<!-- 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. -->
Yepes_2e-05_0404_ES6
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: 0.0896
- Precision: 0.5644
- Recall: 0.4461
- F1: 0.4983
- Accuracy: 0.9814
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 |
---|---|---|---|---|---|---|---|
0.9221 | 0.43 | 25 | 0.2037 | 0.0 | 0.0 | 0.0 | 0.9705 |
0.2085 | 0.86 | 50 | 0.1930 | 0.0 | 0.0 | 0.0 | 0.9705 |
0.1808 | 1.29 | 75 | 0.1849 | 0.0 | 0.0 | 0.0 | 0.9705 |
0.1783 | 1.72 | 100 | 0.1334 | 0.0 | 0.0 | 0.0 | 0.9705 |
0.1266 | 2.16 | 125 | 0.1131 | 0.2967 | 0.1856 | 0.2284 | 0.9736 |
0.1098 | 2.59 | 150 | 0.1064 | 0.3735 | 0.2874 | 0.3249 | 0.9759 |
0.1088 | 3.02 | 175 | 0.0997 | 0.4567 | 0.2844 | 0.3506 | 0.9771 |
0.09 | 3.45 | 200 | 0.0917 | 0.4034 | 0.3563 | 0.3784 | 0.9773 |
0.0906 | 3.88 | 225 | 0.0865 | 0.4281 | 0.3743 | 0.3994 | 0.9781 |
0.0883 | 4.31 | 250 | 0.0850 | 0.4879 | 0.3623 | 0.4158 | 0.9796 |
0.0718 | 4.74 | 275 | 0.0864 | 0.5741 | 0.3713 | 0.4509 | 0.9808 |
0.0661 | 5.17 | 300 | 0.0860 | 0.5055 | 0.4102 | 0.4529 | 0.9799 |
0.0659 | 5.6 | 325 | 0.0765 | 0.5056 | 0.4072 | 0.4511 | 0.9799 |
0.0599 | 6.03 | 350 | 0.0796 | 0.4832 | 0.4311 | 0.4557 | 0.9795 |
0.0518 | 6.47 | 375 | 0.0959 | 0.6058 | 0.4371 | 0.5078 | 0.9809 |
0.0552 | 6.9 | 400 | 0.0804 | 0.4676 | 0.4760 | 0.4718 | 0.9781 |
0.0517 | 7.33 | 425 | 0.0917 | 0.6070 | 0.4671 | 0.5279 | 0.9815 |
0.0425 | 7.76 | 450 | 0.0859 | 0.5714 | 0.4671 | 0.5140 | 0.9807 |
0.0379 | 8.19 | 475 | 0.0896 | 0.5644 | 0.4461 | 0.4983 | 0.9814 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.2