Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0527

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0527
File size: 2,427 Bytes 
4e5e52c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9432,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0527/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": 2.3603131771087646,
      "learning_rate": 0.00025606601717798207,
      "loss": 0.5584,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8949333333333334,
      "eval_loss": 0.3504687547683716,
      "eval_runtime": 12.7574,
      "eval_samples_per_second": 293.947,
      "eval_steps_per_second": 4.625,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.15052078664302826,
      "learning_rate": 0.00015,
      "loss": 0.195,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9184,
      "eval_loss": 0.2843656539916992,
      "eval_runtime": 12.9941,
      "eval_samples_per_second": 288.593,
      "eval_steps_per_second": 4.541,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.032707396894693375,
      "learning_rate": 4.3933982822017876e-05,
      "loss": 0.0538,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9362666666666667,
      "eval_loss": 0.22691646218299866,
      "eval_runtime": 12.7995,
      "eval_samples_per_second": 292.98,
      "eval_steps_per_second": 4.61,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.5480501651763916,
      "learning_rate": 0.0,
      "loss": 0.0089,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9432,
      "eval_loss": 0.21355003118515015,
      "eval_runtime": 12.3334,
      "eval_samples_per_second": 304.052,
      "eval_steps_per_second": 4.784,
      "step": 1332
    }
  ],
  "logging_steps": 500,
  "max_steps": 1332,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 6.58965282490368e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}