Hugging Face's logo

henilp105
/
wav2vec2-large-xls-r-300m-te

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Inference Endpoints
Model card Files Metrics Community
henilp105 commited on
Commit
53e034f
•
1 Parent(s): b08d88a

Upload checkpoint-4000/trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. checkpoint-4000/trainer_state.json +184 -0
checkpoint-4000/trainer_state.json ADDED
@@ -0,0 +1,184 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 19.230215827338128,
5
+ "global_step": 4000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.44,
12
+ "learning_rate": 0.00017879999999999998,
13
+ "loss": 3.4798,
14
+ "step": 300
15
+ },
16
+ {
17
+ "epoch": 1.92,
18
+ "eval_loss": 4.179981231689453,
19
+ "eval_runtime": 203.6334,
20
+ "eval_samples_per_second": 10.966,
21
+ "eval_steps_per_second": 1.375,
22
+ "eval_wer": 0.9931173409434279,
23
+ "step": 400
24
+ },
25
+ {
26
+ "epoch": 2.88,
27
+ "learning_rate": 0.0002948780487804878,
28
+ "loss": 3.4274,
29
+ "step": 600
30
+ },
31
+ {
32
+ "epoch": 3.84,
33
+ "eval_loss": 3.7398014068603516,
34
+ "eval_runtime": 203.914,
35
+ "eval_samples_per_second": 10.951,
36
+ "eval_steps_per_second": 1.373,
37
+ "eval_wer": 0.9930334060768843,
38
+ "step": 800
39
+ },
40
+ {
41
+ "epoch": 4.33,
42
+ "learning_rate": 0.00027919860627177696,
43
+ "loss": 3.3742,
44
+ "step": 900
45
+ },
46
+ {
47
+ "epoch": 5.77,
48
+ "learning_rate": 0.0002635191637630662,
49
+ "loss": 3.3302,
50
+ "step": 1200
51
+ },
52
+ {
53
+ "epoch": 5.77,
54
+ "eval_loss": 3.6393752098083496,
55
+ "eval_runtime": 206.073,
56
+ "eval_samples_per_second": 10.836,
57
+ "eval_steps_per_second": 1.359,
58
+ "eval_wer": 0.995971126405909,
59
+ "step": 1200
60
+ },
61
+ {
62
+ "epoch": 7.21,
63
+ "learning_rate": 0.0002478397212543554,
64
+ "loss": 3.2912,
65
+ "step": 1500
66
+ },
67
+ {
68
+ "epoch": 7.69,
69
+ "eval_loss": 3.7553415298461914,
70
+ "eval_runtime": 204.658,
71
+ "eval_samples_per_second": 10.911,
72
+ "eval_steps_per_second": 1.368,
73
+ "eval_wer": 0.9923619271445359,
74
+ "step": 1600
75
+ },
76
+ {
77
+ "epoch": 8.65,
78
+ "learning_rate": 0.0002321602787456446,
79
+ "loss": 3.2096,
80
+ "step": 1800
81
+ },
82
+ {
83
+ "epoch": 9.61,
84
+ "eval_loss": 3.4753119945526123,
85
+ "eval_runtime": 204.5164,
86
+ "eval_samples_per_second": 10.918,
87
+ "eval_steps_per_second": 1.369,
88
+ "eval_wer": 0.9903474903474904,
89
+ "step": 2000
90
+ },
91
+ {
92
+ "epoch": 10.1,
93
+ "learning_rate": 0.0002164808362369338,
94
+ "loss": 3.1291,
95
+ "step": 2100
96
+ },
97
+ {
98
+ "epoch": 11.54,
99
+ "learning_rate": 0.0002009059233449477,
100
+ "loss": 3.0236,
101
+ "step": 2400
102
+ },
103
+ {
104
+ "epoch": 11.54,
105
+ "eval_loss": 3.3585305213928223,
106
+ "eval_runtime": 201.3035,
107
+ "eval_samples_per_second": 11.093,
108
+ "eval_steps_per_second": 1.391,
109
+ "eval_wer": 0.9937888198757764,
110
+ "step": 2400
111
+ },
112
+ {
113
+ "epoch": 12.98,
114
+ "learning_rate": 0.0001852264808362369,
115
+ "loss": 2.8714,
116
+ "step": 2700
117
+ },
118
+ {
119
+ "epoch": 13.46,
120
+ "eval_loss": 3.3223414421081543,
121
+ "eval_runtime": 204.2132,
122
+ "eval_samples_per_second": 10.935,
123
+ "eval_steps_per_second": 1.371,
124
+ "eval_wer": 0.9984891724022159,
125
+ "step": 2800
126
+ },
127
+ {
128
+ "epoch": 14.42,
129
+ "learning_rate": 0.00016954703832752614,
130
+ "loss": 2.7351,
131
+ "step": 3000
132
+ },
133
+ {
134
+ "epoch": 15.38,
135
+ "eval_loss": 3.2935783863067627,
136
+ "eval_runtime": 202.4119,
137
+ "eval_samples_per_second": 11.032,
138
+ "eval_steps_per_second": 1.383,
139
+ "eval_wer": 0.9994963908007386,
140
+ "step": 3200
141
+ },
142
+ {
143
+ "epoch": 15.86,
144
+ "learning_rate": 0.00015386759581881532,
145
+ "loss": 2.5377,
146
+ "step": 3300
147
+ },
148
+ {
149
+ "epoch": 17.31,
150
+ "learning_rate": 0.00013818815331010452,
151
+ "loss": 2.4208,
152
+ "step": 3600
153
+ },
154
+ {
155
+ "epoch": 17.31,
156
+ "eval_loss": 3.3104729652404785,
157
+ "eval_runtime": 203.9464,
158
+ "eval_samples_per_second": 10.949,
159
+ "eval_steps_per_second": 1.373,
160
+ "eval_wer": 1.0033573946617425,
161
+ "step": 3600
162
+ },
163
+ {
164
+ "epoch": 18.75,
165
+ "learning_rate": 0.00012250871080139372,
166
+ "loss": 2.2863,
167
+ "step": 3900
168
+ },
169
+ {
170
+ "epoch": 19.23,
171
+ "eval_loss": 3.474734306335449,
172
+ "eval_runtime": 201.7307,
173
+ "eval_samples_per_second": 11.069,
174
+ "eval_steps_per_second": 1.388,
175
+ "eval_wer": 1.011499076716468,
176
+ "step": 4000
177
+ }
178
+ ],
179
+ "max_steps": 6240,
180
+ "num_train_epochs": 30,
181
+ "total_flos": 6.355921309017135e+18,
182
+ "trial_name": null,
183
+ "trial_params": null
184
+ }