Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0659

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0659
File size: 4,066 Bytes 
fd0cc7e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8808,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0659/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": 4.850126564054637e-05,
      "loss": 1.9547,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7853333333333333,
      "eval_loss": 0.8353696465492249,
      "eval_runtime": 6.0703,
      "eval_samples_per_second": 617.761,
      "eval_steps_per_second": 9.719,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 11.011552810668945,
      "learning_rate": 4.416794553834106e-05,
      "loss": 0.5705,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8394666666666667,
      "eval_loss": 0.5569896697998047,
      "eval_runtime": 5.2508,
      "eval_samples_per_second": 714.176,
      "eval_steps_per_second": 11.236,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 5.660791873931885,
      "learning_rate": 3.7522688315464166e-05,
      "loss": 0.2861,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8477333333333333,
      "eval_loss": 0.5053679943084717,
      "eval_runtime": 5.7321,
      "eval_samples_per_second": 654.213,
      "eval_steps_per_second": 10.293,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.3628094792366028,
      "learning_rate": 2.936701006654613e-05,
      "loss": 0.1467,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8626666666666667,
      "eval_loss": 0.4576970636844635,
      "eval_runtime": 5.7182,
      "eval_samples_per_second": 655.799,
      "eval_steps_per_second": 10.318,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.17120695114135742,
      "learning_rate": 2.0684605953398183e-05,
      "loss": 0.0674,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8645333333333334,
      "eval_loss": 0.4857991635799408,
      "eval_runtime": 5.41,
      "eval_samples_per_second": 693.164,
      "eval_steps_per_second": 10.906,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.1415909230709076,
      "learning_rate": 1.2522702050703538e-05,
      "loss": 0.027,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8730666666666667,
      "eval_loss": 0.48656797409057617,
      "eval_runtime": 5.2489,
      "eval_samples_per_second": 714.441,
      "eval_steps_per_second": 11.241,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 2.546767473220825,
      "learning_rate": 5.865744425999756e-06,
      "loss": 0.0106,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8789333333333333,
      "eval_loss": 0.47502315044403076,
      "eval_runtime": 5.23,
      "eval_samples_per_second": 717.011,
      "eval_steps_per_second": 11.281,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 1.4437414407730103,
      "learning_rate": 1.5166604150571306e-06,
      "loss": 0.0067,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8808,
      "eval_loss": 0.47619518637657166,
      "eval_runtime": 5.24,
      "eval_samples_per_second": 715.649,
      "eval_steps_per_second": 11.26,
      "step": 2664
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.317930564980736e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}