greatakela/mistral_instruct_classifyFPB

1---2license: apache-2.03library_name: peft4tags:5- trl6- sft7- generated_from_trainer8datasets:9- generator10base_model: mistralai/Mistral-7B-Instruct-v0.111model-index:12- name: mistral_instruct_classifyFPB13  results: []14---15 16<!-- This model card has been generated automatically according to the information the Trainer had access to. You17should probably proofread and complete it, then remove this comment. -->18 19# mistral_instruct_classifyFPB20 21This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the generator dataset.22It achieves the following results on the evaluation set:23- Loss: 0.820124 25## Model description26 27More information needed28 29## Intended uses & limitations30 31More information needed32 33## Training and evaluation data34 35More information needed36 37## Training procedure38 39### Training hyperparameters40 41The following hyperparameters were used during training:42- learning_rate: 0.000243- train_batch_size: 644- eval_batch_size: 845- seed: 4246- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0847- lr_scheduler_type: constant48- lr_scheduler_warmup_steps: 0.0349- num_epochs: 550 51### Training results52 53| Training Loss | Epoch | Step | Validation Loss |54|:-------------:|:-----:|:----:|:---------------:|55| 1.1689        | 1.0   | 13   | 0.9276          |56| 0.9467        | 2.0   | 26   | 0.8534          |57| 0.8709        | 3.0   | 39   | 0.8265          |58| 0.7713        | 4.0   | 52   | 0.8196          |59| 0.7215        | 5.0   | 65   | 0.8201          |60 61 62### Framework versions63 64- PEFT 0.8.265- Transformers 4.37.266- Pytorch 2.2.0+cu12167- Datasets 2.17.068- Tokenizers 0.15.2