File size: 1,628 Bytes
1e459bb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
56
57
58
59
60
61
62
63
64
{
  "best_metric": 0.38878916468148733,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-536",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 536,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.547015905380249,
      "eval_matthews_correlation": 0.21965396568843812,
      "eval_runtime": 0.7987,
      "eval_samples_per_second": 1305.815,
      "eval_steps_per_second": 82.631,
      "step": 268
    },
    {
      "epoch": 1.8656716417910446,
      "grad_norm": 5.013413906097412,
      "learning_rate": 2.4916450268020124e-06,
      "loss": 0.5406,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5194542407989502,
      "eval_matthews_correlation": 0.38878916468148733,
      "eval_runtime": 0.9473,
      "eval_samples_per_second": 1100.981,
      "eval_steps_per_second": 69.669,
      "step": 536
    }
  ],
  "logging_steps": 500,
  "max_steps": 1072,
  "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": 95049498141888.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 4.669656413866708e-06,
    "num_train_epochs": 4,
    "per_device_train_batch_size": 32,
    "seed": 15
  }
}