Hugging Face's logo

tomaarsen
/
span-marker-mbert-base-multinerd

Token Classification
SpanMarker
PyTorch
TensorBoard
Safetensors
multilingual
ner
named-entity-recognition
Eval Results
Model card Files Metrics Community
3
tomaarsen HF staff commited on
Commit
b95aaaa
·
1 Parent(s): 3e91af6

Extend README heavily

Browse files
Files changed (1) hide show
  1. README.md +218 -4
README.md CHANGED
@@ -8,11 +8,95 @@ tags:
8
  - ner
9
  - named-entity-recognition
10
  pipeline_tag: token-classification
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  ---
12
 
13
- # SpanMarker for Named Entity Recognition
14
 
15
- This is a [SpanMarker](https://github.com/tomaarsen/SpanMarkerNER) model that can be used for Named Entity Recognition. In particular, this SpanMarker model uses [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) as the underlying encoder.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
16
 
17
  ## Usage
18
 
@@ -28,9 +112,139 @@ You can then run inference with this model like so:
28
  from span_marker import SpanMarkerModel
29
 
30
  # Download from the 🤗 Hub
31
- model = SpanMarkerModel.from_pretrained("span_marker_model_name")
32
  # Run inference
33
  entities = model.predict("Amelia Earhart flew her single engine Lockheed Vega 5B across the Atlantic to Paris.")
34
  ```
35
 
36
- See the [SpanMarker](https://github.com/tomaarsen/SpanMarkerNER) repository for documentation and additional information on this library.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  - ner
9
  - named-entity-recognition
10
  pipeline_tag: token-classification
11
+ widget:
12
+ - text: "Amelia Earthart voló su Lockheed Vega 5B monomotor a través del Océano Atlántico hasta París ."
13
+ example_title: "Spanish"
14
+ - text: "Amelia Earhart flew her single engine Lockheed Vega 5B across the Atlantic to Paris ."
15
+ example_title: "English"
16
+ - text: "Amelia Earthart a fait voler son monomoteur Lockheed Vega 5B à travers l' ocean Atlantique jusqu'à Paris ."
17
+ example_title: "French"
18
+ - text: "Amelia Earthart flog mit ihrer einmotorigen Lockheed Vega 5B über den Atlantik nach Paris ."
19
+ example_title: "German"
20
+ - text: "Амелия Эртхарт перелетела на своем одномоторном самолете Lockheed Vega 5B через Атлантический океан в Париж ."
21
+ example_title: "Russian"
22
+ - text: "Amelia Earthart vloog met haar één-motorige Lockheed Vega 5B over de Atlantische Oceaan naar Parijs ."
23
+ example_title: "Dutch"
24
+ - text: "Amelia Earthart przeleciała swoim jednosilnikowym samolotem Lockheed Vega 5B przez Ocean Atlantycki do Paryża ."
25
+ example_title: "Polish"
26
+ - text: "Amelia Earthart flaug eins hreyfils Lockheed Vega 5B yfir Atlantshafið til Parísar ."
27
+ example_title: "Icelandic"
28
+ - text: "Η Amelia Earthart πέταξε το μονοκινητήριο Lockheed Vega 5B της πέρα ​​από τον Ατλαντικό Ωκεανό στο Παρίσι ."
29
+ example_title: "Greek"
30
+ model-index:
31
+ - name: SpanMarker w. bert-base-multilingual-cased on MultiNERD by Tom Aarsen
32
+ results:
33
+ - task:
34
+ type: token-classification
35
+ name: Named Entity Recognition
36
+ dataset:
37
+ type: Babelscape/multinerd
38
+ name: MultiNERD
39
+ split: test
40
+ revision: 2814b78e7af4b5a1f1886fe7ad49632de4d9dd25
41
+ metrics:
42
+ - type: f1
43
+ value: 0.92478
44
+ name: F1
45
+ - type: precision
46
+ value: 0.93385
47
+ name: Precision
48
+ - type: recall
49
+ value: 0.91588
50
+ name: Recall
51
+ datasets:
52
+ - Babelscape/multinerd
53
+ language:
54
+ - multilingual
55
+ metrics:
56
+ - f1
57
+ - recall
58
+ - precision
59
  ---
60
 
61
+ # SpanMarker for Multilingual Named Entity Recognition
62
 
63
+ This is a [SpanMarker](https://github.com/tomaarsen/SpanMarkerNER) model that can be used for multilingual Named Entity Recognition trained on the [MultiNERD](https://huggingface.co/datasets/Babelscape/multinerd) dataset. In particular, this SpanMarker model uses [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) as the underlying encoder. See [train.py](train.py) for the training script.
