bloom-560m-finetuned-liability

This model is a fine-tuned version of bigscience/bloom-560m on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1486

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: 2e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
0.5359	1.0	524	0.2425
0.1736	2.0	1048	0.1741
0.1045	3.0	1572	0.1550
0.0745	4.0	2096	0.1486
0.0549	5.0	2620	0.1486

Framework versions

• Transformers 4.27.4
• Pytorch 2.0.0+cu118
• Datasets 2.11.0
• Tokenizers 0.13.3