metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: distilbert-base-uncased
datasets:
- pubmed-summarization
model-index:
- name: distilbert-base-uncased-finetuned-pubmed-lora-trained-tabbas97
results: []
distilbert-base-uncased-finetuned-pubmed-lora-trained-tabbas97
This model is a fine-tuned version of distilbert-base-uncased on the pubmed-summarization dataset. It achieves the following results on the evaluation set:
- Loss: 1.9835
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: 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: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.2356 | 0.4 | 500 | 2.0414 |
| 2.161 | 0.8 | 1000 | 2.0307 |
| 2.1446 | 1.2 | 1500 | 1.9946 |
| 2.143 | 1.6 | 2000 | 2.0254 |
| 2.1318 | 2.0 | 2500 | 1.9951 |
| 2.133 | 2.4 | 3000 | 2.0143 |
| 2.1321 | 2.8 | 3500 | 1.9991 |
| 2.1268 | 3.2 | 4000 | 1.9789 |
| 2.1169 | 3.6 | 4500 | 1.9736 |
| 2.1254 | 4.0 | 5000 | 1.9745 |
Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1