Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0963

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0963
File size: 3,913 Bytes 
a4b3989
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8776,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0963/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": 5e-05,
      "loss": 1.7423,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.824,
      "eval_loss": 0.6848140358924866,
      "eval_runtime": 10.8831,
      "eval_samples_per_second": 344.572,
      "eval_steps_per_second": 5.421,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 4.372657775878906,
      "learning_rate": 5e-05,
      "loss": 0.4945,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8410666666666666,
      "eval_loss": 0.5425292253494263,
      "eval_runtime": 10.7018,
      "eval_samples_per_second": 350.408,
      "eval_steps_per_second": 5.513,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 4.650074005126953,
      "learning_rate": 5e-05,
      "loss": 0.2515,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8629333333333333,
      "eval_loss": 0.44143491983413696,
      "eval_runtime": 10.6336,
      "eval_samples_per_second": 352.656,
      "eval_steps_per_second": 5.548,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.1244722455739975,
      "learning_rate": 5e-05,
      "loss": 0.148,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8629333333333333,
      "eval_loss": 0.47771361470222473,
      "eval_runtime": 11.249,
      "eval_samples_per_second": 333.363,
      "eval_steps_per_second": 5.245,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.0782694816589355,
      "learning_rate": 5e-05,
      "loss": 0.0881,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8618666666666667,
      "eval_loss": 0.4898619055747986,
      "eval_runtime": 10.0454,
      "eval_samples_per_second": 373.305,
      "eval_steps_per_second": 5.873,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.5502500534057617,
      "learning_rate": 5e-05,
      "loss": 0.0563,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8704,
      "eval_loss": 0.49286630749702454,
      "eval_runtime": 10.3578,
      "eval_samples_per_second": 362.045,
      "eval_steps_per_second": 5.696,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.03944874927401543,
      "learning_rate": 5e-05,
      "loss": 0.0487,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8661333333333333,
      "eval_loss": 0.5093781352043152,
      "eval_runtime": 10.3202,
      "eval_samples_per_second": 363.364,
      "eval_steps_per_second": 5.717,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.024426963180303574,
      "learning_rate": 5e-05,
      "loss": 0.0361,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8776,
      "eval_loss": 0.53902667760849,
      "eval_runtime": 11.63,
      "eval_samples_per_second": 322.443,
      "eval_steps_per_second": 5.073,
      "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
}