bert_12_layer_model_v1_complete_training_new_wt_init_72
This model is a fine-tuned version of gokuls/bert_12_layer_model_v1_complete_training_new_wt_init_48 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.4160
- Accuracy: 0.5550
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 |
|---|---|---|---|---|
| 2.7356 | 0.08 | 10000 | 2.6109 | 0.5289 |
| 2.7065 | 0.16 | 20000 | 2.5861 | 0.5320 |
| 2.6771 | 0.25 | 30000 | 2.5637 | 0.5353 |
| 2.6618 | 0.33 | 40000 | 2.5359 | 0.5390 |
| 2.6259 | 0.41 | 50000 | 2.5093 | 0.5425 |
| 2.6085 | 0.49 | 60000 | 2.4897 | 0.5452 |
| 2.5789 | 0.57 | 70000 | 2.4685 | 0.5479 |
| 2.5586 | 0.66 | 80000 | 2.4488 | 0.5502 |
| 2.5367 | 0.74 | 90000 | 2.4289 | 0.5525 |
| 2.5189 | 0.82 | 100000 | 2.4160 | 0.5550 |
Framework versions
- Transformers 4.29.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3