dealFindr-finetuned-v3

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: 0.9704

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: 50

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	8	12.2678
No log	2.0	16	11.3441
No log	3.0	24	10.2220
No log	4.0	32	8.6566
No log	5.0	40	6.4217
No log	6.0	48	5.3282
No log	7.0	56	4.8098
No log	8.0	64	4.4019
No log	9.0	72	4.1157
No log	10.0	80	3.8796
No log	11.0	88	3.6642
No log	12.0	96	3.4801
No log	13.0	104	3.3123
No log	14.0	112	3.1491
No log	15.0	120	3.0019
No log	16.0	128	2.8685
No log	17.0	136	2.7340
No log	18.0	144	2.6073
No log	19.0	152	2.4897
No log	20.0	160	2.3747
No log	21.0	168	2.2723
No log	22.0	176	2.1683
No log	23.0	184	2.0714
No log	24.0	192	1.9811
No log	25.0	200	1.8965
No log	26.0	208	1.8128
No log	27.0	216	1.7375
No log	28.0	224	1.6632
No log	29.0	232	1.5932
No log	30.0	240	1.5299
No log	31.0	248	1.4716
No log	32.0	256	1.4156
No log	33.0	264	1.3637
No log	34.0	272	1.3164
No log	35.0	280	1.2711
No log	36.0	288	1.2284
No log	37.0	296	1.1908
No log	38.0	304	1.1568
No log	39.0	312	1.1272
No log	40.0	320	1.0996
No log	41.0	328	1.0742
No log	42.0	336	1.0522
No log	43.0	344	1.0321
No log	44.0	352	1.0150
No log	45.0	360	1.0015
No log	46.0	368	0.9905
No log	47.0	376	0.9820
No log	48.0	384	0.9756
No log	49.0	392	0.9718
No log	50.0	400	0.9704

Framework versions

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