metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: google/flan-t5-small
model-index:
- name: LoRA-FlanT5-small-v2
results: []
LoRA-FlanT5-small-v2
This model is a fine-tuned version of google/flan-t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1186
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.266 | 0.32 | 250 | 0.1635 |
| 0.181 | 0.64 | 500 | 0.1331 |
| 0.1639 | 0.96 | 750 | 0.1239 |
| 0.1576 | 1.28 | 1000 | 0.1211 |
| 0.154 | 1.61 | 1250 | 0.1196 |
| 0.1527 | 1.93 | 1500 | 0.1192 |
| 0.1535 | 2.25 | 1750 | 0.1189 |
| 0.1527 | 2.57 | 2000 | 0.1188 |
| 0.1525 | 2.89 | 2250 | 0.1187 |
| 0.153 | 3.21 | 2500 | 0.1187 |
| 0.153 | 3.53 | 2750 | 0.1186 |
| 0.1519 | 3.85 | 3000 | 0.1186 |
| 0.152 | 4.17 | 3250 | 0.1186 |
| 0.1508 | 4.49 | 3500 | 0.1186 |
| 0.1531 | 4.82 | 3750 | 0.1186 |
| 0.1513 | 5.14 | 4000 | 0.1186 |
| 0.1513 | 5.46 | 4250 | 0.1186 |
| 0.1518 | 5.78 | 4500 | 0.1186 |
Framework versions
- PEFT 0.10.0
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.15.2