metadata
base_model: agusbrusco/bert_adaptation_martin_fierro
tags:
- generated_from_trainer
model-index:
- name: bert_adaptation_peppa_pig
results: []
bert_adaptation_peppa_pig
This model is a fine-tuned version of agusbrusco/bert_adaptation_martin_fierro on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.7256
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.1797 | 1.0 | 70 | 2.5543 |
| 2.3384 | 2.0 | 140 | 2.5390 |
| 2.2091 | 3.0 | 210 | 2.3234 |
| 1.9889 | 4.0 | 280 | 2.0118 |
| 1.9684 | 5.0 | 350 | 2.0932 |
| 1.8202 | 6.0 | 420 | 1.8260 |
| 1.6815 | 7.0 | 490 | 1.8649 |
| 1.6206 | 8.0 | 560 | 2.0040 |
| 1.5818 | 9.0 | 630 | 1.8634 |
| 1.529 | 10.0 | 700 | 1.9388 |
| 1.5113 | 11.0 | 770 | 1.7657 |
| 1.3993 | 12.0 | 840 | 1.7469 |
| 1.4784 | 13.0 | 910 | 1.7877 |
| 1.434 | 14.0 | 980 | 1.8657 |
| 1.3549 | 15.0 | 1050 | 1.8388 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0