Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0316

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0316
File size: 3,260 Bytes 
93134e1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.5826666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0316/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": 0.00041691691691691694,
      "loss": 3.1707,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.2632,
      "eval_loss": 2.7203543186187744,
      "eval_runtime": 12.0814,
      "eval_samples_per_second": 310.395,
      "eval_steps_per_second": 4.884,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.00033383383383383386,
      "loss": 2.5127,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.37706666666666666,
      "eval_loss": 2.239413261413574,
      "eval_runtime": 10.9375,
      "eval_samples_per_second": 342.857,
      "eval_steps_per_second": 5.394,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 10.975059509277344,
      "learning_rate": 0.0002505005005005005,
      "loss": 2.0425,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.4437333333333333,
      "eval_loss": 2.006087303161621,
      "eval_runtime": 11.2448,
      "eval_samples_per_second": 333.488,
      "eval_steps_per_second": 5.247,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 16.34186553955078,
      "learning_rate": 0.00016716716716716717,
      "loss": 1.6223,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.4938666666666667,
      "eval_loss": 1.7571539878845215,
      "eval_runtime": 10.8487,
      "eval_samples_per_second": 345.664,
      "eval_steps_per_second": 5.438,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 17.104764938354492,
      "learning_rate": 8.383383383383383e-05,
      "loss": 1.1689,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.5565333333333333,
      "eval_loss": 1.5550533533096313,
      "eval_runtime": 12.0067,
      "eval_samples_per_second": 312.325,
      "eval_steps_per_second": 4.914,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 3.469691038131714,
      "learning_rate": 5.005005005005005e-07,
      "loss": 0.705,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.5826666666666667,
      "eval_loss": 1.5131789445877075,
      "eval_runtime": 11.1385,
      "eval_samples_per_second": 336.669,
      "eval_steps_per_second": 5.297,
      "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
}