Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0076

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0076
File size: 4,058 Bytes 
c95b05a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9002666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0076/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": 4.376876876876877e-05,
      "loss": 1.8159,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8109333333333333,
      "eval_loss": 0.7509312033653259,
      "eval_runtime": 6.1069,
      "eval_samples_per_second": 614.063,
      "eval_steps_per_second": 9.661,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 3.7537537537537536e-05,
      "loss": 0.4876,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8586666666666667,
      "eval_loss": 0.4876919984817505,
      "eval_runtime": 5.7532,
      "eval_samples_per_second": 651.812,
      "eval_steps_per_second": 10.255,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.957433819770813,
      "learning_rate": 3.128753753753754e-05,
      "loss": 0.2272,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8824,
      "eval_loss": 0.4154290556907654,
      "eval_runtime": 5.7465,
      "eval_samples_per_second": 652.574,
      "eval_steps_per_second": 10.267,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.2741589844226837,
      "learning_rate": 2.5037537537537537e-05,
      "loss": 0.1145,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8776,
      "eval_loss": 0.4124266803264618,
      "eval_runtime": 5.9322,
      "eval_samples_per_second": 632.142,
      "eval_steps_per_second": 9.946,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.2854139506816864,
      "learning_rate": 1.8787537537537537e-05,
      "loss": 0.0567,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8909333333333334,
      "eval_loss": 0.3859509229660034,
      "eval_runtime": 7.3379,
      "eval_samples_per_second": 511.046,
      "eval_steps_per_second": 8.04,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.11716092377901077,
      "learning_rate": 1.2537537537537538e-05,
      "loss": 0.0225,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8949333333333334,
      "eval_loss": 0.4038940370082855,
      "eval_runtime": 6.9113,
      "eval_samples_per_second": 542.592,
      "eval_steps_per_second": 8.537,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.28137606382369995,
      "learning_rate": 6.287537537537539e-06,
      "loss": 0.0101,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8973333333333333,
      "eval_loss": 0.38434699177742004,
      "eval_runtime": 10.4682,
      "eval_samples_per_second": 358.228,
      "eval_steps_per_second": 5.636,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.111387237906456,
      "learning_rate": 3.753753753753754e-08,
      "loss": 0.0062,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9002666666666667,
      "eval_loss": 0.38581550121307373,
      "eval_runtime": 5.7226,
      "eval_samples_per_second": 655.299,
      "eval_steps_per_second": 10.31,
      "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
}