Hugging Face's logo

pplantinga
/
whisper-small-sw

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
Swahili
whisper
whisper-event
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
2
pplantinga commited on
Commit
cebd1e7
•
1 Parent(s): 4160ff8

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_15-36-01_ip-172-31-0-249/events.out.tfevents.1671052642.ip-172-31-0-249.13393.2 +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": 3.12,
3
+ "eval_loss": 0.5596538782119751,
4
+ "eval_runtime": 3062.4004,
5
+ "eval_samples_per_second": 3.343,
6
+ "eval_steps_per_second": 0.052,
7
+ "eval_wer": 27.62114587994997,
8
+ "train_loss": 0.6662537975311279,
9
+ "train_runtime": 10584.1971,
10
+ "train_samples_per_second": 6.047,
11
+ "train_steps_per_second": 0.047
12
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.12,
3
+ "eval_loss": 0.5596538782119751,
4
+ "eval_runtime": 3062.4004,
5
+ "eval_samples_per_second": 3.343,
6
+ "eval_steps_per_second": 0.052,
7
+ "eval_wer": 27.62114587994997
8
+ }
runs/Dec14_15-36-01_ip-172-31-0-249/events.out.tfevents.1671052642.ip-172-31-0-249.13393.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e09430a8303e13e023930b50fcb1abc1311a2a52ac04e5930d55e4e7121f3095
3
+ size 358
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.12,
3
+ "train_loss": 0.6662537975311279,
4
+ "train_runtime": 10584.1971,
5
+ "train_samples_per_second": 6.047,
6
+ "train_steps_per_second": 0.047
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,145 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.125,
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": 0.16,
12
+ "learning_rate": 1.0000000000000002e-06,
13
+ "loss": 2.1368,
14
+ "step": 25
15
+ },
16
+ {
17
+ "epoch": 0.31,
18
+ "learning_rate": 2.0000000000000003e-06,
19
+ "loss": 1.6266,
20
+ "step": 50
21
+ },
22
+ {
23
+ "epoch": 0.47,
24
+ "learning_rate": 3e-06,
25
+ "loss": 1.1649,
26
+ "step": 75
27
+ },
28
+ {
29
+ "epoch": 0.62,
30
+ "learning_rate": 4.000000000000001e-06,
31
+ "loss": 0.9517,
32
+ "step": 100
33
+ },
34
+ {
35
+ "epoch": 0.78,
36
+ "learning_rate": 5e-06,
37
+ "loss": 0.8344,
38
+ "step": 125
39
+ },
40
+ {
41
+ "epoch": 0.94,
42
+ "learning_rate": 6e-06,
43
+ "loss": 0.7346,
44
+ "step": 150
45
+ },
46
+ {
47
+ "epoch": 1.09,
48
+ "learning_rate": 7e-06,
49
+ "loss": 0.633,
50
+ "step": 175
51
+ },
52
+ {
53
+ "epoch": 1.25,
54
+ "learning_rate": 8.000000000000001e-06,
55
+ "loss": 0.5706,
56
+ "step": 200
57
+ },
58
+ {
59
+ "epoch": 1.41,
60
+ "learning_rate": 9e-06,
61
+ "loss": 0.5311,
62
+ "step": 225
63
+ },
64
+ {
65
+ "epoch": 1.56,
66
+ "learning_rate": 1e-05,
67
+ "loss": 0.5041,
68
+ "step": 250
69
+ },
70
+ {
71
+ "epoch": 1.72,
72
+ "learning_rate": 9e-06,
73
+ "loss": 0.4821,
74
+ "step": 275
75
+ },
76
+ {
77
+ "epoch": 1.88,
78
+ "learning_rate": 8.000000000000001e-06,
79
+ "loss": 0.4497,
80
+ "step": 300
81
+ },
82
+ {
83
+ "epoch": 2.03,
84
+ "learning_rate": 7e-06,
85
+ "loss": 0.4379,
86
+ "step": 325
87
+ },
88
+ {
89
+ "epoch": 2.19,
90
+ "learning_rate": 6e-06,
91
+ "loss": 0.3421,
92
+ "step": 350
93
+ },
94
+ {
95
+ "epoch": 2.34,
96
+ "learning_rate": 5e-06,
97
+ "loss": 0.3355,
98
+ "step": 375
99
+ },
100
+ {
101
+ "epoch": 2.5,
102
+ "learning_rate": 4.000000000000001e-06,
103
+ "loss": 0.3401,
104
+ "step": 400
105
+ },
106
+ {
107
+ "epoch": 2.66,
108
+ "learning_rate": 3e-06,
109
+ "loss": 0.3302,
110
+ "step": 425
111
+ },
112
+ {
113
+ "epoch": 2.81,
114
+ "learning_rate": 2.0000000000000003e-06,
115
+ "loss": 0.3229,
116
+ "step": 450
117
+ },
118
+ {
119
+ "epoch": 2.97,
120
+ "learning_rate": 1.0000000000000002e-06,
121
+ "loss": 0.3128,
122
+ "step": 475
123
+ },
124
+ {
125
+ "epoch": 3.12,
126
+ "learning_rate": 0.0,
127
+ "loss": 0.2841,
128
+ "step": 500
129
+ },
130
+ {
131
+ "epoch": 3.12,
132
+ "step": 500,
133
+ "total_flos": 1.845734503366656e+19,
134
+ "train_loss": 0.6662537975311279,
135
+ "train_runtime": 10584.1971,
136
+ "train_samples_per_second": 6.047,
137
+ "train_steps_per_second": 0.047
138
+ }
139
+ ],
140
+ "max_steps": 500,
141
+ "num_train_epochs": 4,
142
+ "total_flos": 1.845734503366656e+19,
143
+ "trial_name": null,
144
+ "trial_params": null
145
+ }