|
|
--- |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
base_model: google/flan-t5-large |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: t5-large-fft |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# t5-large-fft |
|
|
|
|
|
This model is a fine-tuned version of [google/flan-t5-large](https://huggingface.co/google/flan-t5-large) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.0427 |
|
|
|
|
|
## 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: 0.0001 |
|
|
- train_batch_size: 16 |
|
|
- eval_batch_size: 16 |
|
|
- seed: 42 |
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 2 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 0.0725 | 0.2 | 500 | 0.1335 | |
|
|
| 0.0884 | 0.4 | 1000 | 0.0830 | |
|
|
| 0.0535 | 0.6 | 1500 | 0.0643 | |
|
|
| 0.0713 | 0.8 | 2000 | 0.0449 | |
|
|
| 0.0486 | 1.0 | 2500 | 0.0437 | |
|
|
| 0.041 | 1.2 | 3000 | 0.0433 | |
|
|
| 0.0478 | 1.4 | 3500 | 0.0430 | |
|
|
| 0.0472 | 1.6 | 4000 | 0.0428 | |
|
|
| 0.0461 | 1.8 | 4500 | 0.0427 | |
|
|
| 0.0667 | 2.0 | 5000 | 0.0427 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.47.1 |
|
|
- Pytorch 2.5.1+cu124 |
|
|
- Datasets 3.2.0 |
|
|
- Tokenizers 0.21.0 |
|
|
|
