scenario-KD-PR-CDF-EN-FROM-EN-D2_data-en-cardiff_eng_only55

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: 1.3581
• Accuracy: 0.4652
• F1: 0.4628

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: 55
• 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	1.3031	0.4771	0.4716
No log	3.45	200	1.3400	0.4683	0.4652
No log	5.17	300	1.3825	0.4519	0.4469
No log	6.9	400	1.3630	0.4506	0.4420
1.1126	8.62	500	1.3707	0.4638	0.4582
1.1126	10.34	600	1.3829	0.4586	0.4484
1.1126	12.07	700	1.3900	0.4515	0.4453
1.1126	13.79	800	1.3686	0.4533	0.4524
1.1126	15.52	900	1.3663	0.4691	0.4671
0.9617	17.24	1000	1.3568	0.4634	0.4633
0.9617	18.97	1100	1.3790	0.4687	0.4636
0.9617	20.69	1200	1.3537	0.4744	0.4719
0.9617	22.41	1300	1.3759	0.4735	0.4682
0.9617	24.14	1400	1.3573	0.4687	0.4675
0.9417	25.86	1500	1.3581	0.4740	0.4734
0.9417	27.59	1600	1.3547	0.4608	0.4588
0.9417	29.31	1700	1.3581	0.4652	0.4628

Framework versions

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