metadata
license: apache-2.0
base_model: google/flan-t5-base
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: results
results: []
results
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: 1.9124
- Rouge1: 0.5216
- Rouge2: 0.4128
- Rougel: 0.4922
- Rougelsum: 0.4921
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: 0.0003
- train_batch_size: 8
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 67 | 1.7935 | 0.4943 | 0.3583 | 0.4569 | 0.4571 |
| No log | 2.0 | 134 | 1.8658 | 0.4965 | 0.3727 | 0.4638 | 0.4660 |
| No log | 3.0 | 201 | 1.9759 | 0.5087 | 0.3890 | 0.4802 | 0.4787 |
| No log | 4.0 | 268 | 1.9421 | 0.5115 | 0.4107 | 0.4907 | 0.4891 |
| No log | 5.0 | 335 | 1.9124 | 0.5216 | 0.4128 | 0.4922 | 0.4921 |
Framework versions
- Transformers 4.39.0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2