metadata

license: apache-2.0
library_name: peft
tags:
  - generated_from_trainer
metrics:
  - rouge
  - f1
base_model: google/flan-t5-base
model-index:
  - name: flan-t5-small-esnli-lora
    results: []

flan-t5-small-esnli-lora

This model is a fine-tuned version of google/flan-t5-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.6258
Rouge1: 0.6257
Rouge2: 0.4156
Rougel: 0.5682
F1: 0.8850

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: 0.001
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	F1
1.1793	0.25	8584	1.7215	0.6161	0.4037	0.5577	0.8738
1.1408	0.5	17168	1.6903	0.6194	0.4096	0.5615	0.8730
1.1122	0.75	25752	1.6155	0.6267	0.4179	0.5693	0.8832
1.0929	1.0	34336	1.6258	0.6257	0.4156	0.5682	0.8850

Framework versions

PEFT 0.8.2
Transformers 4.38.1
Pytorch 2.1.2
Datasets 2.17.1
Tokenizers 0.15.1