File size: 1,263 Bytes
aa7b0ff
 
 
 
 
45550b4
aa7b0ff
 
 
 
 
45550b4
 
 
aa7b0ff
 
 
45550b4
 
 
aa7b0ff
 
45550b4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
aa7b0ff
 
45550b4
 
 
 
 
 
aa7b0ff
 
 
45550b4
aa7b0ff
 
45550b4
aa7b0ff
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 2931,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.51,
      "learning_rate": 4.14704878880928e-05,
      "loss": 0.3586,
      "step": 500
    },
    {
      "epoch": 1.02,
      "learning_rate": 3.294097577618561e-05,
      "loss": 0.2728,
      "step": 1000
    },
    {
      "epoch": 1.54,
      "learning_rate": 2.4411463664278406e-05,
      "loss": 0.2668,
      "step": 1500
    },
    {
      "epoch": 2.05,
      "learning_rate": 1.5881951552371206e-05,
      "loss": 0.2508,
      "step": 2000
    },
    {
      "epoch": 2.56,
      "learning_rate": 7.3524394404640055e-06,
      "loss": 0.2471,
      "step": 2500
    },
    {
      "epoch": 3.0,
      "step": 2931,
      "total_flos": 74769472487424.0,
      "train_loss": 0.2741566179393298,
      "train_runtime": 830.8843,
      "train_samples_per_second": 14.107,
      "train_steps_per_second": 3.528
    }
  ],
  "logging_steps": 500,
  "max_steps": 2931,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 74769472487424.0,
  "trial_name": null,
  "trial_params": null
}