File size: 1,545 Bytes
09fb6ad
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 1.92,
  "eval_steps": 500,
  "global_step": 18,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11,
      "learning_rate": 0.0001,
      "loss": 0.6469,
      "step": 1
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00018314696123025454,
      "loss": 0.4383,
      "step": 5
    },
    {
      "epoch": 0.96,
      "eval_loss": 0.2286338359117508,
      "eval_runtime": 5.2482,
      "eval_samples_per_second": 19.054,
      "eval_steps_per_second": 2.477,
      "step": 9
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0001,
      "loss": 0.23,
      "step": 10
    },
    {
      "epoch": 1.6,
      "learning_rate": 1.6853038769745467e-05,
      "loss": 0.2047,
      "step": 15
    },
    {
      "epoch": 1.92,
      "eval_loss": 0.21630115807056427,
      "eval_runtime": 4.1963,
      "eval_samples_per_second": 23.83,
      "eval_steps_per_second": 3.098,
      "step": 18
    },
    {
      "epoch": 1.92,
      "step": 18,
      "total_flos": 19174999326720.0,
      "train_loss": 0.2861863639619615,
      "train_runtime": 207.9549,
      "train_samples_per_second": 2.885,
      "train_steps_per_second": 0.087
    }
  ],
  "logging_steps": 5,
  "max_steps": 18,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 19174999326720.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}