File size: 1,246 Bytes
25c23f3
 
 
efc63d1
25c23f3
efc63d1
25c23f3
 
 
 
 
 
efc63d1
 
 
 
25c23f3
 
 
 
efc63d1
 
 
 
 
 
 
25c23f3
 
 
efc63d1
25c23f3
efc63d1
25c23f3
 
 
 
 
 
 
 
 
 
 
 
 
efc63d1
25c23f3
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 145,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.6896551724137931,
      "eval_loss": 21.947891235351562,
      "eval_runtime": 168.4847,
      "eval_samples_per_second": 14.34,
      "eval_steps_per_second": 1.792,
      "eval_wer": 1.0003446578040374,
      "step": 100
    },
    {
      "epoch": 1.0,
      "step": 145,
      "total_flos": 6.105598680744346e+17,
      "train_loss": 18.518729795258622,
      "train_runtime": 625.4328,
      "train_samples_per_second": 7.403,
      "train_steps_per_second": 0.232
    }
  ],
  "logging_steps": 500,
  "max_steps": 145,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 400,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.105598680744346e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}