finetune-mistral-cleaner-v2

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.1 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.7539

Model description

A Mistral model finetuned for cleaning web source.

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e-07
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• lr_scheduler_warmup_steps: 0.03
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
1.9886	0.13	20	1.7551
1.7559	0.27	40	1.7549
2.0012	0.4	60	1.7547
1.6501	0.53	80	1.7545
1.8329	0.67	100	1.7543
1.9872	0.8	120	1.7541
1.7711	0.93	140	1.7539

Framework versions

• PEFT 0.7.1
• Transformers 4.36.2
• Pytorch 2.1.1
• Datasets 2.16.1
• Tokenizers 0.15.0