|
|
--- |
|
|
license: mit |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: BERiT_2000_enriched_optimized |
|
|
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. --> |
|
|
|
|
|
# BERiT_2000_enriched_optimized |
|
|
|
|
|
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: 6.5710 |
|
|
|
|
|
## 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: 6.732413659252984e-05 |
|
|
- train_batch_size: 8 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 10 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
|
| 6.4676 | 0.19 | 500 | 6.1516 | |
|
|
| 6.0191 | 0.39 | 1000 | 5.8660 | |
|
|
| 5.9008 | 0.58 | 1500 | 5.9956 | |
|
|
| 5.7806 | 0.77 | 2000 | 5.7032 | |
|
|
| 5.6932 | 0.97 | 2500 | 5.6910 | |
|
|
| 6.4953 | 1.16 | 3000 | 6.6394 | |
|
|
| 6.6419 | 1.36 | 3500 | 6.6176 | |
|
|
| 6.6462 | 1.55 | 4000 | 6.5961 | |
|
|
| 6.6402 | 1.74 | 4500 | 6.6224 | |
|
|
| 6.6169 | 1.94 | 5000 | 6.6091 | |
|
|
| 6.6396 | 2.13 | 5500 | 6.6443 | |
|
|
| 6.6599 | 2.32 | 6000 | 6.6150 | |
|
|
| 6.5956 | 2.52 | 6500 | 6.6173 | |
|
|
| 6.6397 | 2.71 | 7000 | 6.6038 | |
|
|
| 6.6261 | 2.9 | 7500 | 6.6214 | |
|
|
| 6.6162 | 3.1 | 8000 | 6.6271 | |
|
|
| 6.6102 | 3.29 | 8500 | 6.5843 | |
|
|
| 6.6116 | 3.49 | 9000 | 6.6044 | |
|
|
| 6.6146 | 3.68 | 9500 | 6.6092 | |
|
|
| 6.5922 | 3.87 | 10000 | 6.6182 | |
|
|
| 6.6246 | 4.07 | 10500 | 6.5832 | |
|
|
| 6.6124 | 4.26 | 11000 | 6.6141 | |
|
|
| 6.6002 | 4.45 | 11500 | 6.6385 | |
|
|
| 6.6015 | 4.65 | 12000 | 6.5984 | |
|
|
| 6.6024 | 4.84 | 12500 | 6.6236 | |
|
|
| 6.6097 | 5.03 | 13000 | 6.6254 | |
|
|
| 6.5937 | 5.23 | 13500 | 6.6154 | |
|
|
| 6.5973 | 5.42 | 14000 | 6.5731 | |
|
|
| 6.6141 | 5.62 | 14500 | 6.6308 | |
|
|
| 6.5976 | 5.81 | 15000 | 6.5824 | |
|
|
| 6.5982 | 6.0 | 15500 | 6.6024 | |
|
|
| 6.6032 | 6.2 | 16000 | 6.5891 | |
|
|
| 6.603 | 6.39 | 16500 | 6.5926 | |
|
|
| 6.6089 | 6.58 | 17000 | 6.6090 | |
|
|
| 6.6067 | 6.78 | 17500 | 6.6137 | |
|
|
| 6.5718 | 6.97 | 18000 | 6.5817 | |
|
|
| 6.6036 | 7.16 | 18500 | 6.6008 | |
|
|
| 6.6001 | 7.36 | 19000 | 6.5571 | |
|
|
| 6.6203 | 7.55 | 19500 | 6.5778 | |
|
|
| 6.6055 | 7.75 | 20000 | 6.5805 | |
|
|
| 6.6168 | 7.94 | 20500 | 6.6099 | |
|
|
| 6.5874 | 8.13 | 21000 | 6.6125 | |
|
|
| 6.5932 | 8.33 | 21500 | 6.5701 | |
|
|
| 6.5984 | 8.52 | 22000 | 6.5719 | |
|
|
| 6.5753 | 8.71 | 22500 | 6.6199 | |
|
|
| 6.599 | 8.91 | 23000 | 6.5756 | |
|
|
| 6.579 | 9.1 | 23500 | 6.5926 | |
|
|
| 6.5805 | 9.3 | 24000 | 6.5623 | |
|
|
| 6.5753 | 9.49 | 24500 | 6.5818 | |
|
|
| 6.5645 | 9.68 | 25000 | 6.5726 | |
|
|
| 6.6094 | 9.88 | 25500 | 6.5710 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.24.0 |
|
|
- Pytorch 1.12.1+cu113 |
|
|
- Datasets 2.6.1 |
|
|
- Tokenizers 0.13.2 |
|
|
|
