Hugging Face's logo

pplantinga
/
whisper-small-cy

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Welsh
whisper
whisper-event
generated_from_trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
pplantinga commited on
Commit
2ba6c83
•
1 Parent(s): 3a8276a

End of training

Browse files
Files changed (5) hide show
  1. all_results.json +12 -0
  2. eval_results.json +8 -0
  3. runs/Dec14_15-37-02_ip-172-31-56-18/events.out.tfevents.1671061153.ip-172-31-56-18.33683.2 +3 -0
  4. train_results.json +7 -0
  5. trainer_state.json +145 -0
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 6.1,
3
+ "eval_loss": 0.49994850158691406,
4
+ "eval_runtime": 1362.3823,
5
+ "eval_samples_per_second": 3.865,
6
+ "eval_steps_per_second": 0.121,
7
+ "eval_wer": 32.163568477915476,
8
+ "train_loss": 0.52779975938797,
9
+ "train_runtime": 27469.1066,
10
+ "train_samples_per_second": 2.33,
11
+ "train_steps_per_second": 0.018
12
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 6.1,
3
+ "eval_loss": 0.49994850158691406,
4
+ "eval_runtime": 1362.3823,
5
+ "eval_samples_per_second": 3.865,
6
+ "eval_steps_per_second": 0.121,
7
+ "eval_wer": 32.163568477915476
8
+ }
runs/Dec14_15-37-02_ip-172-31-56-18/events.out.tfevents.1671061153.ip-172-31-56-18.33683.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9444339c0b9987dc8248393fef60ad61757e1f96fba1d17b50c535915a09979f
3
+ size 358
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 6.1,
3
+ "train_loss": 0.52779975938797,
4
+ "train_runtime": 27469.1066,
5
+ "train_samples_per_second": 2.33,
6
+ "train_steps_per_second": 0.018
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,145 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 6.097560975609756,
5
+ "global_step": 500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.3,
12
+ "learning_rate": 1.0000000000000002e-06,
13
+ "loss": 1.7257,
14
+ "step": 25
15
+ },
16
+ {
17
+ "epoch": 0.61,
18
+ "learning_rate": 2.0000000000000003e-06,
19
+ "loss": 1.3069,
20
+ "step": 50
21
+ },
22
+ {
23
+ "epoch": 0.91,
24
+ "learning_rate": 3e-06,
25
+ "loss": 1.0021,
26
+ "step": 75
27
+ },
28
+ {
29
+ "epoch": 1.22,
30
+ "learning_rate": 4.000000000000001e-06,
31
+ "loss": 0.827,
32
+ "step": 100
33
+ },
34
+ {
35
+ "epoch": 1.52,
36
+ "learning_rate": 5e-06,
37
+ "loss": 0.733,
38
+ "step": 125
39
+ },
40
+ {
41
+ "epoch": 1.83,
42
+ "learning_rate": 6e-06,
43
+ "loss": 0.6732,
44
+ "step": 150
45
+ },
46
+ {
47
+ "epoch": 2.13,
48
+ "learning_rate": 7e-06,
49
+ "loss": 0.5834,
50
+ "step": 175
51
+ },
52
+ {
53
+ "epoch": 2.44,
54
+ "learning_rate": 8.000000000000001e-06,
55
+ "loss": 0.5074,
56
+ "step": 200
57
+ },
58
+ {
59
+ "epoch": 2.74,
60
+ "learning_rate": 9e-06,
61
+ "loss": 0.477,
62
+ "step": 225
63
+ },
64
+ {
65
+ "epoch": 3.05,
66
+ "learning_rate": 1e-05,
67
+ "loss": 0.4321,
68
+ "step": 250
69
+ },
70
+ {
71
+ "epoch": 3.35,
72
+ "learning_rate": 9e-06,
73
+ "loss": 0.3351,
74
+ "step": 275
75
+ },
76
+ {
77
+ "epoch": 3.66,
78
+ "learning_rate": 8.000000000000001e-06,
79
+ "loss": 0.3216,
80
+ "step": 300
81
+ },
82
+ {
83
+ "epoch": 3.96,
84
+ "learning_rate": 7e-06,
85
+ "loss": 0.3137,
86
+ "step": 325
87
+ },
88
+ {
89
+ "epoch": 4.27,
90
+ "learning_rate": 6e-06,
91
+ "loss": 0.2335,
92
+ "step": 350
93
+ },
94
+ {
95
+ "epoch": 4.57,
96
+ "learning_rate": 5e-06,
97
+ "loss": 0.2205,
98
+ "step": 375
99
+ },
100
+ {
101
+ "epoch": 4.88,
102
+ "learning_rate": 4.000000000000001e-06,
103
+ "loss": 0.2107,
104
+ "step": 400
105
+ },
106
+ {
107
+ "epoch": 5.18,
108
+ "learning_rate": 3e-06,
109
+ "loss": 0.1833,
110
+ "step": 425
111
+ },
112
+ {
113
+ "epoch": 5.49,
114
+ "learning_rate": 2.0000000000000003e-06,
115
+ "loss": 0.1584,
116
+ "step": 450
117
+ },
118
+ {
119
+ "epoch": 5.79,
120
+ "learning_rate": 1.0000000000000002e-06,
121
+ "loss": 0.1602,
122
+ "step": 475
123
+ },
124
+ {
125
+ "epoch": 6.1,
126
+ "learning_rate": 0.0,
127
+ "loss": 0.1511,
128
+ "step": 500
129
+ },
130
+ {
131
+ "epoch": 6.1,
132
+ "step": 500,
133
+ "total_flos": 1.846600259567616e+19,
134
+ "train_loss": 0.52779975938797,
135
+ "train_runtime": 27469.1066,
136
+ "train_samples_per_second": 2.33,
137
+ "train_steps_per_second": 0.018
138
+ }
139
+ ],
140
+ "max_steps": 500,
141
+ "num_train_epochs": 7,
142
+ "total_flos": 1.846600259567616e+19,
143
+ "trial_name": null,
144
+ "trial_params": null
145
+ }