Hugging Face's logo

groderg
/
BeitEAU-base-patch16-384-2025_11_07_78282-bs32_freeze

TensorBoard
Safetensors
English
beit
multilabel-image-classification
multilabel
Generated from Trainer
Model card Files
xet
Metrics Community
groderg commited on
Commit
cbd6fc7
·
verified ·
1 Parent(s): 7ac4848

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +198 -101
README.md CHANGED
@@ -1,125 +1,222 @@
 
1
  ---
2
- library_name: transformers
3
- license: apache-2.0
4
- base_model: microsoft/beit-base-patch16-384
5
  tags:
 
 
6
  - generated_from_trainer
7
- metrics:
8
- - accuracy
9
  model-index:
10
  - name: BeitEAU-base-patch16-384-2025_11_07_78282-bs32_freeze
11
  results: []
12
  ---
13
 
14
- <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
- should probably proofread and complete it, then remove this comment. -->
16
 
17
- # BeitEAU-base-patch16-384-2025_11_07_78282-bs32_freeze
18
 
19
- This model is a fine-tuned version of [microsoft/beit-base-patch16-384](https://huggingface.co/microsoft/beit-base-patch16-384) on the None dataset.
20
- It achieves the following results on the evaluation set:
21
  - Loss: 0.1647
22
  - F1 Micro: 0.7446
23
  - F1 Macro: 0.6015
24
  - Accuracy: 0.2171
25
- - Learning Rate: 0.0000
26
 
27
- ## Model description
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28
 
