<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
MultiCorp_all_label_2e-05_0404_ES2_strict_tok
This model is a fine-tuned version of microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1100
- Precision: 0.4037
- Recall: 0.3514
- F1: 0.3758
- Accuracy: 0.9710
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 2000
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
1.2964 | 0.08 | 25 | 0.2548 | 0.0 | 0.0 | 0.0 | 0.9637 |
0.2614 | 0.15 | 50 | 0.2361 | 0.0 | 0.0 | 0.0 | 0.9637 |
0.2316 | 0.23 | 75 | 0.2148 | 0.0 | 0.0 | 0.0 | 0.9637 |
0.2108 | 0.31 | 100 | 0.1937 | 0.0 | 0.0 | 0.0 | 0.9637 |
0.2106 | 0.39 | 125 | 0.1708 | 0.0 | 0.0 | 0.0 | 0.9637 |
0.156 | 0.46 | 150 | 0.1536 | 0.3404 | 0.0149 | 0.0285 | 0.9652 |
0.1593 | 0.54 | 175 | 0.1449 | 0.1691 | 0.0107 | 0.0201 | 0.9656 |
0.1577 | 0.62 | 200 | 0.1404 | 0.1888 | 0.0501 | 0.0792 | 0.9647 |
0.1569 | 0.7 | 225 | 0.1441 | 0.2921 | 0.0734 | 0.1173 | 0.9652 |
0.1404 | 0.77 | 250 | 0.1355 | 0.2096 | 0.1119 | 0.1459 | 0.9664 |
0.146 | 0.85 | 275 | 0.1332 | 0.2794 | 0.0529 | 0.0890 | 0.9670 |
0.1455 | 0.93 | 300 | 0.1278 | 0.2724 | 0.1230 | 0.1695 | 0.9662 |
0.1413 | 1.01 | 325 | 0.1240 | 0.2865 | 0.1147 | 0.1638 | 0.9675 |
0.108 | 1.08 | 350 | 0.1210 | 0.2487 | 0.1602 | 0.1949 | 0.9684 |
0.1264 | 1.16 | 375 | 0.1160 | 0.3218 | 0.1811 | 0.2317 | 0.9694 |
0.1068 | 1.24 | 400 | 0.1197 | 0.4168 | 0.1931 | 0.2640 | 0.9693 |
0.1195 | 1.32 | 425 | 0.1153 | 0.3716 | 0.2507 | 0.2994 | 0.9702 |
0.1042 | 1.39 | 450 | 0.1093 | 0.3984 | 0.2094 | 0.2745 | 0.9710 |
0.1106 | 1.47 | 475 | 0.1157 | 0.3918 | 0.3203 | 0.3525 | 0.9685 |
0.1172 | 1.55 | 500 | 0.1100 | 0.4037 | 0.3514 | 0.3758 | 0.9710 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3