File size: 1,605 Bytes
d227e75
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 1.7508754377188596,
  "eval_steps": 500,
  "global_step": 3500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.25,
      "grad_norm": 40.72060012817383,
      "learning_rate": 1.8999499749874938e-05,
      "loss": 0.416,
      "step": 500
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.45640167593955994,
      "learning_rate": 1.7998999499749875e-05,
      "loss": 0.259,
      "step": 1000
    },
    {
      "epoch": 0.75,
      "grad_norm": 24.118961334228516,
      "learning_rate": 1.6998499249624815e-05,
      "loss": 0.2726,
      "step": 1500
    },
    {
      "epoch": 1.0,
      "grad_norm": 43.76200485229492,
      "learning_rate": 1.599799899949975e-05,
      "loss": 0.2471,
      "step": 2000
    },
    {
      "epoch": 1.25,
      "grad_norm": 31.93831443786621,
      "learning_rate": 1.4997498749374688e-05,
      "loss": 0.1518,
      "step": 2500
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.02012985199689865,
      "learning_rate": 1.3996998499249626e-05,
      "loss": 0.1421,
      "step": 3000
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.22942015528678894,
      "learning_rate": 1.2996498249124563e-05,
      "loss": 0.1463,
      "step": 3500
    }
  ],
  "logging_steps": 500,
  "max_steps": 9995,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 6523053577614336.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}