metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: google/flan-t5-large
metrics:
- rouge
model-index:
- name: flan-t5-large-peft-combinedhub
results: []
flan-t5-large-peft-combinedhub
This model is a fine-tuned version of google/flan-t5-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.7588
- Rouge1: 43.5001
- Rouge2: 17.8611
- Rougel: 31.5148
- Rougelsum: 40.2359
- Gen Len: 98.7718
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: 6
- eval_batch_size: 6
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 1.9097 | 1.0 | 2812 | 1.7698 | 43.3373 | 17.6766 | 31.4769 | 40.0561 | 97.4492 |
| 1.8901 | 2.0 | 5624 | 1.7603 | 43.4367 | 17.8114 | 31.5721 | 40.1962 | 100.2230 |
| 1.8854 | 3.0 | 8436 | 1.7588 | 43.5001 | 17.8611 | 31.5148 | 40.2359 | 98.7718 |
Framework versions
- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2