Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0084

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0084
File size: 4,461 Bytes 
9042c93
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8677333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0084/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": 0.00026676676676676677,
      "loss": 2.4075,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6682666666666667,
      "eval_loss": 1.152270793914795,
      "eval_runtime": 7.6866,
      "eval_samples_per_second": 487.862,
      "eval_steps_per_second": 7.676,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.5095269680023193,
      "learning_rate": 0.00023343343343343342,
      "loss": 0.8266,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7816,
      "eval_loss": 0.703055202960968,
      "eval_runtime": 7.0333,
      "eval_samples_per_second": 533.179,
      "eval_steps_per_second": 8.389,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.25592198967933655,
      "learning_rate": 0.00020010010010010007,
      "loss": 0.3848,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8034666666666667,
      "eval_loss": 0.6375019550323486,
      "eval_runtime": 6.3423,
      "eval_samples_per_second": 591.272,
      "eval_steps_per_second": 9.303,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.08299722522497177,
      "learning_rate": 0.00016676676676676675,
      "loss": 0.1805,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8314666666666667,
      "eval_loss": 0.6055590510368347,
      "eval_runtime": 6.4741,
      "eval_samples_per_second": 579.232,
      "eval_steps_per_second": 9.113,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.5929628610610962,
      "learning_rate": 0.00013343343343343343,
      "loss": 0.0793,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8378666666666666,
      "eval_loss": 0.5855091214179993,
      "eval_runtime": 6.4105,
      "eval_samples_per_second": 584.978,
      "eval_steps_per_second": 9.204,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.9704152345657349,
      "learning_rate": 0.00010010010010010008,
      "loss": 0.0331,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8426666666666667,
      "eval_loss": 0.6151939034461975,
      "eval_runtime": 6.5449,
      "eval_samples_per_second": 572.968,
      "eval_steps_per_second": 9.015,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.026865333318710327,
      "learning_rate": 6.676676676676677e-05,
      "loss": 0.0089,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.852,
      "eval_loss": 0.6132980585098267,
      "eval_runtime": 6.3088,
      "eval_samples_per_second": 594.409,
      "eval_steps_per_second": 9.352,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.01385582610964775,
      "learning_rate": 3.343343343343343e-05,
      "loss": 0.0017,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8656,
      "eval_loss": 0.5507284998893738,
      "eval_runtime": 6.4722,
      "eval_samples_per_second": 579.399,
      "eval_steps_per_second": 9.116,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.005359232425689697,
      "learning_rate": 1.001001001001001e-07,
      "loss": 0.0008,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.8677333333333334,
      "eval_loss": 0.5497774481773376,
      "eval_runtime": 6.2958,
      "eval_samples_per_second": 595.636,
      "eval_steps_per_second": 9.371,
      "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
}