Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0727

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0727
File size: 4,028 Bytes 
4dccfa8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9008,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0727/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": 7.442104816436768,
      "learning_rate": 6.125e-05,
      "loss": 1.5933,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8194666666666667,
      "eval_loss": 0.6661399006843567,
      "eval_runtime": 5.9329,
      "eval_samples_per_second": 632.064,
      "eval_steps_per_second": 9.944,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 5.252627627627627e-05,
      "loss": 0.4621,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8538666666666667,
      "eval_loss": 0.48177170753479004,
      "eval_runtime": 5.8917,
      "eval_samples_per_second": 636.485,
      "eval_steps_per_second": 10.014,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 4.3802552552552546e-05,
      "loss": 0.2541,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8661333333333333,
      "eval_loss": 0.4511376917362213,
      "eval_runtime": 5.9348,
      "eval_samples_per_second": 631.871,
      "eval_steps_per_second": 9.941,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.967535674571991,
      "learning_rate": 3.5052552552552544e-05,
      "loss": 0.1486,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8805333333333333,
      "eval_loss": 0.39778977632522583,
      "eval_runtime": 6.1124,
      "eval_samples_per_second": 613.51,
      "eval_steps_per_second": 9.653,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.1634528934955597,
      "learning_rate": 2.630255255255255e-05,
      "loss": 0.0868,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8866666666666667,
      "eval_loss": 0.3903479278087616,
      "eval_runtime": 6.021,
      "eval_samples_per_second": 622.815,
      "eval_steps_per_second": 9.799,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.28644588589668274,
      "learning_rate": 1.7552552552552552e-05,
      "loss": 0.0443,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.888,
      "eval_loss": 0.4072471857070923,
      "eval_runtime": 5.9047,
      "eval_samples_per_second": 635.091,
      "eval_steps_per_second": 9.992,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.6804221272468567,
      "learning_rate": 8.802552552552553e-06,
      "loss": 0.0218,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8965333333333333,
      "eval_loss": 0.3906264901161194,
      "eval_runtime": 5.9079,
      "eval_samples_per_second": 634.743,
      "eval_steps_per_second": 9.987,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 2.485240936279297,
      "learning_rate": 5.255255255255255e-08,
      "loss": 0.0104,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9008,
      "eval_loss": 0.38071388006210327,
      "eval_runtime": 6.4265,
      "eval_samples_per_second": 583.519,
      "eval_steps_per_second": 9.181,
      "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
}