metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: google/bigbird-pegasus-large-bigpatent
metrics:
- rouge
model-index:
- name: bigbird_lora_multi_lexsum_bfloat16
results: []
bigbird_lora_multi_lexsum_bfloat16
This model is a fine-tuned version of google/bigbird-pegasus-large-bigpatent on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 9.2417
- Rouge1: 0.1892
- Rouge2: 0.0164
- Rougel: 0.1384
- Rougelsum: 0.1384
- Gen Len: 214.7444
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: 2e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 9.2381 | 1.0 | 648 | 9.2448 | 0.1912 | 0.0175 | 0.1409 | 0.141 | 225.5222 |
| 9.1638 | 2.0 | 1296 | 9.2417 | 0.1892 | 0.0164 | 0.1384 | 0.1384 | 214.7444 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.0.dev0
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2