File size: 2,810 Bytes
4d768f4
a3a117d
 
 
 
4d768f4
 
 
 
 
 
a3a117d
 
4d768f4
 
 
 
a3a117d
 
 
 
 
4d768f4
 
 
 
a3a117d
 
4d768f4
 
 
 
a3a117d
 
 
 
 
4d768f4
 
 
 
a3a117d
 
4d768f4
 
 
 
a3a117d
 
 
 
 
4d768f4
 
 
 
a3a117d
 
4d768f4
 
 
 
a3a117d
 
 
 
 
4d768f4
 
 
 
a3a117d
 
4d768f4
 
 
 
a3a117d
 
 
 
 
4d768f4
 
 
 
a3a117d
 
4d768f4
 
 
 
a3a117d
 
 
 
 
4d768f4
 
 
a3a117d
 
 
 
 
 
 
4d768f4
 
 
 
a3a117d
4d768f4
 
 
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
{
  "best_metric": 0.4606306850910187,
  "best_model_checkpoint": "hBERTv1_new_pretrain_w_init__sst2/checkpoint-527",
  "epoch": 6.0,
  "global_step": 3162,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 3.9200000000000004e-05,
      "loss": 0.363,
      "step": 527
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8038990825688074,
      "eval_loss": 0.4606306850910187,
      "eval_runtime": 1.5758,
      "eval_samples_per_second": 553.365,
      "eval_steps_per_second": 4.442,
      "step": 527
    },
    {
      "epoch": 2.0,
      "learning_rate": 3.8400000000000005e-05,
      "loss": 0.2256,
      "step": 1054
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8119266055045872,
      "eval_loss": 0.6466029286384583,
      "eval_runtime": 1.581,
      "eval_samples_per_second": 551.543,
      "eval_steps_per_second": 4.428,
      "step": 1054
    },
    {
      "epoch": 3.0,
      "learning_rate": 3.76e-05,
      "loss": 0.1754,
      "step": 1581
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8176605504587156,
      "eval_loss": 0.5100513696670532,
      "eval_runtime": 1.5786,
      "eval_samples_per_second": 552.387,
      "eval_steps_per_second": 4.434,
      "step": 1581
    },
    {
      "epoch": 4.0,
      "learning_rate": 3.680000000000001e-05,
      "loss": 0.1394,
      "step": 2108
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8176605504587156,
      "eval_loss": 0.49214717745780945,
      "eval_runtime": 1.5822,
      "eval_samples_per_second": 551.116,
      "eval_steps_per_second": 4.424,
      "step": 2108
    },
    {
      "epoch": 5.0,
      "learning_rate": 3.6e-05,
      "loss": 0.1111,
      "step": 2635
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.819954128440367,
      "eval_loss": 0.5109940767288208,
      "eval_runtime": 1.5752,
      "eval_samples_per_second": 553.567,
      "eval_steps_per_second": 4.444,
      "step": 2635
    },
    {
      "epoch": 6.0,
      "learning_rate": 3.52e-05,
      "loss": 0.0937,
      "step": 3162
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8211009174311926,
      "eval_loss": 0.6468406319618225,
      "eval_runtime": 1.5781,
      "eval_samples_per_second": 552.564,
      "eval_steps_per_second": 4.436,
      "step": 3162
    },
    {
      "epoch": 6.0,
      "step": 3162,
      "total_flos": 5.984501559302554e+16,
      "train_loss": 0.18471441202567845,
      "train_runtime": 2261.4914,
      "train_samples_per_second": 1489.039,
      "train_steps_per_second": 11.652
    }
  ],
  "max_steps": 26350,
  "num_train_epochs": 50,
  "total_flos": 5.984501559302554e+16,
  "trial_name": null,
  "trial_params": null
}