Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0752

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0752
File size: 3,681 Bytes 
da12554
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
 
{
  "best_metric": 0.9157333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0752/checkpoints/checkpoint-2331",
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 2331,
  "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": 9.510675611750168e-05,
      "loss": 0.9444,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8162666666666667,
      "eval_loss": 0.6093758940696716,
      "eval_runtime": 13.919,
      "eval_samples_per_second": 269.416,
      "eval_steps_per_second": 4.239,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 24.474735260009766,
      "learning_rate": 8.127974762931168e-05,
      "loss": 0.3495,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8538666666666667,
      "eval_loss": 0.5116117596626282,
      "eval_runtime": 13.6049,
      "eval_samples_per_second": 275.636,
      "eval_steps_per_second": 4.337,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.29387781023979187,
      "learning_rate": 6.125740150220697e-05,
      "loss": 0.1829,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8637333333333334,
      "eval_loss": 0.5128840208053589,
      "eval_runtime": 13.4647,
      "eval_samples_per_second": 278.506,
      "eval_steps_per_second": 4.382,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.008563895709812641,
      "learning_rate": 3.900538894462112e-05,
      "loss": 0.0896,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8749333333333333,
      "eval_loss": 0.4515041410923004,
      "eval_runtime": 13.4718,
      "eval_samples_per_second": 278.359,
      "eval_steps_per_second": 4.38,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.06152375414967537,
      "learning_rate": 1.893099394660879e-05,
      "loss": 0.0301,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9064,
      "eval_loss": 0.3964678943157196,
      "eval_runtime": 13.2432,
      "eval_samples_per_second": 283.164,
      "eval_steps_per_second": 4.455,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.12715013325214386,
      "learning_rate": 5.0101966338242764e-06,
      "loss": 0.0067,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9154666666666667,
      "eval_loss": 0.35779905319213867,
      "eval_runtime": 12.5063,
      "eval_samples_per_second": 299.85,
      "eval_steps_per_second": 4.718,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.010765562765300274,
      "learning_rate": 1.8164143966159507e-10,
      "loss": 0.0018,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9157333333333333,
      "eval_loss": 0.3583238422870636,
      "eval_runtime": 12.4531,
      "eval_samples_per_second": 301.13,
      "eval_steps_per_second": 4.738,
      "step": 2331
    }
  ],
  "logging_steps": 500,
  "max_steps": 2331,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "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": 1.153189244358144e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}