| --- |
| license: llama3.1 |
| base_model: Crystalcareai/Meta-llama-3.1-8b-instruct |
| tags: |
| - generated_from_trainer |
| model-index: |
| - name: data/sft-full |
| 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. --> |
|
|
| [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) |
| <details><summary>See axolotl config</summary> |
|
|
| axolotl version: `0.4.1` |
| ```yaml |
| base_model: Crystalcareai/Meta-llama-3.1-8b-instruct |
| bf16: 'True' |
| chat_template: chatml |
| dataset_prepared_path: ./sft_processed |
| dataset_processes: 12 |
| datasets: |
| - field_messages: messages |
| path: sft_dataset |
| type: sharegpt |
| deepspeed: /axolotl/deepspeed_configs/zero3_bf16.json |
| eval_batch_size: 1 |
| flash_attention: true |
| gradient_accumulation_steps: 8 |
| gradient_checkpointing: true |
| learning_rate: 5.0e-06 |
| logging_steps: 1 |
| lr_scheduler: cosine |
| micro_batch_size: 2 |
| num_epochs: 3 |
| optimizer: adamw_bnb_8bit |
| output_dir: data/sft-full |
| pad_to_sequence_len: true |
| sample_packing: true |
| save_safetensors: true |
| save_total_limit: 0 |
| saves_per_epoch: 0 |
| seed: 42 |
| sequence_len: 4096 |
| special_tokens: |
| pad_token: <|end_of_text|> |
| tf32: false |
| tokens: [] |
| use_tensorboard: true |
| val_set_size: 0 |
| |
| ``` |
|
|
| </details><br> |
|
|
| # data/sft-full |
|
|
| This model is a fine-tuned version of [Crystalcareai/Meta-llama-3.1-8b-instruct](https://huggingface.co/Crystalcareai/Meta-llama-3.1-8b-instruct) on the None dataset. |
|
|
| ## 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: 5e-06 |
| - train_batch_size: 2 |
| - eval_batch_size: 1 |
| - seed: 42 |
| - distributed_type: multi-GPU |
| - num_devices: 8 |
| - gradient_accumulation_steps: 8 |
| - total_train_batch_size: 128 |
| - total_eval_batch_size: 8 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: cosine |
| - num_epochs: 3 |
|
|
| ### Training results |
|
|
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.43.1 |
| - Pytorch 2.3.0+cu121 |
| - Datasets 2.19.1 |
| - Tokenizers 0.19.1 |
|
|
