Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0701

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0701
File size: 3,906 Bytes 
768e5b3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8706666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0701/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": 7e-05,
      "loss": 1.6869,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.792,
      "eval_loss": 0.7568696737289429,
      "eval_runtime": 6.6995,
      "eval_samples_per_second": 559.743,
      "eval_steps_per_second": 8.807,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 6.767488956451416,
      "learning_rate": 7e-05,
      "loss": 0.5479,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8365333333333334,
      "eval_loss": 0.5525364875793457,
      "eval_runtime": 5.9954,
      "eval_samples_per_second": 625.476,
      "eval_steps_per_second": 9.841,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.6902329325675964,
      "learning_rate": 7e-05,
      "loss": 0.3454,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8568,
      "eval_loss": 0.4893222153186798,
      "eval_runtime": 6.0127,
      "eval_samples_per_second": 623.684,
      "eval_steps_per_second": 9.813,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.5259816646575928,
      "learning_rate": 7e-05,
      "loss": 0.2455,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8581333333333333,
      "eval_loss": 0.46845415234565735,
      "eval_runtime": 5.9952,
      "eval_samples_per_second": 625.502,
      "eval_steps_per_second": 9.841,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 5.132968902587891,
      "learning_rate": 7e-05,
      "loss": 0.1886,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8664,
      "eval_loss": 0.43812045454978943,
      "eval_runtime": 5.9967,
      "eval_samples_per_second": 625.343,
      "eval_steps_per_second": 9.839,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.5418972969055176,
      "learning_rate": 7e-05,
      "loss": 0.1451,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.864,
      "eval_loss": 0.4718008041381836,
      "eval_runtime": 6.0239,
      "eval_samples_per_second": 622.519,
      "eval_steps_per_second": 9.794,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.03438359498977661,
      "learning_rate": 7e-05,
      "loss": 0.12,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8677333333333334,
      "eval_loss": 0.4500684142112732,
      "eval_runtime": 6.0008,
      "eval_samples_per_second": 624.917,
      "eval_steps_per_second": 9.832,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.23980095982551575,
      "learning_rate": 7e-05,
      "loss": 0.095,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8706666666666667,
      "eval_loss": 0.48165297508239746,
      "eval_runtime": 6.4583,
      "eval_samples_per_second": 580.646,
      "eval_steps_per_second": 9.135,
      "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
}