Mistral-Small-24B-Instruct-2501-009

This model is a fine-tuned version of mistralai/Mistral-Small-24B-Instruct-2501 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4463

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: 1
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.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
1.2282	0.8658	100	1.2312
1.0274	1.7273	200	1.0113
0.7934	2.5887	300	0.7905
0.6052	3.4502	400	0.6743
0.5425	4.3117	500	0.5958
0.4601	5.1732	600	0.5434
0.479	6.0346	700	0.5061
0.4181	6.9004	800	0.4801
0.4051	7.7619	900	0.4624
0.3994	8.6234	1000	0.4534
0.3459	9.4848	1100	0.4463

Framework versions

• PEFT 0.15.2
• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 2.14.4
• Tokenizers 0.21.1