64
+
65
+ ## Metrics
66
+
67
+ | **Language** | **F1** | **Precision** | **Recall** |
68
+ |--------------|--------|---------------|------------|
69
+ | **all** | 92.48 | 93.39 | 91.59 |
70
+ | **de** | 94.76 | 95.21 | 94.32 |
71
+ | **en** | 95.18 | 95.07 | 95.29 |
72
+ | **es** | 91.53 | 93.50 | 89.65 |
73
+ | **fr** | 91.92 | 93.86 | 90.07 |
74
+ | **it** | 92.59 | 91.63 | 93.57 |
75
+ | **nl** | 93.27 | 94.86 | 91.74 |
76
+ | **pl** | 92.66 | 93.51 | 91.83 |
77
+ | **pt** | 92.86 | 94.48 | 91.30 |
78
+ | **ru** | 93.39 | 93.70 | 93.10 |
79
+ | **zh** | 87.02 | 88.36 | 85.71 |
80
+
81
+ ## Label set
82
+
83
+ | Class | Description | Examples |
84
+ |-------|-------------|----------|
85
+ PER (person) | People | Ray Charles, Jessica Alba, Leonardo DiCaprio, Roger Federer, Anna Massey. |
86
+ ORG (organization) | Associations, companies, agencies, institutions, nationalities and religious or political groups | University of Edinburgh, San Francisco Giants, Google, Democratic Party. |
87
+ LOC (location) | Physical locations (e.g. mountains, bodies of water), geopolitical entities (e.g. cities, states), and facilities (e.g. bridges, buildings, airports). | Rome, Lake Paiku, Chrysler Building, Mount Rushmore, Mississippi River. |
88
+ ANIM (animal) | Breeds of dogs, cats and other animals, including their scientific names. | Maine Coon, African Wild Dog, Great White Shark, New Zealand Bellbird. |
89
+ BIO (biological) | Genus of fungus, bacteria and protoctists, families of viruses, and other biological entities. | Herpes Simplex Virus, Escherichia Coli, Salmonella, Bacillus Anthracis. |
90
+ CEL (celestial) | Planets, stars, asteroids, comets, nebulae, galaxies and other astronomical objects. | Sun, Neptune, Asteroid 187 Lamberta, Proxima Centauri, V838 Monocerotis. |
91
+ DIS (disease) | Physical, mental, infectious, non-infectious, deficiency, inherited, degenerative, social and self-inflicted diseases. | Alzheimer’s Disease, Cystic Fibrosis, Dilated Cardiomyopathy, Arthritis. |
92
+ EVE (event) | Sport events, battles, wars and other events. | American Civil War, 2003 Wimbledon Championships, Cannes Film Festival. |
93
+ FOOD (food) | Foods and drinks. | Carbonara, Sangiovese, Cheddar Beer Fondue, Pizza Margherita. |
94
+ INST (instrument) | Technological instruments, mechanical instruments, musical instruments, and other tools. | Spitzer Space Telescope, Commodore 64, Skype, Apple Watch, Fender Stratocaster. |
95
+ MEDIA (media) | Titles of films, books, magazines, songs and albums, fictional characters and languages. | Forbes, American Psycho, Kiss Me Once, Twin Peaks, Disney Adventures. |
96
+ PLANT (plant) | Types of trees, flowers, and other plants, including their scientific names. | Salix, Quercus Petraea, Douglas Fir, Forsythia, Artemisia Maritima. |
97
+ MYTH (mythological) | Mythological and religious entities. | Apollo, Persephone, Aphrodite, Saint Peter, Pope Gregory I, Hercules. |
98
+ TIME (time) | Specific and well-defined time intervals, such as eras, historical periods, centuries, years and important days. No months and days of the week. | Renaissance, Middle Ages, Christmas, Great Depression, 17th Century, 2012. |
99
+ VEHI (vehicle) | Cars, motorcycles and other vehicles. | Ferrari Testarossa, Suzuki Jimny, Honda CR-X, Boeing 747, Fairey Fulmar.
