Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0436

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0436
File size: 3,247 Bytes 
03e426f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.7685333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0436/checkpoints/checkpoint-1998",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1998,
  "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": 0.0002800215775878589,
      "loss": 3.0374,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.3512,
      "eval_loss": 2.3977603912353516,
      "eval_runtime": 5.7059,
      "eval_samples_per_second": 657.21,
      "eval_steps_per_second": 10.34,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.00022540814184580826,
      "loss": 1.8643,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5754666666666667,
      "eval_loss": 1.3894833326339722,
      "eval_runtime": 5.9488,
      "eval_samples_per_second": 630.378,
      "eval_steps_per_second": 9.918,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 0.00015070756328895485,
      "loss": 0.9853,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7005333333333333,
      "eval_loss": 1.0108407735824585,
      "eval_runtime": 6.7235,
      "eval_samples_per_second": 557.747,
      "eval_steps_per_second": 8.775,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.4446276128292084,
      "learning_rate": 7.561360219734159e-05,
      "loss": 0.4134,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7538666666666667,
      "eval_loss": 0.8418761491775513,
      "eval_runtime": 5.7055,
      "eval_samples_per_second": 657.264,
      "eval_steps_per_second": 10.341,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 5.952701568603516,
      "learning_rate": 2.0451416324810927e-05,
      "loss": 0.1048,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.7645333333333333,
      "eval_loss": 0.8070570230484009,
      "eval_runtime": 6.2501,
      "eval_samples_per_second": 599.987,
      "eval_steps_per_second": 9.44,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.39875176548957825,
      "learning_rate": 1.668828642892306e-09,
      "loss": 0.0259,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.7685333333333333,
      "eval_loss": 0.7948288321495056,
      "eval_runtime": 6.1181,
      "eval_samples_per_second": 612.932,
      "eval_steps_per_second": 9.643,
      "step": 1998
    }
  ],
  "logging_steps": 500,
  "max_steps": 1998,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}