| | --- |
| | license: apache-2.0 |
| | base_model: bert-large-uncased |
| | tags: |
| | - generated_from_trainer |
| | model-index: |
| | - name: bert-large-22 |
| | results: [] |
| | --- |
| | |
| | <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| | should probably proofread and complete it, then remove this comment. --> |
| |
|
| | # bert-large-22 |
| |
|
| | This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on an unknown dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 5.9292 |
| |
|
| | ## 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: 2e-05 |
| | - train_batch_size: 16 |
| | - eval_batch_size: 16 |
| | - seed: 42 |
| | - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| | - lr_scheduler_type: linear |
| | - num_epochs: 3 |
| |
|
| | ### Training results |
| |
|
| | | Training Loss | Epoch | Step | Validation Loss | |
| | |:-------------:|:-----:|:----:|:---------------:| |
| | | 6.0375 | 0.09 | 5 | 6.0219 | |
| | | 6.0415 | 0.18 | 10 | 6.0159 | |
| | | 6.0408 | 0.27 | 15 | 6.0100 | |
| | | 5.9961 | 0.36 | 20 | 6.0042 | |
| | | 6.0668 | 0.45 | 25 | 5.9988 | |
| | | 6.0106 | 0.55 | 30 | 5.9936 | |
| | | 6.0434 | 0.64 | 35 | 5.9886 | |
| | | 5.9975 | 0.73 | 40 | 5.9838 | |
| | | 6.025 | 0.82 | 45 | 5.9792 | |
| | | 5.9994 | 0.91 | 50 | 5.9746 | |
| | | 5.9914 | 1.0 | 55 | 5.9704 | |
| | | 5.9746 | 1.09 | 60 | 5.9667 | |
| | | 5.9869 | 1.18 | 65 | 5.9629 | |
| | | 5.9517 | 1.27 | 70 | 5.9593 | |
| | | 5.9952 | 1.36 | 75 | 5.9562 | |
| | | 5.9493 | 1.45 | 80 | 5.9531 | |
| | | 5.9658 | 1.55 | 85 | 5.9503 | |
| | | 5.9816 | 1.64 | 90 | 5.9480 | |
| | | 5.9311 | 1.73 | 95 | 5.9456 | |
| | | 5.9632 | 1.82 | 100 | 5.9433 | |
| | | 5.9399 | 1.91 | 105 | 5.9413 | |
| | | 5.935 | 2.0 | 110 | 5.9393 | |
| | | 5.9181 | 2.09 | 115 | 5.9375 | |
| | | 5.8885 | 2.18 | 120 | 5.9360 | |
| | | 5.9249 | 2.27 | 125 | 5.9344 | |
| | | 5.9314 | 2.36 | 130 | 5.9335 | |
| | | 5.904 | 2.45 | 135 | 5.9321 | |
| | | 5.9061 | 2.55 | 140 | 5.9313 | |
| | | 5.932 | 2.64 | 145 | 5.9306 | |
| | | 5.9327 | 2.73 | 150 | 5.9300 | |
| | | 5.9391 | 2.82 | 155 | 5.9296 | |
| | | 5.9608 | 2.91 | 160 | 5.9293 | |
| | | 5.9388 | 3.0 | 165 | 5.9292 | |
| |
|
| |
|
| | ### Framework versions |
| |
|
| | - Transformers 4.34.1 |
| | - Pytorch 2.0.1+cu118 |
| | - Datasets 2.14.5 |
| | - Tokenizers 0.14.1 |
| |
|
