File size: 2,003 Bytes
d0aa996
b3694db
 
 
d0aa996
b3694db
d0aa996
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
20e5dc9
 
 
 
 
 
 
 
 
 
 
 
 
 
9838038
 
 
 
 
 
 
 
 
 
 
 
 
 
1661055
 
 
 
 
 
 
 
 
 
 
 
 
 
b3694db
 
 
 
 
 
 
 
 
 
 
 
 
 
d0aa996
 
 
 
 
 
b3694db
d0aa996
 
 
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
{
  "best_metric": 1.7718570232391357,
  "best_model_checkpoint": "./outputs/checkpoint-500",
  "epoch": 0.36429872495446264,
  "eval_steps": 100,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 2.1831,
      "step": 100
    },
    {
      "epoch": 0.07,
      "eval_loss": 2.0129995346069336,
      "eval_runtime": 143.7126,
      "eval_samples_per_second": 43.657,
      "eval_steps_per_second": 5.462,
      "step": 100
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 1.9629,
      "step": 200
    },
    {
      "epoch": 0.15,
      "eval_loss": 1.9196887016296387,
      "eval_runtime": 143.7285,
      "eval_samples_per_second": 43.652,
      "eval_steps_per_second": 5.462,
      "step": 200
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 1.8881,
      "step": 300
    },
    {
      "epoch": 0.22,
      "eval_loss": 1.8589884042739868,
      "eval_runtime": 143.706,
      "eval_samples_per_second": 43.659,
      "eval_steps_per_second": 5.463,
      "step": 300
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 1.8368,
      "step": 400
    },
    {
      "epoch": 0.29,
      "eval_loss": 1.813078761100769,
      "eval_runtime": 143.7443,
      "eval_samples_per_second": 43.647,
      "eval_steps_per_second": 5.461,
      "step": 400
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 1.7849,
      "step": 500
    },
    {
      "epoch": 0.36,
      "eval_loss": 1.7718570232391357,
      "eval_runtime": 143.7117,
      "eval_samples_per_second": 43.657,
      "eval_steps_per_second": 5.462,
      "step": 500
    }
  ],
  "logging_steps": 100,
  "max_steps": 4116,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 2.9834861985890304e+16,
  "trial_name": null,
  "trial_params": null
}