File size: 1,133 Bytes
1c8f3ce
d95c13c
 
 
1c8f3ce
 
 
 
 
 
 
 
d95c13c
 
 
 
 
 
 
 
 
 
 
 
 
 
1c8f3ce
 
 
 
d95c13c
1c8f3ce
d95c13c
1c8f3ce
 
d95c13c
1c8f3ce
 
d95c13c
 
 
 
1c8f3ce
 
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
{
  "best_metric": 0.1836734693877551,
  "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-1\\checkpoint-69",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 138,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.1836734693877551,
      "eval_loss": 2.384721279144287,
      "eval_runtime": 1.179,
      "eval_samples_per_second": 207.804,
      "eval_steps_per_second": 13.571,
      "step": 69
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.1836734693877551,
      "eval_loss": 2.3813865184783936,
      "eval_runtime": 1.1696,
      "eval_samples_per_second": 209.477,
      "eval_steps_per_second": 13.68,
      "step": 138
    }
  ],
  "logging_steps": 500,
  "max_steps": 138,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 1.0017079803752642e-06,
    "num_train_epochs": 2,
    "per_device_train_batch_size": 32,
    "seed": 24
  }
}