scibert_scivocab_uncased-finetuned-Astronomy_Thesaurus

This model is a fine-tuned version of allenai/scibert_scivocab_uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.3610

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: 0.0001
• 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: 10

Training results

Training Loss	Epoch	Step	Validation Loss
1.5303	1.0	879	1.3800
1.4977	2.0	1758	1.4101
1.4942	3.0	2637	1.3678
1.4662	4.0	3516	1.3817
1.4748	5.0	4395	1.3750
1.4629	6.0	5274	1.3611
1.4763	7.0	6153	1.3643
1.453	8.0	7032	1.3713
1.4603	9.0	7911	1.3871
1.4697	10.0	8790	1.3610

Framework versions

• PEFT 0.10.0
• Transformers 4.40.2
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1