File size: 2,865 Bytes
5c32551
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
{
  "best_metric": 0.3778666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0713/checkpoints/checkpoint-1665",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1665,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 21.62734031677246,
      "learning_rate": 0.00027168440174204405,
      "loss": 3.3691,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.20666666666666667,
      "eval_loss": 3.0120861530303955,
      "eval_runtime": 10.5314,
      "eval_samples_per_second": 356.078,
      "eval_steps_per_second": 5.602,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 24.19246482849121,
      "learning_rate": 0.00019689056597036855,
      "loss": 2.8672,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.27093333333333336,
      "eval_loss": 2.722993850708008,
      "eval_runtime": 10.9804,
      "eval_samples_per_second": 341.517,
      "eval_steps_per_second": 5.373,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 0.00010445571134029838,
      "loss": 2.5387,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.328,
      "eval_loss": 2.50201153755188,
      "eval_runtime": 10.3102,
      "eval_samples_per_second": 363.719,
      "eval_steps_per_second": 5.723,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 29.745256423950195,
      "learning_rate": 2.9148468506836763e-05,
      "loss": 2.1928,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.3701333333333333,
      "eval_loss": 2.3468685150146484,
      "eval_runtime": 10.1683,
      "eval_samples_per_second": 368.794,
      "eval_steps_per_second": 5.802,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 52.09635925292969,
      "learning_rate": 2.4031112851152778e-09,
      "loss": 1.8666,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.3778666666666667,
      "eval_loss": 2.3312628269195557,
      "eval_runtime": 10.1695,
      "eval_samples_per_second": 368.749,
      "eval_steps_per_second": 5.802,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 1665,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}