SN_chatbot

This model is a fine-tuned version of facebook/bart-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0279

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: 2e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss
1.0592	1.0	292	0.7812
0.7337	2.0	584	0.5628
0.6646	3.0	876	0.4559
0.4933	4.0	1168	0.3821
0.4057	5.0	1460	0.3166
0.3147	6.0	1752	0.2566
0.2798	7.0	2044	0.2055
0.2091	8.0	2336	0.1655
0.1806	9.0	2628	0.1358
0.1563	10.0	2920	0.1085
0.1288	11.0	3212	0.0952
0.1192	12.0	3504	0.0785
0.1071	13.0	3796	0.0687
0.0869	14.0	4088	0.0601
0.07	15.0	4380	0.0547
0.0671	16.0	4672	0.0503
0.0666	17.0	4964	0.0466
0.0563	18.0	5256	0.0454
0.0504	19.0	5548	0.0414
0.0515	20.0	5840	0.0398
0.0461	21.0	6132	0.0388
0.041	22.0	6424	0.0362
0.041	23.0	6716	0.0349
0.0402	24.0	7008	0.0335
0.0352	25.0	7300	0.0333
0.0351	26.0	7592	0.0314
0.0308	27.0	7884	0.0314
0.0308	28.0	8176	0.0305
0.0322	29.0	8468	0.0306
0.03	30.0	8760	0.0303
0.0301	31.0	9052	0.0300
0.0286	32.0	9344	0.0299
0.0258	33.0	9636	0.0293
0.025	34.0	9928	0.0294
0.0264	35.0	10220	0.0292
0.0262	36.0	10512	0.0289
0.0256	37.0	10804	0.0291
0.0263	38.0	11096	0.0287
0.025	39.0	11388	0.0289
0.0236	40.0	11680	0.0282
0.0231	41.0	11972	0.0282
0.0241	42.0	12264	0.0281
0.023	43.0	12556	0.0278
0.0216	44.0	12848	0.0280
0.0236	45.0	13140	0.0281
0.0216	46.0	13432	0.0279
0.024	47.0	13724	0.0280
0.0222	48.0	14016	0.0279
0.0225	49.0	14308	0.0279
0.021	50.0	14600	0.0279

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1