Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0346

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0346
File size: 3,938 Bytes 
41ff424
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
 
{
  "best_metric": 0.8621333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0346/checkpoints/checkpoint-2664",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 2664,
  "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": 3e-05,
      "loss": 2.3183,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7426666666666667,
      "eval_loss": 1.1040794849395752,
      "eval_runtime": 5.7739,
      "eval_samples_per_second": 649.48,
      "eval_steps_per_second": 10.218,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 18.814632415771484,
      "learning_rate": 3e-05,
      "loss": 0.7615,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8154666666666667,
      "eval_loss": 0.6663826704025269,
      "eval_runtime": 6.0757,
      "eval_samples_per_second": 617.214,
      "eval_steps_per_second": 9.711,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 3e-05,
      "loss": 0.4068,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8565333333333334,
      "eval_loss": 0.5098052024841309,
      "eval_runtime": 5.7017,
      "eval_samples_per_second": 657.695,
      "eval_steps_per_second": 10.348,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": Infinity,
      "learning_rate": 3e-05,
      "loss": 0.2333,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8589333333333333,
      "eval_loss": 0.4995664656162262,
      "eval_runtime": 5.7187,
      "eval_samples_per_second": 655.743,
      "eval_steps_per_second": 10.317,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 6.915184020996094,
      "learning_rate": 3e-05,
      "loss": 0.1316,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8557333333333333,
      "eval_loss": 0.49549999833106995,
      "eval_runtime": 5.7597,
      "eval_samples_per_second": 651.077,
      "eval_steps_per_second": 10.244,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.362394094467163,
      "learning_rate": 3e-05,
      "loss": 0.0798,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8562666666666666,
      "eval_loss": 0.5158490538597107,
      "eval_runtime": 5.8049,
      "eval_samples_per_second": 646.003,
      "eval_steps_per_second": 10.164,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 1.5563570261001587,
      "learning_rate": 3e-05,
      "loss": 0.0499,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8533333333333334,
      "eval_loss": 0.5637221336364746,
      "eval_runtime": 5.782,
      "eval_samples_per_second": 648.57,
      "eval_steps_per_second": 10.204,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 1.712234377861023,
      "learning_rate": 3e-05,
      "loss": 0.0349,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8621333333333333,
      "eval_loss": 0.5528004169464111,
      "eval_runtime": 5.6748,
      "eval_samples_per_second": 660.818,
      "eval_steps_per_second": 10.397,
      "step": 2664
    }
  ],
  "logging_steps": 500,
  "max_steps": 2664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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": 1.317930564980736e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}