Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0836

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0836
File size: 3,941 Bytes 
d36e140
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.42346666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0836/checkpoints/checkpoint-2664",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 2664,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 21.9869327545166,
      "learning_rate": 0.0003,
      "loss": 3.2615,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.23546666666666666,
      "eval_loss": 2.81964373588562,
      "eval_runtime": 11.7053,
      "eval_samples_per_second": 320.367,
      "eval_steps_per_second": 5.04,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0003,
      "loss": 2.6783,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.2949333333333333,
      "eval_loss": 2.5831120014190674,
      "eval_runtime": 11.1809,
      "eval_samples_per_second": 335.392,
      "eval_steps_per_second": 5.277,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 20.75516128540039,
      "learning_rate": 0.0003,
      "loss": 2.4637,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.3293333333333333,
      "eval_loss": 2.4647600650787354,
      "eval_runtime": 11.0571,
      "eval_samples_per_second": 339.147,
      "eval_steps_per_second": 5.336,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 26.54750633239746,
      "learning_rate": 0.0003,
      "loss": 2.3185,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.336,
      "eval_loss": 2.4368479251861572,
      "eval_runtime": 11.0645,
      "eval_samples_per_second": 338.922,
      "eval_steps_per_second": 5.332,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 20.638452529907227,
      "learning_rate": 0.0003,
      "loss": 2.1757,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.36746666666666666,
      "eval_loss": 2.286107063293457,
      "eval_runtime": 11.3388,
      "eval_samples_per_second": 330.723,
      "eval_steps_per_second": 5.203,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 22.473981857299805,
      "learning_rate": 0.0003,
      "loss": 2.0448,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.3912,
      "eval_loss": 2.1793930530548096,
      "eval_runtime": 10.9109,
      "eval_samples_per_second": 343.693,
      "eval_steps_per_second": 5.407,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 20.979331970214844,
      "learning_rate": 0.0003,
      "loss": 1.9278,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.39386666666666664,
      "eval_loss": 2.1987478733062744,
      "eval_runtime": 10.9731,
      "eval_samples_per_second": 341.745,
      "eval_steps_per_second": 5.377,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 12.307392120361328,
      "learning_rate": 0.0003,
      "loss": 1.8213,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.42346666666666666,
      "eval_loss": 2.0403189659118652,
      "eval_runtime": 11.284,
      "eval_samples_per_second": 332.33,
      "eval_steps_per_second": 5.229,
      "step": 2664
    }
  ],
  "logging_steps": 500,
  "max_steps": 2664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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": 1.317930564980736e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}