metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: sa_bert_12_layer_model_complete_training_new
results: []
sa_bert_12_layer_model_complete_training_new
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 7.4351
- Accuracy: 0.0442
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: 0.001
- train_batch_size: 64
- eval_batch_size: 64
- 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 |
|---|---|---|---|---|
| 7.2755 | 0.11 | 10000 | 7.2838 | 0.0466 |
| 7.2773 | 0.22 | 20000 | 7.2702 | 0.0466 |
| 7.2658 | 0.33 | 30000 | 7.2628 | 0.0481 |
| 7.2999 | 0.44 | 40000 | 7.3364 | 0.0469 |
| 7.3 | 0.55 | 50000 | 7.3381 | 0.0470 |
| 7.342 | 0.66 | 60000 | 7.3410 | 0.0477 |
| 7.3392 | 0.76 | 70000 | 7.3417 | 0.0477 |
| 7.3357 | 0.87 | 80000 | 7.3412 | 0.0476 |
| 7.3331 | 0.98 | 90000 | 7.4346 | 0.0442 |
| 7.3351 | 1.09 | 100000 | 7.4346 | 0.0443 |
| 7.3352 | 1.2 | 110000 | 7.4352 | 0.0442 |
| 7.3306 | 1.31 | 120000 | 7.4347 | 0.0442 |
| 7.3281 | 1.42 | 130000 | 7.4351 | 0.0442 |
Framework versions
- Transformers 4.29.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3