Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0267

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0267
File size: 4,450 Bytes 
3de41c3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.4266666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0267/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": Infinity,
      "learning_rate": 0.0004451117784451118,
      "loss": 3.417,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.19946666666666665,
      "eval_loss": 2.983363628387451,
      "eval_runtime": 11.3891,
      "eval_samples_per_second": 329.261,
      "eval_steps_per_second": 5.18,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 21.614505767822266,
      "learning_rate": 0.0003895562228895562,
      "loss": 2.8908,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.22826666666666667,
      "eval_loss": 2.897721290588379,
      "eval_runtime": 11.4952,
      "eval_samples_per_second": 326.224,
      "eval_steps_per_second": 5.133,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 26.5220947265625,
      "learning_rate": 0.0003340006673340007,
      "loss": 2.7153,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.2888,
      "eval_loss": 2.606062412261963,
      "eval_runtime": 11.2208,
      "eval_samples_per_second": 334.202,
      "eval_steps_per_second": 5.258,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 26.944602966308594,
      "learning_rate": 0.0002784451117784451,
      "loss": 2.5224,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.2984,
      "eval_loss": 2.5512733459472656,
      "eval_runtime": 11.3561,
      "eval_samples_per_second": 330.218,
      "eval_steps_per_second": 5.195,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 22.619873046875,
      "learning_rate": 0.00022288955622288957,
      "loss": 2.3596,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.34373333333333334,
      "eval_loss": 2.372529983520508,
      "eval_runtime": 11.4302,
      "eval_samples_per_second": 328.079,
      "eval_steps_per_second": 5.162,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 27.375268936157227,
      "learning_rate": 0.00016733400066733402,
      "loss": 2.1933,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.3794666666666667,
      "eval_loss": 2.2151029109954834,
      "eval_runtime": 11.4988,
      "eval_samples_per_second": 326.12,
      "eval_steps_per_second": 5.131,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 27.010622024536133,
      "learning_rate": 0.00011177844511177845,
      "loss": 2.0281,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.3957333333333333,
      "eval_loss": 2.154024600982666,
      "eval_runtime": 12.4819,
      "eval_samples_per_second": 300.435,
      "eval_steps_per_second": 4.727,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 23.485023498535156,
      "learning_rate": 5.622288955622289e-05,
      "loss": 1.8313,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.4208,
      "eval_loss": 2.0994207859039307,
      "eval_runtime": 11.7792,
      "eval_samples_per_second": 318.358,
      "eval_steps_per_second": 5.009,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 7.662201404571533,
      "learning_rate": 6.67334000667334e-07,
      "loss": 1.6304,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.4266666666666667,
      "eval_loss": 2.0822739601135254,
      "eval_runtime": 11.4161,
      "eval_samples_per_second": 328.484,
      "eval_steps_per_second": 5.168,
      "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
}