Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0241

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0241
File size: 3,157 Bytes 
93ba36d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
 
{
  "best_metric": 0.8464,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0241/checkpoints/checkpoint-1998",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1998,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 1.1163309812545776,
      "learning_rate": 9e-05,
      "loss": 1.7339,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7253333333333334,
      "eval_loss": 0.9704575538635254,
      "eval_runtime": 6.0028,
      "eval_samples_per_second": 624.709,
      "eval_steps_per_second": 9.829,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 9e-05,
      "loss": 0.5941,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8154666666666667,
      "eval_loss": 0.6149970293045044,
      "eval_runtime": 6.2231,
      "eval_samples_per_second": 602.596,
      "eval_steps_per_second": 9.481,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 4.3631978034973145,
      "learning_rate": 9e-05,
      "loss": 0.3598,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8202666666666667,
      "eval_loss": 0.5989220142364502,
      "eval_runtime": 6.5675,
      "eval_samples_per_second": 570.995,
      "eval_steps_per_second": 8.984,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 14.057211875915527,
      "learning_rate": 9e-05,
      "loss": 0.2494,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8306666666666667,
      "eval_loss": 0.5829501152038574,
      "eval_runtime": 6.1758,
      "eval_samples_per_second": 607.209,
      "eval_steps_per_second": 9.553,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.49229931831359863,
      "learning_rate": 9e-05,
      "loss": 0.1792,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8309333333333333,
      "eval_loss": 0.5903207063674927,
      "eval_runtime": 5.9646,
      "eval_samples_per_second": 628.71,
      "eval_steps_per_second": 9.892,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.04699142277240753,
      "learning_rate": 9e-05,
      "loss": 0.1418,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8464,
      "eval_loss": 0.566008448600769,
      "eval_runtime": 6.6545,
      "eval_samples_per_second": 563.525,
      "eval_steps_per_second": 8.866,
      "step": 1998
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}