terry69/feedback_p0.1_seed42_level2_syntaxcleanbatch16_reverse

1---2library_name: transformers3license: apache-2.04base_model: mistralai/Mistral-7B-Instruct-v0.25tags:6- alignment-handbook7- trl8- sft9- generated_from_trainer10- trl11- sft12- generated_from_trainer13datasets:14- preference-data15model-index:16- name: feedback_p0.1_seed42_level2_syntaxcleanbatch16_reverse17  results: []18---19 20<!-- This model card has been generated automatically according to the information the Trainer had access to. You21should probably proofread and complete it, then remove this comment. -->22 23# feedback_p0.1_seed42_level2_syntaxcleanbatch16_reverse24 25This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the preference-data dataset.26 27## Model description28 29More information needed30 31## Intended uses & limitations32 33More information needed34 35## Training and evaluation data36 37More information needed38 39## Training procedure40 41### Training hyperparameters42 43The following hyperparameters were used during training:44- learning_rate: 1e-0545- train_batch_size: 446- eval_batch_size: 147- seed: 4248- distributed_type: multi-GPU49- num_devices: 450- total_train_batch_size: 1651- total_eval_batch_size: 452- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0853- lr_scheduler_type: cosine54- lr_scheduler_warmup_ratio: 0.155- num_epochs: 156 57### Training results58 59 60 61### Framework versions62 63- Transformers 4.44.264- Pytorch 2.3.1+cu12165- Datasets 2.19.166- Tokenizers 0.19.167