DataEntSN

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: 0.0687

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: 4
• eval_batch_size: 4
• 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	251	1.3488
2.3455	2.0	502	1.0949
2.3455	3.0	753	0.9507
1.1903	4.0	1004	0.8535
1.1903	5.0	1255	0.7726
0.9919	6.0	1506	0.7113
0.9919	7.0	1757	0.6525
0.8619	8.0	2008	0.5946
0.8619	9.0	2259	0.5537
0.7583	10.0	2510	0.5091
0.7583	11.0	2761	0.4706
0.6822	12.0	3012	0.4411
0.6822	13.0	3263	0.4077
0.6136	14.0	3514	0.3799
0.6136	15.0	3765	0.3484
0.5561	16.0	4016	0.3260
0.5561	17.0	4267	0.3050
0.5015	18.0	4518	0.2850
0.5015	19.0	4769	0.2621
0.4587	20.0	5020	0.2461
0.4587	21.0	5271	0.2296
0.4163	22.0	5522	0.2122
0.4163	23.0	5773	0.1998
0.3901	24.0	6024	0.1876
0.3901	25.0	6275	0.1764
0.3589	26.0	6526	0.1641
0.3589	27.0	6777	0.1553
0.3294	28.0	7028	0.1449
0.3294	29.0	7279	0.1380
0.3098	30.0	7530	0.1277
0.3098	31.0	7781	0.1226
0.2893	32.0	8032	0.1161
0.2893	33.0	8283	0.1081
0.2713	34.0	8534	0.1047
0.2713	35.0	8785	0.1014
0.2568	36.0	9036	0.0948
0.2568	37.0	9287	0.0906
0.2436	38.0	9538	0.0879
0.2436	39.0	9789	0.0841
0.2344	40.0	10040	0.0811
0.2344	41.0	10291	0.0794
0.2252	42.0	10542	0.0776
0.2252	43.0	10793	0.0752
0.2142	44.0	11044	0.0736
0.2142	45.0	11295	0.0715
0.2104	46.0	11546	0.0706
0.2104	47.0	11797	0.0704
0.2051	48.0	12048	0.0692
0.2051	49.0	12299	0.0688
0.2008	50.0	12550	0.0687

Framework versions

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