| --- |
| license: apache-2.0 |
| library_name: peft |
| tags: |
| - trl-sft |
| - generated_from_trainer |
| base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T |
| model-index: |
| - name: tinyllama_lora_adcopy |
| 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. --> |
|
|
| # tinyllama_lora_adcopy |
|
|
| This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.8992 |
|
|
| ## 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: 8 |
| - eval_batch_size: 8 |
| - seed: 42 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: cosine |
| - lr_scheduler_warmup_ratio: 0.1 |
| - num_epochs: 10 |
| - mixed_precision_training: Native AMP |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | |
| |:-------------:|:-----:|:----:|:---------------:| |
| | 0.9386 | 1.0 | 129 | 0.8662 | |
| | 0.7821 | 2.0 | 258 | 0.7954 | |
| | 0.5269 | 3.0 | 387 | 0.7621 | |
| | 0.4121 | 4.0 | 516 | 0.7183 | |
| | 0.2169 | 5.0 | 645 | 0.7358 | |
| | 0.1206 | 6.0 | 774 | 0.7757 | |
| | 0.057 | 7.0 | 903 | 0.8003 | |
| | 0.0291 | 8.0 | 1032 | 0.8342 | |
| | 0.0097 | 9.0 | 1161 | 0.8800 | |
| | 0.0077 | 10.0 | 1290 | 0.8992 | |
| |
| |
| ### Framework versions |
| |
| - PEFT 0.7.2.dev0 |
| - Transformers 4.37.0.dev0 |
| - Pytorch 2.1.2+cu121 |
| - Datasets 2.15.0 |
| - Tokenizers 0.15.0 |
