Hugging Face's logo

ALM
/
whisper-it-small

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
Italian
whisper
whisper-event
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
1
Moreno La Quatra commited on
Commit
2842e64
•
1 Parent(s): ce4df21

End of training

Browse files
Files changed (5) hide show
  1. all_results.json +12 -0
  2. eval_results.json +8 -0
  3. runs/Dec07_23-08-05_rhodes/events.out.tfevents.1670495999.rhodes +3 -0
  4. train_results.json +7 -0
  5. trainer_state.json +151 -0
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "eval_loss": 0.25167033076286316,
4
+ "eval_runtime": 5691.8774,
5
+ "eval_samples_per_second": 2.636,
6
+ "eval_steps_per_second": 0.082,
7
+ "eval_wer": 11.271395917499468,
8
+ "train_loss": 0.2830442016216818,
9
+ "train_runtime": 31129.4467,
10
+ "train_samples_per_second": 1.913,
11
+ "train_steps_per_second": 0.03
12
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "eval_loss": 0.25167033076286316,
4
+ "eval_runtime": 5691.8774,
5
+ "eval_samples_per_second": 2.636,
6
+ "eval_steps_per_second": 0.082,
7
+ "eval_wer": 11.271395917499468
8
+ }
runs/Dec07_23-08-05_rhodes/events.out.tfevents.1670495999.rhodes ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cffd4d61c19d45057ca0f976a3ae680ee6fd70b04e7245d9d20b279b9dd89880
3
+ size 40
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "train_loss": 0.2830442016216818,
4
+ "train_runtime": 31129.4467,
5
+ "train_samples_per_second": 1.913,
6
+ "train_steps_per_second": 0.03
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,151 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 11.271395917499468,
3
+ "best_model_checkpoint": "whisper-it-small/checkpoint-932",
4
+ "epoch": 2.0,
5
+ "global_step": 932,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.11,
12
+ "learning_rate": 9.600000000000001e-07,
13
+ "loss": 0.9816,
14
+ "step": 50
15
+ },
16
+ {
17
+ "epoch": 0.21,
18
+ "learning_rate": 1.9600000000000003e-06,
19
+ "loss": 0.519,
20
+ "step": 100
21
+ },
22
+ {
23
+ "epoch": 0.32,
24
+ "learning_rate": 2.96e-06,
25
+ "loss": 0.3418,
26
+ "step": 150
27
+ },
28
+ {
29
+ "epoch": 0.43,
30
+ "learning_rate": 3.96e-06,
31
+ "loss": 0.3032,
32
+ "step": 200
33
+ },
34
+ {
35
+ "epoch": 0.54,
36
+ "learning_rate": 4.960000000000001e-06,
37
+ "loss": 0.2901,
38
+ "step": 250
39
+ },
40
+ {
41
+ "epoch": 0.64,
42
+ "learning_rate": 5.9600000000000005e-06,
43
+ "loss": 0.2783,
44
+ "step": 300
45
+ },
46
+ {
47
+ "epoch": 0.75,
48
+ "learning_rate": 6.96e-06,
49
+ "loss": 0.2771,
50
+ "step": 350
51
+ },
52
+ {
53
+ "epoch": 0.86,
54
+ "learning_rate": 7.960000000000002e-06,
55
+ "loss": 0.2659,
56
+ "step": 400
57
+ },
58
+ {
59
+ "epoch": 0.97,
60
+ "learning_rate": 8.96e-06,
61
+ "loss": 0.2529,
62
+ "step": 450
63
+ },
64
+ {
65
+ "epoch": 1.0,
66
+ "eval_loss": 0.2758234441280365,
67
+ "eval_runtime": 5945.4592,
68
+ "eval_samples_per_second": 2.523,
69
+ "eval_steps_per_second": 0.079,
70
+ "eval_wer": 12.490697427174144,
71
+ "step": 466
72
+ },
73
+ {
74
+ "epoch": 1.07,
75
+ "learning_rate": 9.960000000000001e-06,
76
+ "loss": 0.2122,
77
+ "step": 500
78
+ },
79
+ {
80
+ "epoch": 1.18,
81
+ "learning_rate": 8.888888888888888e-06,
82
+ "loss": 0.1893,
83
+ "step": 550
84
+ },
85
+ {
86
+ "epoch": 1.29,
87
+ "learning_rate": 7.731481481481483e-06,
88
+ "loss": 0.1872,
89
+ "step": 600
90
+ },
91
+ {
92
+ "epoch": 1.39,
93
+ "learning_rate": 6.574074074074075e-06,
94
+ "loss": 0.1803,
95
+ "step": 650
96
+ },
97
+ {
98
+ "epoch": 1.5,
99
+ "learning_rate": 5.416666666666667e-06,
100
+ "loss": 0.1843,
101
+ "step": 700
102
+ },
103
+ {
104
+ "epoch": 1.61,
105
+ "learning_rate": 4.2592592592592596e-06,
106
+ "loss": 0.1806,
107
+ "step": 750
108
+ },
109
+ {
110
+ "epoch": 1.72,
111
+ "learning_rate": 3.101851851851852e-06,
112
+ "loss": 0.1787,
113
+ "step": 800
114
+ },
115
+ {
116
+ "epoch": 1.82,
117
+ "learning_rate": 1.944444444444445e-06,
118
+ "loss": 0.1761,
119
+ "step": 850
120
+ },
121
+ {
122
+ "epoch": 1.93,
123
+ "learning_rate": 7.870370370370371e-07,
124
+ "loss": 0.1711,
125
+ "step": 900
126
+ },
127
+ {
128
+ "epoch": 2.0,
129
+ "eval_loss": 0.25167033076286316,
130
+ "eval_runtime": 5711.8942,
131
+ "eval_samples_per_second": 2.627,
132
+ "eval_steps_per_second": 0.082,
133
+ "eval_wer": 11.271395917499468,
134
+ "step": 932
135
+ },
136
+ {
137
+ "epoch": 2.0,
138
+ "step": 932,
139
+ "total_flos": 1.718295190585344e+19,
140
+ "train_loss": 0.2830442016216818,
141
+ "train_runtime": 31129.4467,
142
+ "train_samples_per_second": 1.913,
143
+ "train_steps_per_second": 0.03
144
+ }
145
+ ],
146
+ "max_steps": 932,
147
+ "num_train_epochs": 2,
148
+ "total_flos": 1.718295190585344e+19,
149
+ "trial_name": null,
150
+ "trial_params": null
151
+ }