100
 
101
  ## Usage
102
 
 
112
  from span_marker import SpanMarkerModel
113
 
114
  # Download from the 🤗 Hub
115
+ model = SpanMarkerModel.from_pretrained("tomaarsen/span-marker-mbert-base-multinerd")
116
  # Run inference
117
  entities = model.predict("Amelia Earhart flew her single engine Lockheed Vega 5B across the Atlantic to Paris.")
118
  ```
119
 
120
+ See the [SpanMarker](https://github.com/tomaarsen/SpanMarkerNER) repository for documentation and additional information on this library.
121
+
122
+ ## Training procedure
123
+
124
+ ### Training hyperparameters
125
+
126
+ The following hyperparameters were used during training:
127
+ - learning_rate: 5e-05
128
+ - train_batch_size: 32
129
+ - eval_batch_size: 32
130
+ - seed: 42
131
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
132
+ - lr_scheduler_type: linear
133
+ - lr_scheduler_warmup_ratio: 0.1
134
+ - num_epochs: 1
135
+
136
+ ### Training results
137
+
138
+ | Training Loss | Epoch | Step | Validation Loss | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
139
+ |:-------------:|:-----:|:------:|:---------------:|:-----------------:|:--------------:|:----------:|:----------------:|
140
+ | 0.0179 | 0.01 | 1000 | 0.0146 | 0.8101 | 0.7616 | 0.7851 | 0.9530 |
141
+ | 0.0099 | 0.02 | 2000 | 0.0091 | 0.8571 | 0.8425 | 0.8498 | 0.9663 |
142
+ | 0.0085 | 0.03 | 3000 | 0.0078 | 0.8729 | 0.8579 | 0.8653 | 0.9700 |
143
+ | 0.0075 | 0.04 | 4000 | 0.0072 | 0.8821 | 0.8724 | 0.8772 | 0.9739 |
144
+ | 0.0074 | 0.05 | 5000 | 0.0075 | 0.8622 | 0.8841 | 0.8730 | 0.9722 |
145
+ | 0.0074 | 0.06 | 6000 | 0.0067 | 0.9056 | 0.8568 | 0.8805 | 0.9749 |
146
+ | 0.0066 | 0.07 | 7000 | 0.0065 | 0.9082 | 0.8543 | 0.8804 | 0.9737 |
147
+ | 0.0063 | 0.08 | 8000 | 0.0066 | 0.9039 | 0.8617 | 0.8823 | 0.9745 |
148
+ | 0.0062 | 0.09 | 9000 | 0.0062 | 0.9323 | 0.8425 | 0.8852 | 0.9754 |
149
+ | 0.007 | 0.1 | 10000 | 0.0066 | 0.8898 | 0.8758 | 0.8827 | 0.9746 |
150
+ | 0.006 | 0.11 | 11000 | 0.0061 | 0.8986 | 0.8841 | 0.8913 | 0.9766 |
151
+ | 0.006 | 0.12 | 12000 | 0.0061 | 0.9171 | 0.8628 | 0.8891 | 0.9763 |
152
+ | 0.0062 | 0.13 | 13000 | 0.0060 | 0.9264 | 0.8634 | 0.8938 | 0.9772 |
153
+ | 0.0059 | 0.14 | 14000 | 0.0059 | 0.9323 | 0.8508 | 0.8897 | 0.9763 |
154
+ | 0.0059 | 0.15 | 15000 | 0.0060 | 0.9011 | 0.8815 | 0.8912 | 0.9758 |
