Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0845

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0845
File size: 4,329 Bytes 
fdc0045
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.45626666666666665,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0845/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": 19.720232009887695,
      "learning_rate": 0.0003,
      "loss": 3.3525,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.2016,
      "eval_loss": 2.965362548828125,
      "eval_runtime": 13.2049,
      "eval_samples_per_second": 283.986,
      "eval_steps_per_second": 4.468,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 27.46491813659668,
      "learning_rate": 0.0003,
      "loss": 2.7451,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.2613333333333333,
      "eval_loss": 2.776667594909668,
      "eval_runtime": 14.0066,
      "eval_samples_per_second": 267.732,
      "eval_steps_per_second": 4.212,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 26.793907165527344,
      "learning_rate": 0.0003,
      "loss": 2.5189,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.31066666666666665,
      "eval_loss": 2.5293843746185303,
      "eval_runtime": 13.4576,
      "eval_samples_per_second": 278.654,
      "eval_steps_per_second": 4.384,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 26.829078674316406,
      "learning_rate": 0.0003,
      "loss": 2.3522,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.34346666666666664,
      "eval_loss": 2.441683292388916,
      "eval_runtime": 13.3365,
      "eval_samples_per_second": 281.184,
      "eval_steps_per_second": 4.424,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 19.63928985595703,
      "learning_rate": 0.0003,
      "loss": 2.1968,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.344,
      "eval_loss": 2.431791067123413,
      "eval_runtime": 13.4302,
      "eval_samples_per_second": 279.22,
      "eval_steps_per_second": 4.393,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 16.608274459838867,
      "learning_rate": 0.0003,
      "loss": 2.0554,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.41226666666666667,
      "eval_loss": 2.1903562545776367,
      "eval_runtime": 13.4642,
      "eval_samples_per_second": 278.516,
      "eval_steps_per_second": 4.382,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 22.161073684692383,
      "learning_rate": 0.0003,
      "loss": 1.9343,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.4224,
      "eval_loss": 2.119584798812866,
      "eval_runtime": 14.4742,
      "eval_samples_per_second": 259.081,
      "eval_steps_per_second": 4.076,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 18.078876495361328,
      "learning_rate": 0.0003,
      "loss": 1.8028,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.4338666666666667,
      "eval_loss": 2.076885223388672,
      "eval_runtime": 13.4379,
      "eval_samples_per_second": 279.062,
      "eval_steps_per_second": 4.391,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 22.238357543945312,
      "learning_rate": 0.0003,
      "loss": 1.6993,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.45626666666666665,
      "eval_loss": 1.9849841594696045,
      "eval_runtime": 13.6007,
      "eval_samples_per_second": 275.721,
      "eval_steps_per_second": 4.338,
      "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
}