File size: 1,871 Bytes
7efa5ae
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
72
73
74
75
76
77
{
  "best_metric": 0.46875,
  "best_model_checkpoint": "resnet-18-please-work/checkpoint-6",
  "epoch": 2.6666666666666665,
  "eval_steps": 500,
  "global_step": 18,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8888888888888888,
      "eval_accuracy": 0.46875,
      "eval_loss": NaN,
      "eval_runtime": 0.5279,
      "eval_samples_per_second": 181.87,
      "eval_steps_per_second": 5.683,
      "step": 6
    },
    {
      "epoch": 1.4814814814814814,
      "grad_norm": NaN,
      "learning_rate": 2.5e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 1.925925925925926,
      "eval_accuracy": 0.46875,
      "eval_loss": NaN,
      "eval_runtime": 0.3091,
      "eval_samples_per_second": 310.537,
      "eval_steps_per_second": 9.704,
      "step": 13
    },
    {
      "epoch": 2.6666666666666665,
      "eval_accuracy": 0.46875,
      "eval_loss": NaN,
      "eval_runtime": 0.2963,
      "eval_samples_per_second": 323.973,
      "eval_steps_per_second": 10.124,
      "step": 18
    },
    {
      "epoch": 2.6666666666666665,
      "step": 18,
      "total_flos": 2.326039595266867e+16,
      "train_loss": 0.0,
      "train_runtime": 17.8085,
      "train_samples_per_second": 145.549,
      "train_steps_per_second": 1.011
    }
  ],
  "logging_steps": 10,
  "max_steps": 18,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.326039595266867e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}