File size: 1,170 Bytes
0082016
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": 0.7876712328767124,
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-17/checkpoint-766",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 766,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 3.036878824234009,
      "learning_rate": 6.985166134218099e-05,
      "loss": 0.5738,
      "step": 766
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7876712328767124,
      "eval_f1": 0.8121212121212121,
      "eval_loss": 0.4637316167354584,
      "eval_precision": 0.7282608695652174,
      "eval_recall": 0.9178082191780822,
      "eval_runtime": 132.0721,
      "eval_samples_per_second": 7.738,
      "eval_steps_per_second": 1.938,
      "step": 766
    }
  ],
  "logging_steps": 500,
  "max_steps": 5362,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 500,
  "total_flos": 235695197280.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.9998794266799103,
    "learning_rate": 8.149360489921117e-05,
    "num_train_epochs": 7,
    "temperature": 5
  }
}