Bloom-1b1-Summarization-QLoRa – AI Model by pkbiswas | AlphaNeural AI

You can deploy this model and start earning money today!

pkbiswas/
Bloom-1b1-Summarization-QLoRa

like

0

generated_from_trainer

bigscience/bloom-1b1

bigscience-bloom-rail-1.0

Views

No views yet

Bloom-1b1-Summarization-QLoRa

This model is a fine-tuned version of bigscience/bloom-1b1 on the scitldr dataset. It achieves the following results on the evaluation set:

Loss: 2.7202

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
2.6959	0.2510	500	2.7513
2.6632	0.5020	1000	2.7296
2.6724	0.7530	1500	2.7230
2.6625	1.0040	2000	2.7177
2.5181	1.2550	2500	2.7247
2.4633	1.5060	3000	2.7230
2.4341	1.7570	3500	2.7202

Framework versions

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