scenario-KD-PO-CDF-EN-FROM-EN-D2_data-en-cardiff_eng_only66

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: 24.7382
• Accuracy: 0.4550
• F1: 0.4534

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	1.72	100	15.4704	0.4568	0.4535
No log	3.45	200	16.0314	0.4669	0.4628
No log	5.17	300	19.1999	0.4568	0.4479
No log	6.9	400	21.8826	0.4546	0.4456
9.984	8.62	500	21.4137	0.4572	0.4573
9.984	10.34	600	23.3766	0.4396	0.4365
9.984	12.07	700	24.2726	0.4475	0.4365
9.984	13.79	800	24.3246	0.4502	0.4440
9.984	15.52	900	24.9899	0.4634	0.4616
1.9269	17.24	1000	24.6384	0.4616	0.4583
1.9269	18.97	1100	24.3379	0.4493	0.4454
1.9269	20.69	1200	24.6032	0.4625	0.4577
1.9269	22.41	1300	24.1732	0.4608	0.4572
1.9269	24.14	1400	25.5374	0.4493	0.4448
0.6962	25.86	1500	24.3690	0.4563	0.4553
0.6962	27.59	1600	24.9417	0.4515	0.4488
0.6962	29.31	1700	24.7382	0.4550	0.4534

Framework versions

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