gyr66/relation_extraction_roberta_base

1---2license: mit3base_model: roberta-base4tags:5- generated_from_trainer6metrics:7- f18model-index:9- name: relation_extraction_roberta_base10  results: []11---12 13<!-- This model card has been generated automatically according to the information the Trainer had access to. You14should probably proofread and complete it, then remove this comment. -->15 16# relation_extraction_roberta_base17 18This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.19It achieves the following results on the evaluation set:20- Loss: 2.512021- F1: 0.429222 23## Model description24 25More information needed26 27## Intended uses & limitations28 29More information needed30 31## Training and evaluation data32 33More information needed34 35## Training procedure36 37### Training hyperparameters38 39The following hyperparameters were used during training:40- learning_rate: 5e-0541- train_batch_size: 6442- eval_batch_size: 6443- seed: 4244- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0845- lr_scheduler_type: linear46- num_epochs: 10.047 48### Training results49 50| Training Loss | Epoch | Step | Validation Loss | F1     |51|:-------------:|:-----:|:----:|:---------------:|:------:|52| 2.8498        | 1.0   | 107  | 2.6698          | 0.0540 |53| 2.4514        | 2.0   | 214  | 2.2383          | 0.1557 |54| 2.0199        | 3.0   | 321  | 1.9596          | 0.2756 |55| 1.6452        | 4.0   | 428  | 1.9246          | 0.3251 |56| 1.2583        | 5.0   | 535  | 1.9095          | 0.3797 |57| 0.9493        | 6.0   | 642  | 2.2248          | 0.3964 |58| 0.6915        | 7.0   | 749  | 2.1882          | 0.4008 |59| 0.4993        | 8.0   | 856  | 2.3672          | 0.4258 |60| 0.354         | 9.0   | 963  | 2.5120          | 0.4292 |61| 0.262         | 10.0  | 1070 | 2.5574          | 0.4290 |62 63 64### Framework versions65 66- Transformers 4.35.267- Pytorch 2.1.0+cu12168- Datasets 2.16.069- Tokenizers 0.15.070