Howard881010/heat_transfer_sft_5000_1epoch_fs

sft_5000

This model is a fine-tuned version of mistralai/Mistral-Nemo-Instruct-2407 on the heat_transfer_5000_fs dataset. It achieves the following results on the evaluation set:

• Loss: 0.0013

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: 12
• eval_batch_size: 12
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• total_train_batch_size: 24
• total_eval_batch_size: 24
• 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
0.009	0.1064	20	0.0042
0.0033	0.2128	40	0.0030
0.0026	0.3191	60	0.0022
0.0025	0.4255	80	0.0019
0.0019	0.5319	100	0.0017
0.0017	0.6383	120	0.0016
0.0016	0.7447	140	0.0014
0.0018	0.8511	160	0.0013
0.0016	0.9574	180	0.0013

Framework versions

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