29
- More information needed
30
 
31
- ## Intended uses & limitations
 
32
 
33
- More information needed
34
 
35
- ## Training and evaluation data
 
 
36
 
37
- More information needed
 
38
 
39
- ## Training procedure
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
 
41
- ### Training hyperparameters
 
 
42
 
43
  The following hyperparameters were used during training:
44
- - learning_rate: 0.001
45
- - train_batch_size: 32
46
- - eval_batch_size: 32
47
- - seed: 42
48
- - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
49
- - lr_scheduler_type: linear
50
- - num_epochs: 150
51
- - mixed_precision_training: Native AMP
52
-
53
- ### Training results
54
-
55
- | Training Loss | Epoch | Step | Validation Loss | F1 Micro | F1 Macro | Accuracy | Rate |
56
- |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|:--------:|:------:|
57
- | No log | 1.0 | 273 | 0.2007 | 0.6701 | 0.4414 | 0.1609 | 0.001 |
58
- | 0.2398 | 2.0 | 546 | 0.1895 | 0.7090 | 0.5352 | 0.1825 | 0.001 |
59
- | 0.2398 | 3.0 | 819 | 0.1867 | 0.7166 | 0.5614 | 0.1763 | 0.001 |
60
- | 0.2093 | 4.0 | 1092 | 0.1814 | 0.7215 | 0.5564 | 0.1798 | 0.001 |
61
- | 0.2093 | 5.0 | 1365 | 0.1815 | 0.7243 | 0.5929 | 0.1923 | 0.001 |
62
- | 0.2033 | 6.0 | 1638 | 0.1793 | 0.7348 | 0.5779 | 0.1962 | 0.001 |
63
- | 0.2033 | 7.0 | 1911 | 0.1755 | 0.7318 | 0.5828 | 0.1997 | 0.001 |
64
- | 0.1995 | 8.0 | 2184 | 0.1758 | 0.7272 | 0.5792 | 0.2059 | 0.001 |
65
- | 0.1995 | 9.0 | 2457 | 0.1740 | 0.7299 | 0.5864 | 0.1937 | 0.001 |
66
- | 0.1975 | 10.0 | 2730 | 0.1748 | 0.7276 | 0.5768 | 0.1874 | 0.001 |
67
- | 0.1961 | 11.0 | 3003 | 0.1735 | 0.7381 | 0.6032 | 0.1979 | 0.001 |
68
- | 0.1961 | 12.0 | 3276 | 0.1722 | 0.7353 | 0.5857 | 0.2112 | 0.001 |
69
- | 0.1938 | 13.0 | 3549 | 0.1720 | 0.7369 | 0.5801 | 0.2161 | 0.001 |
70
- | 0.1938 | 14.0 | 3822 | 0.1754 | 0.7266 | 0.5724 | 0.1923 | 0.001 |
71
- | 0.1938 | 15.0 | 4095 | 0.1706 | 0.7413 | 0.5973 | 0.1986 | 0.001 |
72
- | 0.1938 | 16.0 | 4368 | 0.1739 | 0.7282 | 0.6014 | 0.2059 | 0.001 |
73
- | 0.1919 | 17.0 | 4641 | 0.1716 | 0.7463 | 0.6158 | 0.1997 | 0.001 |
74
- | 0.1919 | 18.0 | 4914 | 0.1716 | 0.7337 | 0.5882 | 0.2042 | 0.001 |
75
- | 0.1922 | 19.0 | 5187 | 0.1741 | 0.7237 | 0.5876 | 0.2094 | 0.001 |
76
- | 0.1922 | 20.0 | 5460 | 0.1718 | 0.7294 | 0.5808 | 0.2094 | 0.001 |
77
- | 0.1908 | 21.0 | 5733 | 0.1722 | 0.7369 | 0.5918 | 0.1986 | 0.001 |
78
- | 0.187 | 22.0 | 6006 | 0.1666 | 0.7486 | 0.6174 | 0.2115 | 0.0001 |
79
- | 0.187 | 23.0 | 6279 | 0.1657 | 0.7474 | 0.6164 | 0.2059 | 0.0001 |
80
- | 0.1841 | 24.0 | 6552 | 0.1660 | 0.7473 | 0.6207 | 0.2077 | 0.0001 |
81
- | 0.1841 | 25.0 | 6825 | 0.1654 | 0.7474 | 0.6136 | 0.2119 | 0.0001 |
82
- | 0.1827 | 26.0 | 7098 | 0.1654 | 0.7498 | 0.6169 | 0.2098 | 0.0001 |
83
- | 0.1827 | 27.0 | 7371 | 0.1656 | 0.7497 | 0.6185 | 0.2115 | 0.0001 |
84
- | 0.1841 | 28.0 | 7644 | 0.1657 | 0.7455 | 0.6091 | 0.2101 | 0.0001 |
85
