scenario-KD-PR-CDF-EN-FROM-CL-D2_data-en-cardiff_eng_only44

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: 1.3448
• Accuracy: 0.4780
• F1: 0.4765

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	1.3140	0.4810	0.4710
No log	3.45	200	1.3058	0.4859	0.4712
No log	5.17	300	1.3692	0.4810	0.4758
No log	6.9	400	1.3751	0.4872	0.4822
1.1234	8.62	500	1.3743	0.4780	0.4771
1.1234	10.34	600	1.3539	0.4757	0.4743
1.1234	12.07	700	1.3873	0.4709	0.4680
1.1234	13.79	800	1.3612	0.4819	0.4821
1.1234	15.52	900	1.3503	0.4956	0.4957
0.9609	17.24	1000	1.3617	0.4841	0.4841
0.9609	18.97	1100	1.3602	0.4877	0.4849
0.9609	20.69	1200	1.3520	0.4881	0.4864
0.9609	22.41	1300	1.3598	0.4802	0.4738
0.9609	24.14	1400	1.3580	0.4722	0.4679
0.9422	25.86	1500	1.3409	0.4797	0.4797
0.9422	27.59	1600	1.3385	0.4903	0.4888
0.9422	29.31	1700	1.3448	0.4780	0.4765

Framework versions

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