155
+ | 0.0059 | 0.16 | 16000 | 0.0060 | 0.9221 | 0.8598 | 0.8898 | 0.9763 |
156
+ | 0.0056 | 0.17 | 17000 | 0.0058 | 0.9098 | 0.8839 | 0.8967 | 0.9775 |
157
+ | 0.0055 | 0.18 | 18000 | 0.0060 | 0.9103 | 0.8739 | 0.8917 | 0.9765 |
158
+ | 0.0054 | 0.19 | 19000 | 0.0056 | 0.9135 | 0.8726 | 0.8925 | 0.9774 |
159
+ | 0.0052 | 0.2 | 20000 | 0.0058 | 0.9108 | 0.8834 | 0.8969 | 0.9773 |
160
+ | 0.0053 | 0.21 | 21000 | 0.0058 | 0.9038 | 0.8866 | 0.8951 | 0.9773 |
161
+ | 0.0057 | 0.22 | 22000 | 0.0057 | 0.9130 | 0.8762 | 0.8942 | 0.9775 |
162
+ | 0.0056 | 0.23 | 23000 | 0.0053 | 0.9375 | 0.8604 | 0.8973 | 0.9781 |
163
+ | 0.005 | 0.24 | 24000 | 0.0054 | 0.9253 | 0.8822 | 0.9032 | 0.9784 |
164
+ | 0.0055 | 0.25 | 25000 | 0.0055 | 0.9182 | 0.8807 | 0.8991 | 0.9787 |
165
+ | 0.0049 | 0.26 | 26000 | 0.0053 | 0.9311 | 0.8702 | 0.8997 | 0.9783 |
166
+ | 0.0051 | 0.27 | 27000 | 0.0054 | 0.9192 | 0.8877 | 0.9032 | 0.9787 |
167
+ | 0.0051 | 0.28 | 28000 | 0.0053 | 0.9332 | 0.8783 | 0.9049 | 0.9795 |
168
+ | 0.0049 | 0.29 | 29000 | 0.0054 | 0.9311 | 0.8672 | 0.8981 | 0.9789 |
169
+ | 0.0047 | 0.3 | 30000 | 0.0054 | 0.9165 | 0.8954 | 0.9058 | 0.9796 |
170
+ | 0.005 | 0.31 | 31000 | 0.0052 | 0.9079 | 0.9016 | 0.9047 | 0.9787 |
171
+ | 0.0051 | 0.32 | 32000 | 0.0051 | 0.9157 | 0.9001 | 0.9078 | 0.9796 |
172
+ | 0.0046 | 0.33 | 33000 | 0.0051 | 0.9147 | 0.8935 | 0.9040 | 0.9788 |
173
+ | 0.0046 | 0.34 | 34000 | 0.0050 | 0.9229 | 0.8847 | 0.9034 | 0.9793 |
174
+ | 0.005 | 0.35 | 35000 | 0.0051 | 0.9198 | 0.8922 | 0.9058 | 0.9796 |
175
+ | 0.0047 | 0.36 | 36000 | 0.0050 | 0.9321 | 0.8890 | 0.9100 | 0.9807 |
176
+ | 0.0048 | 0.37 | 37000 | 0.0050 | 0.9046 | 0.9133 | 0.9089 | 0.9800 |
177
+ | 0.0046 | 0.38 | 38000 | 0.0051 | 0.9170 | 0.8973 | 0.9071 | 0.9806 |
178
+ | 0.0048 | 0.39 | 39000 | 0.0050 | 0.9417 | 0.8775 | 0.9084 | 0.9805 |
179
+ | 0.0042 | 0.4 | 40000 | 0.0049 | 0.9238 | 0.8937 | 0.9085 | 0.9797 |
180
+ | 0.0038 | 0.41 | 41000 | 0.0048 | 0.9371 | 0.8920 | 0.9140 | 0.9812 |
181
+ | 0.0042 | 0.42 | 42000 | 0.0048 | 0.9359 | 0.8862 | 0.9104 | 0.9808 |
182
+ | 0.0051 | 0.43 | 43000 | 0.0049 | 0.9080 | 0.9060 | 0.9070 | 0.9805 |
183
+ | 0.0037 | 0.44 | 44000 | 0.0049 | 0.9328 | 0.8877 | 0.9097 | 0.9801 |
184
+ | 0.0041 | 0.45 | 45000 | 0.0049 | 0.9231 | 0.8975 | 0.9101 | 0.9813 |
185
