Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0269

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0269
File size: 4,443 Bytes 
78886ca
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8797333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0269/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": 1.7857272624969482,
      "learning_rate": 8.003003003003004e-05,
      "loss": 1.3687,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7906666666666666,
      "eval_loss": 0.707594096660614,
      "eval_runtime": 4.161,
      "eval_samples_per_second": 901.217,
      "eval_steps_per_second": 14.179,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.9791254997253418,
      "learning_rate": 7.003003003003004e-05,
      "loss": 0.4585,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8288,
      "eval_loss": 0.557952344417572,
      "eval_runtime": 3.9087,
      "eval_samples_per_second": 959.394,
      "eval_steps_per_second": 15.094,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.9436779022216797,
      "learning_rate": 6.003003003003003e-05,
      "loss": 0.2532,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8496,
      "eval_loss": 0.5063246488571167,
      "eval_runtime": 4.0115,
      "eval_samples_per_second": 934.817,
      "eval_steps_per_second": 14.708,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.09931182116270065,
      "learning_rate": 5.003003003003004e-05,
      "loss": 0.1396,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8690666666666667,
      "eval_loss": 0.45184609293937683,
      "eval_runtime": 4.0795,
      "eval_samples_per_second": 919.228,
      "eval_steps_per_second": 14.463,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.042947668582201004,
      "learning_rate": 4.003003003003003e-05,
      "loss": 0.0765,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8725333333333334,
      "eval_loss": 0.48188066482543945,
      "eval_runtime": 3.9041,
      "eval_samples_per_second": 960.538,
      "eval_steps_per_second": 15.112,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": Infinity,
      "learning_rate": 3.0060060060060065e-05,
      "loss": 0.0389,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8584,
      "eval_loss": 0.5618187785148621,
      "eval_runtime": 4.6531,
      "eval_samples_per_second": 805.922,
      "eval_steps_per_second": 12.68,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.0476762130856514,
      "learning_rate": 2.0060060060060062e-05,
      "loss": 0.0162,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8712,
      "eval_loss": 0.5057010650634766,
      "eval_runtime": 5.2876,
      "eval_samples_per_second": 709.21,
      "eval_steps_per_second": 11.158,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.017669668421149254,
      "learning_rate": 1.0060060060060061e-05,
      "loss": 0.0056,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.876,
      "eval_loss": 0.48914003372192383,
      "eval_runtime": 4.7658,
      "eval_samples_per_second": 786.855,
      "eval_steps_per_second": 12.38,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.061433542519807816,
      "learning_rate": 6.006006006006006e-08,
      "loss": 0.0027,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.8797333333333334,
      "eval_loss": 0.48338672518730164,
      "eval_runtime": 4.2371,
      "eval_samples_per_second": 885.034,
      "eval_steps_per_second": 13.925,
      "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
}