Hugging Face's logo

rocky250
/
ASR_Extend

Safetensors
whisper
Model card Files
xet
 Community
ASR_Extend
File size: 2,713 Bytes
68a830c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.5060240963855422,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "learning_rate": 5.000000000000001e-07,
      "loss": 0.2303,
      "step": 100
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.21,
      "step": 200
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.5e-06,
      "loss": 0.2118,
      "step": 300
    },
    {
      "epoch": 0.3,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.2131,
      "step": 400
    },
    {
      "epoch": 0.38,
      "learning_rate": 2.5e-06,
      "loss": 0.2076,
      "step": 500
    },
    {
      "epoch": 0.45,
      "learning_rate": 3e-06,
      "loss": 0.2116,
      "step": 600
    },
    {
      "epoch": 0.53,
      "learning_rate": 3.5e-06,
      "loss": 0.2154,
      "step": 700
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.2129,
      "step": 800
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.5e-06,
      "loss": 0.211,
      "step": 900
    },
    {
      "epoch": 0.75,
      "learning_rate": 5e-06,
      "loss": 0.2178,
      "step": 1000
    },
    {
      "epoch": 0.83,
      "learning_rate": 5.500000000000001e-06,
      "loss": 0.2104,
      "step": 1100
    },
    {
      "epoch": 0.9,
      "learning_rate": 6e-06,
      "loss": 0.215,
      "step": 1200
    },
    {
      "epoch": 0.98,
      "learning_rate": 6.5000000000000004e-06,
      "loss": 0.2107,
      "step": 1300
    },
    {
      "epoch": 1.05,
      "learning_rate": 7e-06,
      "loss": 0.2091,
      "step": 1400
    },
    {
      "epoch": 1.13,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.207,
      "step": 1500
    },
    {
      "epoch": 1.2,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.1942,
      "step": 1600
    },
    {
      "epoch": 1.28,
      "learning_rate": 8.5e-06,
      "loss": 0.2037,
      "step": 1700
    },
    {
      "epoch": 1.36,
      "learning_rate": 9e-06,
      "loss": 0.2071,
      "step": 1800
    },
    {
      "epoch": 1.43,
      "learning_rate": 9.5e-06,
      "loss": 0.2072,
      "step": 1900
    },
    {
      "epoch": 1.51,
      "learning_rate": 1e-05,
      "loss": 0.2035,
      "step": 2000
    }
  ],
  "logging_steps": 100,
  "max_steps": 5000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 1000,
  "total_flos": 4.61707781971968e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}