metadata
library_name: peft
license: apache-2.0
base_model: bert-base-uncased
tags:
- base_model:adapter:bert-base-uncased
- lora
- transformers
model-index:
- name: bert-from-single-text-file
results: []
bert-from-single-text-file
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.7947
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.9659 | 0.1050 | 200 | 2.9105 |
| 2.8784 | 0.2100 | 400 | 2.8161 |
| 2.83 | 0.3150 | 600 | 2.8043 |
| 2.8066 | 0.4199 | 800 | 2.8001 |
| 2.8438 | 0.5249 | 1000 | 2.7993 |
| 2.8466 | 0.6299 | 1200 | 2.7969 |
| 2.7455 | 0.7349 | 1400 | 2.7961 |
| 2.8339 | 0.8399 | 1600 | 2.7949 |
| 2.7977 | 0.9449 | 1800 | 2.7947 |
Framework versions
- PEFT 0.17.0
- Transformers 4.55.1
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.21.4