ap-normistral-7b-sft-qlora

This model is a fine-tuned version of norallm/normistral-7b-warm on the hugodk-sch/aftonposten_title_sft dataset. It achieves the following results on the evaluation set:

• Loss: 1.6055

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: 0.0002
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
2.063	1.0	264	2.1618
1.2293	2.0	528	1.9121
0.6985	3.0	792	1.6916
0.4922	4.0	1056	1.6054
0.3396	5.0	1320	1.6055

Framework versions

• PEFT 0.10.0
• Transformers 4.39.0.dev0
• Pytorch 2.1.2+cu121
• Datasets 2.14.6
• Tokenizers 0.15.1