File size: 1,527 Bytes
cb1236d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 66.66666666666667,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.67,
      "learning_rate": 0.0002,
      "loss": 1.8198,
      "step": 10
    },
    {
      "epoch": 13.33,
      "learning_rate": 0.0002,
      "loss": 0.5831,
      "step": 20
    },
    {
      "epoch": 20.0,
      "learning_rate": 0.0002,
      "loss": 0.1285,
      "step": 30
    },
    {
      "epoch": 26.67,
      "learning_rate": 0.0002,
      "loss": 0.0797,
      "step": 40
    },
    {
      "epoch": 33.33,
      "learning_rate": 0.0002,
      "loss": 0.0755,
      "step": 50
    },
    {
      "epoch": 40.0,
      "learning_rate": 0.0002,
      "loss": 0.0748,
      "step": 60
    },
    {
      "epoch": 46.67,
      "learning_rate": 0.0002,
      "loss": 0.0739,
      "step": 70
    },
    {
      "epoch": 53.33,
      "learning_rate": 0.0002,
      "loss": 0.074,
      "step": 80
    },
    {
      "epoch": 60.0,
      "learning_rate": 0.0002,
      "loss": 0.074,
      "step": 90
    },
    {
      "epoch": 66.67,
      "learning_rate": 0.0002,
      "loss": 0.0735,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
  "save_steps": 100,
  "total_flos": 616647229145088.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}