File size: 1,871 Bytes
1a4bf79
 
 
2051b35
1a4bf79
2051b35
1a4bf79
 
 
 
 
 
862289d
dc00cbb
862289d
1a4bf79
f46db50
 
 
 
 
 
 
e9d9f1e
 
 
 
 
 
 
64dfaa7
 
 
 
 
 
 
8156721
 
 
 
 
 
 
fb14efa
 
 
 
 
 
 
69af666
 
 
 
 
 
 
b442e8a
 
 
 
 
 
 
2051b35
 
 
 
 
 
 
1a4bf79
 
 
dbb75cb
1a4bf79
dbb75cb
1a4bf79
2051b35
862289d
1a4bf79
 
 
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
76
77
78
79
80
81
82
83
84
85
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00014008545212579673,
  "eval_steps": 500,
  "global_step": 180,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 2.555440902709961,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 3.6397,
      "step": 20
    },
    {
      "epoch": 0.0,
      "grad_norm": 2.218903064727783,
      "learning_rate": 6.666666666666667e-06,
      "loss": 3.6917,
      "step": 40
    },
    {
      "epoch": 0.0,
      "grad_norm": 0.9262466430664062,
      "learning_rate": 1e-05,
      "loss": 3.5828,
      "step": 60
    },
    {
      "epoch": 0.0,
      "grad_norm": 2.782036542892456,
      "learning_rate": 1.3166666666666665e-05,
      "loss": 3.5865,
      "step": 80
    },
    {
      "epoch": 0.0,
      "grad_norm": 1.9482054710388184,
      "learning_rate": 1.65e-05,
      "loss": 3.3337,
      "step": 100
    },
    {
      "epoch": 0.0,
      "grad_norm": 4.047863006591797,
      "learning_rate": 1.9833333333333335e-05,
      "loss": 3.1903,
      "step": 120
    },
    {
      "epoch": 0.0,
      "grad_norm": 3.08722186088562,
      "learning_rate": 2.3166666666666666e-05,
      "loss": 3.5379,
      "step": 140
    },
    {
      "epoch": 0.0,
      "grad_norm": 3.540940046310425,
      "learning_rate": 2.6500000000000004e-05,
      "loss": 3.16,
      "step": 160
    },
    {
      "epoch": 0.0,
      "grad_norm": 5.391817092895508,
      "learning_rate": 2.9833333333333335e-05,
      "loss": 3.2489,
      "step": 180
    }
  ],
  "logging_steps": 20,
  "max_steps": 10000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 20,
  "total_flos": 901465913585664.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}