Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0223

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0223
File size: 4,433 Bytes
311de5d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.4784,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0223/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": 0.0002911145304096916,
      "loss": 3.3249,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.21013333333333334,
      "eval_loss": 2.9632043838500977,
      "eval_runtime": 7.0685,
      "eval_samples_per_second": 530.525,
      "eval_steps_per_second": 8.347,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 19.11616325378418,
      "learning_rate": 0.00026520930752569493,
      "loss": 2.7775,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.2936,
      "eval_loss": 2.5994362831115723,
      "eval_runtime": 8.0473,
      "eval_samples_per_second": 465.997,
      "eval_steps_per_second": 7.332,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 26.806764602661133,
      "learning_rate": 0.00022540814184580826,
      "loss": 2.499,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.3218666666666667,
      "eval_loss": 2.441415309906006,
      "eval_runtime": 8.7459,
      "eval_samples_per_second": 428.773,
      "eval_steps_per_second": 6.746,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 23.459814071655273,
      "learning_rate": 0.00017651164135367125,
      "loss": 2.2484,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.35786666666666667,
      "eval_loss": 2.2868402004241943,
      "eval_runtime": 10.5599,
      "eval_samples_per_second": 355.118,
      "eval_steps_per_second": 5.587,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 21.436779022216797,
      "learning_rate": 0.00012441744564412654,
      "loss": 2.0102,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.4032,
      "eval_loss": 2.0858917236328125,
      "eval_runtime": 7.1065,
      "eval_samples_per_second": 527.688,
      "eval_steps_per_second": 8.302,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 39.06045913696289,
      "learning_rate": 7.540888354819138e-05,
      "loss": 1.7605,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.44026666666666664,
      "eval_loss": 1.9819227457046509,
      "eval_runtime": 7.023,
      "eval_samples_per_second": 533.957,
      "eval_steps_per_second": 8.401,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 43.499610900878906,
      "learning_rate": 3.5397110943979596e-05,
      "loss": 1.4788,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.46826666666666666,
      "eval_loss": 1.9337013959884644,
      "eval_runtime": 7.5278,
      "eval_samples_per_second": 498.155,
      "eval_steps_per_second": 7.838,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 29.397188186645508,
      "learning_rate": 9.20813811843163e-06,
      "loss": 1.1917,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.47786666666666666,
      "eval_loss": 1.9579426050186157,
      "eval_runtime": 7.2815,
      "eval_samples_per_second": 515.004,
      "eval_steps_per_second": 8.103,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": Infinity,
      "learning_rate": 1.3185811692517645e-09,
      "loss": 1.0349,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.4784,
      "eval_loss": 2.022280693054199,
      "eval_runtime": 7.3221,
      "eval_samples_per_second": 512.145,
      "eval_steps_per_second": 8.058,
      "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
}