scenario-KD-PO-CDF-EN-FROM-CL-D2_data-en-cardiff_eng_only_delta-jason

This model is a fine-tuned version of haryoaw/scenario-TCR_data-cl-cardiff_cl_only2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 16.2614
• Accuracy: 0.3911
• F1: 0.3741

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: 7777
• 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	12.7454	0.3338	0.1921
No log	3.45	200	12.5764	0.3792	0.3477
No log	5.17	300	12.7859	0.3911	0.3622
No log	6.9	400	12.6337	0.3955	0.3966
12.945	8.62	500	13.0332	0.3920	0.3842
12.945	10.34	600	13.7887	0.3955	0.3882
12.945	12.07	700	14.4400	0.3924	0.3773
12.945	13.79	800	15.9912	0.3805	0.3378
12.945	15.52	900	15.2262	0.3902	0.3688
8.3121	17.24	1000	14.6109	0.3968	0.3856
8.3121	18.97	1100	15.0076	0.3990	0.3777
8.3121	20.69	1200	15.1415	0.4012	0.3918
8.3121	22.41	1300	15.4897	0.4096	0.3931
8.3121	24.14	1400	16.0139	0.4021	0.3922
5.8446	25.86	1500	15.8831	0.4008	0.3849
5.8446	27.59	1600	16.0754	0.3915	0.3708
5.8446	29.31	1700	16.2614	0.3911	0.3741

Framework versions

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