File size: 1,314 Bytes
139e538
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0067114093959733,
  "eval_steps": 500,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.34,
      "grad_norm": 3.309788227081299,
      "learning_rate": 4.440715883668904e-05,
      "loss": 0.5291,
      "step": 500
    },
    {
      "epoch": 0.67,
      "grad_norm": 8.38113784790039,
      "learning_rate": 3.881431767337807e-05,
      "loss": 0.4834,
      "step": 1000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8244186046511628,
      "eval_f1": 0.700990099009901,
      "eval_loss": 0.40849873423576355,
      "eval_precision": 0.6679245283018868,
      "eval_recall": 0.7375,
      "eval_runtime": 1.415,
      "eval_samples_per_second": 607.771,
      "eval_steps_per_second": 76.325,
      "step": 1490
    },
    {
      "epoch": 1.01,
      "grad_norm": 4.857753753662109,
      "learning_rate": 3.3221476510067115e-05,
      "loss": 0.4743,
      "step": 1500
    }
  ],
  "logging_steps": 500,
  "max_steps": 4470,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 635261087615520.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}