metadata
tags:
- generated_from_trainer
datasets:
- becasv2
model-index:
- name: legalectra-small-spanish-becasv3-1
results: []
legalectra-small-spanish-becasv3-1
This model is a fine-tuned version of mrm8488/legalectra-small-spanish on the becasv2 dataset. It achieves the following results on the evaluation set:
- Loss: 5.6803
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: 10
- eval_batch_size: 10
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 8 | 5.8973 |
| No log | 2.0 | 16 | 5.8415 |
| No log | 3.0 | 24 | 5.7953 |
| No log | 4.0 | 32 | 5.7559 |
| No log | 5.0 | 40 | 5.7244 |
| No log | 6.0 | 48 | 5.7005 |
| No log | 7.0 | 56 | 5.6857 |
| No log | 8.0 | 64 | 5.6803 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0+cu113
- Datasets 2.3.2
- Tokenizers 0.12.1