| --- |
| license: apache-2.0 |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| - precision |
| - recall |
| model-index: |
| - name: baseline_nli_bert |
| 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. --> |
|
|
| # baseline_nli_bert |
|
|
| This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.9280 |
| - Accuracy: 0.6063 |
| - Precision: 0.6063 |
| - Recall: 0.6063 |
| - F1 Score: 0.6088 |
|
|
| ## 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: 3e-06 |
| - train_batch_size: 4 |
| - eval_batch_size: 4 |
| - seed: 101 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: linear |
| - num_epochs: 6 |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 Score | |
| |:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|:--------:| |
| | 1.0366 | 1.0 | 2583 | 0.9579 | 0.5603 | 0.5603 | 0.5603 | 0.5638 | |
| | 0.9416 | 2.0 | 5166 | 0.9206 | 0.5826 | 0.5826 | 0.5826 | 0.5877 | |
| | 0.8889 | 3.0 | 7749 | 0.9085 | 0.5981 | 0.5981 | 0.5981 | 0.6025 | |
| | 0.8539 | 4.0 | 10332 | 0.9176 | 0.6054 | 0.6054 | 0.6054 | 0.6089 | |
| | 0.8323 | 5.0 | 12915 | 0.9201 | 0.6049 | 0.6049 | 0.6049 | 0.6066 | |
| | 0.811 | 6.0 | 15498 | 0.9280 | 0.6063 | 0.6063 | 0.6063 | 0.6088 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.27.3 |
| - Pytorch 1.12.1 |
| - Datasets 2.11.0 |
| - Tokenizers 0.13.2 |
|
|
