metadata
library_name: peft
tags:
- generated_from_trainer
base_model: allenai/scibert_scivocab_uncased
model-index:
- name: scibert_scivocab_uncased-finetuned-Astronomy_Thesaurus
results: []
scibert_scivocab_uncased-finetuned-Astronomy_Thesaurus
This model is a fine-tuned version of allenai/scibert_scivocab_uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3610
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.5303 | 1.0 | 879 | 1.3800 |
| 1.4977 | 2.0 | 1758 | 1.4101 |
| 1.4942 | 3.0 | 2637 | 1.3678 |
| 1.4662 | 4.0 | 3516 | 1.3817 |
| 1.4748 | 5.0 | 4395 | 1.3750 |
| 1.4629 | 6.0 | 5274 | 1.3611 |
| 1.4763 | 7.0 | 6153 | 1.3643 |
| 1.453 | 8.0 | 7032 | 1.3713 |
| 1.4603 | 9.0 | 7911 | 1.3871 |
| 1.4697 | 10.0 | 8790 | 1.3610 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1