File size: 1,403 Bytes
c625507
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 100,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.0,
      "step": 9,
      "total_flos": 1963891858500.0,
      "train_loss": 0.6781148910522461,
      "train_runtime": 527.8082,
      "train_samples_per_second": 0.483,
      "train_steps_per_second": 0.017
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.25,
      "eval_accuracy_label_ELIGIBLE": 0.0,
      "eval_accuracy_label_NOT ELIGIBLE": 0.3333333333333333,
      "eval_f1": 0.30000000000000004,
      "eval_loss": 0.7826551795005798,
      "eval_precision": 0.375,
      "eval_recall": 0.25,
      "eval_runtime": 5.0134,
      "eval_samples_per_second": 1.596,
      "eval_steps_per_second": 0.199,
      "step": 9
    }
  ],
  "logging_steps": 10,
  "max_steps": 9,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1963891858500.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}