flan-t5-loratuned
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: 1.0054
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: 0.001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.2532 | 0.3 | 230 | 1.1089 |
1.2188 | 0.59 | 460 | 1.0727 |
1.1733 | 0.89 | 690 | 1.0573 |
1.1732 | 1.18 | 920 | 1.0404 |
1.1153 | 1.48 | 1150 | 1.0268 |
1.1292 | 1.77 | 1380 | 1.0281 |
1.06 | 2.07 | 1610 | 1.0142 |
1.0786 | 2.36 | 1840 | 1.0093 |
1.0486 | 2.66 | 2070 | 1.0096 |
1.03 | 2.95 | 2300 | 1.0054 |
Framework versions
- PEFT 0.11.1
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 10
Unable to determine this model’s pipeline type. Check the
docs
.