| --- |
| license: mit |
| tags: |
| - generated_from_trainer |
| metrics: |
| - precision |
| - recall |
| - f1 |
| - accuracy |
| model-index: |
| - name: RoBERTa_token_classification_14_techs_basic_fixed |
| results: [] |
| --- |
| |
| <!-- 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. --> |
|
|
| # RoBERTa_token_classification_14_techs_basic_fixed |
|
|
| This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 1.2455 |
| - Precision: 0.0809 |
| - Recall: 0.0915 |
| - F1: 0.0859 |
| - Accuracy: 0.7099 |
|
|
| ## 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: 8 |
| - eval_batch_size: 8 |
| - seed: 42 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: linear |
| - num_epochs: 10 |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
| |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
| | 1.1723 | 1.0 | 664 | 0.9597 | 0.1022 | 0.0284 | 0.0445 | 0.7705 | |
| | 1.0015 | 2.0 | 1328 | 0.9761 | 0.0908 | 0.0906 | 0.0907 | 0.7382 | |
| | 0.8659 | 3.0 | 1992 | 0.9519 | 0.1174 | 0.0808 | 0.0957 | 0.7578 | |
| | 0.6297 | 4.0 | 2656 | 1.0252 | 0.0920 | 0.0995 | 0.0956 | 0.7285 | |
| | 0.5716 | 5.0 | 3320 | 1.0423 | 0.1004 | 0.0879 | 0.0938 | 0.7402 | |
| | 0.5236 | 6.0 | 3984 | 1.0918 | 0.1041 | 0.0906 | 0.0969 | 0.7435 | |
| | 0.3943 | 7.0 | 4648 | 1.1581 | 0.0911 | 0.1030 | 0.0967 | 0.7060 | |
| | 0.3713 | 8.0 | 5312 | 1.2021 | 0.0902 | 0.0933 | 0.0917 | 0.7099 | |
| | 0.3525 | 9.0 | 5976 | 1.2281 | 0.0918 | 0.0986 | 0.0951 | 0.7148 | |
| | 0.296 | 10.0 | 6640 | 1.2455 | 0.0809 | 0.0915 | 0.0859 | 0.7099 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.30.2 |
| - Pytorch 2.3.1+cu121 |
| - Datasets 2.20.0 |
| - Tokenizers 0.13.3 |
|
|
