File size: 1,642 Bytes
f988a7d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
71
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.6666666666666665,
  "eval_steps": 25,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 20.528797149658203,
      "learning_rate": 0.00015000000000000001,
      "loss": 72.0964,
      "step": 1
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 35.755401611328125,
      "learning_rate": 0.0001,
      "loss": 66.6014,
      "step": 2
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 21.73655128479004,
      "learning_rate": 5e-05,
      "loss": 68.7338,
      "step": 3
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 38.31291198730469,
      "learning_rate": 0.0,
      "loss": 60.6627,
      "step": 4
    },
    {
      "epoch": 1.6666666666666665,
      "step": 4,
      "total_flos": 16296977689776.0,
      "train_loss": 67.02359962463379,
      "train_runtime": 75.0366,
      "train_samples_per_second": 1.119,
      "train_steps_per_second": 0.053
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 4,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 16296977689776.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}