combined_sft_10000_mcq_1epoch

This model is a fine-tuned version of mistralai/Mistral-Nemo-Instruct-2407 on the combined_10000_mcq dataset. It achieves the following results on the evaluation set:

• Loss: 0.0039

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: 0.0001
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• total_train_batch_size: 64
• total_eval_batch_size: 64
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
0.005	0.1064	30	0.0048
0.0046	0.2128	60	0.0047
0.0045	0.3191	90	0.0046
0.0045	0.4255	120	0.0045
0.0045	0.5319	150	0.0044
0.0042	0.6383	180	0.0043
0.0042	0.7447	210	0.0041
0.0042	0.8511	240	0.0040
0.004	0.9574	270	0.0040

Framework versions

• PEFT 0.12.0
• Transformers 4.46.0
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.20.1