metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- big_patent
model-index:
- name: led-base-16384-finetuned-big_patent
results: []
led-base-16384-finetuned-big_patent
This model is a fine-tuned version of allenai/led-base-16384 on the big_patent dataset. It achieves the following results on the evaluation set:
- Loss: 2.5094
- Rouge2 Precision: 0.128
- Rouge2 Recall: 0.1325
- Rouge2 Fmeasure: 0.125
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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
|---|---|---|---|---|---|---|
| 2.6657 | 0.4 | 500 | 2.6048 | 0.1211 | 0.131 | 0.121 |
| 2.6099 | 0.8 | 1000 | 2.5094 | 0.128 | 0.1325 | 0.125 |
Framework versions
- Transformers 4.19.3
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1