| --- |
| tags: |
| - generated_from_trainer |
| model-index: |
| - name: Llama-360M |
| 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. --> |
|
|
| # Llama-360M |
|
|
| This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 3.4949 |
|
|
| ## 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: 0.0003 |
| - train_batch_size: 16 |
| - eval_batch_size: 8 |
| - seed: 42 |
| - gradient_accumulation_steps: 8 |
| - total_train_batch_size: 128 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: cosine |
| - lr_scheduler_warmup_steps: 50 |
| - num_epochs: 15 |
| - mixed_precision_training: Native AMP |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | |
| |:-------------:|:-----:|:----:|:---------------:| |
| | 8.4028 | 1.0 | 3 | 8.2019 | |
| | 7.206 | 2.0 | 6 | 7.1714 | |
| | 6.3044 | 3.0 | 9 | 6.4447 | |
| | 5.835 | 4.0 | 12 | 6.0518 | |
| | 5.2116 | 5.0 | 15 | 5.3661 | |
| | 4.5014 | 6.0 | 18 | 4.9977 | |
| | 4.0994 | 7.0 | 21 | 4.6291 | |
| | 3.8803 | 8.0 | 24 | 4.2823 | |
| | 3.6287 | 9.0 | 27 | 4.1548 | |
| | 3.3333 | 10.0 | 30 | 3.8924 | |
| | 3.016 | 11.0 | 33 | 3.6889 | |
| | 2.841 | 12.0 | 36 | 3.5575 | |
| | 2.4063 | 13.0 | 39 | 3.5160 | |
| | 2.324 | 14.0 | 42 | 3.5069 | |
| | 1.8726 | 15.0 | 45 | 3.4949 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.39.1 |
| - Pytorch 2.1.2+cu121 |
| - Datasets 2.16.1 |
| - Tokenizers 0.15.0 |
|
|
