scenario-NON-KD-PO-COPY-CDF-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: 5.0783
• Accuracy: 0.4696
• F1: 0.4675

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	1.7241	100	1.2348	0.4608	0.4572
No log	3.4483	200	1.4918	0.4828	0.4811
No log	5.1724	300	1.6208	0.4890	0.4892
No log	6.8966	400	2.2442	0.4757	0.4744
0.5368	8.6207	500	2.8887	0.4828	0.4780
0.5368	10.3448	600	3.2901	0.4643	0.4608
0.5368	12.0690	700	3.5079	0.4630	0.4577
0.5368	13.7931	800	3.9045	0.4771	0.4771
0.5368	15.5172	900	4.0691	0.4586	0.4537
0.0674	17.2414	1000	4.3815	0.4718	0.4709
0.0674	18.9655	1100	4.5190	0.4674	0.4660
0.0674	20.6897	1200	4.7439	0.4656	0.4637
0.0674	22.4138	1300	4.9470	0.4678	0.4650
0.0674	24.1379	1400	4.9131	0.4727	0.4725
0.0123	25.8621	1500	4.9607	0.4793	0.4788
0.0123	27.5862	1600	4.9727	0.4784	0.4783
0.0123	29.3103	1700	5.0783	0.4696	0.4675

Framework versions

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