Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0399

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0399
File size: 2,837 Bytes 
362ddb7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.4461333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0399/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": 0.00024054054054054052,
      "loss": 3.3015,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.2312,
      "eval_loss": 2.8676962852478027,
      "eval_runtime": 10.4747,
      "eval_samples_per_second": 358.004,
      "eval_steps_per_second": 5.633,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 54.41494369506836,
      "learning_rate": 0.0001805405405405405,
      "loss": 2.7265,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.2981333333333333,
      "eval_loss": 2.562734842300415,
      "eval_runtime": 10.5159,
      "eval_samples_per_second": 356.604,
      "eval_steps_per_second": 5.611,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 29.150209426879883,
      "learning_rate": 0.00012054054054054053,
      "loss": 2.368,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.3584,
      "eval_loss": 2.326631784439087,
      "eval_runtime": 10.4755,
      "eval_samples_per_second": 357.979,
      "eval_steps_per_second": 5.632,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 30.750194549560547,
      "learning_rate": 6.054054054054053e-05,
      "loss": 2.0169,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.4056,
      "eval_loss": 2.1518137454986572,
      "eval_runtime": 10.9294,
      "eval_samples_per_second": 343.111,
      "eval_steps_per_second": 5.398,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 73.38581848144531,
      "learning_rate": 5.405405405405405e-07,
      "loss": 1.5825,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.4461333333333333,
      "eval_loss": 2.084540843963623,
      "eval_runtime": 10.4197,
      "eval_samples_per_second": 359.895,
      "eval_steps_per_second": 5.662,
      "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
}