Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0004

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0004
File size: 3,247 Bytes 
2d48b55
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.5253333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0004/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": 44.079341888427734,
      "learning_rate": 0.0002506006006006006,
      "loss": 3.1807,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.272,
      "eval_loss": 2.7126667499542236,
      "eval_runtime": 5.7594,
      "eval_samples_per_second": 651.115,
      "eval_steps_per_second": 10.244,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 57.76839828491211,
      "learning_rate": 0.00020060060060060058,
      "loss": 2.4839,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.3504,
      "eval_loss": 2.367837429046631,
      "eval_runtime": 5.964,
      "eval_samples_per_second": 628.771,
      "eval_steps_per_second": 9.893,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 36.21134567260742,
      "learning_rate": 0.00015060060060060059,
      "loss": 2.1762,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.4189333333333333,
      "eval_loss": 2.135026216506958,
      "eval_runtime": 6.1879,
      "eval_samples_per_second": 606.022,
      "eval_steps_per_second": 9.535,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 37.509727478027344,
      "learning_rate": 0.00010060060060060059,
      "loss": 1.9045,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.4592,
      "eval_loss": 1.9614495038986206,
      "eval_runtime": 5.9492,
      "eval_samples_per_second": 630.34,
      "eval_steps_per_second": 9.917,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 37.03412628173828,
      "learning_rate": 5.0600600600600595e-05,
      "loss": 1.6289,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.49306666666666665,
      "eval_loss": 1.8140467405319214,
      "eval_runtime": 5.8639,
      "eval_samples_per_second": 639.504,
      "eval_steps_per_second": 10.062,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 2.788090229034424,
      "learning_rate": 6.006006006006005e-07,
      "loss": 1.3446,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.5253333333333333,
      "eval_loss": 1.7320013046264648,
      "eval_runtime": 6.2654,
      "eval_samples_per_second": 598.53,
      "eval_steps_per_second": 9.417,
      "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
}