--- license: apache-2.0 library_name: peft tags: - generated_from_trainer base_model: togethercomputer/evo-1-8k-base model-index: - name: lora_evo_ta_all_layers_12 results: [] --- # lora_evo_ta_all_layers_12 This model is a fine-tuned version of [togethercomputer/evo-1-8k-base](https://huggingface.co/togethercomputer/evo-1-8k-base) on the None dataset. It achieves the following results on the evaluation set: - Loss: 2.5374 ## Model description Trained on 1K dataset instead of 400 lora_alpha = 32 lora_dropout = 0.05 lora_r = 16 epochs = 3 learning rate = 3e-4 warmup_steps=100 gradient_accumulation_steps = 1 train_batch = 1 eval_batch = 1 ## 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: 1 - eval_batch_size: 1 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: constant - lr_scheduler_warmup_steps: 100 - num_epochs: 3 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:-----:|:---------------:| | 2.7255 | 1.0 | 3523 | 2.5890 | | 2.5718 | 2.0 | 7046 | 2.5513 | | 2.5237 | 3.0 | 10569 | 2.5374 | ### Framework versions - PEFT 0.11.1 - Transformers 4.41.1 - Pytorch 2.3.0+cu121 - Datasets 2.19.1 - Tokenizers 0.19.1