Martin-Fierro / README.md
100realnofake's picture
Upload tokenizer
641ccff verified
metadata
base_model: DeepESP/gpt2-spanish
library_name: transformers
license: mit
tags:
  - generated_from_trainer
model-index:
  - name: Martin-Fierro
    results: []

Martin-Fierro

This model is a fine-tuned version of DeepESP/gpt2-spanish on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 4.8181

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: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 4

Training results

Training Loss Epoch Step Validation Loss
4.9885 1.0 40 4.9655
4.6591 2.0 80 4.8694
4.3143 3.0 120 4.8294
4.1236 4.0 160 4.8181

Framework versions

  • Transformers 4.45.1
  • Pytorch 2.4.1+cu121
  • Datasets 3.0.1
  • Tokenizers 0.20.0