scenario-KD-PO-CDF-EN-FROM-EN-D2_data-en-cardiff_eng_only44

This model is a fine-tuned version of haryoaw/scenario-MDBT-TCR_data-en-cardiff_eng_only on the None dataset. It achieves the following results on the evaluation set:

• Loss: 24.0917
• Accuracy: 0.4546
• F1: 0.4505

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: 44
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	1.72	100	16.0432	0.4242	0.3867
No log	3.45	200	17.7282	0.4621	0.4593
No log	5.17	300	18.0044	0.4484	0.4411
No log	6.9	400	21.5620	0.4515	0.4438
9.8167	8.62	500	22.0929	0.4731	0.4704
9.8167	10.34	600	22.7825	0.4466	0.4401
9.8167	12.07	700	22.9565	0.4577	0.4534
9.8167	13.79	800	24.1151	0.4669	0.4637
9.8167	15.52	900	24.2695	0.4625	0.4618
1.6934	17.24	1000	24.0846	0.4630	0.4624
1.6934	18.97	1100	24.3096	0.4696	0.4678
1.6934	20.69	1200	24.4776	0.4533	0.4499
1.6934	22.41	1300	24.1912	0.4528	0.4524
1.6934	24.14	1400	25.2024	0.4427	0.4388
0.6672	25.86	1500	23.8862	0.4674	0.4664
0.6672	27.59	1600	24.0086	0.4524	0.4467
0.6672	29.31	1700	24.0917	0.4546	0.4505

Framework versions

• Transformers 4.33.3
• Pytorch 2.1.1+cu121
• Datasets 2.14.5
• Tokenizers 0.13.3