metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: add_bert_12_layer_model_complete_training_new
results: []
add_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: 6.0612
- Accuracy: 0.1510
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 |
|---|---|---|---|---|
| 6.6173 | 0.08 | 10000 | 6.5823 | 0.1275 |
| 6.4901 | 0.16 | 20000 | 6.3925 | 0.1398 |
| 6.2875 | 0.25 | 30000 | 6.3106 | 0.1439 |
| 6.2516 | 0.33 | 40000 | 6.2511 | 0.1465 |
| 6.2457 | 0.41 | 50000 | 6.2064 | 0.1478 |
| 6.1715 | 0.49 | 60000 | 6.1655 | 0.1486 |
| 6.0838 | 0.57 | 70000 | 6.1332 | 0.1494 |
| 6.1575 | 0.66 | 80000 | 6.1049 | 0.1503 |
| 6.0773 | 0.74 | 90000 | 6.0814 | 0.1504 |
| 6.1838 | 0.82 | 100000 | 6.0612 | 0.1510 |
Framework versions
- Transformers 4.30.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3