+ | 0.0046 | 0.46 | 46000 | 0.0046 | 0.9308 | 0.8943 | 0.9122 | 0.9812 |
186
+ | 0.0038 | 0.47 | 47000 | 0.0047 | 0.9291 | 0.8969 | 0.9127 | 0.9815 |
187
+ | 0.0043 | 0.48 | 48000 | 0.0046 | 0.9308 | 0.8909 | 0.9104 | 0.9804 |
188
+ | 0.0043 | 0.49 | 49000 | 0.0046 | 0.9278 | 0.8954 | 0.9113 | 0.9800 |
189
+ | 0.0039 | 0.5 | 50000 | 0.0047 | 0.9173 | 0.9073 | 0.9123 | 0.9817 |
190
+ | 0.0043 | 0.51 | 51000 | 0.0045 | 0.9347 | 0.8962 | 0.9150 | 0.9821 |
191
+ | 0.0047 | 0.52 | 52000 | 0.0045 | 0.9266 | 0.9016 | 0.9139 | 0.9810 |
192
+ | 0.0035 | 0.53 | 53000 | 0.0046 | 0.9165 | 0.9122 | 0.9144 | 0.9820 |
193
+ | 0.0038 | 0.54 | 54000 | 0.0046 | 0.9231 | 0.9050 | 0.9139 | 0.9823 |
194
+ | 0.0036 | 0.55 | 55000 | 0.0046 | 0.9331 | 0.9005 | 0.9165 | 0.9828 |
195
+ | 0.0037 | 0.56 | 56000 | 0.0047 | 0.9246 | 0.9016 | 0.9129 | 0.9821 |
196
+ | 0.0035 | 0.57 | 57000 | 0.0044 | 0.9351 | 0.9003 | 0.9174 | 0.9829 |
197
+ | 0.0043 | 0.57 | 58000 | 0.0043 | 0.9257 | 0.9079 | 0.9167 | 0.9826 |
198
+ | 0.004 | 0.58 | 59000 | 0.0043 | 0.9286 | 0.9065 | 0.9174 | 0.9823 |
199
+ | 0.0041 | 0.59 | 60000 | 0.0044 | 0.9324 | 0.9050 | 0.9185 | 0.9825 |
200
+ | 0.0039 | 0.6 | 61000 | 0.0044 | 0.9268 | 0.9041 | 0.9153 | 0.9815 |
201
+ | 0.0038 | 0.61 | 62000 | 0.0043 | 0.9367 | 0.8918 | 0.9137 | 0.9819 |
202
+ | 0.0037 | 0.62 | 63000 | 0.0044 | 0.9249 | 0.9160 | 0.9205 | 0.9833 |
203
+ | 0.0036 | 0.63 | 64000 | 0.0043 | 0.9398 | 0.8975 | 0.9181 | 0.9827 |
204
+ | 0.0036 | 0.64 | 65000 | 0.0043 | 0.9260 | 0.9118 | 0.9188 | 0.9829 |
205
+ | 0.0035 | 0.65 | 66000 | 0.0044 | 0.9375 | 0.8988 | 0.9178 | 0.9828 |
206
+ | 0.0034 | 0.66 | 67000 | 0.0043 | 0.9272 | 0.9143 | 0.9207 | 0.9833 |
207
+ | 0.0033 | 0.67 | 68000 | 0.0044 | 0.9332 | 0.9024 | 0.9176 | 0.9827 |
208
+ | 0.0035 | 0.68 | 69000 | 0.0044 | 0.9396 | 0.8981 | 0.9184 | 0.9825 |
209
+ | 0.0038 | 0.69 | 70000 | 0.0042 | 0.9265 | 0.9163 | 0.9214 | 0.9827 |
210
+ | 0.0035 | 0.7 | 71000 | 0.0044 | 0.9375 | 0.9013 | 0.9191 | 0.9827 |
211
+ | 0.0037 | 0.71 | 72000 | 0.0042 | 0.9264 | 0.9171 | 0.9217 | 0.9830 |
212
+ | 0.0039 | 0.72 | 73000 | 0.0043 | 0.9399 | 0.9003 | 0.9197 | 0.9826 |
213
+ | 0.0039 | 0.73 | 74000 | 0.0041 | 0.9341 | 0.9094 | 0.9216 | 0.9832 |
214
+ | 0.0035 | 0.74 | 75000 | 0.0042 | 0.9301 | 0.9160 | 0.9230 | 0.9837 |
215
