File size: 3,172 Bytes
23ad7bd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": 0.22921106219291687,
  "best_model_checkpoint": "ernie-2.0-base-en-Tweet_About_Disaster_Or_Not/checkpoint-286",
  "epoch": 5.0,
  "global_step": 715,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 1.9972027972027975e-05,
      "loss": 0.6437,
      "step": 1
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.347,
      "step": 143
    },
    {
      "epoch": 1.0,
      "eval_F1": 0.7342256214149139,
      "eval_Precision": 0.6153846153846154,
      "eval_Recall": 0.909952606635071,
      "eval_accuracy": 0.8777484608619174,
      "eval_loss": 0.2663082480430603,
      "eval_runtime": 94.3482,
      "eval_samples_per_second": 12.051,
      "eval_steps_per_second": 0.191,
      "step": 143
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.2e-05,
      "loss": 0.2192,
      "step": 286
    },
    {
      "epoch": 2.0,
      "eval_F1": 0.7876106194690267,
      "eval_Precision": 0.7385892116182573,
      "eval_Recall": 0.8436018957345972,
      "eval_accuracy": 0.9155672823218998,
      "eval_loss": 0.22921106219291687,
      "eval_runtime": 90.2713,
      "eval_samples_per_second": 12.595,
      "eval_steps_per_second": 0.199,
      "step": 286
    },
    {
      "epoch": 3.0,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.132,
      "step": 429
    },
    {
      "epoch": 3.0,
      "eval_F1": 0.7843137254901961,
      "eval_Precision": 0.7258064516129032,
      "eval_Recall": 0.8530805687203792,
      "eval_accuracy": 0.9129287598944591,
      "eval_loss": 0.26291149854660034,
      "eval_runtime": 90.0373,
      "eval_samples_per_second": 12.628,
      "eval_steps_per_second": 0.2,
      "step": 429
    },
    {
      "epoch": 4.0,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0767,
      "step": 572
    },
    {
      "epoch": 4.0,
      "eval_F1": 0.780701754385965,
      "eval_Precision": 0.726530612244898,
      "eval_Recall": 0.8436018957345972,
      "eval_accuracy": 0.9120492524186455,
      "eval_loss": 0.32662004232406616,
      "eval_runtime": 89.7111,
      "eval_samples_per_second": 12.674,
      "eval_steps_per_second": 0.201,
      "step": 572
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.0,
      "loss": 0.0532,
      "step": 715
    },
    {
      "epoch": 5.0,
      "eval_F1": 0.7787610619469026,
      "eval_Precision": 0.7302904564315352,
      "eval_Recall": 0.8341232227488151,
      "eval_accuracy": 0.9120492524186455,
      "eval_loss": 0.36217325925827026,
      "eval_runtime": 99.3483,
      "eval_samples_per_second": 11.445,
      "eval_steps_per_second": 0.181,
      "step": 715
    },
    {
      "epoch": 5.0,
      "step": 715,
      "total_flos": 1776246290294400.0,
      "train_loss": 0.16604990333943934,
      "train_runtime": 14546.7071,
      "train_samples_per_second": 3.126,
      "train_steps_per_second": 0.049
    }
  ],
  "max_steps": 715,
  "num_train_epochs": 5,
  "total_flos": 1776246290294400.0,
  "trial_name": null,
  "trial_params": null
}