| | --- |
| | base_model: meta-llama/Llama-2-7b-hf |
| | tags: |
| | - generated_from_trainer |
| | datasets: |
| | - Salesforce/dialogstudio |
| | model-index: |
| | - name: experiments |
| | 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. --> |
| |
|
| | # experiments |
| |
|
| | This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the Salesforce/dialogstudio dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 1.7918 |
| |
|
| | ## 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: 0.0001 |
| | - train_batch_size: 4 |
| | - eval_batch_size: 8 |
| | - seed: 42 |
| | - gradient_accumulation_steps: 4 |
| | - total_train_batch_size: 16 |
| | - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| | - lr_scheduler_type: cosine |
| | - lr_scheduler_warmup_ratio: 0.05 |
| | - num_epochs: 2 |
| |
|
| | ### Training results |
| |
|
| | | Training Loss | Epoch | Step | Validation Loss | |
| | |:-------------:|:-----:|:----:|:---------------:| |
| | | 2.0878 | 0.4 | 22 | 2.0826 | |
| | | 1.9213 | 0.8 | 44 | 1.9025 | |
| | | 1.7334 | 1.2 | 66 | 1.8022 | |
| | | 1.7909 | 1.6 | 88 | 1.7930 | |
| | | 1.7901 | 2.0 | 110 | 1.7918 | |
| |
|
| |
|
| | ### Framework versions |
| |
|
| | - Transformers 4.32.1 |
| | - Pytorch 2.0.1+cu117 |
| | - Datasets 2.14.6 |
| | - Tokenizers 0.13.3 |
| |
|
