pkbiswas/Bloom-560m-Summarization-QLoRa

Summarization-Bloom-560m

This model is a fine-tuned version of bigscience/bloom-560m on the scitldr dataset. It achieves the following results on the evaluation set:

• Loss: 2.8578

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: 1
• eval_batch_size: 1
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.8487	0.2510	500	2.9019
2.8069	0.5020	1000	2.8799
2.8195	0.7530	1500	2.8660
2.8024	1.0040	2000	2.8556
2.661	1.2550	2500	2.8637
2.6136	1.5060	3000	2.8608
2.5816	1.7570	3500	2.8578

Framework versions

• PEFT 0.11.1
• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1