scenario-KD-PO-CDF-EN-FROM-CL-D2_data-en-cardiff_eng_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: 37.0272
• Accuracy: 0.4806
• F1: 0.4795

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	24.0569	0.4577	0.4398
No log	3.45	200	25.0253	0.4771	0.4645
No log	5.17	300	28.2599	0.4806	0.4762
No log	6.9	400	32.2495	0.4647	0.4453
14.5381	8.62	500	35.5757	0.4572	0.4482
14.5381	10.34	600	34.9804	0.4691	0.4635
14.5381	12.07	700	37.5424	0.4691	0.4625
14.5381	13.79	800	35.0894	0.4757	0.4759
14.5381	15.52	900	36.5681	0.4815	0.4793
2.3358	17.24	1000	36.3619	0.4872	0.4861
2.3358	18.97	1100	36.5862	0.4797	0.4765
2.3358	20.69	1200	37.9705	0.4824	0.4781
2.3358	22.41	1300	36.6460	0.4771	0.4756
2.3358	24.14	1400	37.6184	0.4766	0.4758
0.7489	25.86	1500	37.7229	0.4731	0.4695
0.7489	27.59	1600	36.3382	0.4824	0.4799
0.7489	29.31	1700	37.0272	0.4806	0.4795

Framework versions

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