Hugging Face's logo

zemaia
/
e500_lr2e-05

Fill-Mask
Transformers
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
e500_lr2e-05 / README.md
zemaia's picture
zemaia
End of training
f40213e verified
preview code
|
raw
history blame
1.61 kB
metadata
library_name: transformers
base_model: adalbertojunior/distilbert-portuguese-cased
tags:
  - generated_from_trainer
model-index:
  - name: e500_lr2e-05
    results: []

e500_lr2e-05

This model is a fine-tuned version of adalbertojunior/distilbert-portuguese-cased on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 2.8984

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: 256
  • eval_batch_size: 512
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 500
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
6.2503 100.0 100 4.9669
4.2273 200.0 200 3.8103
3.384 300.0 300 3.3028
2.989 400.0 400 2.8012
2.8123 500.0 500 2.9104

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.1+cu121
  • Datasets 3.0.1
  • Tokenizers 0.19.1