test-trainer / README.md
abischoff's picture
Training completed!
eb40e14 verified
|
Raw History Blame Contribute Delete
1.61 kB
metadata
library_name: transformers
license: mit
base_model: xlm-roberta-base
tags:
  - generated_from_trainer
datasets:
  - generator
model-index:
  - name: test-trainer
    results: []

test-trainer

This model is a fine-tuned version of xlm-roberta-base on the generator dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0057
  • Mse: 0.1064

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: 1
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss Mse
0.0041 1.0 25720 0.0053 0.1029
0.0033 2.0 51440 0.0061 0.1105
0.0042 3.0 77160 0.0061 0.1106
0.0037 4.0 102880 0.0055 0.1044
0.0037 5.0 128600 0.0057 0.1064

Framework versions

  • Transformers 4.45.2
  • Pytorch 2.5.1+cu124
  • Datasets 3.2.0
  • Tokenizers 0.20.3