|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: rel-cl-transformer-2 |
|
|
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. --> |
|
|
|
|
|
# rel-cl-transformer-2 |
|
|
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 3.8701 |
|
|
|
|
|
## 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: 5e-05 |
|
|
- train_batch_size: 32 |
|
|
- eval_batch_size: 32 |
|
|
- seed: 2 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- training_steps: 3052726 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.2371 | 0.03 | 76319 | 4.2004 | |
|
|
| 4.0294 | 0.03 | 152638 | 4.0314 | |
|
|
| 3.9211 | 0.03 | 228957 | 3.9574 | |
|
|
| 3.8523 | 0.03 | 305276 | 3.9164 | |
|
|
| 3.8001 | 0.03 | 381595 | 3.8913 | |
|
|
| 3.7553 | 0.03 | 457914 | 3.8747 | |
|
|
| 3.7228 | 0.03 | 534233 | 3.8648 | |
|
|
| 3.6953 | 0.03 | 610552 | 3.8573 | |
|
|
| 3.6645 | 0.03 | 686871 | 3.8537 | |
|
|
| 3.6436 | 0.03 | 763190 | 3.8506 | |
|
|
| 3.6231 | 1.03 | 839509 | 3.8503 | |
|
|
| 3.5992 | 0.03 | 915829 | 3.8441 | |
|
|
| 3.577 | 1.03 | 992149 | 3.8451 | |
|
|
| 3.5583 | 0.03 | 1068469 | 3.8452 | |
|
|
| 3.5441 | 1.03 | 1144789 | 3.8459 | |
|
|
| 3.5334 | 0.03 | 1221109 | 3.8479 | |
|
|
| 3.5167 | 1.03 | 1297429 | 3.8502 | |
|
|
| 3.5026 | 0.03 | 1373749 | 3.8508 | |
|
|
| 3.4876 | 1.03 | 1450069 | 3.8539 | |
|
|
| 3.4805 | 0.03 | 1526389 | 3.8549 | |
|
|
| 3.4714 | 1.03 | 1602709 | 3.8570 | |
|
|
| 3.4625 | 0.03 | 1679029 | 3.8585 | |
|
|
| 3.4532 | 1.03 | 1755349 | 3.8609 | |
|
|
| 3.441 | 0.03 | 1831669 | 3.8635 | |
|
|
| 3.4268 | 1.03 | 1907989 | 3.8636 | |
|
|
| 3.4129 | 0.03 | 1984309 | 3.8653 | |
|
|
| 3.4015 | 1.03 | 2060629 | 3.8678 | |
|
|
| 3.3925 | 0.03 | 2136949 | 3.8691 | |
|
|
| 3.3798 | 1.03 | 2213269 | 3.8692 | |
|
|
| 3.3677 | 0.03 | 2289589 | 3.8705 | |
|
|
| 3.3609 | 1.03 | 2365909 | 3.8714 | |
|
|
| 3.3531 | 0.03 | 2442229 | 3.8720 | |
|
|
| 3.3438 | 1.03 | 2518549 | 3.8738 | |
|
|
| 3.3347 | 0.03 | 2594869 | 3.8732 | |
|
|
| 3.3247 | 0.03 | 2671189 | 3.8724 | |
|
|
| 3.3184 | 1.03 | 2747509 | 3.8731 | |
|
|
| 3.3125 | 0.03 | 2823829 | 3.8732 | |
|
|
| 3.304 | 1.03 | 2900149 | 3.8727 | |
|
|
| 3.2998 | 0.03 | 2976469 | 3.8713 | |
|
|
| 3.293 | 1.02 | 3052726 | 3.8701 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