- | 0.1841 | 29.0 | 7917 | 0.1653 | 0.7467 | 0.6130 | 0.2077 | 0.0001 |
86
- | 0.1831 | 30.0 | 8190 | 0.1656 | 0.7484 | 0.6168 | 0.2119 | 0.0001 |
87
- | 0.1831 | 31.0 | 8463 | 0.1655 | 0.7498 | 0.6121 | 0.2115 | 0.0001 |
88
- | 0.184 | 32.0 | 8736 | 0.1654 | 0.7466 | 0.6116 | 0.2073 | 0.0001 |
89
- | 0.1822 | 33.0 | 9009 | 0.1652 | 0.7470 | 0.6166 | 0.2147 | 0.0001 |
90
- | 0.1822 | 34.0 | 9282 | 0.1652 | 0.7467 | 0.6174 | 0.2188 | 0.0001 |
91
- | 0.1826 | 35.0 | 9555 | 0.1650 | 0.7503 | 0.6175 | 0.2115 | 0.0001 |
92
- | 0.1826 | 36.0 | 9828 | 0.1652 | 0.7479 | 0.6171 | 0.2105 | 0.0001 |
93
- | 0.1828 | 37.0 | 10101 | 0.1650 | 0.7489 | 0.6121 | 0.2154 | 0.0001 |
94
- | 0.1828 | 38.0 | 10374 | 0.1653 | 0.7489 | 0.6105 | 0.2164 | 0.0001 |
95
- | 0.1815 | 39.0 | 10647 | 0.1652 | 0.7506 | 0.6167 | 0.2164 | 0.0001 |
96
- | 0.1815 | 40.0 | 10920 | 0.1651 | 0.7511 | 0.6164 | 0.2140 | 0.0001 |
97
- | 0.1837 | 41.0 | 11193 | 0.1650 | 0.7508 | 0.6149 | 0.2129 | 0.0001 |
98
- | 0.1837 | 42.0 | 11466 | 0.1648 | 0.7512 | 0.6145 | 0.2136 | 1e-05 |
99
- | 0.1825 | 43.0 | 11739 | 0.1647 | 0.7490 | 0.6136 | 0.2122 | 1e-05 |
100
- | 0.1817 | 44.0 | 12012 | 0.1646 | 0.7502 | 0.6148 | 0.2126 | 1e-05 |
101
- | 0.1817 | 45.0 | 12285 | 0.1647 | 0.7512 | 0.6161 | 0.2140 | 1e-05 |
102
- | 0.1813 | 46.0 | 12558 | 0.1647 | 0.7511 | 0.6148 | 0.2126 | 1e-05 |
103
- | 0.1813 | 47.0 | 12831 | 0.1647 | 0.7510 | 0.6149 | 0.2136 | 1e-05 |
104
- | 0.1816 | 48.0 | 13104 | 0.1646 | 0.7500 | 0.6143 | 0.2126 | 1e-05 |
105
- | 0.1816 | 49.0 | 13377 | 0.1647 | 0.7508 | 0.6153 | 0.2126 | 1e-05 |
106
- | 0.1821 | 50.0 | 13650 | 0.1646 | 0.7494 | 0.6139 | 0.2126 | 1e-05 |
107
- | 0.1821 | 51.0 | 13923 | 0.1645 | 0.7498 | 0.6143 | 0.2129 | 1e-05 |
108
- | 0.1818 | 52.0 | 14196 | 0.1646 | 0.7504 | 0.6142 | 0.2133 | 1e-05 |
109
- | 0.1818 | 53.0 | 14469 | 0.1646 | 0.7505 | 0.6146 | 0.2122 | 1e-05 |
110
- | 0.1826 | 54.0 | 14742 | 0.1646 | 0.7504 | 0.6158 | 0.2129 | 1e-05 |
111
- | 0.181 | 55.0 | 15015 | 0.1646 | 0.7505 | 0.6153 | 0.2119 | 1e-05 |
112
- | 0.181 | 56.0 | 15288 | 0.1646 | 0.7504 | 0.6145 | 0.2115 | 1e-05 |
113
- | 0.1822 | 57.0 | 15561 | 0.1646 | 0.7501 | 0.6140 | 0.2115 | 1e-05 |
114
- | 0.1822 | 58.0 | 15834 | 0.1646 | 0.7500 | 0.6138 | 0.2115 | 0.0000 |
115
- | 0.1821 | 59.0 | 16107 | 0.1646 | 0.7502 | 0.6139 | 0.2126 | 0.0000 |
116
- | 0.1821 | 60.0 | 16380 | 0.1646 | 0.7502 | 0.6139 | 0.2126 | 0.0000 |
117
- | 0.182 | 61.0 | 16653 | 0.1646 | 0.7505 | 0.6143 | 0.2126 | 0.0000 |
118
-
119
-
120
- ### Framework versions
121
-
122
- - Transformers 4.56.0.dev0
123
- - Pytorch 2.6.0+cu124
124
- - Datasets 3.0.2
125
- - Tokenizers 0.21.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
  ---
3
+ language:
4
+ - eng
5
+ license: cc0-1.0
6
  tags:
7
+ - multilabel-image-classification
8
+ - multilabel
9
  - generated_from_trainer
10
+ base_model: BeitEAU-base-patch16-384-2025_11_07_78282-bs32_freeze
 
