch": 39.39,
102
+ "learning_rate": 5.3651785714285706e-05,
103
+ "loss": 0.8824,
104
+ "step": 1300
105
+ },
106
+ {
107
+ "epoch": 42.42,
108
+ "learning_rate": 5.0973214285714276e-05,
109
+ "loss": 0.8012,
110
+ "step": 1400
111
+ },
112
+ {
113
+ "epoch": 45.45,
114
+ "learning_rate": 4.829464285714285e-05,
115
+ "loss": 0.7415,
116
+ "step": 1500
117
+ },
118
+ {
119
+ "epoch": 45.45,
120
+ "eval_loss": 0.30774399638175964,
121
+ "eval_runtime": 20.0347,
122
+ "eval_samples_per_second": 21.313,
123
+ "eval_steps_per_second": 1.348,
124
+ "eval_wer": 0.33156370656370654,
125
+ "step": 1500
126
+ },
127
+ {
128
+ "epoch": 48.48,
129
+ "learning_rate": 4.561607142857142e-05,
130
+ "loss": 0.6777,
131
+ "step": 1600
132
+ },
133
+ {
134
+ "epoch": 51.52,
135
+ "learning_rate": 4.29375e-05,
136
+ "loss": 0.6458,
137
+ "step": 1700
138
+ },
139
+ {
140
+ "epoch": 54.55,
141
+ "learning_rate": 4.025892857142857e-05,
142
+ "loss": 0.6332,
143
+ "step": 1800
144
+ },
145
+ {
146
+ "epoch": 57.58,
147
+ "learning_rate": 3.758035714285714e-05,
148
+ "loss": 0.5732,
149
+ "step": 1900
150
+ },
151
+ {
152
+ "epoch": 60.61,
153
+ "learning_rate": 3.490178571428571e-05,
154
+ "loss": 0.5575,
155
+ "step": 2000
156
+ },
157
+ {
158
+ "epoch": 60.61,
159
+ "eval_loss": 0.2735135853290558,
160
+ "eval_runtime": 19.9705,
161
+ "eval_samples_per_second": 21.382,
162
+ "eval_steps_per_second": 1.352,
163
+ "eval_wer": 0.2953667953667954,
164
+ "step": 2000
165
+ },
166
+ {
167
+ "epoch": 63.64,
168
+ "learning_rate": 3.222321428571428e-05,
169
+ "loss": 0.5202,
170
+ "step": 2100
171
+ },
172
+ {
173
+ "epoch": 66.67,
174
+ "learning_rate": 2.954464285714285e-05,
175
+ "loss": 0.5067,
176
+ "step": 2200
177
+ },
178
+ {
179
+ "epoch": 69.7,
180
+ "learning_rate": 2.6866071428571425e-05,
181
+ "loss": 0.4894,
182
+ "step": 2300
183
+ },
184
+ {
185
+ "epoch": 72.73,
186
+ "learning_rate": 2.41875e-05,
187
+ "loss": 0.472,
188
+ "step": 2400
189
+ },
190
+ {
191
+ "epoch": 75.76,
192
+ "learning_rate": 2.1508928571428572e-05,
193
+ "loss": 0.4581,
194
+ "step": 2500
195
+ },
196
+ {
197
+ "epoch": 75.76,
198
+ "eval_loss": 0.27067553997039795,
199
+ "eval_runtime": 19.7341,
200
+ "eval_samples_per_second": 21.638,
201
+ "eval_steps_per_second": 1.368,
202
+ "eval_wer": 0.28016409266409265,
203
+ "step": 2500
204
+ },
205
+ {
206
+ "epoch": 78.79,
207
+ "learning_rate": 1.883035714285714e-05,
208
+ "loss": 0.4364,
209
+ "step": 2600
210
+ },
211
+ {
212
+ "epoch": 81.82,
213
+ "learning_rate": 1.6151785714285712e-05,
214
+ "loss": 0.4457,
215
+ "step": 2700
216
+ },
217
+ {
218
+ "epoch": 84.85,
219
+ "learning_rate": 1.3473214285714284e-05,
220
+ "loss": 0.4142,
221
+ "step": 2800
222
+ },
223
+ {
224
+ "epoch": 87.88,
225
+ "learning_rate": 1.0794642857142856e-05,
226
+ "loss": 0.418,
227
+ "step": 2900
228
+ },
229
+ {
230
+ "epoch": 90.91,
231
+ "learning_rate": 8.116071428571428e-06,
232
+ "loss": 0.3977,
233
+ "step": 3000
234
+ },
235
+ {
236
+ "epoch": 90.91,
237
+ "eval_loss": 0.2785268723964691,
238
+ "eval_runtime": 19.7902,
239
+ "eval_samples_per_second": 21.576,
240
+ "eval_steps_per_second": 1.364,
241
+ "eval_wer": 0.2808880308880309,
242
+ "step": 3000
243
+ },
244
+ {
245
+ "epoch": 93.94,
246
+ "learning_rate": 5.437499999999999e-06,
247
+ "loss": 0.3984,
248
+ "step": 3100
249
+ },
250
+ {
251
+ "epoch": 96.97,
252
+ "learning_rate": 2.758928571428571e-06,
253
+ "loss": 0.3919,
254
+ "step": 3200
255
+ },
256
+ {
257
+ "epoch": 100.0,
258
+ "learning_rate": 8.035714285714285e-08,
259
+ "loss": 0.384,
260
+ "step": 3300
261
+ },
262
+ {
263
+ "epoch": 100.0,
264
+ "step": 3300,
265
+ "total_flos": 2.0644460727363166e+19,
266
+ "train_loss": 1.620846695177483,
267
+ "train_runtime": 7377.7284,
268
+ "train_samples_per_second": 13.893,
269
+ "train_steps_per_second": 0.447
270
+ }
271
+ ],
272
+ "max_steps": 3300,
273
+ "num_train_epochs": 100,
274
+ "total_flos": 2.0644460727363166e+19,
275
+ "trial_name": null,
276
+ "trial_params": null
277
+ }