Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0853

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0853
File size: 3,659 Bytes 
0d0cbba
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.6290666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0853/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": 0.0004810825448943271,
      "loss": 3.0032,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.29786666666666667,
      "eval_loss": 2.578808307647705,
      "eval_runtime": 13.7195,
      "eval_samples_per_second": 273.334,
      "eval_steps_per_second": 4.3,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0004271931404387096,
      "loss": 2.2604,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.39413333333333334,
      "eval_loss": 2.142023801803589,
      "eval_runtime": 13.5306,
      "eval_samples_per_second": 277.15,
      "eval_steps_per_second": 4.36,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 8.582889556884766,
      "learning_rate": 0.0003462153462094779,
      "loss": 1.8326,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.47226666666666667,
      "eval_loss": 1.8428372144699097,
      "eval_runtime": 13.521,
      "eval_samples_per_second": 277.346,
      "eval_steps_per_second": 4.364,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 9.992016792297363,
      "learning_rate": 0.00025058963771413845,
      "loss": 1.466,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.516,
      "eval_loss": 1.6780189275741577,
      "eval_runtime": 13.5247,
      "eval_samples_per_second": 277.271,
      "eval_steps_per_second": 4.362,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 5.6153459548950195,
      "learning_rate": 0.00015487416222190068,
      "loss": 1.0774,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.5618666666666666,
      "eval_loss": 1.5338225364685059,
      "eval_runtime": 13.7613,
      "eval_samples_per_second": 272.504,
      "eval_steps_per_second": 4.287,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.562627375125885,
      "learning_rate": 7.36407332135117e-05,
      "loss": 0.6838,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.6133333333333333,
      "eval_loss": 1.4478487968444824,
      "eval_runtime": 13.9931,
      "eval_samples_per_second": 267.99,
      "eval_steps_per_second": 4.216,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 16.792430877685547,
      "learning_rate": 1.9256403872631112e-05,
      "loss": 0.3819,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.6290666666666667,
      "eval_loss": 1.4039924144744873,
      "eval_runtime": 13.5111,
      "eval_samples_per_second": 277.549,
      "eval_steps_per_second": 4.367,
      "step": 2331
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.153189244358144e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}