Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0359

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0359
File size: 4,459 Bytes 
5fff424
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9048,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0359/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": 76.94051361083984,
      "learning_rate": 9.702037987560858e-05,
      "loss": 0.9937,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7912,
      "eval_loss": 0.6967100501060486,
      "eval_runtime": 6.7988,
      "eval_samples_per_second": 551.569,
      "eval_steps_per_second": 8.678,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 8.840310250856498e-05,
      "loss": 0.3989,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8330666666666666,
      "eval_loss": 0.5438385605812073,
      "eval_runtime": 6.9275,
      "eval_samples_per_second": 541.321,
      "eval_steps_per_second": 8.517,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.04838882386684418,
      "learning_rate": 7.513604728193609e-05,
      "loss": 0.2231,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8298666666666666,
      "eval_loss": 0.6059944033622742,
      "eval_runtime": 6.5634,
      "eval_samples_per_second": 571.351,
      "eval_steps_per_second": 8.989,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.2594028413295746,
      "learning_rate": 5.8837213784557087e-05,
      "loss": 0.126,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8594666666666667,
      "eval_loss": 0.5178276300430298,
      "eval_runtime": 6.4211,
      "eval_samples_per_second": 584.017,
      "eval_steps_per_second": 9.189,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.0016577113419771194,
      "learning_rate": 4.147248188137552e-05,
      "loss": 0.0662,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8717333333333334,
      "eval_loss": 0.5517342686653137,
      "eval_runtime": 6.5581,
      "eval_samples_per_second": 571.815,
      "eval_steps_per_second": 8.997,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 28.946643829345703,
      "learning_rate": 2.5136294516063797e-05,
      "loss": 0.0292,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8826666666666667,
      "eval_loss": 0.516573965549469,
      "eval_runtime": 6.2633,
      "eval_samples_per_second": 598.727,
      "eval_steps_per_second": 9.42,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.007138674613088369,
      "learning_rate": 1.1799036981326533e-05,
      "loss": 0.0091,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8914666666666666,
      "eval_loss": 0.4850046932697296,
      "eval_runtime": 6.3604,
      "eval_samples_per_second": 589.586,
      "eval_steps_per_second": 9.276,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.09252654761075974,
      "learning_rate": 3.0693793728105435e-06,
      "loss": 0.0017,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9021333333333333,
      "eval_loss": 0.44660866260528564,
      "eval_runtime": 6.9021,
      "eval_samples_per_second": 543.31,
      "eval_steps_per_second": 8.548,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.001264469581656158,
      "learning_rate": 2.472341277037771e-10,
      "loss": 0.001,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9048,
      "eval_loss": 0.44629785418510437,
      "eval_runtime": 6.3606,
      "eval_samples_per_second": 589.571,
      "eval_steps_per_second": 9.276,
      "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
}