Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0168

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0168
File size: 3,278 Bytes 
484f635
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.47386666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0168/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": 20.271753311157227,
      "learning_rate": 0.0002887841425059038,
      "loss": 3.356,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.23146666666666665,
      "eval_loss": 2.938288688659668,
      "eval_runtime": 11.9523,
      "eval_samples_per_second": 313.747,
      "eval_steps_per_second": 4.936,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 23.26625633239746,
      "learning_rate": 0.0002564405961135417,
      "loss": 2.7639,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.27573333333333333,
      "eval_loss": 2.6832222938537598,
      "eval_runtime": 11.974,
      "eval_samples_per_second": 313.179,
      "eval_steps_per_second": 4.927,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 19.279315948486328,
      "learning_rate": 0.0002078924338492993,
      "loss": 2.4481,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.344,
      "eval_loss": 2.4459779262542725,
      "eval_runtime": 11.9866,
      "eval_samples_per_second": 312.85,
      "eval_steps_per_second": 4.922,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 34.44410705566406,
      "learning_rate": 0.00015053067332772077,
      "loss": 2.1459,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.40346666666666664,
      "eval_loss": 2.2199318408966064,
      "eval_runtime": 12.0413,
      "eval_samples_per_second": 311.428,
      "eval_steps_per_second": 4.9,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 26.674732208251953,
      "learning_rate": 9.308812260256249e-05,
      "loss": 1.7836,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.44266666666666665,
      "eval_loss": 2.1035990715026855,
      "eval_runtime": 11.9136,
      "eval_samples_per_second": 314.766,
      "eval_steps_per_second": 4.952,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 33.97932052612305,
      "learning_rate": 4.4309889303710674e-05,
      "loss": 1.3547,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.47386666666666666,
      "eval_loss": 2.083454132080078,
      "eval_runtime": 11.8389,
      "eval_samples_per_second": 316.753,
      "eval_steps_per_second": 4.984,
      "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
}