Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0201

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0201
File size: 3,248 Bytes 
cc8eb7f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9069333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0201/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": 5.09152364730835,
      "learning_rate": 4.665063509461097e-05,
      "loss": 1.718,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7965333333333333,
      "eval_loss": 0.7528939247131348,
      "eval_runtime": 12.3979,
      "eval_samples_per_second": 302.47,
      "eval_steps_per_second": 4.759,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.6822611093521118,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.4922,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8677333333333334,
      "eval_loss": 0.46462807059288025,
      "eval_runtime": 12.4352,
      "eval_samples_per_second": 301.563,
      "eval_steps_per_second": 4.745,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 7.081845760345459,
      "learning_rate": 2.5e-05,
      "loss": 0.269,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.884,
      "eval_loss": 0.38520702719688416,
      "eval_runtime": 12.2497,
      "eval_samples_per_second": 306.129,
      "eval_steps_per_second": 4.816,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 4.163509368896484,
      "learning_rate": 1.2500000000000006e-05,
      "loss": 0.1518,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8989333333333334,
      "eval_loss": 0.3326055407524109,
      "eval_runtime": 12.3582,
      "eval_samples_per_second": 303.442,
      "eval_steps_per_second": 4.774,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.9003303050994873,
      "learning_rate": 3.3493649053890326e-06,
      "loss": 0.0829,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9042666666666667,
      "eval_loss": 0.31168699264526367,
      "eval_runtime": 12.4888,
      "eval_samples_per_second": 300.269,
      "eval_steps_per_second": 4.724,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.1567180156707764,
      "learning_rate": 0.0,
      "loss": 0.0541,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9069333333333334,
      "eval_loss": 0.30885618925094604,
      "eval_runtime": 12.6405,
      "eval_samples_per_second": 296.664,
      "eval_steps_per_second": 4.668,
      "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
}