Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0424

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0424
File size: 4,464 Bytes 
277bf07
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.6069333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0424/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": 0.0004850126564054637,
      "loss": 3.0959,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.2674666666666667,
      "eval_loss": 2.6598265171051025,
      "eval_runtime": 7.8194,
      "eval_samples_per_second": 479.575,
      "eval_steps_per_second": 7.545,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.00044184758936602033,
      "loss": 2.4433,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.3736,
      "eval_loss": 2.2412760257720947,
      "eval_runtime": 7.4984,
      "eval_samples_per_second": 500.105,
      "eval_steps_per_second": 7.868,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 9.357409477233887,
      "learning_rate": 0.0003754536287075859,
      "loss": 1.9951,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.4397333333333333,
      "eval_loss": 1.9704962968826294,
      "eval_runtime": 6.9153,
      "eval_samples_per_second": 542.277,
      "eval_steps_per_second": 8.532,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 16.954750061035156,
      "learning_rate": 0.000293928108928647,
      "loss": 1.6398,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.49573333333333336,
      "eval_loss": 1.771036148071289,
      "eval_runtime": 7.0007,
      "eval_samples_per_second": 535.659,
      "eval_steps_per_second": 8.428,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.6292563676834106,
      "learning_rate": 0.00020710421090307243,
      "loss": 1.2725,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.5378666666666667,
      "eval_loss": 1.6080013513565063,
      "eval_runtime": 7.1198,
      "eval_samples_per_second": 526.703,
      "eval_steps_per_second": 8.287,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 9.923975944519043,
      "learning_rate": 0.00012545417811701015,
      "loss": 0.8674,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.5749333333333333,
      "eval_loss": 1.510210394859314,
      "eval_runtime": 6.8094,
      "eval_samples_per_second": 550.713,
      "eval_steps_per_second": 8.665,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 22.104650497436523,
      "learning_rate": 5.882620955060414e-05,
      "loss": 0.5078,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.5954666666666667,
      "eval_loss": 1.4831739664077759,
      "eval_runtime": 7.0203,
      "eval_samples_per_second": 534.163,
      "eval_steps_per_second": 8.404,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 3.3509016036987305,
      "learning_rate": 1.5256621537052151e-05,
      "loss": 0.2489,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.6053333333333333,
      "eval_loss": 1.4958287477493286,
      "eval_runtime": 6.9316,
      "eval_samples_per_second": 541.003,
      "eval_steps_per_second": 8.512,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 2.5019710063934326,
      "learning_rate": 5.494094242330939e-10,
      "loss": 0.1574,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.6069333333333333,
      "eval_loss": 1.4841878414154053,
      "eval_runtime": 7.3524,
      "eval_samples_per_second": 510.04,
      "eval_steps_per_second": 8.025,
      "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
}