Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0599

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0599
File size: 2,846 Bytes 
ee666d5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.45786666666666664,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0599/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": Infinity,
      "learning_rate": 0.0004003003003003003,
      "loss": 3.2941,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.17493333333333333,
      "eval_loss": 3.002009868621826,
      "eval_runtime": 6.8258,
      "eval_samples_per_second": 549.389,
      "eval_steps_per_second": 8.644,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0003006006006006006,
      "loss": 2.7278,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.28613333333333335,
      "eval_loss": 2.5787806510925293,
      "eval_runtime": 5.8255,
      "eval_samples_per_second": 643.723,
      "eval_steps_per_second": 10.128,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 12.307065963745117,
      "learning_rate": 0.00020060060060060058,
      "loss": 2.3109,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.3592,
      "eval_loss": 2.2620911598205566,
      "eval_runtime": 6.4531,
      "eval_samples_per_second": 581.112,
      "eval_steps_per_second": 9.143,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0001009009009009009,
      "loss": 1.9043,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.4149333333333333,
      "eval_loss": 2.0395491123199463,
      "eval_runtime": 5.8795,
      "eval_samples_per_second": 637.809,
      "eval_steps_per_second": 10.035,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 24.44965362548828,
      "learning_rate": 9.00900900900901e-07,
      "loss": 1.4624,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.45786666666666664,
      "eval_loss": 1.9076690673828125,
      "eval_runtime": 5.8676,
      "eval_samples_per_second": 639.101,
      "eval_steps_per_second": 10.055,
      "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
}