dealFindr-finetuned-v2

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: 1.2667

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: 1e-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: 60

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	6	13.4493
No log	2.0	12	12.2565
No log	3.0	18	11.4010
No log	4.0	24	10.2832
No log	5.0	30	8.8511
No log	6.0	36	7.0976
No log	7.0	42	5.9832
No log	8.0	48	5.2993
No log	9.0	54	4.9107
No log	10.0	60	4.5861
No log	11.0	66	4.3329
No log	12.0	72	4.1270
No log	13.0	78	3.9392
No log	14.0	84	3.7658
No log	15.0	90	3.6182
No log	16.0	96	3.4915
No log	17.0	102	3.3719
No log	18.0	108	3.2467
No log	19.0	114	3.1374
No log	20.0	120	3.0331
No log	21.0	126	2.9368
No log	22.0	132	2.8411
No log	23.0	138	2.7430
No log	24.0	144	2.6521
No log	25.0	150	2.5733
No log	26.0	156	2.4918
No log	27.0	162	2.4123
No log	28.0	168	2.3377
No log	29.0	174	2.2648
No log	30.0	180	2.1950
No log	31.0	186	2.1286
No log	32.0	192	2.0646
No log	33.0	198	2.0045
No log	34.0	204	1.9476
No log	35.0	210	1.8927
No log	36.0	216	1.8419
No log	37.0	222	1.7924
No log	38.0	228	1.7420
No log	39.0	234	1.6980
No log	40.0	240	1.6592
No log	41.0	246	1.6197
No log	42.0	252	1.5805
No log	43.0	258	1.5428
No log	44.0	264	1.5082
No log	45.0	270	1.4784
No log	46.0	276	1.4517
No log	47.0	282	1.4265
No log	48.0	288	1.4019
No log	49.0	294	1.3798
No log	50.0	300	1.3596
No log	51.0	306	1.3419
No log	52.0	312	1.3262
No log	53.0	318	1.3122
No log	54.0	324	1.3003
No log	55.0	330	1.2902
No log	56.0	336	1.2821
No log	57.0	342	1.2757
No log	58.0	348	1.2709
No log	59.0	354	1.2678
No log	60.0	360	1.2667

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.4
• Tokenizers 0.13.3