long-t5-local-base-finetuned-justification-v02

This model is a fine-tuned version of google/long-t5-local-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.2775

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: 1
• eval_batch_size: 1
• 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
6.0497	1.0	676	2.2283
1.811	2.0	1352	1.9126
1.4433	3.0	2028	1.7826
1.3989	4.0	2704	1.6820
1.3378	5.0	3380	1.6180
1.26	6.0	4056	1.5683
1.2133	7.0	4732	1.5377
1.185	8.0	5408	1.4941
1.155	9.0	6084	1.4668
1.1085	10.0	6760	1.4391
1.154	11.0	7436	1.4168
1.0465	12.0	8112	1.3928
1.035	13.0	8788	1.3739
1.0478	14.0	9464	1.3731
0.9639	15.0	10140	1.3544
0.988	16.0	10816	1.3440
0.9586	17.0	11492	1.3308
0.9125	18.0	12168	1.3297
0.9782	19.0	12844	1.3204
0.9121	20.0	13520	1.3122
0.9173	21.0	14196	1.3080
0.8898	22.0	14872	1.2981
0.8791	23.0	15548	1.2953
0.899	24.0	16224	1.3028
0.8537	25.0	16900	1.2898
0.8808	26.0	17576	1.2864
0.8557	27.0	18252	1.2777
0.8132	28.0	18928	1.2797
0.8439	29.0	19604	1.2806
0.8313	30.0	20280	1.2821
0.8225	31.0	20956	1.2848
0.8364	32.0	21632	1.2806
0.7918	33.0	22308	1.2758
0.7988	34.0	22984	1.2761
0.8262	35.0	23660	1.2757
0.7876	36.0	24336	1.2783
0.7981	37.0	25012	1.2734
0.8019	38.0	25688	1.2783
0.7482	39.0	26364	1.2745
0.7558	40.0	27040	1.2724
0.7691	41.0	27716	1.2721
0.762	42.0	28392	1.2739
0.7942	43.0	29068	1.2748
0.7577	44.0	29744	1.2769
0.7386	45.0	30420	1.2765
0.7519	46.0	31096	1.2770
0.7614	47.0	31772	1.2779
0.7578	48.0	32448	1.2761
0.7666	49.0	33124	1.2771
0.7692	50.0	33800	1.2775

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.2+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2