Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0007

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0007
File size: 4,053 Bytes 
c706036
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.6026666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0007/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": 0.0004810825448943271,
      "loss": 3.2011,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.24933333333333332,
      "eval_loss": 2.7806179523468018,
      "eval_runtime": 6.9697,
      "eval_samples_per_second": 538.044,
      "eval_steps_per_second": 8.465,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0004271931404387096,
      "loss": 2.5259,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.3858666666666667,
      "eval_loss": 2.26847243309021,
      "eval_runtime": 7.5083,
      "eval_samples_per_second": 499.444,
      "eval_steps_per_second": 7.858,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0003464873897488322,
      "loss": 2.0843,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.43493333333333334,
      "eval_loss": 2.0192508697509766,
      "eval_runtime": 7.3583,
      "eval_samples_per_second": 509.632,
      "eval_steps_per_second": 8.018,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 16.615558624267578,
      "learning_rate": 0.00025088445554620134,
      "loss": 1.7039,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.4856,
      "eval_loss": 1.8206737041473389,
      "eval_runtime": 7.2081,
      "eval_samples_per_second": 520.249,
      "eval_steps_per_second": 8.185,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.056095972657203674,
      "learning_rate": 0.00015514687100427082,
      "loss": 1.3055,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.5613333333333334,
      "eval_loss": 1.5949479341506958,
      "eval_runtime": 7.1085,
      "eval_samples_per_second": 527.536,
      "eval_steps_per_second": 8.3,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 2.334106922149658,
      "learning_rate": 7.384981550618446e-05,
      "loss": 0.8737,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.5909333333333333,
      "eval_loss": 1.5004363059997559,
      "eval_runtime": 7.1996,
      "eval_samples_per_second": 520.866,
      "eval_steps_per_second": 8.195,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 5.488366603851318,
      "learning_rate": 1.9370028791882848e-05,
      "loss": 0.5186,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.5989333333333333,
      "eval_loss": 1.4821934700012207,
      "eval_runtime": 7.1498,
      "eval_samples_per_second": 524.493,
      "eval_steps_per_second": 8.252,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 3.643709421157837,
      "learning_rate": 1.5645281219167639e-09,
      "loss": 0.3523,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.6026666666666667,
      "eval_loss": 1.4820199012756348,
      "eval_runtime": 7.1027,
      "eval_samples_per_second": 527.971,
      "eval_steps_per_second": 8.307,
      "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
}