Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0837

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0837
File size: 3,171 Bytes 
3c44bd9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8845333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0837/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": 34.62366485595703,
      "learning_rate": 5e-05,
      "loss": 0.7937,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8448,
      "eval_loss": 0.5024492740631104,
      "eval_runtime": 10.9962,
      "eval_samples_per_second": 341.028,
      "eval_steps_per_second": 5.366,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.09152399003505707,
      "learning_rate": 5e-05,
      "loss": 0.2514,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8821333333333333,
      "eval_loss": 0.4257860779762268,
      "eval_runtime": 10.9815,
      "eval_samples_per_second": 341.485,
      "eval_steps_per_second": 5.373,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.7688146829605103,
      "learning_rate": 5e-05,
      "loss": 0.1407,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8744,
      "eval_loss": 0.441001296043396,
      "eval_runtime": 11.5372,
      "eval_samples_per_second": 325.036,
      "eval_steps_per_second": 5.114,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 24.606260299682617,
      "learning_rate": 5e-05,
      "loss": 0.0987,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8794666666666666,
      "eval_loss": 0.49058687686920166,
      "eval_runtime": 10.6878,
      "eval_samples_per_second": 350.868,
      "eval_steps_per_second": 5.52,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.22695006430149078,
      "learning_rate": 5e-05,
      "loss": 0.0844,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8834666666666666,
      "eval_loss": 0.4685409367084503,
      "eval_runtime": 11.0395,
      "eval_samples_per_second": 339.688,
      "eval_steps_per_second": 5.344,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 23.25039291381836,
      "learning_rate": 5e-05,
      "loss": 0.0668,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8845333333333333,
      "eval_loss": 0.4939088523387909,
      "eval_runtime": 10.742,
      "eval_samples_per_second": 349.097,
      "eval_steps_per_second": 5.492,
      "step": 1998
    }
  ],
  "logging_steps": 500,
  "max_steps": 2997,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "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
}