scibert_scivocab_uncased-finetuned-molstm-lpm-0.3-25epochs

This model is a fine-tuned version of allenai/scibert_scivocab_uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0407

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 25
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.1073	1.0	3301	0.0633
0.0657	2.0	6602	0.0563
0.059	3.0	9903	0.0536
0.0556	4.0	13204	0.0518
0.0531	5.0	16505	0.0496
0.0511	6.0	19806	0.0489
0.0498	7.0	23107	0.0477
0.0488	8.0	26408	0.0468
0.0478	9.0	29709	0.0464
0.0467	10.0	33010	0.0455
0.0467	11.0	36311	0.0450
0.0458	12.0	39612	0.0454
0.0449	13.0	42913	0.0441
0.0447	14.0	46214	0.0432
0.044	15.0	49515	0.0428
0.0436	16.0	52816	0.0429
0.0433	17.0	56117	0.0428
0.0431	18.0	59418	0.0423
0.0427	19.0	62719	0.0419
0.0425	20.0	66020	0.0420
0.0422	21.0	69321	0.0412
0.0422	22.0	72622	0.0413
0.0416	23.0	75923	0.0407
0.0415	24.0	79224	0.0410
0.0411	25.0	82525	0.0408

Framework versions

• Transformers 4.38.2
• Pytorch 2.0.1
• Datasets 2.18.0
• Tokenizers 0.15.2