File size: 1,564 Bytes
21e38a4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.6737967914438503,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5695608258247375,
      "eval_loss": 0.6931408643722534,
      "eval_runtime": 14.7678,
      "eval_samples_per_second": 201.994,
      "eval_steps_per_second": 12.663,
      "step": 187
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5115655660629272,
      "eval_loss": 0.6931466460227966,
      "eval_runtime": 14.1666,
      "eval_samples_per_second": 210.566,
      "eval_steps_per_second": 13.2,
      "step": 374
    },
    {
      "epoch": 2.6737967914438503,
      "grad_norm": 0.5249342918395996,
      "learning_rate": 6.592302596343259e-05,
      "loss": 0.6952,
      "step": 500
    }
  ],
  "logging_steps": 500,
  "max_steps": 1870,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1551788349290184.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 8.99825244902328e-05,
    "per_device_train_batch_size": 64
  }
}