mistral-7b-instruct-v0.3-mimic4-adapt-l2r

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.3 on the None dataset. It achieves the following results on the evaluation set:

• Loss: -443630515076000256.0000
• Ndcg: 0.9572
• Ndcg@25: 0.8320
• Precision@25: 0.9131

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: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 4
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Ndcg	Ndcg@25	Precision@25
-820244910218569344.0000	1.0	44	-138641363343365152.0000	0.9556	0.1965	0.0
-92176210412856928.0000	2.0	88	-325691602546540992.0000	0.9565	0.6500	0.5451
-1386633586255750656.0000	3.0	132	-437409861527509376.0000	0.9569	0.7879	0.9086
-352078631547594368.0000	4.0	176	-441613587243874944.0000	0.9572	0.8426	0.9143
-4554006957848212480.0000	4.9017	215	-443630515076000256.0000	0.9572	0.8320	0.9131

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0
• Datasets 3.6.0
• Tokenizers 0.21.1