scenario-KD-PO-CDF-EN-FROM-EN-D2_data-en-cardiff_eng_only_alpha-jason

This model is a fine-tuned version of haryoaw/scenario-TCR_data-en-cardiff_eng_only2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 25.9311
• Accuracy: 0.4056
• F1: 0.3983

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: 2222
• 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	21.3190	0.3576	0.3272
No log	3.45	200	21.9669	0.3765	0.3322
No log	5.17	300	21.3943	0.3880	0.3770
No log	6.9	400	22.4346	0.3937	0.3679
21.6763	8.62	500	22.0732	0.3898	0.3832
21.6763	10.34	600	22.3971	0.3915	0.3870
21.6763	12.07	700	22.5065	0.3946	0.3879
21.6763	13.79	800	22.9460	0.3942	0.3906
21.6763	15.52	900	22.6589	0.4123	0.4073
15.4435	17.24	1000	23.3626	0.4039	0.3969
15.4435	18.97	1100	23.8309	0.3990	0.3925
15.4435	20.69	1200	24.5910	0.3955	0.3914
15.4435	22.41	1300	24.9435	0.3893	0.3778
15.4435	24.14	1400	25.2576	0.3920	0.3836
11.044	25.86	1500	25.6593	0.3951	0.3861
11.044	27.59	1600	25.6976	0.3973	0.3902
11.044	29.31	1700	25.9311	0.4056	0.3983

Framework versions

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