crossroderick's picture
Upload model
2ce12ca verified
|
raw
history blame
1.53 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
base_model: crossroderick/occitan-distilgpt2-medium
model-index:
  - name: occitan-distilgpt2-medium
    results: []

occitan-distilgpt2-medium

This model is a fine-tuned version of crossroderick/occitan-distilgpt2-medium on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 3.3200

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: 5e-05
  • train_batch_size: 12
  • eval_batch_size: 12
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 48
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3.0

Training results

Training Loss Epoch Step Validation Loss
No log 1.0 208 3.5158
No log 2.0 417 3.3596
3.6598 2.99 624 3.3200

Framework versions

  • Transformers 4.38.1
  • Pytorch 2.0.1+cu117
  • Datasets 2.17.1
  • Tokenizers 0.15.2