Hyva/Color-Llama

1---2license: apache-2.03library_name: peft4tags:5- trl6- sft7- generated_from_trainer8base_model: PY007/TinyLlama-1.1B-Chat-v0.39model-index:10- name: Color-Llama11  results: []12---13 14<!-- This model card has been generated automatically according to the information the Trainer had access to. You15should probably proofread and complete it, then remove this comment. -->16 17# Color-Llama18 19This model is a fine-tuned version of [PY007/TinyLlama-1.1B-Chat-v0.3](https://huggingface.co/PY007/TinyLlama-1.1B-Chat-v0.3) on the None dataset.20 21## Model description22 23More information needed24 25## Intended uses & limitations26 27More information needed28 29## Training and evaluation data30 31More information needed32 33## Training procedure34 35### Training hyperparameters36 37The following hyperparameters were used during training:38- learning_rate: 0.000239- train_batch_size: 840- eval_batch_size: 841- seed: 4242- gradient_accumulation_steps: 443- total_train_batch_size: 3244- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0845- lr_scheduler_type: cosine46- training_steps: 20047- mixed_precision_training: Native AMP48 49### Training results50 51 52 53### Framework versions54 55- PEFT 0.8.256- Transformers 4.37.257- Pytorch 2.2.0+cu12158- Datasets 2.17.059- Tokenizers 0.15.2