Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0176

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0176
File size: 4,030 Bytes 
462e1f6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
 
{
  "best_metric": 0.42933333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0176/checkpoints/checkpoint-2664",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 2664,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 16.663148880004883,
      "learning_rate": 0.0004382507507507508,
      "loss": 3.498,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.184,
      "eval_loss": 3.08363938331604,
      "eval_runtime": 5.9436,
      "eval_samples_per_second": 630.931,
      "eval_steps_per_second": 9.927,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 21.147462844848633,
      "learning_rate": 0.0003757507507507508,
      "loss": 2.9108,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.2304,
      "eval_loss": 2.874598503112793,
      "eval_runtime": 6.3134,
      "eval_samples_per_second": 593.974,
      "eval_steps_per_second": 9.345,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 16.027099609375,
      "learning_rate": 0.0003132507507507508,
      "loss": 2.6933,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.2696,
      "eval_loss": 2.697446346282959,
      "eval_runtime": 6.6293,
      "eval_samples_per_second": 565.674,
      "eval_steps_per_second": 8.9,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 19.708677291870117,
      "learning_rate": 0.0002507507507507508,
      "loss": 2.5053,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.32426666666666665,
      "eval_loss": 2.4639010429382324,
      "eval_runtime": 6.4518,
      "eval_samples_per_second": 581.233,
      "eval_steps_per_second": 9.145,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 14.150619506835938,
      "learning_rate": 0.00018825075075075076,
      "loss": 2.3121,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.35146666666666665,
      "eval_loss": 2.3326478004455566,
      "eval_runtime": 5.7679,
      "eval_samples_per_second": 650.153,
      "eval_steps_per_second": 10.229,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 18.873497009277344,
      "learning_rate": 0.00012575075075075076,
      "loss": 2.1274,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.3856,
      "eval_loss": 2.2203073501586914,
      "eval_runtime": 5.7848,
      "eval_samples_per_second": 648.249,
      "eval_steps_per_second": 10.199,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 26.936660766601562,
      "learning_rate": 6.325075075075074e-05,
      "loss": 1.9526,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.4224,
      "eval_loss": 2.1080636978149414,
      "eval_runtime": 5.7754,
      "eval_samples_per_second": 649.307,
      "eval_steps_per_second": 10.216,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 32.12211990356445,
      "learning_rate": 7.507507507507508e-07,
      "loss": 1.7667,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.42933333333333334,
      "eval_loss": 2.0680899620056152,
      "eval_runtime": 5.8558,
      "eval_samples_per_second": 640.39,
      "eval_steps_per_second": 10.075,
      "step": 2664
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.317930564980736e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}