File size: 1,638 Bytes
9c992e1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
65
66
67
68
69
70
{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0661333333333334,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.21333333333333335,
      "grad_norm": 1.715923547744751,
      "learning_rate": 0.00027878464818763325,
      "loss": 2.0994,
      "step": 200
    },
    {
      "epoch": 0.4266666666666667,
      "grad_norm": 1.554486870765686,
      "learning_rate": 0.00025746268656716415,
      "loss": 1.7202,
      "step": 400
    },
    {
      "epoch": 0.64,
      "grad_norm": 1.6873255968093872,
      "learning_rate": 0.00023614072494669507,
      "loss": 1.6231,
      "step": 600
    },
    {
      "epoch": 0.8533333333333334,
      "grad_norm": 1.6301352977752686,
      "learning_rate": 0.000214818763326226,
      "loss": 1.6,
      "step": 800
    },
    {
      "epoch": 1.0661333333333334,
      "grad_norm": 1.7343031167984009,
      "learning_rate": 0.0001934968017057569,
      "loss": 1.4666,
      "step": 1000
    }
  ],
  "logging_steps": 200,
  "max_steps": 2814,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 1081922360967168.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}