File size: 1,550 Bytes
0014c77
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 2.9554140127388537,
  "eval_steps": 1,
  "global_step": 58,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.97,
      "grad_norm": 1.752838134765625,
      "learning_rate": 0.00013103448275862068,
      "loss": 1.9056,
      "step": 19
    },
    {
      "epoch": 0.97,
      "eval_loss": 1.2314808368682861,
      "eval_runtime": 41.0888,
      "eval_samples_per_second": 3.407,
      "eval_steps_per_second": 3.407,
      "step": 19
    },
    {
      "epoch": 1.99,
      "grad_norm": 0.3157634139060974,
      "learning_rate": 0.000197828447339848,
      "loss": 0.7969,
      "step": 39
    },
    {
      "epoch": 1.99,
      "eval_loss": 0.6621134877204895,
      "eval_runtime": 41.1024,
      "eval_samples_per_second": 3.406,
      "eval_steps_per_second": 3.406,
      "step": 39
    },
    {
      "epoch": 2.96,
      "grad_norm": 0.46234801411628723,
      "learning_rate": 0.0001937024972855592,
      "loss": 0.564,
      "step": 58
    },
    {
      "epoch": 2.96,
      "eval_loss": 0.5718151330947876,
      "eval_runtime": 41.1043,
      "eval_samples_per_second": 3.406,
      "eval_steps_per_second": 3.406,
      "step": 58
    }
  ],
  "logging_steps": 1,
  "max_steps": 950,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 1,
  "total_flos": 1.976635488918528e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}