Mistral_12B_CSAT_0.5

This model is a fine-tuned version of nbeerbower/mistral-nemo-wissenschaft-12B on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.9048
• Accuracy: 0.8291
• F1: 0.8310

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: 1e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• 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
• lr_scheduler_warmup_steps: 100
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.5828	0.1683	300	0.8905	0.8141	0.8153
1.0418	0.3365	600	0.9473	0.8241	0.8256
0.2862	0.5048	900	0.7215	0.8191	0.8228
0.3758	0.6730	1200	0.8167	0.8241	0.8255
0.5865	0.8413	1500	0.9048	0.8291	0.8310

Framework versions

• PEFT 0.13.2
• Transformers 4.46.2
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3