scenario-KD-PR-CDF-EN-FROM-CL-D2_data-en-cardiff_eng_only55

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

• Loss: 1.3279
• Accuracy: 0.4881
• F1: 0.4855

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	1.72	100	1.3136	0.4599	0.4267
No log	3.45	200	1.4057	0.4506	0.4056
No log	5.17	300	1.3382	0.4797	0.4752
No log	6.9	400	1.3472	0.4890	0.4858
1.1235	8.62	500	1.3400	0.4863	0.4865
1.1235	10.34	600	1.3593	0.4837	0.4776
1.1235	12.07	700	1.3787	0.4638	0.4526
1.1235	13.79	800	1.3508	0.4868	0.4853
1.1235	15.52	900	1.3393	0.4912	0.4895
0.9596	17.24	1000	1.3570	0.4802	0.4693
0.9596	18.97	1100	1.3359	0.4929	0.4905
0.9596	20.69	1200	1.3386	0.4846	0.4816
0.9596	22.41	1300	1.3372	0.4916	0.4903
0.9596	24.14	1400	1.3271	0.4956	0.4932
0.9384	25.86	1500	1.3313	0.4921	0.4913
0.9384	27.59	1600	1.3341	0.4907	0.4897
0.9384	29.31	1700	1.3279	0.4881	0.4855

Framework versions

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