|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- generator |
|
model-index: |
|
- name: bnc_spoken-cbt-notm-log-rarity-seed |
|
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. --> |
|
|
|
# bnc_spoken-cbt-notm-log-rarity-seed |
|
|
|
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 4.1404 |
|
|
|
## 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: 0.0005 |
|
- train_batch_size: 64 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 1000 |
|
- num_epochs: 6 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 6.3631 | 0.29 | 500 | 5.3434 | |
|
| 5.0481 | 0.59 | 1000 | 4.9361 | |
|
| 4.7177 | 0.88 | 1500 | 4.7045 | |
|
| 4.4593 | 1.17 | 2000 | 4.5683 | |
|
| 4.3118 | 1.46 | 2500 | 4.4484 | |
|
| 4.2082 | 1.76 | 3000 | 4.3453 | |
|
| 4.0886 | 2.05 | 3500 | 4.2725 | |
|
| 3.9027 | 2.34 | 4000 | 4.2271 | |
|
| 3.8826 | 2.63 | 4500 | 4.1747 | |
|
| 3.8396 | 2.93 | 5000 | 4.1241 | |
|
| 3.645 | 3.22 | 5500 | 4.1184 | |
|
| 3.5953 | 3.51 | 6000 | 4.0930 | |
|
| 3.5812 | 3.81 | 6500 | 4.0604 | |
|
| 3.4807 | 4.1 | 7000 | 4.0629 | |
|
| 3.3286 | 4.39 | 7500 | 4.0557 | |
|
| 3.325 | 4.68 | 8000 | 4.0463 | |
|
| 3.3134 | 4.98 | 8500 | 4.0327 | |
|
| 3.1583 | 5.27 | 9000 | 4.0488 | |
|
| 3.1455 | 5.56 | 9500 | 4.0474 | |
|
| 3.1459 | 5.85 | 10000 | 4.0466 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.1 |
|
- Pytorch 1.11.0+cu113 |
|
- Datasets 2.13.0 |
|
- Tokenizers 0.13.3 |
|
|
