80 lines
2.3 KiB
Markdown
80 lines
2.3 KiB
Markdown
---
|
|
license: mit
|
|
tags:
|
|
- generated_from_trainer
|
|
datasets:
|
|
- generator
|
|
model-index:
|
|
- name: cbt-guten-log-rarity-all-no-cut-mixed
|
|
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. -->
|
|
|
|
# cbt-guten-log-rarity-all-no-cut-mixed
|
|
|
|
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: 4.3188
|
|
|
|
## 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 |
|
|
|:-------------:|:-----:|:-----:|:---------------:|
|
|
| 6.6937 | 0.29 | 500 | 5.6332 |
|
|
| 5.3475 | 0.58 | 1000 | 5.1998 |
|
|
| 4.9924 | 0.87 | 1500 | 4.9522 |
|
|
| 4.7225 | 1.17 | 2000 | 4.8038 |
|
|
| 4.565 | 1.46 | 2500 | 4.6827 |
|
|
| 4.4479 | 1.75 | 3000 | 4.5721 |
|
|
| 4.3359 | 2.04 | 3500 | 4.4944 |
|
|
| 4.1336 | 2.33 | 4000 | 4.4442 |
|
|
| 4.1041 | 2.62 | 4500 | 4.3954 |
|
|
| 4.063 | 2.91 | 5000 | 4.3376 |
|
|
| 3.8757 | 3.21 | 5500 | 4.3348 |
|
|
| 3.8025 | 3.5 | 6000 | 4.3031 |
|
|
| 3.7886 | 3.79 | 6500 | 4.2700 |
|
|
| 3.7012 | 4.08 | 7000 | 4.2676 |
|
|
| 3.5218 | 4.37 | 7500 | 4.2626 |
|
|
| 3.5166 | 4.66 | 8000 | 4.2503 |
|
|
| 3.5012 | 4.95 | 8500 | 4.2361 |
|
|
| 3.3576 | 5.24 | 9000 | 4.2482 |
|
|
| 3.3265 | 5.54 | 9500 | 4.2487 |
|
|
| 3.3229 | 5.83 | 10000 | 4.2470 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.26.1
|
|
- Pytorch 1.11.0+cu113
|
|
- Datasets 2.13.0
|
|
- Tokenizers 0.13.3
|