File size: 3,547 Bytes
86574ed
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": null,
  "best_model_checkpoint": null,
  "epoch": 24.0256,
  "global_step": 7000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.02,
      "learning_rate": 9.960000000000001e-06,
      "loss": 0.5615,
      "step": 500
    },
    {
      "epoch": 3.02,
      "learning_rate": 1e-05,
      "loss": 0.3273,
      "step": 1000
    },
    {
      "epoch": 3.02,
      "eval_loss": 0.4225325584411621,
      "eval_runtime": 1489.9228,
      "eval_samples_per_second": 3.09,
      "eval_steps_per_second": 0.193,
      "eval_wer": 20.82533081951615,
      "step": 1000
    },
    {
      "epoch": 5.01,
      "learning_rate": 1e-05,
      "loss": 0.1859,
      "step": 1500
    },
    {
      "epoch": 7.0,
      "learning_rate": 1e-05,
      "loss": 0.0923,
      "step": 2000
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.46434369683265686,
      "eval_runtime": 1504.5618,
      "eval_samples_per_second": 3.06,
      "eval_steps_per_second": 0.191,
      "eval_wer": 21.22002361108664,
      "step": 2000
    },
    {
      "epoch": 8.03,
      "learning_rate": 1e-05,
      "loss": 0.0369,
      "step": 2500
    },
    {
      "epoch": 10.02,
      "learning_rate": 1e-05,
      "loss": 0.0164,
      "step": 3000
    },
    {
      "epoch": 10.02,
      "eval_loss": 0.5403426885604858,
      "eval_runtime": 1504.7378,
      "eval_samples_per_second": 3.06,
      "eval_steps_per_second": 0.191,
      "eval_wer": 22.962662766725987,
      "step": 3000
    },
    {
      "epoch": 12.01,
      "learning_rate": 1e-05,
      "loss": 0.0089,
      "step": 3500
    },
    {
      "epoch": 14.01,
      "learning_rate": 1e-05,
      "loss": 0.006,
      "step": 4000
    },
    {
      "epoch": 14.01,
      "eval_loss": 0.5819889307022095,
      "eval_runtime": 1478.853,
      "eval_samples_per_second": 3.113,
      "eval_steps_per_second": 0.195,
      "eval_wer": 21.086109985375224,
      "step": 4000
    },
    {
      "epoch": 16.0,
      "learning_rate": 1e-05,
      "loss": 0.0057,
      "step": 4500
    },
    {
      "epoch": 17.02,
      "learning_rate": 1e-05,
      "loss": 0.0046,
      "step": 5000
    },
    {
      "epoch": 17.02,
      "eval_loss": 0.5851565003395081,
      "eval_runtime": 1532.3442,
      "eval_samples_per_second": 3.005,
      "eval_steps_per_second": 0.188,
      "eval_wer": 22.072841964301446,
      "step": 5000
    },
    {
      "epoch": 19.02,
      "learning_rate": 1e-05,
      "loss": 0.0042,
      "step": 5500
    },
    {
      "epoch": 21.01,
      "learning_rate": 1e-05,
      "loss": 0.0034,
      "step": 6000
    },
    {
      "epoch": 21.01,
      "eval_loss": 0.6112661361694336,
      "eval_runtime": 1497.7325,
      "eval_samples_per_second": 3.074,
      "eval_steps_per_second": 0.192,
      "eval_wer": 21.6622909802125,
      "step": 6000
    },
    {
      "epoch": 23.0,
      "learning_rate": 1e-05,
      "loss": 0.004,
      "step": 6500
    },
    {
      "epoch": 24.03,
      "learning_rate": 1e-05,
      "loss": 0.0028,
      "step": 7000
    },
    {
      "epoch": 24.03,
      "eval_loss": 0.6582160592079163,
      "eval_runtime": 1517.5965,
      "eval_samples_per_second": 3.034,
      "eval_steps_per_second": 0.19,
      "eval_wer": 22.326573044596763,
      "step": 7000
    }
  ],
  "max_steps": 10000,
  "num_train_epochs": 9223372036854775807,
  "total_flos": 1.449439306186752e+19,
  "trial_name": null,
  "trial_params": null
}