heat_transfer_sft_10000_mcq_f_1epoch

This model is a fine-tuned version of mistralai/Mistral-Nemo-Instruct-2407 on the heat_transfer_10000_mcq_f dataset. It achieves the following results on the evaluation set:

• Loss: 0.0006

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: 2
• total_train_batch_size: 20
• total_eval_batch_size: 20
• 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
0.0024	0.1111	50	0.0013
0.0011	0.2222	100	0.0010
0.0009	0.3333	150	0.0008
0.001	0.4444	200	0.0008
0.0009	0.5556	250	0.0008
0.0006	0.6667	300	0.0007
0.0007	0.7778	350	0.0007
0.0007	0.8889	400	0.0006
0.0009	1.0	450	0.0006

Framework versions

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