Tinyllama LoRA Finetuned Howto

--- library_name: peft license: apache-2.0 base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0 tags: - base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0 - lora - transformers pipeline_tag: text-generation model-index: - name: tinyllama-lora-finetuned-howto 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. --> # tinyllama-lora-finetuned-howto This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on the None dataset. It achieves the following results on the evaluation set: - Loss: 2.5784 ## 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: 2e-05 - train_batch_size: 6 - eval_batch_size: 6 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 24 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 20 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 2.6684 | 1.0 | 4 | 2.8707 | | 2.5353 | 2.0 | 8 | 2.8572 | | 2.5517 | 3.0 | 12 | 2.8328 | | 2.5643 | 4.0 | 16 | 2.8103 | | 2.4755 | 5.0 | 20 | 2.7889 | | 2.6151 | 6.0 | 24 | 2.7682 | | 2.6296 | 7.0 | 28 | 2.7448 | | 2.5886 | 8.0 | 32 | 2.7221 | | 2.4931 | 9.0 | 36 | 2.7000 | | 2.3930 | 10.0 | 40 | 2.6795 | | 2.4767 | 11.0 | 44 | 2.6651 | | 2.2675 | 12.0 | 48 | 2.6471 | | 2.5827 | 13.0 | 52 | 2.6343 | | 2.2991 | 14.0 | 56 | 2.6193 | | 2.4421 | 15.0 | 60 | 2.6031 | | 2.5563 | 16.0 | 64 | 2.5950 | | 2.4413 | 17.0 | 68 | 2.5885 | | 2.4433 | 18.0 | 72 | 2.5852 | | 2.3778 | 19.0 | 76 | 2.5804 | | 2.3322 | 20.0 | 80 | 2.5784 | ### Framework versions - PEFT 0.19.1 - Transformers 5.14.1 - Pytorch 2.13.0 - Datasets 5.0.0 - Tokenizers 0.22.2

--- library_name: peft license: apache-2.0 base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0 tags: - base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0 - lora - transformers pipeline_tag: text-generation model-index: - name: tinyllama-lora-finetuned-howto 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. --> # tinyllama-lora-finetuned-howto This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.6122 ## 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-05 - train_batch_size: 1 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 4 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 10 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 2.1618 | 1.0 | 22 | 2.4738 | | 2.3424 | 2.0 | 44 | 2.1172 | | 1.8827 | 3.0 | 66 | 1.9271 | | 1.6998 | 4.0 | 88 | 1.8227 | | 1.7143 | 5.0 | 110 | 1.7413 | | 1.8427 | 6.0 | 132 | 1.6840 | | 1.7776 | 7.0 | 154 | 1.6485 | | 1.5365 | 8.0 | 176 | 1.6282 | | 1.3898 | 9.0 | 198 | 1.6154 | | 1.5436 | 10.0 | 220 | 1.6122 | ### Framework versions - PEFT 0.19.1 - Transformers 5.14.1 - Pytorch 2.13.0 - Datasets 5.0.0 - Tokenizers 0.22.2

Source context: 7 downloads · 0 likes · Pipeline text-generation · Library peft · Repo snow-leaoprd/tinyllama-lora-finetuned-howto