Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0741

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0741
File size: 2,860 Bytes 
b322837
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.8853333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0741/checkpoints/checkpoint-1665",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1665,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 2.8458213806152344,
      "learning_rate": 0.0002713525491562421,
      "loss": 1.9176,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7330666666666666,
      "eval_loss": 0.9014183878898621,
      "eval_runtime": 5.8073,
      "eval_samples_per_second": 645.736,
      "eval_steps_per_second": 10.16,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.3794153928756714,
      "learning_rate": 0.0001963525491562421,
      "loss": 0.585,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.796,
      "eval_loss": 0.6807525753974915,
      "eval_runtime": 5.7602,
      "eval_samples_per_second": 651.014,
      "eval_steps_per_second": 10.243,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.12393927574157715,
      "learning_rate": 0.0001036474508437579,
      "loss": 0.2215,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8530666666666666,
      "eval_loss": 0.4846848249435425,
      "eval_runtime": 5.7371,
      "eval_samples_per_second": 653.638,
      "eval_steps_per_second": 10.284,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.03465700522065163,
      "learning_rate": 2.8647450843757897e-05,
      "loss": 0.0495,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8786666666666667,
      "eval_loss": 0.4320946931838989,
      "eval_runtime": 5.7921,
      "eval_samples_per_second": 647.429,
      "eval_steps_per_second": 10.186,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.04144052416086197,
      "learning_rate": 0.0,
      "loss": 0.0078,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8853333333333333,
      "eval_loss": 0.40357688069343567,
      "eval_runtime": 5.7518,
      "eval_samples_per_second": 651.968,
      "eval_steps_per_second": 10.258,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 1665,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}