File size: 3,322 Bytes
49b3f35
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": 26.980130911344357,
  "best_model_checkpoint": "./checkpoint-200",
  "epoch": 0.966183574879227,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.9955,
      "step": 10
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.5e-06,
      "loss": 0.7842,
      "step": 20
    },
    {
      "epoch": 0.14,
      "learning_rate": 7e-06,
      "loss": 0.533,
      "step": 30
    },
    {
      "epoch": 0.19,
      "learning_rate": 9.5e-06,
      "loss": 0.5079,
      "step": 40
    },
    {
      "epoch": 0.24,
      "learning_rate": 9.5e-06,
      "loss": 0.4739,
      "step": 50
    },
    {
      "epoch": 0.29,
      "learning_rate": 8.875e-06,
      "loss": 0.4768,
      "step": 60
    },
    {
      "epoch": 0.34,
      "learning_rate": 8.25e-06,
      "loss": 0.4344,
      "step": 70
    },
    {
      "epoch": 0.39,
      "learning_rate": 7.625e-06,
      "loss": 0.4655,
      "step": 80
    },
    {
      "epoch": 0.43,
      "learning_rate": 7e-06,
      "loss": 0.4108,
      "step": 90
    },
    {
      "epoch": 0.48,
      "learning_rate": 6.375e-06,
      "loss": 0.3908,
      "step": 100
    },
    {
      "epoch": 0.48,
      "eval_loss": 0.5148195028305054,
      "eval_runtime": 2783.9171,
      "eval_samples_per_second": 1.186,
      "eval_steps_per_second": 0.074,
      "eval_wer": 30.706069173864208,
      "step": 100
    },
    {
      "epoch": 0.53,
      "learning_rate": 5.75e-06,
      "loss": 0.3863,
      "step": 110
    },
    {
      "epoch": 0.58,
      "learning_rate": 5.125e-06,
      "loss": 0.3902,
      "step": 120
    },
    {
      "epoch": 0.63,
      "learning_rate": 4.5e-06,
      "loss": 0.3788,
      "step": 130
    },
    {
      "epoch": 0.68,
      "learning_rate": 3.875e-06,
      "loss": 0.403,
      "step": 140
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.2500000000000002e-06,
      "loss": 0.3781,
      "step": 150
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.6250000000000003e-06,
      "loss": 0.4094,
      "step": 160
    },
    {
      "epoch": 0.82,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.3732,
      "step": 170
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.3750000000000002e-06,
      "loss": 0.4084,
      "step": 180
    },
    {
      "epoch": 0.92,
      "learning_rate": 7.5e-07,
      "loss": 0.3786,
      "step": 190
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.2500000000000002e-07,
      "loss": 0.3519,
      "step": 200
    },
    {
      "epoch": 0.97,
      "eval_loss": 0.46850404143333435,
      "eval_runtime": 2556.1826,
      "eval_samples_per_second": 1.292,
      "eval_steps_per_second": 0.081,
      "eval_wer": 26.980130911344357,
      "step": 200
    },
    {
      "epoch": 0.97,
      "step": 200,
      "total_flos": 6.531871408128e+18,
      "train_loss": 0.4665303599834442,
      "train_runtime": 6285.9399,
      "train_samples_per_second": 1.018,
      "train_steps_per_second": 0.032
    }
  ],
  "max_steps": 200,
  "num_train_epochs": 1,
  "total_flos": 6.531871408128e+18,
  "trial_name": null,
  "trial_params": null
}