Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0713

Safetensors
vit
Model card Files
xet
Community
Model-J__SupViT__model_idx_0713
File size: 2,449 Bytes 
7023312
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.9448,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0713/checkpoints/checkpoint-1332",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 1332,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.7107285261154175,
      "learning_rate": 2.7135254915624213e-05,
      "loss": 1.1468,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9336,
      "eval_loss": 0.2739236354827881,
      "eval_runtime": 10.3012,
      "eval_samples_per_second": 364.037,
      "eval_steps_per_second": 5.728,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.25091367959976196,
      "learning_rate": 1.963525491562421e-05,
      "loss": 0.1441,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9392,
      "eval_loss": 0.22623032331466675,
      "eval_runtime": 10.7741,
      "eval_samples_per_second": 348.057,
      "eval_steps_per_second": 5.476,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.14530493319034576,
      "learning_rate": 1.036474508437579e-05,
      "loss": 0.0465,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9421333333333334,
      "eval_loss": 0.2084009051322937,
      "eval_runtime": 10.4866,
      "eval_samples_per_second": 357.598,
      "eval_steps_per_second": 5.626,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.17374251782894135,
      "learning_rate": 2.86474508437579e-06,
      "loss": 0.0198,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9448,
      "eval_loss": 0.20809677243232727,
      "eval_runtime": 10.0821,
      "eval_samples_per_second": 371.945,
      "eval_steps_per_second": 5.852,
      "step": 1332
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.58965282490368e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}