metadata
license: apache-2.0
base_model: bert-base-cased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: imdb
results: []
imdb
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: 0.2749
- Accuracy: 0.9364
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: 0.0005
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.3
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2399 | 1.0 | 2500 | 0.2539 | 0.9037 |
| 0.2454 | 2.0 | 5000 | 0.2753 | 0.9064 |
| 0.2251 | 3.0 | 7500 | 0.2436 | 0.9167 |
| 0.1996 | 4.0 | 10000 | 0.2271 | 0.9246 |
| 0.1845 | 5.0 | 12500 | 0.2116 | 0.9269 |
| 0.205 | 6.0 | 15000 | 0.1946 | 0.9312 |
| 0.1352 | 7.0 | 17500 | 0.2233 | 0.9328 |
| 0.1306 | 8.0 | 20000 | 0.2257 | 0.936 |
| 0.0849 | 9.0 | 22500 | 0.2582 | 0.9372 |
| 0.0609 | 10.0 | 25000 | 0.2749 | 0.9364 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3