|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: ai-forever/mGPT |
|
model-index: |
|
- name: shawgpt-ft |
|
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. --> |
|
|
|
# shawgpt-ft |
|
|
|
This model is a fine-tuned version of [ai-forever/mGPT](https://huggingface.co/ai-forever/mGPT) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.2763 |
|
|
|
## 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: 0.0002 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 16 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 2 |
|
- num_epochs: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 5.2182 | 1.0 | 10 | 4.1588 | |
|
| 4.297 | 2.0 | 20 | 3.9610 | |
|
| 4.0452 | 3.0 | 30 | 3.5918 | |
|
| 3.7856 | 4.0 | 40 | 3.4631 | |
|
| 3.5564 | 5.0 | 50 | 3.3876 | |
|
| 3.5076 | 6.0 | 60 | 3.3417 | |
|
| 3.4227 | 7.0 | 70 | 3.3129 | |
|
| 3.4815 | 8.0 | 80 | 3.2946 | |
|
| 3.4417 | 9.0 | 90 | 3.2829 | |
|
| 3.4683 | 10.0 | 100 | 3.2763 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.11.1 |
|
- Transformers 4.41.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
