SOMD-scibert-3stage-stage1-v1

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

• Loss: 0.0000
• F1: 1.0

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: 5e-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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	F1
No log	1.0	74	0.0187	0.9293
No log	2.0	148	0.0053	0.9746
No log	3.0	222	0.0023	0.9914
No log	4.0	296	0.0013	0.9935
No log	5.0	370	0.0009	0.9974
No log	6.0	444	0.0003	0.9994
No log	7.0	518	0.0007	0.9980
No log	8.0	592	0.0001	0.9994
No log	9.0	666	0.0002	0.9994
No log	10.0	740	0.0001	0.9995
No log	11.0	814	0.0000	1.0
No log	12.0	888	0.0000	1.0
No log	13.0	962	0.0000	1.0
No log	14.0	1036	0.0000	1.0
No log	15.0	1110	0.0000	1.0
No log	16.0	1184	0.0000	1.0
No log	17.0	1258	0.0000	1.0
No log	18.0	1332	0.0000	1.0
No log	19.0	1406	0.0000	1.0
No log	20.0	1480	0.0000	1.0

Framework versions

• Transformers 4.37.0
• Pytorch 2.1.2
• Datasets 2.1.0
• Tokenizers 0.15.1