Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0448

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0448
File size: 4,489 Bytes 
abe5ed8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9229333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0448/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": 112.6886215209961,
      "learning_rate": 8.895562228895563e-05,
      "loss": 0.858,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8288,
      "eval_loss": 0.5697919726371765,
      "eval_runtime": 7.2796,
      "eval_samples_per_second": 515.141,
      "eval_steps_per_second": 8.105,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.5157313346862793,
      "learning_rate": 7.784451117784451e-05,
      "loss": 0.3204,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8493333333333334,
      "eval_loss": 0.5127115845680237,
      "eval_runtime": 6.2578,
      "eval_samples_per_second": 599.253,
      "eval_steps_per_second": 9.428,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 3.539602041244507,
      "learning_rate": 6.67334000667334e-05,
      "loss": 0.1804,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8693333333333333,
      "eval_loss": 0.46511217951774597,
      "eval_runtime": 6.6029,
      "eval_samples_per_second": 567.936,
      "eval_steps_per_second": 8.936,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.32112807035446167,
      "learning_rate": 5.562228895562229e-05,
      "loss": 0.1053,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8866666666666667,
      "eval_loss": 0.4433543086051941,
      "eval_runtime": 6.0976,
      "eval_samples_per_second": 615.0,
      "eval_steps_per_second": 9.676,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.5024523735046387,
      "learning_rate": 4.451117784451118e-05,
      "loss": 0.0646,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8885333333333333,
      "eval_loss": 0.4491003155708313,
      "eval_runtime": 6.3804,
      "eval_samples_per_second": 587.736,
      "eval_steps_per_second": 9.247,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.001149059971794486,
      "learning_rate": 3.340006673340007e-05,
      "loss": 0.0377,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9093333333333333,
      "eval_loss": 0.3750953674316406,
      "eval_runtime": 6.1733,
      "eval_samples_per_second": 607.452,
      "eval_steps_per_second": 9.557,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.10667067766189575,
      "learning_rate": 2.2288955622288957e-05,
      "loss": 0.0136,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9106666666666666,
      "eval_loss": 0.3817509114742279,
      "eval_runtime": 6.3655,
      "eval_samples_per_second": 589.109,
      "eval_steps_per_second": 9.269,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.013708073645830154,
      "learning_rate": 1.1177844511177845e-05,
      "loss": 0.0046,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9157333333333333,
      "eval_loss": 0.34521010518074036,
      "eval_runtime": 6.1541,
      "eval_samples_per_second": 609.353,
      "eval_steps_per_second": 9.587,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.06194830313324928,
      "learning_rate": 6.673340006673341e-08,
      "loss": 0.0022,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9229333333333334,
      "eval_loss": 0.3211786448955536,
      "eval_runtime": 6.2828,
      "eval_samples_per_second": 596.866,
      "eval_steps_per_second": 9.391,
      "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
}