Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0343

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0343
File size: 2,391 Bytes 
82962fe
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.7658666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0343/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": Infinity,
      "learning_rate": 0.0003,
      "loss": 2.2067,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6322666666666666,
      "eval_loss": 1.2969685792922974,
      "eval_runtime": 13.2906,
      "eval_samples_per_second": 282.154,
      "eval_steps_per_second": 4.439,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0003,
      "loss": 0.8955,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7405333333333334,
      "eval_loss": 0.8697797656059265,
      "eval_runtime": 13.2366,
      "eval_samples_per_second": 283.306,
      "eval_steps_per_second": 4.457,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 10.084589004516602,
      "learning_rate": 0.0003,
      "loss": 0.5719,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.756,
      "eval_loss": 0.8228067755699158,
      "eval_runtime": 13.1644,
      "eval_samples_per_second": 284.859,
      "eval_steps_per_second": 4.482,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.375128984451294,
      "learning_rate": 0.0003,
      "loss": 0.3911,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7658666666666667,
      "eval_loss": 0.8272975087165833,
      "eval_runtime": 12.8077,
      "eval_samples_per_second": 292.794,
      "eval_steps_per_second": 4.607,
      "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
}