metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: bert_12_layer_model_v1
results: []
bert_12_layer_model_v1
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.1713
- Accuracy: 0.5905
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: 5e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 10
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 128
- total_eval_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10000
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 6.293 | 1.0 | 22886 | 5.6395 | 0.1723 |
| 3.7477 | 2.0 | 45772 | 2.6625 | 0.5252 |
| 2.5641 | 3.0 | 68658 | 2.3431 | 0.5673 |
| 2.3563 | 4.0 | 91544 | 2.2188 | 0.5839 |
| 2.2692 | 5.0 | 114430 | 2.1713 | 0.5905 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.14.0a0+410ce96
- Datasets 2.10.0
- Tokenizers 0.13.2