joelito/legal-irish-roberta-base

Model

0

stars

7

commits

1

linked in READMEs

Feb 10, 2023

updated

endpoints_compatible
fill-mask
generated_from_trainer
pytorch
roberta
tensorboard
transformers
Browse cluster: Multilingual Legal NLP Models

README

legal-irish-roberta-base

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7328

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: 0.0001
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • distributed_type: tpu
  • num_devices: 8
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 512
  • total_eval_batch_size: 128
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.05
  • training_steps: 200000

Training results

Training LossEpochStepValidation Loss
0.5892228.0500000.7659
0.4497456.01000000.7421
0.3906684.01500000.7443
0.3906913.02000000.7328

Framework versions

  • Transformers 4.20.1
  • Pytorch 1.12.0+cu102
  • Datasets 2.9.0
  • Tokenizers 0.12.0

Contributors

joelniklaus

7 commits

joelito/legal-irish-roberta-base

Model

0

stars

7

commits

1

linked in READMEs

Feb 10, 2023

updated

endpoints_compatible
fill-mask
generated_from_trainer
pytorch
roberta
tensorboard
transformers
Browse cluster: Multilingual Legal NLP Models

README

legal-irish-roberta-base

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7328

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: 0.0001
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • distributed_type: tpu
  • num_devices: 8
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 512
  • total_eval_batch_size: 128
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.05
  • training_steps: 200000

Training results

Training LossEpochStepValidation Loss
0.5892228.0500000.7659
0.4497456.01000000.7421
0.3906684.01500000.7443
0.3906913.02000000.7328

Framework versions

  • Transformers 4.20.1
  • Pytorch 1.12.0+cu102
  • Datasets 2.9.0
  • Tokenizers 0.12.0

Contributors

joelniklaus

7 commits