Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0145

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0145
File size: 4,018 Bytes 
0731106
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9032,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0145/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": 6.790177189676492e-05,
      "loss": 1.6402,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.804,
      "eval_loss": 0.7110654711723328,
      "eval_runtime": 6.8327,
      "eval_samples_per_second": 548.833,
      "eval_steps_per_second": 8.635,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.890190362930298,
      "learning_rate": 6.183512375367748e-05,
      "loss": 0.5145,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8488,
      "eval_loss": 0.5046064257621765,
      "eval_runtime": 6.6029,
      "eval_samples_per_second": 567.934,
      "eval_steps_per_second": 8.935,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 5.2563508019062023e-05,
      "loss": 0.2962,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8632,
      "eval_loss": 0.4620145857334137,
      "eval_runtime": 6.6145,
      "eval_samples_per_second": 566.938,
      "eval_steps_per_second": 8.92,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.0203301906585693,
      "learning_rate": 4.1149935250010576e-05,
      "loss": 0.1697,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8797333333333334,
      "eval_loss": 0.404432475566864,
      "eval_runtime": 6.6701,
      "eval_samples_per_second": 562.213,
      "eval_steps_per_second": 8.845,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.16316266357898712,
      "learning_rate": 2.8994589526430138e-05,
      "loss": 0.092,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8933333333333333,
      "eval_loss": 0.38256797194480896,
      "eval_runtime": 6.6045,
      "eval_samples_per_second": 567.792,
      "eval_steps_per_second": 8.933,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.08973077684640884,
      "learning_rate": 1.756358493638142e-05,
      "loss": 0.0416,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8885333333333333,
      "eval_loss": 0.3828873336315155,
      "eval_runtime": 6.5755,
      "eval_samples_per_second": 570.296,
      "eval_steps_per_second": 8.973,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.08726523071527481,
      "learning_rate": 8.235669337084578e-06,
      "loss": 0.0164,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8997333333333334,
      "eval_loss": 0.3621499240398407,
      "eval_runtime": 6.8779,
      "eval_samples_per_second": 545.226,
      "eval_steps_per_second": 8.578,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.08266827464103699,
      "learning_rate": 2.135927015187301e-06,
      "loss": 0.0091,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9032,
      "eval_loss": 0.3585188686847687,
      "eval_runtime": 6.5274,
      "eval_samples_per_second": 574.501,
      "eval_steps_per_second": 9.039,
      "step": 2664
    }
  ],
  "logging_steps": 500,
  "max_steps": 2997,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.317930564980736e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}