metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: bert-base-cased
model-index:
- name: bert-base-cased-finetuned-Astronomy_Thesaurus
results: []
bert-base-cased-finetuned-Astronomy_Thesaurus
This model is a fine-tuned version of bert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.4679
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 |
|---|---|---|---|
| 8.284 | 1.0 | 879 | 4.3823 |
| 4.4381 | 2.0 | 1758 | 3.9386 |
| 4.1111 | 3.0 | 2637 | 3.7912 |
| 3.986 | 4.0 | 3516 | 3.6484 |
| 3.9316 | 5.0 | 4395 | 3.5765 |
| 3.8624 | 6.0 | 5274 | 3.5439 |
| 3.8162 | 7.0 | 6153 | 3.5072 |
| 3.7915 | 8.0 | 7032 | 3.5043 |
| 3.7814 | 9.0 | 7911 | 3.5015 |
| 3.7804 | 10.0 | 8790 | 3.4679 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1