|
|
--- |
|
|
library_name: peft |
|
|
base_model: roneneldan/TinyStories-1M |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: test_1M_1-2025-02-18-14-21 |
|
|
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. --> |
|
|
|
|
|
# test_1M_1-2025-02-18-14-21 |
|
|
|
|
|
This model is a fine-tuned version of [roneneldan/TinyStories-1M](https://huggingface.co/roneneldan/TinyStories-1M) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 2.7856 |
|
|
|
|
|
## 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: 2.5e-05 |
|
|
- train_batch_size: 4 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 2 |
|
|
- total_train_batch_size: 8 |
|
|
- optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_steps: 1 |
|
|
- num_epochs: 6 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 3.0635 | 0.5 | 297 | 2.9508 | |
|
|
| 2.9856 | 1.0 | 594 | 2.8973 | |
|
|
| 2.8633 | 1.5 | 891 | 2.8620 | |
|
|
| 2.8463 | 2.0 | 1188 | 2.8442 | |
|
|
| 2.8592 | 2.5 | 1485 | 2.8335 | |
|
|
| 2.9088 | 3.0 | 1782 | 2.8218 | |
|
|
| 2.7705 | 3.5 | 2079 | 2.8176 | |
|
|
| 2.8045 | 4.0 | 2376 | 2.8065 | |
|
|
| 2.822 | 4.5 | 2673 | 2.8003 | |
|
|
| 2.9149 | 5.0 | 2970 | 2.7917 | |
|
|
| 2.6928 | 5.5 | 3267 | 2.7886 | |
|
|
| 2.9345 | 6.0 | 3564 | 2.7856 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.14.0 |
|
|
- Transformers 4.48.1 |
|
|
- Pytorch 2.5.1+cu124 |
|
|
- Datasets 3.2.0 |
|
|
- Tokenizers 0.21.0 |
