File size: 1,526 Bytes
441f0fc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.1446540880503147,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6212903225806452,
      "eval_loss": 0.2071644514799118,
      "eval_runtime": 5.7935,
      "eval_samples_per_second": 535.086,
      "eval_steps_per_second": 11.22,
      "step": 318
    },
    {
      "epoch": 1.57,
      "learning_rate": 1.550763701707098e-05,
      "loss": 0.3314,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.82,
      "eval_loss": 0.1023462787270546,
      "eval_runtime": 5.8254,
      "eval_samples_per_second": 532.155,
      "eval_steps_per_second": 11.158,
      "step": 636
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8774193548387097,
      "eval_loss": 0.06782012432813644,
      "eval_runtime": 5.7323,
      "eval_samples_per_second": 540.794,
      "eval_steps_per_second": 11.339,
      "step": 954
    },
    {
      "epoch": 3.14,
      "learning_rate": 1.101527403414196e-05,
      "loss": 0.1175,
      "step": 1000
    }
  ],
  "logging_steps": 500,
  "max_steps": 2226,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 500,
  "total_flos": 259991364709020.0,
  "train_batch_size": 48,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.28786009970392035,
    "num_train_epochs": 7,
    "temperature": 9
  }
}