|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- enoriega/odinsynth_dataset |
|
model-index: |
|
- name: rule_learning_margin_test |
|
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. --> |
|
|
|
# rule_learning_margin_test |
|
|
|
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the enoriega/odinsynth_dataset dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4104 |
|
|
|
## 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: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2000 |
|
- total_train_batch_size: 8000 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3.0 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.6468 | 0.32 | 20 | 0.6191 | |
|
| 0.5185 | 0.64 | 40 | 0.5083 | |
|
| 0.459 | 0.96 | 60 | 0.4521 | |
|
| 0.4352 | 1.29 | 80 | 0.4192 | |
|
| 0.4427 | 1.61 | 100 | 0.4199 | |
|
| 0.4246 | 1.93 | 120 | 0.4131 | |
|
| 0.4301 | 2.26 | 140 | 0.4104 | |
|
| 0.428 | 2.58 | 160 | 0.4099 | |
|
| 0.4161 | 2.9 | 180 | 0.4102 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.19.2 |
|
- Pytorch 1.11.0 |
|
- Datasets 2.2.1 |
|
- Tokenizers 0.12.1 |
|
|
