scenario-KD-PO-CDF-EN-FROM-CL-D2_data-en-cardiff_eng_only_beta-jason

This model is a fine-tuned version of haryoaw/scenario-TCR_data-cl-cardiff_cl_only2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 16.2943
• Accuracy: 0.4026
• F1: 0.3951

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: 6666
• 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	12.5546	0.3884	0.3802
No log	3.45	200	12.5713	0.3889	0.3881
No log	5.17	300	12.7463	0.4017	0.3840
No log	6.9	400	13.0469	0.3884	0.3865
12.7004	8.62	500	13.4306	0.3964	0.3948
12.7004	10.34	600	13.5764	0.3964	0.3952
12.7004	12.07	700	13.8288	0.4074	0.4072
12.7004	13.79	800	14.3994	0.3955	0.3835
12.7004	15.52	900	14.4145	0.4171	0.4126
8.7663	17.24	1000	14.7236	0.4039	0.3966
8.7663	18.97	1100	15.3258	0.3920	0.3750
8.7663	20.69	1200	15.4501	0.3973	0.3945
8.7663	22.41	1300	15.6468	0.4026	0.3945
8.7663	24.14	1400	15.8710	0.4096	0.4019
6.1643	25.86	1500	15.9974	0.4136	0.4077
6.1643	27.59	1600	16.6029	0.3840	0.3721
6.1643	29.31	1700	16.2943	0.4026	0.3951

Framework versions

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