metadata
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
model-index:
- name: plm-nsp-1000
results: []
plm-nsp-1000
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5632
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: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6837 | 1.0 | 16 | 0.6045 |
| 0.531 | 2.0 | 32 | 0.3439 |
| 0.2985 | 3.0 | 48 | 0.3287 |
| 0.1592 | 4.0 | 64 | 0.3131 |
| 0.1162 | 5.0 | 80 | 0.3560 |
| 0.0749 | 6.0 | 96 | 0.4225 |
| 0.0636 | 7.0 | 112 | 0.5632 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1