scenario-KD-PR-MSV-D2_data-cl-cardiff_cl_only66

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

• Loss: 1.3632
• Accuracy: 0.4606
• F1: 0.4587

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: 66
• 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	1.09	250	1.3128	0.4429	0.4291
1.2095	2.17	500	1.3172	0.4545	0.4541
1.2095	3.26	750	1.3477	0.4329	0.4157
1.0582	4.35	1000	1.3487	0.4599	0.4582
1.0582	5.43	1250	1.3579	0.4290	0.4130
0.992	6.52	1500	1.3927	0.4367	0.4200
0.992	7.61	1750	1.3931	0.4398	0.4294
0.9612	8.7	2000	1.3621	0.4630	0.4613
0.9612	9.78	2250	1.3659	0.4529	0.4502
0.9418	10.87	2500	1.3659	0.4498	0.4455
0.9418	11.96	2750	1.3961	0.4483	0.4480
0.9299	13.04	3000	1.3631	0.4506	0.4473
0.9299	14.13	3250	1.3819	0.4498	0.4422
0.9207	15.22	3500	1.3687	0.4637	0.4628
0.9207	16.3	3750	1.3981	0.4313	0.4179
0.9134	17.39	4000	1.3786	0.4529	0.4530
0.9134	18.48	4250	1.3699	0.4637	0.4630
0.9093	19.57	4500	1.3762	0.4599	0.4596
0.9093	20.65	4750	1.3834	0.4375	0.4321
0.9057	21.74	5000	1.3772	0.4529	0.4499
0.9057	22.83	5250	1.3695	0.4568	0.4499
0.9018	23.91	5500	1.3671	0.4614	0.4573
0.9018	25.0	5750	1.3791	0.4468	0.4428
0.8994	26.09	6000	1.3775	0.4491	0.4466
0.8994	27.17	6250	1.3735	0.4483	0.4434
0.8976	28.26	6500	1.3548	0.4668	0.4662
0.8976	29.35	6750	1.3632	0.4606	0.4587

Framework versions

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