metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: bert_base_24
results: []
bert_base_24
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: 6.0090
- Accuracy: 0.1512
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: 1e-05
- train_batch_size: 48
- eval_batch_size: 48
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10000
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 6.4917 | 0.08 | 10000 | 6.4422 | 0.1406 |
| 6.2848 | 0.16 | 20000 | 6.2644 | 0.1478 |
| 6.1988 | 0.25 | 30000 | 6.1852 | 0.1493 |
| 6.148 | 0.33 | 40000 | 6.1287 | 0.1501 |
| 6.1007 | 0.41 | 50000 | 6.0888 | 0.1501 |
| 6.0721 | 0.49 | 60000 | 6.0555 | 0.1499 |
| 6.0414 | 0.57 | 70000 | 6.0274 | 0.1514 |
| 6.0229 | 0.66 | 80000 | 6.0090 | 0.1512 |
Framework versions
- Transformers 4.30.1
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3