--- base_model: TinyLlama/TinyLlama_v1.1 library_name: peft license: apache-2.0 tags: - unsloth - generated_from_trainer model-index: - name: tinyllama_magiccoder_default 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_magiccoder_default This model is a fine-tuned version of [TinyLlama/TinyLlama_v1.1](https://huggingface.co/TinyLlama/TinyLlama_v1.1) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.4775 ## 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: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 8 - total_train_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.02 - num_epochs: 1 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:------:|:----:|:---------------:| | 1.8283 | 0.0262 | 4 | 1.9099 | | 1.8156 | 0.0523 | 8 | 1.8872 | | 1.7063 | 0.0785 | 12 | 1.8112 | | 1.591 | 0.1047 | 16 | 1.6729 | | 1.5878 | 0.1308 | 20 | 1.6188 | | 1.5204 | 0.1570 | 24 | 1.6055 | | 1.5278 | 0.1832 | 28 | 1.6151 | | 1.6098 | 0.2093 | 32 | 1.6174 | | 1.5112 | 0.2355 | 36 | 1.5811 | | 1.6158 | 0.2617 | 40 | 1.5749 | | 1.5373 | 0.2878 | 44 | 1.5431 | | 1.5924 | 0.3140 | 48 | 1.5410 | | 1.5528 | 0.3401 | 52 | 1.5142 | | 1.5049 | 0.3663 | 56 | 1.5183 | | 1.5983 | 0.3925 | 60 | 1.5109 | | 1.5452 | 0.4186 | 64 | 1.5045 | | 1.4746 | 0.4448 | 68 | 1.4973 | | 1.4949 | 0.4710 | 72 | 1.4907 | | 1.451 | 0.4971 | 76 | 1.4963 | | 1.5701 | 0.5233 | 80 | 1.4952 | | 1.5791 | 0.5495 | 84 | 1.4858 | | 1.484 | 0.5756 | 88 | 1.4869 | | 1.4175 | 0.6018 | 92 | 1.4846 | | 1.4127 | 0.6280 | 96 | 1.4826 | | 1.4919 | 0.6541 | 100 | 1.4814 | | 1.4907 | 0.6803 | 104 | 1.4830 | | 1.4656 | 0.7065 | 108 | 1.4812 | | 1.4957 | 0.7326 | 112 | 1.4795 | | 1.4742 | 0.7588 | 116 | 1.4785 | | 1.4694 | 0.7850 | 120 | 1.4759 | | 1.5036 | 0.8111 | 124 | 1.4754 | | 1.4752 | 0.8373 | 128 | 1.4762 | | 1.3607 | 0.8635 | 132 | 1.4766 | | 1.5251 | 0.8896 | 136 | 1.4768 | | 1.3971 | 0.9158 | 140 | 1.4773 | | 1.4457 | 0.9419 | 144 | 1.4771 | | 1.4743 | 0.9681 | 148 | 1.4769 | | 1.4915 | 0.9943 | 152 | 1.4775 | ### Framework versions - PEFT 0.12.0 - Transformers 4.44.0 - Pytorch 2.4.0+cu121 - Datasets 2.20.0 - Tokenizers 0.19.1