File size: 1,376 Bytes
e9cea64
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": 0.8938775510204081,
  "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-6\\checkpoint-414",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 414,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7836734693877551,
      "eval_loss": 0.9130998849868774,
      "eval_runtime": 1.126,
      "eval_samples_per_second": 217.584,
      "eval_steps_per_second": 14.21,
      "step": 138
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8612244897959184,
      "eval_loss": 0.5591093897819519,
      "eval_runtime": 1.146,
      "eval_samples_per_second": 213.787,
      "eval_steps_per_second": 13.962,
      "step": 276
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8938775510204081,
      "eval_loss": 0.4424550533294678,
      "eval_runtime": 1.167,
      "eval_samples_per_second": 209.939,
      "eval_steps_per_second": 13.71,
      "step": 414
    }
  ],
  "logging_steps": 500,
  "max_steps": 690,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 6.696974887952063e-05,
    "num_train_epochs": 5,
    "per_device_train_batch_size": 16,
    "seed": 16
  }
}