Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0224

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0224
File size: 3,281 Bytes 
9f025cd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9010666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0224/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": 9.621650897886543e-05,
      "loss": 1.7262,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7845333333333333,
      "eval_loss": 0.7970544695854187,
      "eval_runtime": 12.4694,
      "eval_samples_per_second": 300.737,
      "eval_steps_per_second": 4.732,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.189880132675171,
      "learning_rate": 8.539700818671957e-05,
      "loss": 0.569,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8194666666666667,
      "eval_loss": 0.635564386844635,
      "eval_runtime": 11.2398,
      "eval_samples_per_second": 333.637,
      "eval_steps_per_second": 5.249,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 16.50010108947754,
      "learning_rate": 6.918863377282392e-05,
      "loss": 0.3539,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8618666666666667,
      "eval_loss": 0.4697021543979645,
      "eval_runtime": 11.2844,
      "eval_samples_per_second": 332.317,
      "eval_steps_per_second": 5.228,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.7012445330619812,
      "learning_rate": 5.005896381241413e-05,
      "loss": 0.2033,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8770666666666667,
      "eval_loss": 0.4208700656890869,
      "eval_runtime": 11.2638,
      "eval_samples_per_second": 332.926,
      "eval_steps_per_second": 5.238,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.07219620048999786,
      "learning_rate": 3.0920317146072576e-05,
      "loss": 0.1105,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8866666666666667,
      "eval_loss": 0.4118160903453827,
      "eval_runtime": 11.1994,
      "eval_samples_per_second": 334.839,
      "eval_steps_per_second": 5.268,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 7.919136047363281,
      "learning_rate": 1.4686379236485708e-05,
      "loss": 0.0551,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9010666666666667,
      "eval_loss": 0.3738054633140564,
      "eval_runtime": 11.1306,
      "eval_samples_per_second": 336.91,
      "eval_steps_per_second": 5.301,
      "step": 1998
    }
  ],
  "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": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}