|
--- |
|
license: mit |
|
base_model: roberta-base |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: roberta-base-nsp-10000-1e-06-16 |
|
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. --> |
|
|
|
# roberta-base-nsp-10000-1e-06-16 |
|
|
|
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2827 |
|
|
|
## 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-06 |
|
- train_batch_size: 64 |
|
- eval_batch_size: 1024 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 40 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| No log | 1.0 | 157 | 0.6924 | |
|
| 0.6939 | 2.0 | 314 | 0.6904 | |
|
| 0.6909 | 3.0 | 471 | 0.6734 | |
|
| 0.6456 | 4.0 | 628 | 0.4767 | |
|
| 0.6456 | 5.0 | 785 | 0.3638 | |
|
| 0.4555 | 6.0 | 942 | 0.3189 | |
|
| 0.3506 | 7.0 | 1099 | 0.3019 | |
|
| 0.3029 | 8.0 | 1256 | 0.3013 | |
|
| 0.2722 | 9.0 | 1413 | 0.3003 | |
|
| 0.2722 | 10.0 | 1570 | 0.2986 | |
|
| 0.2582 | 11.0 | 1727 | 0.2850 | |
|
| 0.237 | 12.0 | 1884 | 0.2805 | |
|
| 0.2182 | 13.0 | 2041 | 0.2884 | |
|
| 0.2182 | 14.0 | 2198 | 0.2844 | |
|
| 0.208 | 15.0 | 2355 | 0.2876 | |
|
| 0.2026 | 16.0 | 2512 | 0.2927 | |
|
| 0.1908 | 17.0 | 2669 | 0.2827 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|