Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0249

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0249
File size: 4,003 Bytes 
84e2216
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8696,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0249/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": 2.626126126126126e-05,
      "loss": 2.4179,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6976,
      "eval_loss": 1.3441110849380493,
      "eval_runtime": 11.9773,
      "eval_samples_per_second": 313.092,
      "eval_steps_per_second": 4.926,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 2.2522522522522523e-05,
      "loss": 0.9374,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8,
      "eval_loss": 0.7621017098426819,
      "eval_runtime": 11.6274,
      "eval_samples_per_second": 322.514,
      "eval_steps_per_second": 5.074,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 31.468202590942383,
      "learning_rate": 1.8772522522522523e-05,
      "loss": 0.5447,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8322666666666667,
      "eval_loss": 0.6037696599960327,
      "eval_runtime": 12.9062,
      "eval_samples_per_second": 290.559,
      "eval_steps_per_second": 4.571,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": Infinity,
      "learning_rate": 1.5033783783783786e-05,
      "loss": 0.3626,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8416,
      "eval_loss": 0.5343086123466492,
      "eval_runtime": 10.9905,
      "eval_samples_per_second": 341.205,
      "eval_steps_per_second": 5.368,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 26.930965423583984,
      "learning_rate": 1.1283783783783783e-05,
      "loss": 0.2478,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8576,
      "eval_loss": 0.48877084255218506,
      "eval_runtime": 11.5537,
      "eval_samples_per_second": 324.571,
      "eval_steps_per_second": 5.107,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 24.69789695739746,
      "learning_rate": 7.533783783783783e-06,
      "loss": 0.1727,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8610666666666666,
      "eval_loss": 0.47552335262298584,
      "eval_runtime": 11.2042,
      "eval_samples_per_second": 334.696,
      "eval_steps_per_second": 5.266,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.9318552613258362,
      "learning_rate": 3.7837837837837835e-06,
      "loss": 0.122,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8685333333333334,
      "eval_loss": 0.4571969509124756,
      "eval_runtime": 11.712,
      "eval_samples_per_second": 320.184,
      "eval_steps_per_second": 5.038,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 1.1089979410171509,
      "learning_rate": 3.3783783783783786e-08,
      "loss": 0.0913,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8696,
      "eval_loss": 0.45212486386299133,
      "eval_runtime": 11.1707,
      "eval_samples_per_second": 335.699,
      "eval_steps_per_second": 5.282,
      "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
}