Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0494

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0494
File size: 4,051 Bytes 
b9ea3a8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8997333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0494/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": 8.753753753753754e-05,
      "loss": 1.5495,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7821333333333333,
      "eval_loss": 0.7489364743232727,
      "eval_runtime": 11.2669,
      "eval_samples_per_second": 332.832,
      "eval_steps_per_second": 5.237,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 7.507507507507507e-05,
      "loss": 0.5427,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8304,
      "eval_loss": 0.5455299615859985,
      "eval_runtime": 11.2038,
      "eval_samples_per_second": 334.708,
      "eval_steps_per_second": 5.266,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 6.261261261261262e-05,
      "loss": 0.3416,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8584,
      "eval_loss": 0.46928781270980835,
      "eval_runtime": 10.9912,
      "eval_samples_per_second": 341.181,
      "eval_steps_per_second": 5.368,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.7652709484100342,
      "learning_rate": 5.011261261261262e-05,
      "loss": 0.2224,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8666666666666667,
      "eval_loss": 0.43605324625968933,
      "eval_runtime": 11.3668,
      "eval_samples_per_second": 329.908,
      "eval_steps_per_second": 5.191,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.2422654926776886,
      "learning_rate": 3.7612612612612614e-05,
      "loss": 0.1331,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8858666666666667,
      "eval_loss": 0.39124882221221924,
      "eval_runtime": 11.7338,
      "eval_samples_per_second": 319.59,
      "eval_steps_per_second": 5.028,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.4413638710975647,
      "learning_rate": 2.5112612612612612e-05,
      "loss": 0.0772,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8909333333333334,
      "eval_loss": 0.3852756917476654,
      "eval_runtime": 11.8866,
      "eval_samples_per_second": 315.481,
      "eval_steps_per_second": 4.964,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.21680592000484467,
      "learning_rate": 1.2612612612612611e-05,
      "loss": 0.038,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8930666666666667,
      "eval_loss": 0.3810526728630066,
      "eval_runtime": 11.0707,
      "eval_samples_per_second": 338.733,
      "eval_steps_per_second": 5.329,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 33.79691696166992,
      "learning_rate": 1.1261261261261262e-07,
      "loss": 0.0254,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8997333333333334,
      "eval_loss": 0.37374147772789,
      "eval_runtime": 11.3398,
      "eval_samples_per_second": 330.695,
      "eval_steps_per_second": 5.203,
      "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
}