scenario-NON-KD-PO-COPY-CDF-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: 5.1166
• Accuracy: 0.4674
• F1: 0.4671

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	1.7241	100	1.1679	0.4577	0.4378
No log	3.4483	200	1.3664	0.4250	0.3876
No log	5.1724	300	1.5985	0.4581	0.4543
No log	6.8966	400	1.8554	0.4705	0.4700
0.5643	8.6207	500	2.7438	0.4568	0.4570
0.5643	10.3448	600	3.2185	0.4757	0.4749
0.5643	12.0690	700	3.4265	0.4643	0.4616
0.5643	13.7931	800	3.6531	0.4652	0.4620
0.5643	15.5172	900	4.1547	0.4634	0.4636
0.0729	17.2414	1000	4.5970	0.4590	0.4553
0.0729	18.9655	1100	4.8117	0.4638	0.4574
0.0729	20.6897	1200	4.8700	0.4652	0.4649
0.0729	22.4138	1300	5.0241	0.4691	0.4683
0.0729	24.1379	1400	5.0585	0.4683	0.4686
0.0104	25.8621	1500	5.0355	0.4660	0.4662
0.0104	27.5862	1600	5.0443	0.4691	0.4684
0.0104	29.3103	1700	5.1166	0.4674	0.4671

Framework versions

• Transformers 4.44.2
• Pytorch 2.1.1+cu121
• Datasets 2.14.5
• Tokenizers 0.19.1