norllm-ai-normistral-7b-sft-qlora

This model is a fine-tuned version of NorLLM-AI/NorMistral-7B on the hugodk-sch/aftonposten_title_sft dataset. It achieves the following results on the evaluation set:

  • Loss: 1.4403

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
1.7274 1.0 274 1.9432
1.1514 2.0 549 1.7111
0.645 3.0 823 1.5109
0.4291 4.0 1098 1.4415
0.3392 4.99 1370 1.4403

Framework versions

  • PEFT 0.10.0
  • Transformers 4.39.0.dev0
  • Pytorch 2.1.2+cu121
  • Datasets 2.14.6
  • Tokenizers 0.15.1
Downloads last month
2
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for hugodk-sch/norllm-ai-normistral-7b-sft-qlora

Adapter
(2)
this model