metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: bert_12_layer_model_v1_complete_training_new_wt_init
results: []
bert_12_layer_model_v1_complete_training_new_wt_init
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.4868
- Accuracy: 0.4070
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 |
|---|---|---|---|---|
| 6.4098 | 0.08 | 10000 | 6.3595 | 0.1321 |
| 6.0989 | 0.16 | 20000 | 6.0506 | 0.1496 |
| 5.8451 | 0.25 | 30000 | 5.7723 | 0.1641 |
| 5.2201 | 0.33 | 40000 | 4.9320 | 0.2601 |
| 4.7956 | 0.41 | 50000 | 4.5292 | 0.2997 |
| 4.5545 | 0.49 | 60000 | 4.3060 | 0.3207 |
| 4.1581 | 0.57 | 70000 | 3.9311 | 0.3599 |
| 3.9322 | 0.66 | 80000 | 3.7415 | 0.3793 |
| 3.768 | 0.74 | 90000 | 3.5992 | 0.3948 |
| 3.6454 | 0.82 | 100000 | 3.4868 | 0.4070 |
Framework versions
- Transformers 4.29.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3