Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0811

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0811
File size: 4,445 Bytes 
49cd397
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.932,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0811/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": 2.9100759384327822e-05,
      "loss": 0.7647,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8864,
      "eval_loss": 0.36436596512794495,
      "eval_runtime": 10.4616,
      "eval_samples_per_second": 358.453,
      "eval_steps_per_second": 5.64,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 13.664288520812988,
      "learning_rate": 2.6500767323004636e-05,
      "loss": 0.1494,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9082666666666667,
      "eval_loss": 0.31151270866394043,
      "eval_runtime": 10.2837,
      "eval_samples_per_second": 364.654,
      "eval_steps_per_second": 5.737,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.14009758830070496,
      "learning_rate": 2.25136129892785e-05,
      "loss": 0.0517,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9010666666666667,
      "eval_loss": 0.3600241541862488,
      "eval_runtime": 10.1993,
      "eval_samples_per_second": 367.673,
      "eval_steps_per_second": 5.785,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.40053290128707886,
      "learning_rate": 1.7620206039927677e-05,
      "loss": 0.0208,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9170666666666667,
      "eval_loss": 0.3532707691192627,
      "eval_runtime": 10.5697,
      "eval_samples_per_second": 354.789,
      "eval_steps_per_second": 5.582,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.08507975190877914,
      "learning_rate": 1.241076357203891e-05,
      "loss": 0.005,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9234666666666667,
      "eval_loss": 0.3390617072582245,
      "eval_runtime": 10.5911,
      "eval_samples_per_second": 354.072,
      "eval_steps_per_second": 5.571,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.0016211767215281725,
      "learning_rate": 7.513621230422123e-06,
      "loss": 0.0014,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9264,
      "eval_loss": 0.3204335868358612,
      "eval_runtime": 10.0429,
      "eval_samples_per_second": 373.399,
      "eval_steps_per_second": 5.875,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.11859909445047379,
      "learning_rate": 3.519446655599853e-06,
      "loss": 0.0006,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9312,
      "eval_loss": 0.3222728371620178,
      "eval_runtime": 11.5388,
      "eval_samples_per_second": 324.991,
      "eval_steps_per_second": 5.113,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.13385862112045288,
      "learning_rate": 9.099962490342784e-07,
      "loss": 0.0002,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9317333333333333,
      "eval_loss": 0.3225942850112915,
      "eval_runtime": 10.3254,
      "eval_samples_per_second": 363.181,
      "eval_steps_per_second": 5.714,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.003533352166414261,
      "learning_rate": 8.24114362751871e-12,
      "loss": 0.0002,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.932,
      "eval_loss": 0.32344210147857666,
      "eval_runtime": 10.3802,
      "eval_samples_per_second": 361.266,
      "eval_steps_per_second": 5.684,
      "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
}