Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0090

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0090
File size: 4,285 Bytes 
5a9329c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8677333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0090/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": 39.74134826660156,
      "learning_rate": 5e-05,
      "loss": 0.8577,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8464,
      "eval_loss": 0.5095455646514893,
      "eval_runtime": 11.8332,
      "eval_samples_per_second": 316.904,
      "eval_steps_per_second": 4.986,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 5e-05,
      "loss": 0.2735,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8672,
      "eval_loss": 0.44607338309288025,
      "eval_runtime": 11.5249,
      "eval_samples_per_second": 325.384,
      "eval_steps_per_second": 5.119,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.489764928817749,
      "learning_rate": 5e-05,
      "loss": 0.1606,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.864,
      "eval_loss": 0.4802369177341461,
      "eval_runtime": 11.8004,
      "eval_samples_per_second": 317.786,
      "eval_steps_per_second": 5.0,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 42.65632629394531,
      "learning_rate": 5e-05,
      "loss": 0.1131,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8568,
      "eval_loss": 0.5703438520431519,
      "eval_runtime": 10.9548,
      "eval_samples_per_second": 342.315,
      "eval_steps_per_second": 5.386,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.03637354448437691,
      "learning_rate": 5e-05,
      "loss": 0.0935,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8674666666666667,
      "eval_loss": 0.5531145334243774,
      "eval_runtime": 10.8986,
      "eval_samples_per_second": 344.08,
      "eval_steps_per_second": 5.414,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.0605844222009182,
      "learning_rate": 5e-05,
      "loss": 0.0803,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8621333333333333,
      "eval_loss": 0.6027858257293701,
      "eval_runtime": 10.9835,
      "eval_samples_per_second": 341.42,
      "eval_steps_per_second": 5.372,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 1.286474347114563,
      "learning_rate": 5e-05,
      "loss": 0.0697,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8602666666666666,
      "eval_loss": 0.5601938366889954,
      "eval_runtime": 11.0202,
      "eval_samples_per_second": 340.284,
      "eval_steps_per_second": 5.354,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 10.402969360351562,
      "learning_rate": 5e-05,
      "loss": 0.0571,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8656,
      "eval_loss": 0.5944740772247314,
      "eval_runtime": 11.8169,
      "eval_samples_per_second": 317.343,
      "eval_steps_per_second": 4.993,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.09439128637313843,
      "learning_rate": 5e-05,
      "loss": 0.0611,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.8677333333333334,
      "eval_loss": 0.5828838348388672,
      "eval_runtime": 10.9317,
      "eval_samples_per_second": 343.038,
      "eval_steps_per_second": 5.397,
      "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
}