T5-PEFT-3 / README.md
jgibb's picture
training completed[prod]: T5-PEFT-3
d4ecda3 verified
---
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: t5-base
model-index:
- name: T5-PEFT-3
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-PEFT-3
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1705
## 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: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 0.18 | 250 | 1.3105 |
| 1.7303 | 0.35 | 500 | 1.2574 |
| 1.7303 | 0.53 | 750 | 1.2259 |
| 1.3176 | 0.71 | 1000 | 1.2101 |
| 1.3176 | 0.89 | 1250 | 1.2009 |
| 1.2971 | 1.06 | 1500 | 1.1895 |
| 1.2971 | 1.24 | 1750 | 1.1828 |
| 1.2582 | 1.42 | 2000 | 1.1804 |
| 1.2582 | 1.6 | 2250 | 1.1763 |
| 1.2579 | 1.77 | 2500 | 1.1730 |
| 1.2579 | 1.95 | 2750 | 1.1705 |
### Framework versions
- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2