File size: 1,608 Bytes
13c3efe
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": 0.0463559874942472,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-536",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 536,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.602029025554657,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 0.7285,
      "eval_samples_per_second": 1431.715,
      "eval_steps_per_second": 90.598,
      "step": 268
    },
    {
      "epoch": 1.8656716417910446,
      "grad_norm": 1.8423285484313965,
      "learning_rate": 9.08259470497268e-07,
      "loss": 0.605,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5747156739234924,
      "eval_matthews_correlation": 0.0463559874942472,
      "eval_runtime": 0.8181,
      "eval_samples_per_second": 1274.974,
      "eval_steps_per_second": 80.679,
      "step": 536
    }
  ],
  "logging_steps": 500,
  "max_steps": 1340,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 96080777538456.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 1.4488901076980227e-06,
    "num_train_epochs": 5,
    "per_device_train_batch_size": 32,
    "seed": 3
  }
}