metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
base_model: gokuls/bert_base_48
model-index:
- name: bert_base_96
results: []
bert_base_96
This model is a fine-tuned version of gokuls/bert_base_48 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.6333
- Accuracy: 0.5281
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 |
|---|---|---|---|---|
| 5.6041 | 0.08 | 10000 | 5.5567 | 0.1751 |
| 5.4727 | 0.16 | 20000 | 5.3950 | 0.1953 |
| 5.3385 | 0.25 | 30000 | 5.2277 | 0.2151 |
| 5.2033 | 0.33 | 40000 | 5.0607 | 0.2335 |
| 4.7807 | 0.41 | 50000 | 4.5611 | 0.2910 |
| 4.1994 | 0.49 | 60000 | 4.0039 | 0.3520 |
| 3.8039 | 0.57 | 70000 | 3.6509 | 0.3906 |
| 3.5516 | 0.66 | 80000 | 3.3794 | 0.4263 |
| 3.3199 | 0.74 | 90000 | 3.1446 | 0.4607 |
| 3.1682 | 0.82 | 100000 | 3.0053 | 0.4795 |
| 3.0597 | 0.9 | 110000 | 2.9135 | 0.4919 |
| 2.9814 | 0.98 | 120000 | 2.8331 | 0.5018 |
| 2.907 | 1.07 | 130000 | 2.7724 | 0.5100 |
| 2.8532 | 1.15 | 140000 | 2.7200 | 0.5170 |
| 2.8044 | 1.23 | 150000 | 2.6759 | 0.5227 |
| 2.7694 | 1.31 | 160000 | 2.6333 | 0.5281 |
Framework versions
- Transformers 4.30.1
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3