File size: 1,373 Bytes
12644a2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": 0.740333586050038,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-multiclass-classification/run-7/checkpoint-660",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 660,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.7575757575757576,
      "grad_norm": 6.107817649841309,
      "learning_rate": 2.4840825476810007e-05,
      "loss": 4.5331,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.740333586050038,
      "eval_loss": 2.2369935512542725,
      "eval_runtime": 91.726,
      "eval_samples_per_second": 28.76,
      "eval_steps_per_second": 1.799,
      "step": 660
    }
  ],
  "logging_steps": 500,
  "max_steps": 2640,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 188924756492288.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 3.064475666298057e-05,
    "num_train_epochs": 4,
    "per_device_train_batch_size": 16,
    "seed": 13
  }
}