scenario-KD-PO-CDF-CL-D2_data-cl-cardiff_cl_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: 33.0330
• Accuracy: 0.4336
• F1: 0.4323

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	1.09	250	20.5521	0.4414	0.4399
23.6236	2.17	500	22.4304	0.4421	0.4312
23.6236	3.26	750	22.3348	0.4468	0.4445
13.7201	4.35	1000	27.4754	0.4344	0.4302
13.7201	5.43	1250	28.1637	0.4468	0.4455
7.366	6.52	1500	29.5979	0.4429	0.4351
7.366	7.61	1750	31.1503	0.4329	0.4298
5.0114	8.7	2000	32.6902	0.4252	0.4138
5.0114	9.78	2250	33.9817	0.4306	0.4292
3.5802	10.87	2500	30.9911	0.4583	0.4558
3.5802	11.96	2750	32.6160	0.4360	0.4307
2.8143	13.04	3000	33.6196	0.4360	0.4328
2.8143	14.13	3250	34.5840	0.4468	0.4458
2.1882	15.22	3500	33.3576	0.4583	0.4580
2.1882	16.3	3750	35.1823	0.4483	0.4479
1.5894	17.39	4000	34.0173	0.4414	0.4416
1.5894	18.48	4250	34.1005	0.4244	0.4232
1.297	19.57	4500	33.2834	0.4313	0.4303
1.297	20.65	4750	33.5127	0.4321	0.4309
1.1221	21.74	5000	33.3669	0.4468	0.4457
1.1221	22.83	5250	34.3508	0.4313	0.4312
0.8953	23.91	5500	33.6077	0.4336	0.4331
0.8953	25.0	5750	33.4164	0.4414	0.4384
0.7681	26.09	6000	32.2372	0.4352	0.4316
0.7681	27.17	6250	33.0334	0.4414	0.4394
0.662	28.26	6500	33.0742	0.4383	0.4364
0.662	29.35	6750	33.0330	0.4336	0.4323

Framework versions

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