Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0769

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0769
File size: 2,397 Bytes 
4e9f75c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.948,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0769/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": 8.527120590209961,
      "learning_rate": 2.4e-05,
      "loss": 1.181,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9261333333333334,
      "eval_loss": 0.30567431449890137,
      "eval_runtime": 12.514,
      "eval_samples_per_second": 299.665,
      "eval_steps_per_second": 4.715,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.6891355514526367,
      "learning_rate": 1.8e-05,
      "loss": 0.1614,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9416,
      "eval_loss": 0.21197418868541718,
      "eval_runtime": 12.4595,
      "eval_samples_per_second": 300.975,
      "eval_steps_per_second": 4.735,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 6.672385215759277,
      "learning_rate": 1.2e-05,
      "loss": 0.0595,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9453333333333334,
      "eval_loss": 0.20083259046077728,
      "eval_runtime": 12.4332,
      "eval_samples_per_second": 301.611,
      "eval_steps_per_second": 4.745,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.33915773034095764,
      "learning_rate": 6e-06,
      "loss": 0.0233,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.948,
      "eval_loss": 0.20247890055179596,
      "eval_runtime": 12.4446,
      "eval_samples_per_second": 301.335,
      "eval_steps_per_second": 4.741,
      "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
}