Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0975

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0975
File size: 4,447 Bytes 
a58e207
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9490666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0975/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": 2.6686686686686688e-05,
      "loss": 0.7672,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9037333333333334,
      "eval_loss": 0.297977089881897,
      "eval_runtime": 9.0136,
      "eval_samples_per_second": 416.038,
      "eval_steps_per_second": 6.546,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 7.636357307434082,
      "learning_rate": 2.3353353353353354e-05,
      "loss": 0.1755,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9176,
      "eval_loss": 0.2618497908115387,
      "eval_runtime": 7.0785,
      "eval_samples_per_second": 529.777,
      "eval_steps_per_second": 8.335,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.03292256221175194,
      "learning_rate": 2.002002002002002e-05,
      "loss": 0.0695,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9282666666666667,
      "eval_loss": 0.24809055030345917,
      "eval_runtime": 7.7463,
      "eval_samples_per_second": 484.1,
      "eval_steps_per_second": 7.617,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.4853302836418152,
      "learning_rate": 1.668668668668669e-05,
      "loss": 0.0313,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9290666666666667,
      "eval_loss": 0.2691165804862976,
      "eval_runtime": 7.0959,
      "eval_samples_per_second": 528.476,
      "eval_steps_per_second": 8.315,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.11609149724245071,
      "learning_rate": 1.3353353353353355e-05,
      "loss": 0.0182,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9344,
      "eval_loss": 0.2527104914188385,
      "eval_runtime": 6.9702,
      "eval_samples_per_second": 538.004,
      "eval_steps_per_second": 8.465,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.026668408885598183,
      "learning_rate": 1.002002002002002e-05,
      "loss": 0.0088,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9402666666666667,
      "eval_loss": 0.2450830340385437,
      "eval_runtime": 6.9578,
      "eval_samples_per_second": 538.963,
      "eval_steps_per_second": 8.48,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.06649462878704071,
      "learning_rate": 6.686686686686687e-06,
      "loss": 0.0031,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.944,
      "eval_loss": 0.2337694615125656,
      "eval_runtime": 6.5795,
      "eval_samples_per_second": 569.949,
      "eval_steps_per_second": 8.967,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.0004330733499955386,
      "learning_rate": 3.353353353353354e-06,
      "loss": 0.0016,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9456,
      "eval_loss": 0.22349531948566437,
      "eval_runtime": 6.6516,
      "eval_samples_per_second": 563.772,
      "eval_steps_per_second": 8.87,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.0026285031344741583,
      "learning_rate": 2.002002002002002e-08,
      "loss": 0.0008,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9490666666666666,
      "eval_loss": 0.2249515950679779,
      "eval_runtime": 6.4458,
      "eval_samples_per_second": 581.774,
      "eval_steps_per_second": 9.153,
      "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
}