| --- |
| license: other |
| base_model: yahma/llama-7b-hf |
| tags: |
| - generated_from_trainer |
| model-index: |
| - name: V0224O2 |
| 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. --> |
|
|
| # V0224O2 |
|
|
| 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: 0.7463 |
|
|
| ## 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 | |
| |:-------------:|:-----:|:----:|:---------------:| |
| | 3.92 | 0.13 | 10 | 2.0370 | |
| | 1.2885 | 0.26 | 20 | 1.0103 | |
| | 0.9359 | 0.39 | 30 | 0.8890 | |
| | 0.8522 | 0.52 | 40 | 0.8425 | |
| | 0.8213 | 0.65 | 50 | 0.8151 | |
| | 0.798 | 0.78 | 60 | 0.8006 | |
| | 0.7714 | 0.91 | 70 | 0.7896 | |
| | 0.7598 | 1.04 | 80 | 0.7814 | |
| | 0.7269 | 1.17 | 90 | 0.7729 | |
| | 0.7398 | 1.3 | 100 | 0.7685 | |
| | 0.7291 | 1.43 | 110 | 0.7637 | |
| | 0.7193 | 1.55 | 120 | 0.7597 | |
| | 0.7097 | 1.68 | 130 | 0.7571 | |
| | 0.7198 | 1.81 | 140 | 0.7536 | |
| | 0.7229 | 1.94 | 150 | 0.7491 | |
| | 0.6964 | 2.07 | 160 | 0.7503 | |
| | 0.6717 | 2.2 | 170 | 0.7484 | |
| | 0.6848 | 2.33 | 180 | 0.7472 | |
| | 0.6767 | 2.46 | 190 | 0.7471 | |
| | 0.6788 | 2.59 | 200 | 0.7468 | |
| | 0.6801 | 2.72 | 210 | 0.7463 | |
| | 0.6778 | 2.85 | 220 | 0.7463 | |
| | 0.6803 | 2.98 | 230 | 0.7463 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.36.0.dev0 |
| - Pytorch 2.1.2+cu121 |
| - Datasets 2.14.6 |
| - Tokenizers 0.14.1 |
|
|
