Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0253

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0253
File size: 3,647 Bytes 
1d92c40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.8722666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0253/checkpoints/checkpoint-2331",
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 2331,
  "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": 0.00025727155727155724,
      "loss": 2.0918,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.672,
      "eval_loss": 1.125277042388916,
      "eval_runtime": 7.6522,
      "eval_samples_per_second": 490.053,
      "eval_steps_per_second": 7.71,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0002145431145431145,
      "loss": 0.7694,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7762666666666667,
      "eval_loss": 0.7675689458847046,
      "eval_runtime": 7.192,
      "eval_samples_per_second": 521.412,
      "eval_steps_per_second": 8.204,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.2432502657175064,
      "learning_rate": 0.00017168597168597168,
      "loss": 0.42,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8213333333333334,
      "eval_loss": 0.6267414093017578,
      "eval_runtime": 7.2462,
      "eval_samples_per_second": 517.511,
      "eval_steps_per_second": 8.142,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.04791967198252678,
      "learning_rate": 0.0001288288288288288,
      "loss": 0.2123,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8117333333333333,
      "eval_loss": 0.6895110011100769,
      "eval_runtime": 7.2578,
      "eval_samples_per_second": 516.683,
      "eval_steps_per_second": 8.129,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.398215651512146,
      "learning_rate": 8.597168597168596e-05,
      "loss": 0.1018,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8496,
      "eval_loss": 0.578416645526886,
      "eval_runtime": 6.7473,
      "eval_samples_per_second": 555.776,
      "eval_steps_per_second": 8.744,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.015443765558302402,
      "learning_rate": 4.311454311454311e-05,
      "loss": 0.0385,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8642666666666666,
      "eval_loss": 0.5297573208808899,
      "eval_runtime": 7.1243,
      "eval_samples_per_second": 526.368,
      "eval_steps_per_second": 8.282,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.010387449525296688,
      "learning_rate": 2.5740025740025737e-07,
      "loss": 0.0121,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8722666666666666,
      "eval_loss": 0.5131955146789551,
      "eval_runtime": 8.3389,
      "eval_samples_per_second": 449.701,
      "eval_steps_per_second": 7.075,
      "step": 2331
    }
  ],
  "logging_steps": 500,
  "max_steps": 2331,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "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": 1.153189244358144e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}