File size: 1,483 Bytes
d4b1e63
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 729,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.14,
      "learning_rate": 0.00048,
      "loss": 7.0366,
      "step": 100
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0004933240611961058,
      "loss": 0.4467,
      "step": 200
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00048643949930458967,
      "loss": 0.3946,
      "step": 300
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0004794853963838665,
      "loss": 0.399,
      "step": 400
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0004726008344923505,
      "loss": 0.3696,
      "step": 500
    },
    {
      "epoch": 0.69,
      "eval_loss": 0.3043254017829895,
      "eval_runtime": 65.1553,
      "eval_samples_per_second": 11.664,
      "eval_steps_per_second": 1.458,
      "eval_wer": 0.265993265993266,
      "step": 500
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0004656467315716273,
      "loss": 0.3677,
      "step": 600
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00045869262865090403,
      "loss": 0.3534,
      "step": 700
    }
  ],
  "logging_steps": 100,
  "max_steps": 7290,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 5.050015040194851e+18,
  "trial_name": null,
  "trial_params": null
}