Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0317

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0317
File size: 3,259 Bytes 
a6eef99
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8869333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0317/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": 6.003003003003003e-05,
      "loss": 2.0279,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7581333333333333,
      "eval_loss": 0.8426274657249451,
      "eval_runtime": 10.0959,
      "eval_samples_per_second": 371.437,
      "eval_steps_per_second": 5.844,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 5.006006006006005e-05,
      "loss": 0.5344,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.836,
      "eval_loss": 0.5520927906036377,
      "eval_runtime": 10.3314,
      "eval_samples_per_second": 362.97,
      "eval_steps_per_second": 5.711,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.0700448751449585,
      "learning_rate": 4.006006006006006e-05,
      "loss": 0.2495,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8642666666666666,
      "eval_loss": 0.45188501477241516,
      "eval_runtime": 13.3636,
      "eval_samples_per_second": 280.614,
      "eval_steps_per_second": 4.415,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 10.459210395812988,
      "learning_rate": 3.0060060060060055e-05,
      "loss": 0.114,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8642666666666666,
      "eval_loss": 0.45609569549560547,
      "eval_runtime": 10.4097,
      "eval_samples_per_second": 360.242,
      "eval_steps_per_second": 5.668,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 4.869626522064209,
      "learning_rate": 2.006006006006006e-05,
      "loss": 0.0453,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8714666666666666,
      "eval_loss": 0.445248007774353,
      "eval_runtime": 10.6263,
      "eval_samples_per_second": 352.899,
      "eval_steps_per_second": 5.552,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.6050701141357422,
      "learning_rate": 1.006006006006006e-05,
      "loss": 0.0165,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8869333333333334,
      "eval_loss": 0.4271000623703003,
      "eval_runtime": 10.305,
      "eval_samples_per_second": 363.902,
      "eval_steps_per_second": 5.725,
      "step": 1998
    }
  ],
  "logging_steps": 500,
  "max_steps": 2331,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "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
}