File size: 1,450 Bytes
ee8c716
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 3159,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.47,
      "learning_rate": 1.6834441278885725e-05,
      "loss": 0.4901,
      "step": 500
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.3668882557771448e-05,
      "loss": 0.2541,
      "step": 1000
    },
    {
      "epoch": 1.42,
      "learning_rate": 1.0503323836657171e-05,
      "loss": 0.2147,
      "step": 1500
    },
    {
      "epoch": 1.9,
      "learning_rate": 7.337765115542894e-06,
      "loss": 0.1957,
      "step": 2000
    },
    {
      "epoch": 2.37,
      "learning_rate": 4.172206394428617e-06,
      "loss": 0.1818,
      "step": 2500
    },
    {
      "epoch": 2.85,
      "learning_rate": 1.00664767331434e-06,
      "loss": 0.1774,
      "step": 3000
    },
    {
      "epoch": 3.0,
      "step": 3159,
      "total_flos": 9.236713141793434e+16,
      "train_loss": 0.24820531837243603,
      "train_runtime": 1181.836,
      "train_samples_per_second": 170.96,
      "train_steps_per_second": 2.673
    }
  ],
  "logging_steps": 500,
  "max_steps": 3159,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 9.236713141793434e+16,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}