Hugging Face's logo

timaeus
/
gpt-2-small-testing

Safetensors
gpt_neox
Model card Files Community
gpt-2-small-testing
File size: 1,989 Bytes 
5326b39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
86
87
88
89
90
91
92
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.009995002498750625,
  "eval_steps": 500,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 3.3340553137590683,
      "learning_rate": 0.0,
      "loss": 11.0,
      "step": 1
    },
    {
      "epoch": 0.0,
      "grad_norm": 2.398799707355898,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 10.125,
      "step": 2
    },
    {
      "epoch": 0.0,
      "grad_norm": 2.3943029297945575,
      "learning_rate": 0.00011999999999999999,
      "loss": 10.1172,
      "step": 3
    },
    {
      "epoch": 0.0,
      "grad_norm": 1.9959117709404242,
      "learning_rate": 0.00017999999999999998,
      "loss": 9.875,
      "step": 4
    },
    {
      "epoch": 0.0,
      "grad_norm": 1.8270696218303057,
      "learning_rate": 0.00023999999999999998,
      "loss": 9.6641,
      "step": 5
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.7854351602113614,
      "learning_rate": 0.0003,
      "loss": 9.4844,
      "step": 6
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.7194174424274788,
      "learning_rate": 0.00035999999999999997,
      "loss": 9.3281,
      "step": 7
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.463772638994466,
      "learning_rate": 0.00041999999999999996,
      "loss": 9.2109,
      "step": 8
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.439323678271545,
      "learning_rate": 0.00047999999999999996,
      "loss": 8.9453,
      "step": 9
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.2936126396494727,
      "learning_rate": 0.00054,
      "loss": 8.7109,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "total_flos": 0.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}