Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0964

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0964
File size: 4,031 Bytes 
8068bb8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8829333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0964/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": 2.4323,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7114666666666667,
      "eval_loss": 1.2539396286010742,
      "eval_runtime": 6.4161,
      "eval_samples_per_second": 584.466,
      "eval_steps_per_second": 9.196,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 2.2522522522522523e-05,
      "loss": 0.9133,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8104,
      "eval_loss": 0.7315922975540161,
      "eval_runtime": 6.4599,
      "eval_samples_per_second": 580.505,
      "eval_steps_per_second": 9.133,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 17.44508171081543,
      "learning_rate": 1.8772522522522523e-05,
      "loss": 0.557,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8370666666666666,
      "eval_loss": 0.5587872266769409,
      "eval_runtime": 6.4041,
      "eval_samples_per_second": 585.566,
      "eval_steps_per_second": 9.213,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": Infinity,
      "learning_rate": 1.5033783783783786e-05,
      "loss": 0.3997,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8664,
      "eval_loss": 0.4646680951118469,
      "eval_runtime": 6.6195,
      "eval_samples_per_second": 566.506,
      "eval_steps_per_second": 8.913,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.5680192708969116,
      "learning_rate": 1.1283783783783783e-05,
      "loss": 0.2948,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8709333333333333,
      "eval_loss": 0.4444133937358856,
      "eval_runtime": 6.8445,
      "eval_samples_per_second": 547.885,
      "eval_steps_per_second": 8.62,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 21.147357940673828,
      "learning_rate": 7.533783783783783e-06,
      "loss": 0.2236,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8728,
      "eval_loss": 0.4198749363422394,
      "eval_runtime": 6.2978,
      "eval_samples_per_second": 595.444,
      "eval_steps_per_second": 9.368,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.34686973690986633,
      "learning_rate": 3.7837837837837835e-06,
      "loss": 0.1716,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8786666666666667,
      "eval_loss": 0.415376752614975,
      "eval_runtime": 6.3397,
      "eval_samples_per_second": 591.512,
      "eval_steps_per_second": 9.306,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 73.93807983398438,
      "learning_rate": 3.3783783783783786e-08,
      "loss": 0.1374,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8829333333333333,
      "eval_loss": 0.39643192291259766,
      "eval_runtime": 6.3625,
      "eval_samples_per_second": 589.388,
      "eval_steps_per_second": 9.273,
      "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
}