Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0924

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0924
File size: 4,064 Bytes 
368d503
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8949333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0924/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": 6.790177189676492e-05,
      "loss": 1.7833,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7773333333333333,
      "eval_loss": 0.8146661520004272,
      "eval_runtime": 7.1061,
      "eval_samples_per_second": 527.719,
      "eval_steps_per_second": 8.303,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 6.185866251124284e-05,
      "loss": 0.6037,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8266666666666667,
      "eval_loss": 0.608482301235199,
      "eval_runtime": 6.9418,
      "eval_samples_per_second": 540.203,
      "eval_steps_per_second": 8.499,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 14.476542472839355,
      "learning_rate": 5.2563508019062023e-05,
      "loss": 0.369,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8517333333333333,
      "eval_loss": 0.5073601603507996,
      "eval_runtime": 6.867,
      "eval_samples_per_second": 546.091,
      "eval_steps_per_second": 8.592,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 27.655790328979492,
      "learning_rate": 4.1149935250010576e-05,
      "loss": 0.234,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8642666666666666,
      "eval_loss": 0.4698965549468994,
      "eval_runtime": 6.9047,
      "eval_samples_per_second": 543.107,
      "eval_steps_per_second": 8.545,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 13.232913970947266,
      "learning_rate": 2.8994589526430138e-05,
      "loss": 0.1413,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8741333333333333,
      "eval_loss": 0.4301223158836365,
      "eval_runtime": 6.8524,
      "eval_samples_per_second": 547.251,
      "eval_steps_per_second": 8.61,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.5944477915763855,
      "learning_rate": 1.756358493638142e-05,
      "loss": 0.0809,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8925333333333333,
      "eval_loss": 0.39260703325271606,
      "eval_runtime": 6.9922,
      "eval_samples_per_second": 536.312,
      "eval_steps_per_second": 8.438,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.41176101565361023,
      "learning_rate": 8.235669337084578e-06,
      "loss": 0.0425,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8832,
      "eval_loss": 0.42353272438049316,
      "eval_runtime": 6.8667,
      "eval_samples_per_second": 546.112,
      "eval_steps_per_second": 8.592,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.872961699962616,
      "learning_rate": 2.135927015187301e-06,
      "loss": 0.0237,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8949333333333334,
      "eval_loss": 0.39834144711494446,
      "eval_runtime": 6.9134,
      "eval_samples_per_second": 542.428,
      "eval_steps_per_second": 8.534,
      "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
}