uplimit-project-3-mistral7b

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the scitldr dataset. It achieves the following results on the evaluation set:

• Loss: 4.3280

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: 0.001
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 2
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
2.8989	0.2	200	2.8317
3.0908	0.4	400	3.2010
3.7518	0.6	600	3.9583
4.275	0.8	800	4.3280

Framework versions

• Transformers 4.35.0
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1