File size: 3,679 Bytes
fb30c12
 
 
8240b04
fb30c12
8240b04
fb30c12
 
 
 
 
 
 
b66816f
fb30c12
 
 
b66816f
 
 
 
fb30c12
 
b66816f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8240b04
 
 
 
b66816f
 
 
 
 
fb30c12
 
 
 
 
 
b66816f
fb30c12
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 1136,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 4.995598591549296e-05,
      "loss": 2.3251,
      "step": 1
    },
    {
      "epoch": 1.0,
      "learning_rate": 4.379401408450705e-05,
      "loss": 1.8881,
      "step": 142
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5851831552023385,
      "eval_loss": 1.8030234575271606,
      "eval_runtime": 68.3081,
      "eval_samples_per_second": 1.801,
      "eval_steps_per_second": 0.234,
      "step": 142
    },
    {
      "epoch": 2.0,
      "learning_rate": 3.7544014084507044e-05,
      "loss": 1.0326,
      "step": 284
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5736850675785703,
      "eval_loss": 1.9792582988739014,
      "eval_runtime": 67.3896,
      "eval_samples_per_second": 1.825,
      "eval_steps_per_second": 0.237,
      "step": 284
    },
    {
      "epoch": 3.0,
      "learning_rate": 3.129401408450705e-05,
      "loss": 0.2979,
      "step": 426
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.5582232177964184,
      "eval_loss": 2.4750924110412598,
      "eval_runtime": 67.4719,
      "eval_samples_per_second": 1.823,
      "eval_steps_per_second": 0.237,
      "step": 426
    },
    {
      "epoch": 4.0,
      "learning_rate": 2.5044014084507045e-05,
      "loss": 0.0966,
      "step": 568
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.5602765895758616,
      "eval_loss": 2.7331745624542236,
      "eval_runtime": 67.3819,
      "eval_samples_per_second": 1.825,
      "eval_steps_per_second": 0.237,
      "step": 568
    },
    {
      "epoch": 5.0,
      "learning_rate": 1.8794014084507046e-05,
      "loss": 0.0519,
      "step": 710
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.5593313236503151,
      "eval_loss": 2.9102349281311035,
      "eval_runtime": 67.3712,
      "eval_samples_per_second": 1.826,
      "eval_steps_per_second": 0.237,
      "step": 710
    },
    {
      "epoch": 6.0,
      "learning_rate": 1.2544014084507044e-05,
      "loss": 0.0211,
      "step": 852
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.5565511297516492,
      "eval_loss": 3.0963499546051025,
      "eval_runtime": 67.3971,
      "eval_samples_per_second": 1.825,
      "eval_steps_per_second": 0.237,
      "step": 852
    },
    {
      "epoch": 7.0,
      "learning_rate": 6.2940140845070425e-06,
      "loss": 0.0038,
      "step": 994
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.5585012371862849,
      "eval_loss": 3.196666955947876,
      "eval_runtime": 67.4214,
      "eval_samples_per_second": 1.824,
      "eval_steps_per_second": 0.237,
      "step": 994
    },
    {
      "epoch": 8.0,
      "learning_rate": 4.4014084507042253e-08,
      "loss": 0.0028,
      "step": 1136
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.5584178313693249,
      "eval_loss": 3.250995397567749,
      "eval_runtime": 67.4231,
      "eval_samples_per_second": 1.824,
      "eval_steps_per_second": 0.237,
      "step": 1136
    },
    {
      "epoch": 8.0,
      "step": 1136,
      "total_flos": 2.845346179967877e+18,
      "train_loss": 0.424729940363429,
      "train_runtime": 26678.4113,
      "train_samples_per_second": 0.681,
      "train_steps_per_second": 0.043
    }
  ],
  "logging_steps": 500,
  "max_steps": 1136,
  "num_train_epochs": 8,
  "save_steps": 500,
  "total_flos": 2.845346179967877e+18,
  "trial_name": null,
  "trial_params": null
}