Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0341

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0341
File size: 4,444 Bytes 
e46b1fe
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9024,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0341/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": 4.446112779446113e-05,
      "loss": 1.8157,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8090666666666667,
      "eval_loss": 0.756287157535553,
      "eval_runtime": 12.761,
      "eval_samples_per_second": 293.864,
      "eval_steps_per_second": 4.623,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 3.892225558892226e-05,
      "loss": 0.5325,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8394666666666667,
      "eval_loss": 0.5426056981086731,
      "eval_runtime": 12.2799,
      "eval_samples_per_second": 305.377,
      "eval_steps_per_second": 4.805,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 3.3383383383383385e-05,
      "loss": 0.3031,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8725333333333334,
      "eval_loss": 0.42890992760658264,
      "eval_runtime": 13.3119,
      "eval_samples_per_second": 281.704,
      "eval_steps_per_second": 4.432,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.9013118147850037,
      "learning_rate": 2.782782782782783e-05,
      "loss": 0.179,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8824,
      "eval_loss": 0.39497533440589905,
      "eval_runtime": 12.4032,
      "eval_samples_per_second": 302.341,
      "eval_steps_per_second": 4.757,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 4.517361640930176,
      "learning_rate": 2.2272272272272273e-05,
      "loss": 0.1098,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8850666666666667,
      "eval_loss": 0.40092653036117554,
      "eval_runtime": 12.3899,
      "eval_samples_per_second": 302.665,
      "eval_steps_per_second": 4.762,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.13426990807056427,
      "learning_rate": 1.6716716716716717e-05,
      "loss": 0.0596,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8922666666666667,
      "eval_loss": 0.393829882144928,
      "eval_runtime": 12.9079,
      "eval_samples_per_second": 290.519,
      "eval_steps_per_second": 4.571,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.09821178019046783,
      "learning_rate": 1.1161161161161162e-05,
      "loss": 0.0322,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8970666666666667,
      "eval_loss": 0.3901839554309845,
      "eval_runtime": 12.4028,
      "eval_samples_per_second": 302.352,
      "eval_steps_per_second": 4.757,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.47111132740974426,
      "learning_rate": 5.605605605605606e-06,
      "loss": 0.0164,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8981333333333333,
      "eval_loss": 0.3769923448562622,
      "eval_runtime": 12.3648,
      "eval_samples_per_second": 303.279,
      "eval_steps_per_second": 4.772,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.655457079410553,
      "learning_rate": 5.005005005005005e-08,
      "loss": 0.0094,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9024,
      "eval_loss": 0.3730998635292053,
      "eval_runtime": 12.5413,
      "eval_samples_per_second": 299.013,
      "eval_steps_per_second": 4.704,
      "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
}