Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0719

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0719
File size: 4,044 Bytes 
d09568b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9245333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0719/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": 8.730227815298347e-05,
      "loss": 1.5827,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8072,
      "eval_loss": 0.7167118191719055,
      "eval_runtime": 12.2748,
      "eval_samples_per_second": 305.504,
      "eval_steps_per_second": 4.807,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.3953825235366821,
      "learning_rate": 7.95023019690139e-05,
      "loss": 0.4582,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8608,
      "eval_loss": 0.4900899827480316,
      "eval_runtime": 10.8404,
      "eval_samples_per_second": 345.929,
      "eval_steps_per_second": 5.443,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 6.3691487312316895,
      "learning_rate": 6.75408389678355e-05,
      "loss": 0.2447,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8693333333333333,
      "eval_loss": 0.44302046298980713,
      "eval_runtime": 10.9503,
      "eval_samples_per_second": 342.458,
      "eval_steps_per_second": 5.388,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.0851072445511818,
      "learning_rate": 5.286061811978304e-05,
      "loss": 0.1306,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8981333333333333,
      "eval_loss": 0.36098816990852356,
      "eval_runtime": 10.971,
      "eval_samples_per_second": 341.809,
      "eval_steps_per_second": 5.378,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.38895273208618164,
      "learning_rate": 3.723229071611673e-05,
      "loss": 0.0658,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8949333333333334,
      "eval_loss": 0.37516477704048157,
      "eval_runtime": 11.1601,
      "eval_samples_per_second": 336.02,
      "eval_steps_per_second": 5.287,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 2.9584529399871826,
      "learning_rate": 2.2540863691266368e-05,
      "loss": 0.0281,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9032,
      "eval_loss": 0.3802386522293091,
      "eval_runtime": 11.166,
      "eval_samples_per_second": 335.84,
      "eval_steps_per_second": 5.284,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.10670076310634613,
      "learning_rate": 1.055833996679956e-05,
      "loss": 0.0121,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.916,
      "eval_loss": 0.32141435146331787,
      "eval_runtime": 11.1087,
      "eval_samples_per_second": 337.574,
      "eval_steps_per_second": 5.311,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.4255896508693695,
      "learning_rate": 2.7299887471028354e-06,
      "loss": 0.0063,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9245333333333333,
      "eval_loss": 0.305776447057724,
      "eval_runtime": 11.4346,
      "eval_samples_per_second": 327.953,
      "eval_steps_per_second": 5.16,
      "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
}