SashaSheykina's picture
Training complete
afe982b verified
|
raw
history blame
1.42 kB
metadata
license: mit
base_model: xlnet-base-cased
tags:
  - Text Generation
  - generated_from_trainer
model-index:
  - name: xLNet-finetuned-cXg-nl-to-code
    results: []

xLNet-finetuned-cXg-nl-to-code

This model is a fine-tuned version of xlnet-base-cased on an unknown dataset. It achieves the following results on the evaluation set:

  • eval_loss: 20.6526
  • eval_rouge1: 0.0685
  • eval_rouge2: 0.0062
  • eval_rougeL: 0.0550
  • eval_bleu: 0.8352
  • eval_meteor: 0.1311
  • eval_codebleu: 0.2193
  • eval_runtime: 265.1606
  • eval_samples_per_second: 0.038
  • eval_steps_per_second: 0.004
  • step: 0

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: 32
  • eval_batch_size: 64
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.42.4
  • Pytorch 2.3.1+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1