metadata
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
model-index:
- name: roberta-base-pretrained-perigon200k
results: []
roberta-base-pretrained-perigon200k
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9840
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: 8.5e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.19
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.4678 | 1.0 | 5480 | 1.3180 |
| 1.3713 | 2.0 | 10960 | 1.2695 |
| 1.2673 | 3.0 | 16440 | 1.1842 |
| 1.211 | 4.0 | 21920 | 1.1350 |
| 1.1646 | 5.0 | 27400 | 1.0997 |
| 1.1181 | 6.0 | 32880 | 1.0630 |
| 1.0859 | 7.0 | 38360 | 1.0344 |
| 1.0561 | 8.0 | 43840 | 1.0126 |
| 1.0244 | 9.0 | 49320 | 0.9944 |
| 1.0006 | 10.0 | 54800 | 0.9881 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3