Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0655

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0655
File size: 4,007 Bytes 
2c59923
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.9048,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0655/checkpoints/checkpoint-2664",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 2664,
  "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": 2.886495269365963e-05,
      "loss": 2.1317,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7866666666666666,
      "eval_loss": 1.0088863372802734,
      "eval_runtime": 7.0364,
      "eval_samples_per_second": 532.946,
      "eval_steps_per_second": 8.385,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 11.596940040588379,
      "learning_rate": 2.5619102456015873e-05,
      "loss": 0.6491,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8429333333333333,
      "eval_loss": 0.6053131222724915,
      "eval_runtime": 7.3687,
      "eval_samples_per_second": 508.907,
      "eval_steps_per_second": 8.007,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 2.0772920772568672e-05,
      "loss": 0.3637,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8789333333333333,
      "eval_loss": 0.44306817650794983,
      "eval_runtime": 7.3171,
      "eval_samples_per_second": 512.499,
      "eval_steps_per_second": 8.063,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": Infinity,
      "learning_rate": 1.5053067332772079e-05,
      "loss": 0.2278,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8912,
      "eval_loss": 0.3935328722000122,
      "eval_runtime": 6.8531,
      "eval_samples_per_second": 547.201,
      "eval_steps_per_second": 8.609,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 3.099303960800171,
      "learning_rate": 9.30881226025625e-06,
      "loss": 0.1393,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8944,
      "eval_loss": 0.3867528736591339,
      "eval_runtime": 6.863,
      "eval_samples_per_second": 546.407,
      "eval_steps_per_second": 8.597,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 15.028138160705566,
      "learning_rate": 4.430988930371068e-06,
      "loss": 0.0894,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9008,
      "eval_loss": 0.3505653440952301,
      "eval_runtime": 6.9107,
      "eval_samples_per_second": 542.636,
      "eval_steps_per_second": 8.537,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.29325589537620544,
      "learning_rate": 1.1622017275129709e-06,
      "loss": 0.0623,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9042666666666667,
      "eval_loss": 0.3437579870223999,
      "eval_runtime": 6.8205,
      "eval_samples_per_second": 549.813,
      "eval_steps_per_second": 8.65,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.2025875300168991,
      "learning_rate": 9.387168731500584e-11,
      "loss": 0.0523,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9048,
      "eval_loss": 0.34914806485176086,
      "eval_runtime": 7.2291,
      "eval_samples_per_second": 518.735,
      "eval_steps_per_second": 8.161,
      "step": 2664
    }
  ],
  "logging_steps": 500,
  "max_steps": 2664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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": 1.317930564980736e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}