Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0398

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0398
File size: 3,278 Bytes 
88b2a3a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9301333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0398/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": 6.00206995010376,
      "learning_rate": 2.886495269365963e-05,
      "loss": 0.806,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8842666666666666,
      "eval_loss": 0.4054957628250122,
      "eval_runtime": 10.3926,
      "eval_samples_per_second": 360.835,
      "eval_steps_per_second": 5.677,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 23.289579391479492,
      "learning_rate": 2.5619102456015873e-05,
      "loss": 0.1813,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8944,
      "eval_loss": 0.36277422308921814,
      "eval_runtime": 10.7803,
      "eval_samples_per_second": 347.858,
      "eval_steps_per_second": 5.473,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.461469292640686,
      "learning_rate": 2.0756590131847176e-05,
      "loss": 0.0721,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9058666666666667,
      "eval_loss": 0.32754531502723694,
      "eval_runtime": 10.4164,
      "eval_samples_per_second": 360.009,
      "eval_steps_per_second": 5.664,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.036824312061071396,
      "learning_rate": 1.5017689143724237e-05,
      "loss": 0.0351,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9152,
      "eval_loss": 0.3233625590801239,
      "eval_runtime": 10.3562,
      "eval_samples_per_second": 362.101,
      "eval_steps_per_second": 5.697,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.006594556383788586,
      "learning_rate": 9.276095143821772e-06,
      "loss": 0.0109,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9226666666666666,
      "eval_loss": 0.31796860694885254,
      "eval_runtime": 10.6715,
      "eval_samples_per_second": 351.402,
      "eval_steps_per_second": 5.529,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.039321307092905045,
      "learning_rate": 4.4059137709457125e-06,
      "loss": 0.0033,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9301333333333334,
      "eval_loss": 0.31043100357055664,
      "eval_runtime": 10.8526,
      "eval_samples_per_second": 345.54,
      "eval_steps_per_second": 5.436,
      "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
}