Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0779

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0779
File size: 4,495 Bytes 
fbe42ad
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.40453333333333336,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0779/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": 17.57228660583496,
      "learning_rate": 0.00048519088401615274,
      "loss": 3.4703,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.18666666666666668,
      "eval_loss": 3.0453500747680664,
      "eval_runtime": 11.1833,
      "eval_samples_per_second": 335.323,
      "eval_steps_per_second": 5.276,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 17.13241195678711,
      "learning_rate": 0.0004420155125428249,
      "loss": 2.9464,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.22453333333333333,
      "eval_loss": 2.8640048503875732,
      "eval_runtime": 11.0446,
      "eval_samples_per_second": 339.532,
      "eval_steps_per_second": 5.342,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 16.1562557220459,
      "learning_rate": 0.00037568023640968044,
      "loss": 2.7554,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.24266666666666667,
      "eval_loss": 2.771890640258789,
      "eval_runtime": 11.0091,
      "eval_samples_per_second": 340.627,
      "eval_steps_per_second": 5.359,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 12.122749328613281,
      "learning_rate": 0.00029418606892278544,
      "loss": 2.5659,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.28026666666666666,
      "eval_loss": 2.6315364837646484,
      "eval_runtime": 10.8308,
      "eval_samples_per_second": 346.234,
      "eval_steps_per_second": 5.447,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 22.77225685119629,
      "learning_rate": 0.0002073624094068776,
      "loss": 2.4043,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.32293333333333335,
      "eval_loss": 2.4572322368621826,
      "eval_runtime": 11.0614,
      "eval_samples_per_second": 339.016,
      "eval_steps_per_second": 5.334,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 16.535472869873047,
      "learning_rate": 0.00012568147258031897,
      "loss": 2.2037,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.3528,
      "eval_loss": 2.3550593852996826,
      "eval_runtime": 10.929,
      "eval_samples_per_second": 343.123,
      "eval_steps_per_second": 5.398,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 15.841681480407715,
      "learning_rate": 5.899518490663266e-05,
      "loss": 2.0058,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.3874666666666667,
      "eval_loss": 2.2249364852905273,
      "eval_runtime": 10.9031,
      "eval_samples_per_second": 343.938,
      "eval_steps_per_second": 5.411,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 15.18927001953125,
      "learning_rate": 1.534689686405272e-05,
      "loss": 1.8444,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.39866666666666667,
      "eval_loss": 2.2154488563537598,
      "eval_runtime": 10.7521,
      "eval_samples_per_second": 348.768,
      "eval_steps_per_second": 5.487,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 6.721107006072998,
      "learning_rate": 1.2361706385188854e-09,
      "loss": 1.7252,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.40453333333333336,
      "eval_loss": 2.229093313217163,
      "eval_runtime": 11.2377,
      "eval_samples_per_second": 333.697,
      "eval_steps_per_second": 5.25,
      "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
}