Mistral-8B-Instruct-v-02-2025

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3763

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: 2e-05
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.1859	1.0754	100	1.1722
0.8849	2.1507	200	0.9095
0.6861	3.2261	300	0.7201
0.5691	4.3015	400	0.5980
0.4735	5.3769	500	0.5220
0.4154	6.4522	600	0.4653
0.3461	7.5276	700	0.4222
0.2877	8.6030	800	0.3883
0.2651	9.6783	900	0.3763

Framework versions

• PEFT 0.17.1
• Transformers 4.57.1
• Pytorch 2.7.1+cu118
• Datasets 4.2.0
• Tokenizers 0.22.1