11
  model-index:
12
  - name: BeitEAU-base-patch16-384-2025_11_07_78282-bs32_freeze
13
  results: []
14
  ---
15
 
16
+ BeitEAU is a fine-tuned version of [BeitEAU-base-patch16-384-2025_11_07_78282-bs32_freeze](https://huggingface.co/BeitEAU-base-patch16-384-2025_11_07_78282-bs32_freeze). It achieves the following results on the test set:
 
17
 
 
18
 
 
 
19
  - Loss: 0.1647
20
  - F1 Micro: 0.7446
21
  - F1 Macro: 0.6015
22
  - Accuracy: 0.2171
 
23
 
24
+ | Class | F1 per class |
25
+ |----------|-------|
26
+ | Acropore_branched | 0.7982 |
27
+ | Acropore_digitised | 0.4713 |
28
+ | Acropore_sub_massive | 0.2880 |
29
+ | Acropore_tabular | 0.8900 |
30
+ | Algae_assembly | 0.7410 |
31
+ | Algae_drawn_up | 0.3889 |
32
+ | Algae_limestone | 0.6890 |
33
+ | Algae_sodding | 0.8126 |
34
+ | Atra/Leucospilota | 0.6085 |
35
+ | Bleached_coral | 0.6994 |
36
+ | Blurred | 0.3471 |
37
+ | Dead_coral | 0.6977 |
38
+ | Fish | 0.6206 |
39
+ | Homo_sapiens | 0.5546 |
40
+ | Human_object | 0.7174 |
41
+ | Living_coral | 0.6376 |
42
+ | Millepore | 0.6636 |
43
+ | No_acropore_encrusting | 0.5906 |
44
+ | No_acropore_foliaceous | 0.7253 |
45
+ | No_acropore_massive | 0.5968 |
46
+ | No_acropore_solitary | 0.4364 |
47
+ | No_acropore_sub_massive | 0.6084 |
48
+ | Rock | 0.8513 |
49
+ | Rubble | 0.7116 |
50
+ | Sand | 0.8955 |
51
+ | Sea_cucumber | 0.6009 |
52
+ | Sea_urchins | 0.5445 |
53
+ | Sponge | 0.3689 |
54
+ | Syringodium_isoetifolium | 0.9401 |
55
+ | Thalassodendron_ciliatum | 0.9547 |
56
+ | Useless | 0.9686 |
57
+
58
 
