File size: 1,549 Bytes
406a5bd
 
 
 
f97c2f4
406a5bd
 
 
 
 
 
 
f97c2f4
 
 
 
 
 
 
406a5bd
 
 
f97c2f4
 
 
 
 
406a5bd
 
f97c2f4
 
 
 
 
 
 
 
 
406a5bd
 
f97c2f4
 
406a5bd
f97c2f4
406a5bd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 555,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0,
      "eval_f1": 0.13882567137005006,
      "eval_loss": 0.8569005727767944,
      "eval_precision": 0.07566360704539817,
      "eval_recall": 0.8402203856749312,
      "eval_runtime": 50.8375,
      "eval_samples_per_second": 91.92,
      "eval_steps_per_second": 11.507,
      "step": 0
    },
    {
      "epoch": 1.0,
      "grad_norm": 18.535512924194336,
      "learning_rate": 2.4954873646209387e-05,
      "loss": 0.1595,
      "step": 555
    },
    {
      "epoch": 1.0,
      "eval_f1": 0.7377049180327869,
      "eval_loss": 0.11871597915887833,
      "eval_precision": 0.6415478615071283,
      "eval_recall": 0.8677685950413223,
      "eval_runtime": 52.321,
      "eval_samples_per_second": 89.314,
      "eval_steps_per_second": 11.181,
      "step": 555
    }
  ],
  "logging_steps": 500,
  "max_steps": 1108,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 1.929257128088371e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}