Hugging Face's logo

jun-han
/
Whisper-squeezeformer-v3

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
English
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Whisper-squeezeformer-v3
File size: 4,396 Bytes 
23feecc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
 
{
  "best_metric": 7.149650030432136,
  "best_model_checkpoint": "./Whisper-squeezeformer-v3\\checkpoint-20000",
  "epoch": 8.0,
  "eval_steps": 2500,
  "global_step": 20000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 10.493926048278809,
      "learning_rate": 9.972e-06,
      "loss": 4.8718,
      "step": 2500
    },
    {
      "epoch": 1.0,
      "eval_loss": 3.8609094619750977,
      "eval_runtime": 650.8319,
      "eval_samples_per_second": 4.026,
      "eval_steps_per_second": 0.504,
      "eval_wer": 111.85902312842362,
      "step": 2500
    },
    {
      "epoch": 2.0,
      "grad_norm": 6.234286785125732,
      "learning_rate": 8.575428571428573e-06,
      "loss": 2.5628,
      "step": 5000
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.2978440523147583,
      "eval_runtime": 624.1365,
      "eval_samples_per_second": 4.198,
      "eval_steps_per_second": 0.526,
      "eval_wer": 15.619293974437007,
      "step": 5000
    },
    {
      "epoch": 3.0,
      "grad_norm": 3.2328641414642334,
      "learning_rate": 7.146857142857143e-06,
      "loss": 0.1698,
      "step": 7500
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.22175125777721405,
      "eval_runtime": 585.8606,
      "eval_samples_per_second": 4.472,
      "eval_steps_per_second": 0.56,
      "eval_wer": 11.090611685940353,
      "step": 7500
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.424901247024536,
      "learning_rate": 5.718285714285715e-06,
      "loss": 0.0867,
      "step": 10000
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.2011481672525406,
      "eval_runtime": 614.9021,
      "eval_samples_per_second": 4.261,
      "eval_steps_per_second": 0.533,
      "eval_wer": 10.189059646987218,
      "step": 10000
    },
    {
      "epoch": 5.0,
      "grad_norm": 3.77018404006958,
      "learning_rate": 4.290285714285714e-06,
      "loss": 0.1697,
      "step": 12500
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.1640562266111374,
      "eval_runtime": 597.6823,
      "eval_samples_per_second": 4.384,
      "eval_steps_per_second": 0.549,
      "eval_wer": 8.985088253195373,
      "step": 12500
    },
    {
      "epoch": 6.0,
      "grad_norm": 2.6757357120513916,
      "learning_rate": 2.861714285714286e-06,
      "loss": 0.0993,
      "step": 15000
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.15530936419963837,
      "eval_runtime": 585.6998,
      "eval_samples_per_second": 4.473,
      "eval_steps_per_second": 0.56,
      "eval_wer": 7.803940961655509,
      "step": 15000
    },
    {
      "epoch": 7.0,
      "grad_norm": 2.374549388885498,
      "learning_rate": 1.434857142857143e-06,
      "loss": 0.0651,
      "step": 17500
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.1555396020412445,
      "eval_runtime": 585.2066,
      "eval_samples_per_second": 4.477,
      "eval_steps_per_second": 0.56,
      "eval_wer": 7.244750456482045,
      "step": 17500
    },
    {
      "epoch": 8.0,
      "grad_norm": 1.977560043334961,
      "learning_rate": 6.2857142857142855e-09,
      "loss": 0.0468,
      "step": 20000
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.15691713988780975,
      "eval_runtime": 580.4295,
      "eval_samples_per_second": 4.514,
      "eval_steps_per_second": 0.565,
      "eval_wer": 7.149650030432136,
      "step": 20000
    },
    {
      "epoch": 8.0,
      "step": 20000,
      "total_flos": 1.38658480128e+20,
      "train_loss": 0.047600341033935546,
      "train_runtime": 48327.6236,
      "train_samples_per_second": 8.277,
      "train_steps_per_second": 0.414
    }
  ],
  "logging_steps": 2500,
  "max_steps": 20000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "save_steps": 2500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.38658480128e+20,
  "train_batch_size": 20,
  "trial_name": null,
  "trial_params": null
}