59
+ ---
60
 
61
+ # Model description
62
+ BeitEAU is a model built on top of BeitEAU-base-patch16-384-2025_11_07_78282-bs32_freeze model for underwater multilabel image classification.The classification head is a combination of linear, ReLU, batch normalization, and dropout layers.
63
 
64
+ The source code for training the model can be found in this [Git repository](https://github.com/SeatizenDOI/DinoVdeau).
65
 
66
+ - **Developed by:** [lombardata](https://huggingface.co/lombardata), credits to [César Leblanc](https://huggingface.co/CesarLeblanc) and [Victor Illien](https://huggingface.co/groderg)
67
+
68
+ ---
69
 
70
+ # Intended uses & limitations
71
+ You can use the raw model for classify diverse marine species, encompassing coral morphotypes classes taken from the Global Coral Reef Monitoring Network (GCRMN), habitats classes and seagrass species.
72
 
73
+ ---
74
+
75
+ # Training and evaluation data
76
+ Details on the number of images for each class are given in the following table:
77
+ | Class | train | test | val | Total |
78
+ |:-------------------------|--------:|-------:|------:|--------:|
79
+ | Acropore_branched | 1480 | 469 | 459 | 2408 |
80
+ | Acropore_digitised | 571 | 156 | 161 | 888 |
81
+ | Acropore_sub_massive | 150 | 52 | 41 | 243 |
82
+ | Acropore_tabular | 999 | 292 | 298 | 1589 |
83
+ | Algae_assembly | 2554 | 842 | 842 | 4238 |
84
+ | Algae_drawn_up | 367 | 130 | 123 | 620 |
85
+ | Algae_limestone | 1651 | 562 | 559 | 2772 |
86
+ | Algae_sodding | 3142 | 994 | 981 | 5117 |
87
+ | Atra/Leucospilota | 1084 | 349 | 359 | 1792 |
88
+ | Bleached_coral | 219 | 69 | 72 | 360 |
89
+ | Blurred | 191 | 68 | 61 | 320 |
90
+ | Dead_coral | 1980 | 648 | 636 | 3264 |
91
+ | Fish | 2018 | 661 | 642 | 3321 |
92
+ | Homo_sapiens | 161 | 63 | 58 | 282 |
93
+ | Human_object | 156 | 55 | 59 | 270 |
94
+ | Living_coral | 397 | 151 | 153 | 701 |
95
+ | Millepore | 386 | 127 | 124 | 637 |
96
+ | No_acropore_encrusting | 442 | 141 | 142 | 725 |
97
+ | No_acropore_foliaceous | 204 | 47 | 35 | 286 |
98
+ | No_acropore_massive | 1030 | 341 | 334 | 1705 |
99
+ | No_acropore_solitary | 202 | 55 | 46 | 303 |
100
+ | No_acropore_sub_massive | 1402 | 428 | 426 | 2256 |
101
+ | Rock | 4481 | 1495 | 1481 | 7457 |
102
+ | Rubble | 3092 | 1015 | 1016 | 5123 |
103
+ | Sand | 5839 | 1945 | 1935 | 9719 |
104
+ | Sea_cucumber | 1407 | 437 | 450 | 2294 |
105
+ | Sea_urchins | 328 | 110 | 107 | 545 |
106
+ | Sponge | 267 | 98 | 105 | 470 |
107
+ | Syringodium_isoetifolium | 1213 | 392 | 390 | 1995 |
108
+ | Thalassodendron_ciliatum | 781 | 262 | 260 | 1303 |
109
+ | Useless | 579 | 193 | 193 | 965 |
110
+
111
+ ---
112
 
