Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0770

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0770
File size: 4,347 Bytes 
5fb93ff
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.25653333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0770/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": 18.09488868713379,
      "learning_rate": 0.0005,
      "loss": 3.791,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.11573333333333333,
      "eval_loss": 3.3961968421936035,
      "eval_runtime": 12.1247,
      "eval_samples_per_second": 309.286,
      "eval_steps_per_second": 4.866,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 20.62027931213379,
      "learning_rate": 0.0005,
      "loss": 3.2466,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.16906666666666667,
      "eval_loss": 3.122330665588379,
      "eval_runtime": 11.984,
      "eval_samples_per_second": 312.916,
      "eval_steps_per_second": 4.923,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 15.040054321289062,
      "learning_rate": 0.0005,
      "loss": 3.0788,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.19413333333333332,
      "eval_loss": 3.099750518798828,
      "eval_runtime": 11.8999,
      "eval_samples_per_second": 315.13,
      "eval_steps_per_second": 4.958,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 52.033077239990234,
      "learning_rate": 0.0005,
      "loss": 2.98,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.21226666666666666,
      "eval_loss": 2.942399501800537,
      "eval_runtime": 12.0165,
      "eval_samples_per_second": 312.071,
      "eval_steps_per_second": 4.91,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 34.843788146972656,
      "learning_rate": 0.0005,
      "loss": 2.9427,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.20906666666666668,
      "eval_loss": 2.9958038330078125,
      "eval_runtime": 12.1523,
      "eval_samples_per_second": 308.585,
      "eval_steps_per_second": 4.855,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 14.597577095031738,
      "learning_rate": 0.0005,
      "loss": 2.8874,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.22106666666666666,
      "eval_loss": 2.8962862491607666,
      "eval_runtime": 11.9332,
      "eval_samples_per_second": 314.248,
      "eval_steps_per_second": 4.944,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 13.998554229736328,
      "learning_rate": 0.0005,
      "loss": 2.8492,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.23573333333333332,
      "eval_loss": 2.873903751373291,
      "eval_runtime": 11.8233,
      "eval_samples_per_second": 317.17,
      "eval_steps_per_second": 4.99,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 9.585179328918457,
      "learning_rate": 0.0005,
      "loss": 2.7568,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.248,
      "eval_loss": 2.7675232887268066,
      "eval_runtime": 12.5165,
      "eval_samples_per_second": 299.605,
      "eval_steps_per_second": 4.714,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 23.5278263092041,
      "learning_rate": 0.0005,
      "loss": 2.7131,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.25653333333333334,
      "eval_loss": 2.76081919670105,
      "eval_runtime": 12.1234,
      "eval_samples_per_second": 309.318,
      "eval_steps_per_second": 4.867,
      "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
}