epidemiology_sft_10000_mcq_2epoch

This model is a fine-tuned version of mistralai/Mistral-Nemo-Instruct-2407 on the epidemiology_10000_mcq dataset. It achieves the following results on the evaluation set:

• Loss: 0.0020

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: 10
• eval_batch_size: 10
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• total_train_batch_size: 40
• total_eval_batch_size: 40
• 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: 2

Training results

Training Loss	Epoch	Step	Validation Loss
0.0042	0.1333	30	0.0041
0.0039	0.2667	60	0.0039
0.0039	0.4	90	0.0039
0.0039	0.5333	120	0.0039
0.0033	0.6667	150	0.0031
0.0029	0.8	180	0.0029
0.0028	0.9333	210	0.0025
0.0025	1.0667	240	0.0024
0.0024	1.2	270	0.0024
0.0027	1.3333	300	0.0024
0.0025	1.4667	330	0.0023
0.0023	1.6	360	0.0022
0.0023	1.7333	390	0.0021
0.002	1.8667	420	0.0020
0.0022	2.0	450	0.0020

Framework versions

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