Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0406

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0406
File size: 2,460 Bytes 
b8a5d67
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9624,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0406/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": 0.9736495018005371,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.8026,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9490666666666666,
      "eval_loss": 0.19063836336135864,
      "eval_runtime": 10.5696,
      "eval_samples_per_second": 354.793,
      "eval_steps_per_second": 5.582,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.13617996871471405,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.1086,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9530666666666666,
      "eval_loss": 0.1679835319519043,
      "eval_runtime": 10.2937,
      "eval_samples_per_second": 364.302,
      "eval_steps_per_second": 5.732,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.07775311172008514,
      "learning_rate": 2.5e-05,
      "loss": 0.0368,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9565333333333333,
      "eval_loss": 0.15937045216560364,
      "eval_runtime": 10.0339,
      "eval_samples_per_second": 373.732,
      "eval_steps_per_second": 5.88,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.05360400676727295,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.0132,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9624,
      "eval_loss": 0.13999928534030914,
      "eval_runtime": 10.224,
      "eval_samples_per_second": 366.784,
      "eval_steps_per_second": 5.771,
      "step": 1332
    }
  ],
  "logging_steps": 500,
  "max_steps": 1998,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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
}