Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0834

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0834
File size: 2,438 Bytes 
715e386
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.492,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0834/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": 0.0004271931404387096,
      "loss": 3.201,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.22933333333333333,
      "eval_loss": 2.7884559631347656,
      "eval_runtime": 10.8657,
      "eval_samples_per_second": 345.122,
      "eval_steps_per_second": 5.43,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.00025117927214825806,
      "loss": 2.4875,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.35413333333333336,
      "eval_loss": 2.242738962173462,
      "eval_runtime": 10.7192,
      "eval_samples_per_second": 349.84,
      "eval_steps_per_second": 5.504,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 12.034568786621094,
      "learning_rate": 7.405914276967749e-05,
      "loss": 1.9561,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.46986666666666665,
      "eval_loss": 1.8725781440734863,
      "eval_runtime": 10.8909,
      "eval_samples_per_second": 344.325,
      "eval_steps_per_second": 5.417,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 15.290120124816895,
      "learning_rate": 2.7813810714871766e-09,
      "loss": 1.5503,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.492,
      "eval_loss": 1.748207688331604,
      "eval_runtime": 11.642,
      "eval_samples_per_second": 322.109,
      "eval_steps_per_second": 5.068,
      "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
}