enriquesaou's picture
End of training
bfa3f03 verified
metadata
license: apache-2.0
base_model: VMware/roberta-base-mrqa
tags:
  - generated_from_trainer
model-index:
  - name: roberta-vmw-mrqa
    results: []

Visualize in Weights & Biases

roberta-vmw-mrqa

This model is a fine-tuned version of VMware/roberta-base-mrqa on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.7997

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: 0.0002
  • train_batch_size: 20
  • eval_batch_size: 20
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss
2.2285 1.0 1399 1.8940
1.521 2.0 2798 1.6821
1.0055 3.0 4197 1.7997

Framework versions

  • Transformers 4.42.0.dev0
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.2
  • Tokenizers 0.19.1