scenario-KD-PO-CDF-CL-D2_data-cl-cardiff_cl_only66

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: 31.9406
• Accuracy: 0.4514
• F1: 0.4492

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	1.09	250	20.8325	0.4190	0.4115
23.5832	2.17	500	21.6265	0.4383	0.4264
23.5832	3.26	750	24.4598	0.4390	0.4314
13.3807	4.35	1000	25.7243	0.4306	0.4204
13.3807	5.43	1250	27.8222	0.4421	0.4357
7.1567	6.52	1500	30.2248	0.4290	0.4199
7.1567	7.61	1750	32.3466	0.4352	0.4337
4.6016	8.7	2000	31.6725	0.4460	0.4463
4.6016	9.78	2250	33.4776	0.4506	0.4513
3.1024	10.87	2500	31.5436	0.4606	0.4599
3.1024	11.96	2750	35.7505	0.4452	0.4382
2.4119	13.04	3000	34.6801	0.4244	0.4166
2.4119	14.13	3250	33.5802	0.4568	0.4556
1.9999	15.22	3500	33.1767	0.4498	0.4447
1.9999	16.3	3750	35.5967	0.4174	0.3975
1.4653	17.39	4000	33.7180	0.4537	0.4452
1.4653	18.48	4250	32.4131	0.4468	0.4408
1.2591	19.57	4500	33.4033	0.4352	0.4323
1.2591	20.65	4750	34.4563	0.4290	0.4207
1.0464	21.74	5000	33.1647	0.4514	0.4498
1.0464	22.83	5250	32.5475	0.4414	0.4385
0.7931	23.91	5500	33.5871	0.4498	0.4466
0.7931	25.0	5750	33.1142	0.4452	0.4455
0.7164	26.09	6000	33.0320	0.4321	0.4300
0.7164	27.17	6250	34.2533	0.4306	0.4257
0.6057	28.26	6500	32.7754	0.4483	0.4464
0.6057	29.35	6750	31.9406	0.4514	0.4492

Framework versions

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