Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0086

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0086
File size: 4,475 Bytes 
5348114
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0086/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": 17.78867530822754,
      "learning_rate": 8.731834188804772e-05,
      "loss": 0.8802,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8189333333333333,
      "eval_loss": 0.5798799395561218,
      "eval_runtime": 10.8993,
      "eval_samples_per_second": 344.06,
      "eval_steps_per_second": 5.413,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.3221278190612793,
      "learning_rate": 7.953256608588366e-05,
      "loss": 0.3227,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8293333333333334,
      "eval_loss": 0.5555654168128967,
      "eval_runtime": 10.6686,
      "eval_samples_per_second": 351.5,
      "eval_steps_per_second": 5.53,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.11046082526445389,
      "learning_rate": 6.758165316736547e-05,
      "loss": 0.176,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8458666666666667,
      "eval_loss": 0.5522292852401733,
      "eval_runtime": 11.6414,
      "eval_samples_per_second": 322.125,
      "eval_steps_per_second": 5.068,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.043449465185403824,
      "learning_rate": 5.2907059607156464e-05,
      "loss": 0.0986,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8584,
      "eval_loss": 0.5313470959663391,
      "eval_runtime": 10.8368,
      "eval_samples_per_second": 346.042,
      "eval_steps_per_second": 5.444,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.003326371544972062,
      "learning_rate": 3.727875796255304e-05,
      "loss": 0.0482,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8778666666666667,
      "eval_loss": 0.5179239511489868,
      "eval_runtime": 10.8037,
      "eval_samples_per_second": 347.103,
      "eval_steps_per_second": 5.461,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.002493133768439293,
      "learning_rate": 2.258175206106183e-05,
      "loss": 0.0194,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8882666666666666,
      "eval_loss": 0.4742130935192108,
      "eval_runtime": 10.7475,
      "eval_samples_per_second": 348.918,
      "eval_steps_per_second": 5.49,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.0005630390369333327,
      "learning_rate": 1.0588717719108745e-05,
      "loss": 0.0046,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8949333333333334,
      "eval_loss": 0.46587762236595154,
      "eval_runtime": 10.7204,
      "eval_samples_per_second": 349.801,
      "eval_steps_per_second": 5.504,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 6.117782322689891e-05,
      "learning_rate": 2.7461918766693875e-06,
      "loss": 0.0015,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8989333333333334,
      "eval_loss": 0.4493691325187683,
      "eval_runtime": 10.6214,
      "eval_samples_per_second": 353.061,
      "eval_steps_per_second": 5.555,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.004379989113658667,
      "learning_rate": 9.889369636195689e-11,
      "loss": 0.0006,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9,
      "eval_loss": 0.4380263686180115,
      "eval_runtime": 10.6863,
      "eval_samples_per_second": 350.918,
      "eval_steps_per_second": 5.521,
      "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
}