Mistral-7B-Instruct-v0.3-009-3000

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.3 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3700

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
1.2602	1.0861	100	1.1349
0.8209	2.1723	200	0.8572
0.6502	3.2584	300	0.6589
0.5165	4.3445	400	0.5444
0.4176	5.4307	500	0.4736
0.3864	6.5168	600	0.4283
0.3301	7.6030	700	0.3977
0.3067	8.6891	800	0.3791
0.2775	9.7752	900	0.3700

Framework versions

• PEFT 0.15.2
• Transformers 4.51.3
• Pytorch 2.7.0+cu126
• Datasets 3.6.0
• Tokenizers 0.21.1