113
+ # Training procedure
114
+
115
+ ## Training hyperparameters
116
 
117
  The following hyperparameters were used during training:
118
+
119
+ - **Number of Epochs**: 61.0
120
+ - **Learning Rate**: 0.001
121
+ - **Train Batch Size**: 32
122
+ - **Eval Batch Size**: 32
123
+ - **Optimizer**: Adam
124
+ - **LR Scheduler Type**: ReduceLROnPlateau with a patience of 5 epochs and a factor of 0.1
125
+ - **Freeze Encoder**: Yes
126
+ - **Data Augmentation**: Yes
127
+
128
+
129
+ ## Data Augmentation
130
+ Data were augmented using the following transformations :
131
+
132
+ Train Transforms
133
+ - **PreProcess**: No additional parameters
134
+ - **Resize**: probability=1.00
135
+ - **RandomHorizontalFlip**: probability=0.25
136
+ - **RandomVerticalFlip**: probability=0.25
137
+ - **ColorJiggle**: probability=0.25
138
+ - **RandomPerspective**: probability=0.25
139
+ - **Normalize**: probability=1.00
140
+
141
+ Val Transforms
142
+ - **PreProcess**: No additional parameters
143
+ - **Resize**: probability=1.00
144
+ - **Normalize**: probability=1.00
145
+
146
+
147
+
148
+ ## Training results
149
+ Epoch | Validation Loss | Accuracy | F1 Macro | F1 Micro | Learning Rate
150
+ --- | --- | --- | --- | --- | ---
151
+ 1 | 0.2007167786359787 | 0.1609 | 0.6701 | 0.4414 | 0.001
152
+ 2 | 0.18952292203903198 | 0.1825 | 0.7090 | 0.5352 | 0.001
153
+ 3 | 0.18667148053646088 | 0.1763 | 0.7166 | 0.5614 | 0.001
154
+ 4 | 0.1814328134059906 | 0.1798 | 0.7215 | 0.5564 | 0.001
155
+ 5 | 0.18154974281787872 | 0.1923 | 0.7243 | 0.5929 | 0.001
156
+ 6 | 0.17931246757507324 | 0.1962 | 0.7348 | 0.5779 | 0.001
157
+ 7 | 0.17549261450767517 | 0.1997 | 0.7318 | 0.5828 | 0.001
158
+ 8 | 0.17576082050800323 | 0.2059 | 0.7272 | 0.5792 | 0.001
159
+ 9 | 0.1740318238735199 | 0.1937 | 0.7299 | 0.5864 | 0.001
160
+ 10 | 0.17477667331695557 | 0.1874 | 0.7276 | 0.5768 | 0.001
161
+ 11 | 0.17347504198551178 | 0.1979 | 0.7381 | 0.6032 | 0.001
162
+ 12 | 0.17222067713737488 | 0.2112 | 0.7353 | 0.5857 | 0.001
163
+ 13 | 0.1720178872346878 | 0.2161 | 0.7369 | 0.5801 | 0.001
164
+ 14 | 0.17544052004814148 | 0.1923 | 0.7266 | 0.5724 | 0.001
165
+ 15 | 0.1705772429704666 | 0.1986 | 0.7413 | 0.5973 | 0.001
166
+ 16 | 0.17385560274124146 | 0.2059 | 0.7282 | 0.6014 | 0.001
167
+ 17 | 0.17162470519542694 | 0.1997 | 0.7463 | 0.6158 | 0.001
168
+ 18 | 0.17156463861465454 | 0.2042 | 0.7337 | 0.5882 | 0.001
169
+ 19 | 0.174124613404274 | 0.2094 | 0.7237 | 0.5876 | 0.001
170
+ 20 | 0.1717967540025711 | 0.2094 | 0.7294 | 0.5808 | 0.001
171
+ 21 | 0.1721898466348648 | 0.1986 | 0.7369 | 0.5918 | 0.001
172
+ 22 | 0.16664884984493256 | 0.2115 | 0.7486 | 0.6174 | 0.0001
173
+ 23 | 0.16572968661785126 | 0.2059 | 0.7474 | 0.6164 | 0.0001
174
+ 24 | 0.16604110598564148 | 0.2077 | 0.7473 | 0.6207 | 0.0001
175
+ 25 | 0.16543170809745789 | 0.2119 | 0.7474 | 0.6136 | 0.0001
176
+ 26 | 0.16543741524219513 | 0.2098 | 0.7498 | 0.6169 | 0.0001
177
+ 27 | 0.1656235158443451 | 0.2115 | 0.7497 | 0.6185 | 0.0001
178
+ 28 | 0.16566258668899536 | 0.2101 | 0.7455 | 0.6091 | 0.0001
179
+ 29 | 0.1653388887643814 | 0.2077 | 0.7467 | 0.6130 | 0.0001
180
+ 30 | 0.16557003557682037 | 0.2119 | 0.7484 | 0.6168 | 0.0001
181
+ 31 | 0.16546830534934998 | 0.2115 | 0.7498 | 0.6121 | 0.0001
182
+ 32 | 0.1653573364019394 | 0.2073 | 0.7466 | 0.6116 | 0.0001
183
+ 33 | 0.16520579159259796 | 0.2147 | 0.7470 | 0.6166 | 0.0001
184
+ 34 | 0.1652197241783142 | 0.2188 | 0.7467 | 0.6174 | 0.0001
185
+ 35 | 0.16497600078582764 | 0.2115 | 0.7503 | 0.6175 | 0.0001
186
+ 36 | 0.16519583761692047 | 0.2105 | 0.7479 | 0.6171 | 0.0001
187
+ 37 | 0.1649632453918457 | 0.2154 | 0.7489 | 0.6121 | 0.0001
188
+ 38 | 0.16533540189266205 | 0.2164 | 0.7489 | 0.6105 | 0.0001
189
+ 39 | 0.16515697538852692 | 0.2164 | 0.7506 | 0.6167 | 0.0001
190
+ 40 | 0.16513320803642273 | 0.2140 | 0.7511 | 0.6164 | 0.0001
191
+ 41 | 0.16498203575611115 | 0.2129 | 0.7508 | 0.6149 | 0.0001
192
+ 42 | 0.16477563977241516 | 0.2136 | 0.7512 | 0.6145 | 1e-05
193
+ 43 | 0.16469572484493256 | 0.2122 | 0.7490 | 0.6136 | 1e-05
194
+ 44 | 0.16464821994304657 | 0.2126 | 0.7502 | 0.6148 | 1e-05
195
+ 45 | 0.16469135880470276 | 0.2140 | 0.7512 | 0.6161 | 1e-05
196
+ 46 | 0.16468331217765808 | 0.2126 | 0.7511 | 0.6148 | 1e-05
197
+ 47 | 0.16469669342041016 | 0.2136 | 0.7510 | 0.6149 | 1e-05
198
+ 48 | 0.16463501751422882 | 0.2126 | 0.7500 | 0.6143 | 1e-05
199
+ 49 | 0.16467586159706116 | 0.2126 | 0.7508 | 0.6153 | 1e-05
200
+ 50 | 0.16459208726882935 | 0.2126 | 0.7494 | 0.6139 | 1e-05
201
+ 51 | 0.1645309180021286 | 0.2129 | 0.7498 | 0.6143 | 1e-05
202
+ 52 | 0.16459544003009796 | 0.2133 | 0.7504 | 0.6142 | 1e-05
203
+ 53 | 0.16463778913021088 | 0.2122 | 0.7505 | 0.6146 | 1e-05
204
+ 54 | 0.16458478569984436 | 0.2129 | 0.7504 | 0.6158 | 1e-05
205
+ 55 | 0.16461443901062012 | 0.2119 | 0.7505 | 0.6153 | 1e-05
206
+ 56 | 0.1645844429731369 | 0.2115 | 0.7504 | 0.6145 | 1e-05
207
+ 57 | 0.16459982097148895 | 0.2115 | 0.7501 | 0.6140 | 1e-05
208
+ 58 | 0.16459773480892181 | 0.2115 | 0.7500 | 0.6138 | 1.0000000000000002e-06
209
+ 59 | 0.164586141705513 | 0.2126 | 0.7502 | 0.6139 | 1.0000000000000002e-06
210
+ 60 | 0.16457903385162354 | 0.2126 | 0.7502 | 0.6139 | 1.0000000000000002e-06
211
+ 61 | 0.1645755171775818 | 0.2126 | 0.7505 | 0.6143 | 1.0000000000000002e-06
212
+
213
+
214
+ ---
215
+
216
+ # Framework Versions
217
+
218
+ - **Transformers**: 4.56.0.dev0
219
+ - **Pytorch**: 2.6.0+cu124
220
+ - **Datasets**: 3.0.2
221
+ - **Tokenizers**: 0.21.0
222
+