metadata
license: apache-2.0
base_model: bert-large-uncased
tags:
- generated_from_trainer
model-index:
- name: dbw-bert-large-1
results: []
dbw-bert-large-1
This model is a fine-tuned version of bert-large-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0728
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-07
- train_batch_size: 64
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.0555 | 0.36 | 200 | 3.2109 |
| 1.2673 | 0.71 | 400 | 1.0203 |
| 0.3153 | 1.07 | 600 | 0.2516 |
| 0.1461 | 1.42 | 800 | 0.1146 |
| 0.1046 | 1.78 | 1000 | 0.0854 |
| 0.0929 | 2.13 | 1200 | 0.0762 |
| 0.085 | 2.49 | 1400 | 0.0734 |
| 0.0881 | 2.84 | 1600 | 0.0728 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0