| | --- |
| | license: other |
| | base_model: yahma/llama-7b-hf |
| | tags: |
| | - generated_from_trainer |
| | model-index: |
| | - name: V0224P4 |
| | 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. --> |
| |
|
| | # V0224P4 |
| |
|
| | This model is a fine-tuned version of [yahma/llama-7b-hf](https://huggingface.co/yahma/llama-7b-hf) on an unknown dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 0.7469 |
| |
|
| | ## 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: 4 |
| | - eval_batch_size: 8 |
| | - seed: 42 |
| | - gradient_accumulation_steps: 32 |
| | - total_train_batch_size: 128 |
| | - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| | - lr_scheduler_type: cosine_with_restarts |
| | - lr_scheduler_warmup_steps: 20 |
| | - num_epochs: 3 |
| | - mixed_precision_training: Native AMP |
| |
|
| | ### Training results |
| |
|
| | | Training Loss | Epoch | Step | Validation Loss | |
| | |:-------------:|:-----:|:----:|:---------------:| |
| | | 1.0963 | 0.13 | 10 | 1.0447 | |
| | | 0.972 | 0.26 | 20 | 0.9097 | |
| | | 0.8764 | 0.39 | 30 | 0.8531 | |
| | | 0.8256 | 0.52 | 40 | 0.8236 | |
| | | 0.8078 | 0.65 | 50 | 0.8045 | |
| | | 0.7897 | 0.78 | 60 | 0.7927 | |
| | | 0.766 | 0.91 | 70 | 0.7827 | |
| | | 0.7559 | 1.04 | 80 | 0.7754 | |
| | | 0.725 | 1.17 | 90 | 0.7698 | |
| | | 0.7408 | 1.3 | 100 | 0.7650 | |
| | | 0.7293 | 1.43 | 110 | 0.7619 | |
| | | 0.7198 | 1.55 | 120 | 0.7584 | |
| | | 0.7106 | 1.68 | 130 | 0.7554 | |
| | | 0.7208 | 1.81 | 140 | 0.7521 | |
| | | 0.7247 | 1.94 | 150 | 0.7489 | |
| | | 0.7002 | 2.07 | 160 | 0.7496 | |
| | | 0.6782 | 2.2 | 170 | 0.7486 | |
| | | 0.6905 | 2.33 | 180 | 0.7485 | |
| | | 0.6826 | 2.46 | 190 | 0.7475 | |
| | | 0.6851 | 2.59 | 200 | 0.7476 | |
| | | 0.6874 | 2.72 | 210 | 0.7471 | |
| | | 0.6846 | 2.85 | 220 | 0.7469 | |
| | | 0.6864 | 2.98 | 230 | 0.7469 | |
| |
|
| |
|
| | ### Framework versions |
| |
|
| | - Transformers 4.36.0.dev0 |
| | - Pytorch 2.1.2+cu121 |
| | - Datasets 2.14.6 |
| | - Tokenizers 0.14.1 |
| |
|
