File size: 3,450 Bytes
3a00009
4625b60
3a00009
4625b60
 
3a00009
 
 
 
 
 
 
4625b60
 
 
 
3a00009
 
 
 
4625b60
 
 
 
 
3a00009
 
 
 
4625b60
 
 
 
 
3a00009
 
 
 
4625b60
 
3a00009
 
 
 
4625b60
 
 
 
 
3a00009
 
 
 
4625b60
 
 
 
 
3a00009
 
 
 
 
4625b60
 
 
 
3a00009
 
 
 
4625b60
 
3a00009
 
 
 
4625b60
 
 
 
 
3a00009
 
 
 
4625b60
 
 
 
 
3a00009
 
 
4625b60
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3a00009
 
 
 
4625b60
3a00009
 
 
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
{
  "best_metric": 0.7978339350180506,
  "best_model_checkpoint": "./fine-tune/roberta-base/rte/checkpoint-780",
  "epoch": 10.0,
  "global_step": 1560,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.4729241877256318,
      "eval_loss": 0.7023295164108276,
      "eval_runtime": 0.5782,
      "eval_samples_per_second": 479.05,
      "eval_steps_per_second": 60.53,
      "step": 156
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6895306859205776,
      "eval_loss": 0.6356249451637268,
      "eval_runtime": 0.6365,
      "eval_samples_per_second": 435.208,
      "eval_steps_per_second": 54.99,
      "step": 312
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7617328519855595,
      "eval_loss": 0.5177018046379089,
      "eval_runtime": 0.6111,
      "eval_samples_per_second": 453.318,
      "eval_steps_per_second": 57.278,
      "step": 468
    },
    {
      "epoch": 3.21,
      "learning_rate": 7.23055934515689e-06,
      "loss": 0.6131,
      "step": 500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7472924187725631,
      "eval_loss": 0.6237531304359436,
      "eval_runtime": 0.6069,
      "eval_samples_per_second": 456.426,
      "eval_steps_per_second": 57.671,
      "step": 624
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.7978339350180506,
      "eval_loss": 0.5446364283561707,
      "eval_runtime": 0.6019,
      "eval_samples_per_second": 460.195,
      "eval_steps_per_second": 58.147,
      "step": 780
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.7545126353790613,
      "eval_loss": 0.9697452783584595,
      "eval_runtime": 0.6225,
      "eval_samples_per_second": 444.97,
      "eval_steps_per_second": 56.224,
      "step": 936
    },
    {
      "epoch": 6.41,
      "learning_rate": 3.819918144611187e-06,
      "loss": 0.2528,
      "step": 1000
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.7689530685920578,
      "eval_loss": 1.100365161895752,
      "eval_runtime": 0.6174,
      "eval_samples_per_second": 448.691,
      "eval_steps_per_second": 56.694,
      "step": 1092
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.7725631768953068,
      "eval_loss": 1.193679928779602,
      "eval_runtime": 0.6461,
      "eval_samples_per_second": 428.72,
      "eval_steps_per_second": 54.17,
      "step": 1248
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.7725631768953068,
      "eval_loss": 1.331286072731018,
      "eval_runtime": 0.5642,
      "eval_samples_per_second": 490.964,
      "eval_steps_per_second": 62.035,
      "step": 1404
    },
    {
      "epoch": 9.62,
      "learning_rate": 4.092769440654844e-07,
      "loss": 0.1073,
      "step": 1500
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.7725631768953068,
      "eval_loss": 1.353358268737793,
      "eval_runtime": 0.6152,
      "eval_samples_per_second": 450.281,
      "eval_steps_per_second": 56.895,
      "step": 1560
    },
    {
      "epoch": 10.0,
      "step": 1560,
      "total_flos": 1637866319616000.0,
      "train_loss": 0.31504388589125415,
      "train_runtime": 295.0697,
      "train_samples_per_second": 84.387,
      "train_steps_per_second": 5.287
    }
  ],
  "max_steps": 1560,
  "num_train_epochs": 10,
  "total_flos": 1637866319616000.0,
  "trial_name": null,
  "trial_params": null
}