scenario-KD-PR-CDF-EN-FROM-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: 1.3348
• Accuracy: 0.4846
• F1: 0.4848

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	1.72	100	1.3126	0.4718	0.4615
No log	3.45	200	1.3334	0.4638	0.4466
No log	5.17	300	1.3417	0.4810	0.4818
No log	6.9	400	1.3541	0.4766	0.4702
1.1194	8.62	500	1.3613	0.4916	0.4913
1.1194	10.34	600	1.3438	0.4797	0.4784
1.1194	12.07	700	1.3501	0.4713	0.4713
1.1194	13.79	800	1.3617	0.4687	0.4683
1.1194	15.52	900	1.3527	0.4819	0.4812
0.9567	17.24	1000	1.3561	0.4824	0.4777
0.9567	18.97	1100	1.3531	0.4749	0.4732
0.9567	20.69	1200	1.3379	0.4960	0.4965
0.9567	22.41	1300	1.3384	0.4797	0.4793
0.9567	24.14	1400	1.3404	0.4824	0.4807
0.9355	25.86	1500	1.3475	0.4753	0.4755
0.9355	27.59	1600	1.3409	0.4780	0.4776
0.9355	29.31	1700	1.3348	0.4846	0.4848

Framework versions

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