|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: re-irr-sv-agr-transformer-4 |
|
|
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. --> |
|
|
|
|
|
# re-irr-sv-agr-transformer-4 |
|
|
|
|
|
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: 3.8889 |
|
|
|
|
|
## 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: 4 |
|
|
- 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.2133 | 0.03 | 76320 | 4.2076 | |
|
|
| 4.0078 | 1.03 | 152640 | 4.0406 | |
|
|
| 3.9019 | 0.03 | 228960 | 3.9673 | |
|
|
| 3.8342 | 1.03 | 305280 | 3.9273 | |
|
|
| 3.7842 | 0.03 | 381600 | 3.9023 | |
|
|
| 3.7453 | 1.03 | 457920 | 3.8877 | |
|
|
| 3.7122 | 0.03 | 534240 | 3.8773 | |
|
|
| 3.6801 | 0.03 | 610560 | 3.8725 | |
|
|
| 3.6523 | 1.03 | 686880 | 3.8682 | |
|
|
| 3.6281 | 0.03 | 763200 | 3.8650 | |
|
|
| 3.6022 | 1.03 | 839520 | 3.8651 | |
|
|
| 3.5871 | 0.03 | 915840 | 3.8637 | |
|
|
| 3.5709 | 1.03 | 992160 | 3.8647 | |
|
|
| 3.5497 | 0.03 | 1068480 | 3.8658 | |
|
|
| 3.5332 | 0.03 | 1144800 | 3.8667 | |
|
|
| 3.5166 | 1.03 | 1221120 | 3.8687 | |
|
|
| 3.4988 | 0.03 | 1297440 | 3.8686 | |
|
|
| 3.484 | 1.03 | 1373760 | 3.8692 | |
|
|
| 3.4711 | 0.03 | 1450080 | 3.8724 | |
|
|
| 3.463 | 1.03 | 1526400 | 3.8742 | |
|
|
| 3.4548 | 0.03 | 1602720 | 3.8753 | |
|
|
| 3.4478 | 1.03 | 1679040 | 3.8769 | |
|
|
| 3.4397 | 0.03 | 1755360 | 3.8786 | |
|
|
| 3.4264 | 1.03 | 1831680 | 3.8802 | |
|
|
| 3.4143 | 0.03 | 1908000 | 3.8824 | |
|
|
| 3.4034 | 1.03 | 1984320 | 3.8831 | |
|
|
| 3.3907 | 0.03 | 2060640 | 3.8834 | |
|
|
| 3.3843 | 1.03 | 2136960 | 3.8860 | |
|
|
| 3.3732 | 0.03 | 2213280 | 3.8868 | |
|
|
| 3.3616 | 0.03 | 2289600 | 3.8872 | |
|
|
| 3.3499 | 1.03 | 2365920 | 3.8889 | |
|
|
| 3.3388 | 0.03 | 2442240 | 3.8892 | |
|
|
| 3.3263 | 1.03 | 2518560 | 3.8893 | |
|
|
| 3.316 | 0.03 | 2594880 | 3.8906 | |
|
|
| 3.3078 | 1.03 | 2671200 | 3.8908 | |
|
|
| 3.3029 | 0.03 | 2747520 | 3.8910 | |
|
|
| 3.2953 | 1.03 | 2823840 | 3.8906 | |
|
|
| 3.2926 | 0.03 | 2900160 | 3.8910 | |
|
|
| 3.2871 | 1.03 | 2976480 | 3.8899 | |
|
|
| 3.2795 | 0.02 | 3052726 | 3.8889 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
