gpt-for-est-base / README.md
mphi's picture
Newly created GPT for Estonian, base version.
44b40ec
|
raw
history blame
No virus
972 Bytes
metadata
tags:
  - generated_from_trainer
model-index:
  - name: gpt4est-s
    results: []

gpt4est-s

This model is a ...

It achieves the following results on the evaluation set:

  • Loss: 3.9846

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: 0.0003
  • train_batch_size: 6
  • eval_batch_size: 6
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3.0

Training results

Framework versions

  • Transformers 4.13.0.dev0
  • Pytorch 1.10.0+cu102
  • Datasets 1.15.1
  • Tokenizers 0.10.3