+ | 0.0037 | 0.75 | 76000 | 0.0042 | 0.9342 | 0.9107 | 0.9223 | 0.9835 |
216
+ | 0.0034 | 0.76 | 77000 | 0.0042 | 0.9331 | 0.9118 | 0.9223 | 0.9836 |
217
+ | 0.003 | 0.77 | 78000 | 0.0041 | 0.9330 | 0.9135 | 0.9231 | 0.9838 |
218
+ | 0.0034 | 0.78 | 79000 | 0.0041 | 0.9308 | 0.9082 | 0.9193 | 0.9832 |
219
+ | 0.0037 | 0.79 | 80000 | 0.0040 | 0.9346 | 0.9128 | 0.9236 | 0.9839 |
220
+ | 0.0032 | 0.8 | 81000 | 0.0041 | 0.9389 | 0.9128 | 0.9257 | 0.9841 |
221
+ | 0.0031 | 0.81 | 82000 | 0.0040 | 0.9293 | 0.9163 | 0.9227 | 0.9836 |
222
+ | 0.0032 | 0.82 | 83000 | 0.0041 | 0.9305 | 0.9160 | 0.9232 | 0.9835 |
223
+ | 0.0034 | 0.83 | 84000 | 0.0041 | 0.9327 | 0.9118 | 0.9221 | 0.9838 |
224
+ | 0.0028 | 0.84 | 85000 | 0.0041 | 0.9279 | 0.9216 | 0.9247 | 0.9839 |
225
+ | 0.0031 | 0.85 | 86000 | 0.0041 | 0.9326 | 0.9167 | 0.9246 | 0.9838 |
226
+ | 0.0029 | 0.86 | 87000 | 0.0040 | 0.9354 | 0.9158 | 0.9255 | 0.9841 |
227
+ | 0.0031 | 0.87 | 88000 | 0.0041 | 0.9327 | 0.9156 | 0.9241 | 0.9840 |
228
+ | 0.0033 | 0.88 | 89000 | 0.0040 | 0.9367 | 0.9141 | 0.9253 | 0.9846 |
229
+ | 0.0031 | 0.89 | 90000 | 0.0040 | 0.9379 | 0.9141 | 0.9259 | 0.9844 |
230
+ | 0.0031 | 0.9 | 91000 | 0.0040 | 0.9297 | 0.9184 | 0.9240 | 0.9843 |
231
+ | 0.0034 | 0.91 | 92000 | 0.0040 | 0.9299 | 0.9188 | 0.9243 | 0.9843 |
232
+ | 0.0036 | 0.92 | 93000 | 0.0039 | 0.9324 | 0.9175 | 0.9249 | 0.9843 |
233
+ | 0.0028 | 0.93 | 94000 | 0.0039 | 0.9399 | 0.9135 | 0.9265 | 0.9848 |
234
+ | 0.0029 | 0.94 | 95000 | 0.0040 | 0.9342 | 0.9173 | 0.9257 | 0.9845 |
235
+ | 0.003 | 0.95 | 96000 | 0.0040 | 0.9378 | 0.9184 | 0.9280 | 0.9850 |
236
+ | 0.0029 | 0.96 | 97000 | 0.0039 | 0.9380 | 0.9152 | 0.9264 | 0.9847 |
237
+ | 0.003 | 0.97 | 98000 | 0.0039 | 0.9372 | 0.9156 | 0.9263 | 0.9849 |
238
+ | 0.003 | 0.98 | 99000 | 0.0039 | 0.9387 | 0.9167 | 0.9276 | 0.9851 |
239
+ | 0.0031 | 0.99 | 100000 | 0.0039 | 0.9373 | 0.9177 | 0.9274 | 0.9849 |
240
+
241
+ ### Framework versions
242
+
243
+ - SpanMarker 1.2.4
244
+ - Transformers 4.28.1
245
+ - Pytorch 1.13.1+cu117
246
+ - Datasets 2.12.0
247
+ - Tokenizers 0.13.2
248
+
249
+ ## Contributions
250
+ Many thanks to [Simone Tedeschi](https://huggingface.co/sted97) from [Babelscape](https://babelscape.com) for his insight when training this model and his involvement in the creation of the training dataset.