Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0938

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0938
File size: 4,044 Bytes 
f4b9f78
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8978666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0938/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": 2.042102575302124,
      "learning_rate": 8.657457896300791e-05,
      "loss": 1.8973,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7696,
      "eval_loss": 0.8121414184570312,
      "eval_runtime": 6.508,
      "eval_samples_per_second": 576.217,
      "eval_steps_per_second": 9.066,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 7.685730736804761e-05,
      "loss": 0.5548,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8336,
      "eval_loss": 0.550466775894165,
      "eval_runtime": 6.3579,
      "eval_samples_per_second": 589.817,
      "eval_steps_per_second": 9.28,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.7246056795120239,
      "learning_rate": 6.226977039554153e-05,
      "loss": 0.3011,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8493333333333334,
      "eval_loss": 0.4895199239253998,
      "eval_runtime": 7.148,
      "eval_samples_per_second": 524.622,
      "eval_steps_per_second": 8.254,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.830812931060791,
      "learning_rate": 4.505306743117272e-05,
      "loss": 0.1637,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8698666666666667,
      "eval_loss": 0.43225929141044617,
      "eval_runtime": 6.3628,
      "eval_samples_per_second": 589.365,
      "eval_steps_per_second": 9.273,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.19719810783863068,
      "learning_rate": 2.7828285431465317e-05,
      "loss": 0.0867,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8853333333333333,
      "eval_loss": 0.41396790742874146,
      "eval_runtime": 7.2422,
      "eval_samples_per_second": 517.801,
      "eval_steps_per_second": 8.147,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.6764962673187256,
      "learning_rate": 1.3217741312837138e-05,
      "loss": 0.0428,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.888,
      "eval_loss": 0.40302368998527527,
      "eval_runtime": 7.397,
      "eval_samples_per_second": 506.965,
      "eval_steps_per_second": 7.976,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.11161429435014725,
      "learning_rate": 3.4457579724370674e-06,
      "loss": 0.019,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8973333333333333,
      "eval_loss": 0.3717140555381775,
      "eval_runtime": 7.0567,
      "eval_samples_per_second": 531.407,
      "eval_steps_per_second": 8.361,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 2.0223774909973145,
      "learning_rate": 3.12905914479078e-11,
      "loss": 0.0117,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8978666666666667,
      "eval_loss": 0.3789162039756775,
      "eval_runtime": 6.825,
      "eval_samples_per_second": 549.45,
      "eval_steps_per_second": 8.645,
      "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
}