File size: 1,931 Bytes
b852d9b
8d52d2f
 
b852d9b
8d52d2f
b852d9b
 
 
 
 
 
8d52d2f
b852d9b
8d52d2f
b852d9b
 
8d52d2f
 
 
 
b852d9b
 
 
8d52d2f
b852d9b
8d52d2f
b852d9b
 
8d52d2f
 
 
 
b852d9b
 
 
8d52d2f
b852d9b
8d52d2f
b852d9b
 
8d52d2f
 
 
 
b852d9b
 
 
8d52d2f
b852d9b
8d52d2f
b852d9b
 
8d52d2f
 
 
 
b852d9b
 
 
8d52d2f
 
 
 
 
 
b852d9b
 
8d52d2f
b852d9b
8d52d2f
b852d9b
 
 
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
{
  "best_metric": 0.04534918814897537,
  "best_model_checkpoint": "./roberta-large-condaqa-neg-tag-token-classifier/checkpoint-16",
  "epoch": 4.0,
  "global_step": 16,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9587528418317636,
      "eval_f1": 0.0,
      "eval_loss": 0.1548939347267151,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 1.8568,
      "eval_samples_per_second": 66.78,
      "eval_steps_per_second": 2.154,
      "step": 4
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9587528418317636,
      "eval_f1": 0.0,
      "eval_loss": 0.1006716936826706,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 2.0399,
      "eval_samples_per_second": 60.786,
      "eval_steps_per_second": 1.961,
      "step": 8
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9818122767132186,
      "eval_f1": 0.0,
      "eval_loss": 0.0592331625521183,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 2.0042,
      "eval_samples_per_second": 61.87,
      "eval_steps_per_second": 1.996,
      "step": 12
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9857096459889575,
      "eval_f1": 0.0,
      "eval_loss": 0.04534918814897537,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 1.8522,
      "eval_samples_per_second": 66.948,
      "eval_steps_per_second": 2.16,
      "step": 16
    },
    {
      "epoch": 4.0,
      "step": 16,
      "total_flos": 598453706860920.0,
      "train_loss": 0.19345927238464355,
      "train_runtime": 231.2313,
      "train_samples_per_second": 16.434,
      "train_steps_per_second": 0.069
    }
  ],
  "max_steps": 16,
  "num_train_epochs": 4,
  "total_flos": 598453706860920.0,
  "trial_name": null,
  "trial_params": null
}