Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0256

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0256
File size: 4,484 Bytes 
b805dbb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
 
{
  "best_metric": 0.9197333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0256/checkpoints/checkpoint-2997",
  "epoch": 9.0,
  "eval_steps": 500,
  "global_step": 2997,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 25.626827239990234,
      "learning_rate": 2.9100759384327822e-05,
      "loss": 0.8264,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8693333333333333,
      "eval_loss": 0.4198357164859772,
      "eval_runtime": 7.4862,
      "eval_samples_per_second": 500.923,
      "eval_steps_per_second": 7.881,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.026626428589224815,
      "learning_rate": 2.6500767323004636e-05,
      "loss": 0.2205,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8904,
      "eval_loss": 0.33937424421310425,
      "eval_runtime": 6.7389,
      "eval_samples_per_second": 556.474,
      "eval_steps_per_second": 8.755,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 7.013565540313721,
      "learning_rate": 2.25136129892785e-05,
      "loss": 0.1024,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8901333333333333,
      "eval_loss": 0.353370726108551,
      "eval_runtime": 6.7307,
      "eval_samples_per_second": 557.149,
      "eval_steps_per_second": 8.766,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.10132233798503876,
      "learning_rate": 1.7620206039927677e-05,
      "loss": 0.0517,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9008,
      "eval_loss": 0.3504127562046051,
      "eval_runtime": 7.2844,
      "eval_samples_per_second": 514.796,
      "eval_steps_per_second": 8.099,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.284123957157135,
      "learning_rate": 1.241076357203891e-05,
      "loss": 0.0227,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9042666666666667,
      "eval_loss": 0.3736843764781952,
      "eval_runtime": 6.6697,
      "eval_samples_per_second": 562.248,
      "eval_steps_per_second": 8.846,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.07902301847934723,
      "learning_rate": 7.513621230422123e-06,
      "loss": 0.0103,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9146666666666666,
      "eval_loss": 0.35899022221565247,
      "eval_runtime": 6.897,
      "eval_samples_per_second": 543.717,
      "eval_steps_per_second": 8.554,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.00526810297742486,
      "learning_rate": 3.5295725730362483e-06,
      "loss": 0.0035,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9149333333333334,
      "eval_loss": 0.35143187642097473,
      "eval_runtime": 6.7289,
      "eval_samples_per_second": 557.296,
      "eval_steps_per_second": 8.768,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.011652613058686256,
      "learning_rate": 9.153972922231291e-07,
      "loss": 0.0017,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9146666666666666,
      "eval_loss": 0.3580148220062256,
      "eval_runtime": 6.9198,
      "eval_samples_per_second": 541.926,
      "eval_steps_per_second": 8.526,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.020102016627788544,
      "learning_rate": 3.2964565453985627e-11,
      "loss": 0.001,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9197333333333333,
      "eval_loss": 0.34882256388664246,
      "eval_runtime": 6.7187,
      "eval_samples_per_second": 558.144,
      "eval_steps_per_second": 8.781,
      "step": 2997
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.482671885603328e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}