bert_base_lda_5_mrpc

This model is a fine-tuned version of gokulsrinivasagan/bert_base_lda_5 on the GLUE MRPC dataset. It achieves the following results on the evaluation set:

• Loss: 0.6226
• Accuracy: 0.6838
• F1: 0.8122
• Combined Score: 0.7480

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: 0.001
• train_batch_size: 256
• eval_batch_size: 256
• seed: 10
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Combined Score
1.6067	1.0	15	0.6951	0.6838	0.8122	0.7480
0.6503	2.0	30	0.6270	0.6838	0.8122	0.7480
0.6289	3.0	45	0.6279	0.6838	0.8122	0.7480
0.6364	4.0	60	0.6244	0.6838	0.8122	0.7480
0.6368	5.0	75	0.6272	0.6838	0.8122	0.7480
0.6349	6.0	90	0.6252	0.6838	0.8122	0.7480
0.6311	7.0	105	0.6263	0.6838	0.8122	0.7480
0.6339	8.0	120	0.6240	0.6838	0.8122	0.7480
0.6296	9.0	135	0.6287	0.6838	0.8122	0.7480
0.6346	10.0	150	0.6260	0.6838	0.8122	0.7480
0.6359	11.0	165	0.6275	0.6838	0.8122	0.7480
0.6337	12.0	180	0.6242	0.6838	0.8122	0.7480
0.6302	13.0	195	0.6228	0.6838	0.8122	0.7480
0.6351	14.0	210	0.6258	0.6838	0.8122	0.7480
0.6324	15.0	225	0.6226	0.6838	0.8122	0.7480
0.6301	16.0	240	0.6243	0.6838	0.8122	0.7480
0.6316	17.0	255	0.6248	0.6838	0.8122	0.7480
0.63	18.0	270	0.6243	0.6838	0.8122	0.7480
0.6304	19.0	285	0.6230	0.6838	0.8122	0.7480
0.633	20.0	300	0.6250	0.6838	0.8122	0.7480

Framework versions

• Transformers 4.46.3
• Pytorch 2.2.1+cu118
• Datasets 2.17.0
• Tokenizers 0.20.3