Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0438

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0438
File size: 2,410 Bytes 
20959d7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9328,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0438/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": 5.543400764465332,
      "learning_rate": 2.4e-05,
      "loss": 1.3075,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9064,
      "eval_loss": 0.3838406205177307,
      "eval_runtime": 10.9979,
      "eval_samples_per_second": 340.975,
      "eval_steps_per_second": 5.365,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 1.801801801801802e-05,
      "loss": 0.2327,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9232,
      "eval_loss": 0.2752654552459717,
      "eval_runtime": 11.0089,
      "eval_samples_per_second": 340.633,
      "eval_steps_per_second": 5.359,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.21334803104400635,
      "learning_rate": 1.2018018018018019e-05,
      "loss": 0.1112,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.932,
      "eval_loss": 0.2436397522687912,
      "eval_runtime": 10.7188,
      "eval_samples_per_second": 349.852,
      "eval_steps_per_second": 5.504,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.34483709931373596,
      "learning_rate": 6.018018018018018e-06,
      "loss": 0.0622,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9328,
      "eval_loss": 0.23488226532936096,
      "eval_runtime": 10.7194,
      "eval_samples_per_second": 349.832,
      "eval_steps_per_second": 5.504,
      "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
}