Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0352

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0352
File size: 4,335 Bytes 
35ae53e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.3426666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0352/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": 0.0005,
      "loss": 3.3868,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.18586666666666668,
      "eval_loss": 3.0850067138671875,
      "eval_runtime": 14.1599,
      "eval_samples_per_second": 264.833,
      "eval_steps_per_second": 4.167,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 15.762471199035645,
      "learning_rate": 0.0005,
      "loss": 2.9656,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.23093333333333332,
      "eval_loss": 2.8596551418304443,
      "eval_runtime": 13.4654,
      "eval_samples_per_second": 278.492,
      "eval_steps_per_second": 4.382,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 13.771589279174805,
      "learning_rate": 0.0005,
      "loss": 2.8158,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.25066666666666665,
      "eval_loss": 2.752784013748169,
      "eval_runtime": 14.6157,
      "eval_samples_per_second": 256.573,
      "eval_steps_per_second": 4.037,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 14.823169708251953,
      "learning_rate": 0.0005,
      "loss": 2.7082,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.27466666666666667,
      "eval_loss": 2.703087091445923,
      "eval_runtime": 14.2358,
      "eval_samples_per_second": 263.42,
      "eval_steps_per_second": 4.144,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 11.493349075317383,
      "learning_rate": 0.0005,
      "loss": 2.606,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.2816,
      "eval_loss": 2.649627923965454,
      "eval_runtime": 13.2253,
      "eval_samples_per_second": 283.548,
      "eval_steps_per_second": 4.461,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 12.220715522766113,
      "learning_rate": 0.0005,
      "loss": 2.4999,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.3032,
      "eval_loss": 2.545308828353882,
      "eval_runtime": 13.3146,
      "eval_samples_per_second": 281.646,
      "eval_steps_per_second": 4.431,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 13.650389671325684,
      "learning_rate": 0.0005,
      "loss": 2.4132,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.32826666666666665,
      "eval_loss": 2.485001564025879,
      "eval_runtime": 13.2419,
      "eval_samples_per_second": 283.191,
      "eval_steps_per_second": 4.456,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 13.511910438537598,
      "learning_rate": 0.0005,
      "loss": 2.3498,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.33866666666666667,
      "eval_loss": 2.3860666751861572,
      "eval_runtime": 13.4733,
      "eval_samples_per_second": 278.329,
      "eval_steps_per_second": 4.379,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 21.905746459960938,
      "learning_rate": 0.0005,
      "loss": 2.2752,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.3426666666666667,
      "eval_loss": 2.4222896099090576,
      "eval_runtime": 13.3278,
      "eval_samples_per_second": 281.368,
      "eval_steps_per_second": 4.427,
      "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
}