File size: 1,926 Bytes
bdce7f3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": 0.5460649174667868,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-1072",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 1072,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.4662749767303467,
      "eval_matthews_correlation": 0.42386559425174,
      "eval_runtime": 30.5523,
      "eval_samples_per_second": 34.138,
      "eval_steps_per_second": 2.16,
      "step": 268
    },
    {
      "epoch": 1.87,
      "learning_rate": 3.9114607492078965e-05,
      "loss": 0.425,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5247857570648193,
      "eval_matthews_correlation": 0.48074996963903815,
      "eval_runtime": 31.3458,
      "eval_samples_per_second": 33.274,
      "eval_steps_per_second": 2.106,
      "step": 536
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.5911181569099426,
      "eval_matthews_correlation": 0.5325167447166456,
      "eval_runtime": 30.5442,
      "eval_samples_per_second": 34.147,
      "eval_steps_per_second": 2.161,
      "step": 804
    },
    {
      "epoch": 3.73,
      "learning_rate": 4.923517026974974e-06,
      "loss": 0.1387,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.8381235003471375,
      "eval_matthews_correlation": 0.5460649174667868,
      "eval_runtime": 31.6632,
      "eval_samples_per_second": 32.94,
      "eval_steps_per_second": 2.084,
      "step": 1072
    }
  ],
  "logging_steps": 500,
  "max_steps": 1072,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "total_flos": 191447731731420.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 7.330569795718295e-05,
    "num_train_epochs": 4,
    "per_device_train_batch_size": 32,
    "seed": 19
  }
}