Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0192

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0192
File size: 4,481 Bytes 
218f4c8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
 
{
  "best_metric": 0.8986666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0192/checkpoints/checkpoint-2997",
  "epoch": 9.0,
  "eval_steps": 500,
  "global_step": 2997,
  "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": 1.5907,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.792,
      "eval_loss": 0.7598974108695984,
      "eval_runtime": 11.5992,
      "eval_samples_per_second": 323.299,
      "eval_steps_per_second": 5.087,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.5344213843345642,
      "learning_rate": 7.95023019690139e-05,
      "loss": 0.5656,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8162666666666667,
      "eval_loss": 0.6426149606704712,
      "eval_runtime": 11.4558,
      "eval_samples_per_second": 327.346,
      "eval_steps_per_second": 5.15,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 37.371131896972656,
      "learning_rate": 6.75408389678355e-05,
      "loss": 0.3554,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8557333333333333,
      "eval_loss": 0.49452516436576843,
      "eval_runtime": 11.2366,
      "eval_samples_per_second": 333.731,
      "eval_steps_per_second": 5.251,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.3548334836959839,
      "learning_rate": 5.286061811978304e-05,
      "loss": 0.2334,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8626666666666667,
      "eval_loss": 0.48811429738998413,
      "eval_runtime": 11.2757,
      "eval_samples_per_second": 332.573,
      "eval_steps_per_second": 5.232,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 3.827549457550049,
      "learning_rate": 3.723229071611673e-05,
      "loss": 0.1339,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8749333333333333,
      "eval_loss": 0.447792649269104,
      "eval_runtime": 12.3421,
      "eval_samples_per_second": 303.839,
      "eval_steps_per_second": 4.78,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 4.694804668426514,
      "learning_rate": 2.2540863691266368e-05,
      "loss": 0.0721,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8805333333333333,
      "eval_loss": 0.44752752780914307,
      "eval_runtime": 12.2602,
      "eval_samples_per_second": 305.867,
      "eval_steps_per_second": 4.812,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.6462125182151794,
      "learning_rate": 1.055833996679956e-05,
      "loss": 0.039,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8906666666666667,
      "eval_loss": 0.41354700922966003,
      "eval_runtime": 11.0699,
      "eval_samples_per_second": 338.757,
      "eval_steps_per_second": 5.33,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.7667026519775391,
      "learning_rate": 2.7299887471028354e-06,
      "loss": 0.0195,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8922666666666667,
      "eval_loss": 0.4107740521430969,
      "eval_runtime": 12.1827,
      "eval_samples_per_second": 307.813,
      "eval_steps_per_second": 4.843,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.5189184546470642,
      "learning_rate": 2.472343088255613e-11,
      "loss": 0.0133,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.8986666666666666,
      "eval_loss": 0.40958163142204285,
      "eval_runtime": 11.0565,
      "eval_samples_per_second": 339.167,
      "eval_steps_per_second": 5.336,
      "step": 2997
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.482671885603328e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}