Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0721

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0721
File size: 4,045 Bytes 
4dcff12
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8992,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0721/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": 8.753753753753754e-05,
      "loss": 1.5647,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7968,
      "eval_loss": 0.7069309949874878,
      "eval_runtime": 11.4213,
      "eval_samples_per_second": 328.334,
      "eval_steps_per_second": 5.166,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.8710747361183167,
      "learning_rate": 7.503753753753753e-05,
      "loss": 0.5054,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8434666666666667,
      "eval_loss": 0.514112651348114,
      "eval_runtime": 10.8976,
      "eval_samples_per_second": 344.112,
      "eval_steps_per_second": 5.414,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.6819813847541809,
      "learning_rate": 6.253753753753754e-05,
      "loss": 0.287,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8506666666666667,
      "eval_loss": 0.481538325548172,
      "eval_runtime": 11.8257,
      "eval_samples_per_second": 317.107,
      "eval_steps_per_second": 4.989,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": Infinity,
      "learning_rate": 5.0075075075075074e-05,
      "loss": 0.1734,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8757333333333334,
      "eval_loss": 0.4350740909576416,
      "eval_runtime": 10.9564,
      "eval_samples_per_second": 342.266,
      "eval_steps_per_second": 5.385,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 55.98524475097656,
      "learning_rate": 3.7575075075075075e-05,
      "loss": 0.1096,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8773333333333333,
      "eval_loss": 0.4301956295967102,
      "eval_runtime": 10.9621,
      "eval_samples_per_second": 342.088,
      "eval_steps_per_second": 5.382,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 33.37843322753906,
      "learning_rate": 2.5075075075075076e-05,
      "loss": 0.0627,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8858666666666667,
      "eval_loss": 0.4006495475769043,
      "eval_runtime": 11.0053,
      "eval_samples_per_second": 340.745,
      "eval_steps_per_second": 5.361,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.43964463472366333,
      "learning_rate": 1.2575075075075077e-05,
      "loss": 0.0312,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8922666666666667,
      "eval_loss": 0.3968355357646942,
      "eval_runtime": 11.0689,
      "eval_samples_per_second": 338.786,
      "eval_steps_per_second": 5.33,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.12956281006336212,
      "learning_rate": 7.507507507507508e-08,
      "loss": 0.0145,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8992,
      "eval_loss": 0.377765417098999,
      "eval_runtime": 11.8298,
      "eval_samples_per_second": 316.995,
      "eval_steps_per_second": 4.987,
      "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
}