jangmin's picture
maintain safetensors only & newly trained
9f43e8c
metadata
license: mit
base_model: xlm-roberta-large
tags:
  - generated_from_trainer
metrics:
  - f1
model-index:
  - name: refine-good-name-xlm-roberta
    results: []

refine-good-name-xlm-roberta

This model is a fine-tuned version of xlm-roberta-large on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2236
  • F1: 0.8688

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: 1e-05
  • train_batch_size: 64
  • eval_batch_size: 64
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 6

Training results

Training Loss Epoch Step Validation Loss F1
0.2618 1.0 553 0.2357 0.8314
0.2025 2.0 1106 0.2209 0.8661
0.186 3.0 1659 0.2075 0.8588
0.162 4.0 2212 0.2234 0.8609
0.1428 5.0 2765 0.2233 0.8700
0.1328 6.0 3318 0.2236 0.8688

Framework versions

  • Transformers 4.32.0.dev0
  • Pytorch 2.0.0
  • Datasets 2.14.0
  • Tokenizers 0.13.3