Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0206

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0206
File size: 3,934 Bytes 
bb0760c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.5373333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0206/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": 0.0005,
      "loss": 3.1909,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.25226666666666664,
      "eval_loss": 2.7434237003326416,
      "eval_runtime": 5.8914,
      "eval_samples_per_second": 636.518,
      "eval_steps_per_second": 10.015,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0005,
      "loss": 2.5719,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.35306666666666664,
      "eval_loss": 2.314851999282837,
      "eval_runtime": 5.8485,
      "eval_samples_per_second": 641.192,
      "eval_steps_per_second": 10.088,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 10.6204195022583,
      "learning_rate": 0.0005,
      "loss": 2.1673,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.4090666666666667,
      "eval_loss": 2.105984687805176,
      "eval_runtime": 5.819,
      "eval_samples_per_second": 644.441,
      "eval_steps_per_second": 10.139,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0005,
      "loss": 1.8914,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.44853333333333334,
      "eval_loss": 1.9323203563690186,
      "eval_runtime": 5.784,
      "eval_samples_per_second": 648.341,
      "eval_steps_per_second": 10.201,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 8.075751304626465,
      "learning_rate": 0.0005,
      "loss": 1.6446,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.47333333333333333,
      "eval_loss": 1.8710825443267822,
      "eval_runtime": 5.814,
      "eval_samples_per_second": 644.994,
      "eval_steps_per_second": 10.148,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 13.410477638244629,
      "learning_rate": 0.0005,
      "loss": 1.4368,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.5005333333333334,
      "eval_loss": 1.7847108840942383,
      "eval_runtime": 5.8127,
      "eval_samples_per_second": 645.143,
      "eval_steps_per_second": 10.15,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 8.278074264526367,
      "learning_rate": 0.0005,
      "loss": 1.2356,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.5216,
      "eval_loss": 1.7014422416687012,
      "eval_runtime": 5.8234,
      "eval_samples_per_second": 643.957,
      "eval_steps_per_second": 10.132,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 12.110952377319336,
      "learning_rate": 0.0005,
      "loss": 1.0351,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.5373333333333333,
      "eval_loss": 1.6904323101043701,
      "eval_runtime": 6.1221,
      "eval_samples_per_second": 612.534,
      "eval_steps_per_second": 9.637,
      "step": 2664
    }
  ],
  "logging_steps": 500,
  "max_steps": 2997,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.317930564980736e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}