metadata

library_name: transformers
license: other
base_model: facebook/opt-125m
tags:
  - generated_from_trainer
model-index:
  - name: opt-125m-full-billsum
    results: []

opt-125m-full-billsum

This model is a fine-tuned version of facebook/opt-125m on an unknown dataset.

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: 4
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 1
num_epochs: 3

Training results

Evaluation Results (Validation): {'rouge1': 0.3162, 'rouge2': 0.1076, 'rougeL': 0.21, 'rougeLsum': 0.2332}

Evaluation Results (Test): {'rouge1': 0.4993, 'rouge2': 0.3035, 'rougeL': 0.3973, 'rougeLsum': 0.4228}

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.2.0
Tokenizers 0.21.0