File size: 1,469 Bytes
fabbb63
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.1446540880503147,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7290322580645161,
      "eval_loss": 3.165098190307617,
      "eval_runtime": 2.394,
      "eval_samples_per_second": 1294.905,
      "eval_steps_per_second": 27.151,
      "step": 318
    },
    {
      "epoch": 1.57,
      "learning_rate": 1.685534591194969e-05,
      "loss": 3.6948,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.86,
      "eval_loss": 1.5545812845230103,
      "eval_runtime": 2.45,
      "eval_samples_per_second": 1265.306,
      "eval_steps_per_second": 26.531,
      "step": 636
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9132258064516129,
      "eval_loss": 0.7676715850830078,
      "eval_runtime": 2.444,
      "eval_samples_per_second": 1268.413,
      "eval_steps_per_second": 26.596,
      "step": 954
    },
    {
      "epoch": 3.14,
      "learning_rate": 1.371069182389937e-05,
      "loss": 1.3265,
      "step": 1000
    }
  ],
  "logging_steps": 500,
  "max_steps": 3180,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 366230794301232.0,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.3328723302231085,
    "num_train_epochs": 10,
    "temperature": 5
  }
}