|
|
--- |
|
|
library_name: peft |
|
|
license: apache-2.0 |
|
|
base_model: t5-small |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: build_your_circuit_lora |
|
|
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. --> |
|
|
|
|
|
# build_your_circuit_lora |
|
|
|
|
|
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.9179 |
|
|
|
|
|
## 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: 8 |
|
|
- eval_batch_size: 8 |
|
|
- 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: 20 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-------:|:-----:|:---------------:| |
|
|
| 5.6558 | 0.5263 | 500 | 2.7776 | |
|
|
| 2.7422 | 1.0526 | 1000 | 1.9060 | |
|
|
| 2.1288 | 1.5789 | 1500 | 1.6338 | |
|
|
| 1.863 | 2.1053 | 2000 | 1.4802 | |
|
|
| 1.6722 | 2.6316 | 2500 | 1.3769 | |
|
|
| 1.5777 | 3.1579 | 3000 | 1.2927 | |
|
|
| 1.4825 | 3.6842 | 3500 | 1.2269 | |
|
|
| 1.43 | 4.2105 | 4000 | 1.1850 | |
|
|
| 1.3737 | 4.7368 | 4500 | 1.1518 | |
|
|
| 1.323 | 5.2632 | 5000 | 1.1274 | |
|
|
| 1.2881 | 5.7895 | 5500 | 1.0999 | |
|
|
| 1.2751 | 6.3158 | 6000 | 1.0804 | |
|
|
| 1.2417 | 6.8421 | 6500 | 1.0641 | |
|
|
| 1.2058 | 7.3684 | 7000 | 1.0429 | |
|
|
| 1.1967 | 7.8947 | 7500 | 1.0309 | |
|
|
| 1.1881 | 8.4211 | 8000 | 1.0186 | |
|
|
| 1.1615 | 8.9474 | 8500 | 1.0139 | |
|
|
| 1.1486 | 9.4737 | 9000 | 0.9940 | |
|
|
| 1.139 | 10.0 | 9500 | 0.9825 | |
|
|
| 1.1334 | 10.5263 | 10000 | 0.9786 | |
|
|
| 1.1079 | 11.0526 | 10500 | 0.9731 | |
|
|
| 1.1141 | 11.5789 | 11000 | 0.9648 | |
|
|
| 1.1053 | 12.1053 | 11500 | 0.9613 | |
|
|
| 1.0943 | 12.6316 | 12000 | 0.9539 | |
|
|
| 1.0776 | 13.1579 | 12500 | 0.9502 | |
|
|
| 1.1101 | 13.6842 | 13000 | 0.9415 | |
|
|
| 1.0635 | 14.2105 | 13500 | 0.9373 | |
|
|
| 1.0527 | 14.7368 | 14000 | 0.9371 | |
|
|
| 1.0926 | 15.2632 | 14500 | 0.9317 | |
|
|
| 1.0639 | 15.7895 | 15000 | 0.9310 | |
|
|
| 1.0445 | 16.3158 | 15500 | 0.9272 | |
|
|
| 1.0672 | 16.8421 | 16000 | 0.9260 | |
|
|
| 1.0519 | 17.3684 | 16500 | 0.9227 | |
|
|
| 1.0581 | 17.8947 | 17000 | 0.9203 | |
|
|
| 1.0365 | 18.4211 | 17500 | 0.9193 | |
|
|
| 1.0595 | 18.9474 | 18000 | 0.9178 | |
|
|
| 1.0449 | 19.4737 | 18500 | 0.9179 | |
|
|
| 1.0478 | 20.0 | 19000 | 0.9179 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.15.2 |
|
|
- Transformers 4.55.4 |
|
|
- Pytorch 2.6.0+cu124 |
|
|
- Datasets 3.6.0 |
|
|
- Tokenizers 0.21.2 |
