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

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: 1.3472
• Accuracy: 0.4854
• F1: 0.4837

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	1.2889	0.4594	0.4362
No log	3.45	200	1.2863	0.4802	0.4774
No log	5.17	300	1.3275	0.4612	0.4493
No log	6.9	400	1.3428	0.4885	0.4874
1.1183	8.62	500	1.3395	0.4841	0.4835
1.1183	10.34	600	1.3621	0.4705	0.4689
1.1183	12.07	700	1.3524	0.4643	0.4624
1.1183	13.79	800	1.3665	0.4660	0.4617
1.1183	15.52	900	1.3531	0.4793	0.4762
0.9576	17.24	1000	1.3762	0.4669	0.4633
0.9576	18.97	1100	1.3615	0.4718	0.4681
0.9576	20.69	1200	1.3656	0.4691	0.4638
0.9576	22.41	1300	1.3684	0.4722	0.4685
0.9576	24.14	1400	1.3559	0.4740	0.4741
0.9369	25.86	1500	1.3527	0.4753	0.4739
0.9369	27.59	1600	1.3407	0.4762	0.4757
0.9369	29.31	1700	1.3472	0.4854	0.4837

Framework versions

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