metadata
license: mit
tags:
- generated_from_trainer
model-index:
- name: BERiT_7000
results: []
BERiT_7000
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 7.5916
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: 5e-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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 7.9484 | 0.19 | 500 | 7.8474 |
| 7.7968 | 0.39 | 1000 | 7.7020 |
| 7.6992 | 0.58 | 1500 | 7.6949 |
| 7.656 | 0.77 | 2000 | 7.6922 |
| 7.68 | 0.97 | 2500 | 7.6863 |
| 7.5952 | 1.16 | 3000 | 7.6523 |
| 7.6441 | 1.36 | 3500 | 7.6523 |
| 7.6178 | 1.55 | 4000 | 7.6128 |
| 7.5977 | 1.74 | 4500 | 7.6556 |
| 7.6087 | 1.94 | 5000 | 7.5990 |
| 7.5734 | 2.13 | 5500 | 7.5997 |
| 7.566 | 2.32 | 6000 | 7.5961 |
| 7.5715 | 2.52 | 6500 | 7.5505 |
| 7.5604 | 2.71 | 7000 | 7.5788 |
| 7.5749 | 2.9 | 7500 | 7.5916 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.2