metadata
tags:
- generated_from_trainer
model-index:
- name: bert2bert-cnn_dailymail-fp16-finetuned-1.0.0
results: []
bert2bert-cnn_dailymail-fp16-finetuned-1.0.0
This model is a fine-tuned version of patrickvonplaten/bert2bert-cnn_dailymail-fp16 on an unknown dataset. It achieves the following results on the evaluation set:
- eval_loss: 2.4478
- eval_rouge1: 45.3108
- eval_rouge2: 18.3254
- eval_rougeL: 29.71
- eval_rougeLsum: 41.2888
- eval_runtime: 15495.5669
- eval_samples_per_second: 0.038
- eval_steps_per_second: 0.009
- epoch: 1.0
- step: 586
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1
- Datasets 2.10.0
- Tokenizers 0.13.2