fine-tuned-FLAN-T5-20-epochs-wanglab-512-output

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

• Loss: 6.0705
• Rouge1: 0.1508
• Rouge2: 0.0272
• Rougel: 0.1374
• Rougelsum: 0.1351
• Bertscore F1: 0.8553
• Bleurt Score: -1.2097
• Gen Len: 14.69

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: 0.0001
• 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
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Bertscore F1	Bleurt Score	Gen Len
No log	1.0	301	11.0933	0.065	0.0148	0.0596	0.0595	0.7859	-1.4402	18.92
20.9249	2.0	602	9.2324	0.0604	0.0154	0.0556	0.0554	0.7869	-1.3807	17.42
20.9249	3.0	903	7.6254	0.0681	0.0192	0.0632	0.0627	0.7978	-1.4375	18.42
11.3584	4.0	1204	6.7112	0.0614	0.0073	0.0578	0.0582	0.8076	-1.3157	14.34
8.9106	5.0	1505	6.6742	0.0701	0.0204	0.0638	0.0635	0.7968	-1.3894	17.29
8.9106	6.0	1806	5.9658	0.0836	0.0145	0.074	0.0742	0.818	-1.3081	13.76
7.8674	7.0	2107	5.7095	0.113	0.025	0.1061	0.1078	0.8433	-1.4119	13.71
7.8674	8.0	2408	5.6269	0.0987	0.0147	0.0933	0.0939	0.8201	-1.2529	15.32
6.7786	9.0	2709	5.5192	0.1133	0.0203	0.1038	0.1051	0.8484	-1.3751	13.75
6.3646	10.0	3010	5.4626	0.1347	0.0276	0.122	0.1236	0.8501	-1.278	13.16
6.3646	11.0	3311	5.4467	0.103	0.0172	0.0951	0.0943	0.8263	-1.3587	15.48
5.6998	12.0	3612	5.4587	0.126	0.0326	0.1191	0.1183	0.8474	-1.2782	15.86
5.6998	13.0	3913	5.4846	0.1523	0.0325	0.1407	0.1408	0.8528	-1.2406	14.82
5.2971	14.0	4214	5.6166	0.1363	0.0275	0.1279	0.1247	0.8512	-1.2827	14.7
4.9391	15.0	4515	5.6821	0.1479	0.0238	0.136	0.1342	0.8545	-1.2217	14.72
4.9391	16.0	4816	5.7849	0.1577	0.0307	0.1455	0.1445	0.8566	-1.1756	15.25
4.6035	17.0	5117	5.8945	0.1313	0.0234	0.1214	0.1199	0.8525	-1.2609	14.67
4.6035	18.0	5418	5.9956	0.1506	0.0315	0.1367	0.1348	0.8542	-1.2107	14.61
4.3893	19.0	5719	6.0337	0.1449	0.0294	0.1337	0.1317	0.8553	-1.2173	14.49
4.245	20.0	6020	6.0705	0.1508	0.0272	0.1374	0.1351	0.8553	-1.2097	14.69

Framework versions

• Transformers 4.37.2
• Pytorch 2.1.0+cu121
• Datasets 2.17.1
• Tokenizers 0.15.2