Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0467

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0467
File size: 3,630 Bytes 
57fbb7b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9088,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0467/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": 9.62613808353013e-05,
      "loss": 1.0488,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.804,
      "eval_loss": 0.6343722939491272,
      "eval_runtime": 6.4776,
      "eval_samples_per_second": 578.914,
      "eval_steps_per_second": 9.108,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 22.823558807373047,
      "learning_rate": 8.548019870451392e-05,
      "loss": 0.4149,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8410666666666666,
      "eval_loss": 0.5299203991889954,
      "eval_runtime": 6.4525,
      "eval_samples_per_second": 581.167,
      "eval_steps_per_second": 9.144,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.6662688851356506,
      "learning_rate": 6.929747794976645e-05,
      "loss": 0.2407,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8272,
      "eval_loss": 0.6385272741317749,
      "eval_runtime": 6.1601,
      "eval_samples_per_second": 608.761,
      "eval_steps_per_second": 9.578,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.00941783282905817,
      "learning_rate": 5.0176891109240266e-05,
      "loss": 0.1339,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8706666666666667,
      "eval_loss": 0.48646289110183716,
      "eval_runtime": 6.0257,
      "eval_samples_per_second": 622.331,
      "eval_steps_per_second": 9.791,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.0006334611680358648,
      "learning_rate": 3.1029374200854165e-05,
      "loss": 0.0745,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8829333333333333,
      "eval_loss": 0.4897848963737488,
      "eval_runtime": 5.9475,
      "eval_samples_per_second": 630.521,
      "eval_steps_per_second": 9.92,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.45204615592956543,
      "learning_rate": 1.4769963101236895e-05,
      "loss": 0.0306,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8896,
      "eval_loss": 0.4286149740219116,
      "eval_runtime": 6.4016,
      "eval_samples_per_second": 585.795,
      "eval_steps_per_second": 9.217,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.0018683582311496139,
      "learning_rate": 3.87400575837657e-06,
      "loss": 0.0076,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9088,
      "eval_loss": 0.36678001284599304,
      "eval_runtime": 6.4073,
      "eval_samples_per_second": 585.274,
      "eval_steps_per_second": 9.208,
      "step": 2331
    }
  ],
  "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": 1.153189244358144e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}