scenario-KD-PO-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: 23.6899
• Accuracy: 0.4665
• F1: 0.4662

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	15.5667	0.4356	0.4288
No log	3.45	200	17.1164	0.4418	0.4096
No log	5.17	300	18.8679	0.4634	0.4606
No log	6.9	400	19.9135	0.4550	0.4494
9.9963	8.62	500	23.0517	0.4581	0.4517
9.9963	10.34	600	21.4184	0.4493	0.4394
9.9963	12.07	700	22.8898	0.4621	0.4584
9.9963	13.79	800	22.6673	0.4462	0.4352
9.9963	15.52	900	23.8054	0.4616	0.4605
1.7937	17.24	1000	23.0995	0.4586	0.4524
1.7937	18.97	1100	23.2337	0.4709	0.4682
1.7937	20.69	1200	24.9664	0.4669	0.4646
1.7937	22.41	1300	23.8143	0.4700	0.4695
1.7937	24.14	1400	23.9374	0.4581	0.4546
0.6046	25.86	1500	24.0218	0.4647	0.4651
0.6046	27.59	1600	23.0812	0.4740	0.4735
0.6046	29.31	1700	23.6899	0.4665	0.4662

Framework versions

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