metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: led-base-16384-biolaysum-both-annotated_original
results: []
led-base-16384-biolaysum-both-annotated_original
This model is a fine-tuned version of allenai/led-base-16384 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.2291
- Rouge1: 0.4024
- Rouge2: 0.1404
- Rougel: 0.1995
- Rougelsum: 0.1995
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: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 2.3052 | 0.69 | 5000 | 2.2666 | 0.4001 | 0.1388 | 0.1983 | 0.1983 |
| 2.0681 | 1.37 | 10000 | 2.2291 | 0.4024 | 0.1404 | 0.1995 | 0.1995 |
| 1.9434 | 2.06 | 15000 | 2.3015 | 0.4005 | 0.1385 | 0.1992 | 0.1992 |
| 1.9203 | 2.75 | 20000 | 2.3104 | 0.3909 | 0.1315 | 0.1940 | 0.1939 |
| 1.7928 | 3.43 | 25000 | 2.3387 | 0.3912 | 0.1314 | 0.1919 | 0.1918 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1
- Datasets 2.10.1
- Tokenizers 0.12.1