metadata
license: mit
base_model: FacebookAI/roberta-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: mnlp_nli
results: []
mnlp_nli
This model is a fine-tuned version of FacebookAI/roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4447
- Precision: 0.7537
- Recall: 0.7470
- F1: 0.7443
- Accuracy: 0.7574
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.5182 | 1.0 | 12772 | 1.0468 | 0.7424 | 0.7343 | 0.7312 | 0.7452 |
| 0.4623 | 2.0 | 25544 | 1.1475 | 0.7626 | 0.7477 | 0.7424 | 0.7605 |
| 0.3918 | 3.0 | 38316 | 1.3063 | 0.7479 | 0.7410 | 0.7388 | 0.7509 |
| 0.2978 | 4.0 | 51088 | 1.4447 | 0.7537 | 0.7470 | 0.7443 | 0.7574 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1