my_awesome_billsum_model_66

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

• Loss: 1.0931
• Rouge1: 0.9612
• Rouge2: 0.844
• Rougel: 0.9033
• Rougelsum: 0.9017
• Gen Len: 5.0833

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 100
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	12	0.9723	0.9612	0.844	0.9033	0.9017	5.0833
No log	2.0	24	0.9569	0.9612	0.844	0.9033	0.9017	5.0833
No log	3.0	36	0.9556	0.9612	0.844	0.9033	0.9017	5.0833
No log	4.0	48	0.9349	0.9612	0.844	0.9033	0.9017	5.0833
No log	5.0	60	0.9414	0.9641	0.864	0.9121	0.9107	5.1042
No log	6.0	72	0.9466	0.9641	0.864	0.9121	0.9107	5.1042
No log	7.0	84	0.9614	0.9641	0.864	0.9121	0.9107	5.1042
No log	8.0	96	0.9674	0.9641	0.864	0.9121	0.9107	5.1042
No log	9.0	108	0.9679	0.958	0.8387	0.9045	0.9031	5.0625
No log	10.0	120	0.9714	0.9603	0.8504	0.9142	0.9098	5.0417
No log	11.0	132	0.9692	0.9641	0.8748	0.924	0.9224	5.1042
No log	12.0	144	0.9700	0.9641	0.864	0.9121	0.9107	5.1042
No log	13.0	156	0.9649	0.9612	0.844	0.9033	0.9017	5.0833
No log	14.0	168	0.9539	0.9612	0.844	0.9033	0.9017	5.0833
No log	15.0	180	0.9534	0.9641	0.864	0.9121	0.9107	5.1042
No log	16.0	192	0.9646	0.9641	0.864	0.9121	0.9107	5.1042
No log	17.0	204	0.9753	0.9641	0.864	0.9121	0.9107	5.1042
No log	18.0	216	0.9846	0.9641	0.864	0.9121	0.9107	5.1042
No log	19.0	228	0.9885	0.9612	0.844	0.9033	0.9017	5.0833
No log	20.0	240	0.9898	0.9641	0.864	0.9121	0.9107	5.1042
No log	21.0	252	0.9944	0.9612	0.844	0.9033	0.9017	5.0833
No log	22.0	264	0.9961	0.9641	0.8509	0.9068	0.905	5.1042
No log	23.0	276	1.0002	0.9641	0.8509	0.9068	0.905	5.1042
No log	24.0	288	1.0003	0.9641	0.8509	0.9068	0.905	5.1042
No log	25.0	300	1.0077	0.9612	0.844	0.9033	0.9017	5.0833
No log	26.0	312	1.0249	0.9612	0.844	0.9033	0.9017	5.0833
No log	27.0	324	1.0351	0.9612	0.844	0.9033	0.9017	5.0833
No log	28.0	336	1.0177	0.9641	0.864	0.9121	0.9107	5.1042
No log	29.0	348	1.0214	0.9612	0.844	0.9033	0.9017	5.0833
No log	30.0	360	1.0268	0.9612	0.844	0.9033	0.9017	5.0833
No log	31.0	372	1.0304	0.9612	0.844	0.9033	0.9017	5.0833
No log	32.0	384	1.0350	0.9612	0.844	0.9033	0.9017	5.0833
No log	33.0	396	1.0293	0.9612	0.844	0.9033	0.9017	5.0833
No log	34.0	408	1.0266	0.9612	0.844	0.9033	0.9017	5.0833
No log	35.0	420	1.0319	0.9612	0.844	0.9033	0.9017	5.0833
No log	36.0	432	1.0462	0.9612	0.844	0.9033	0.9017	5.0833
No log	37.0	444	1.0478	0.9612	0.844	0.9033	0.9017	5.0833
No log	38.0	456	1.0539	0.9612	0.844	0.9033	0.9017	5.0833
No log	39.0	468	1.0613	0.9612	0.844	0.9033	0.9017	5.0833
No log	40.0	480	1.0575	0.9612	0.844	0.9033	0.9017	5.0833
No log	41.0	492	1.0462	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	42.0	504	1.0411	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	43.0	516	1.0446	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	44.0	528	1.0429	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	45.0	540	1.0420	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	46.0	552	1.0439	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	47.0	564	1.0413	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	48.0	576	1.0420	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	49.0	588	1.0465	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	50.0	600	1.0519	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	51.0	612	1.0570	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	52.0	624	1.0635	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	53.0	636	1.0589	0.9641	0.864	0.9121	0.9107	5.1042
0.0089	54.0	648	1.0580	0.9641	0.864	0.9121	0.9107	5.1042
0.0089	55.0	660	1.0582	0.9641	0.864	0.9121	0.9107	5.1042
0.0089	56.0	672	1.0539	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	57.0	684	1.0407	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	58.0	696	1.0421	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	59.0	708	1.0488	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	60.0	720	1.0579	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	61.0	732	1.0644	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	62.0	744	1.0750	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	63.0	756	1.0848	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	64.0	768	1.0877	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	65.0	780	1.0866	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	66.0	792	1.0889	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	67.0	804	1.0881	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	68.0	816	1.0824	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	69.0	828	1.0787	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	70.0	840	1.0779	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	71.0	852	1.0769	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	72.0	864	1.0769	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	73.0	876	1.0759	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	74.0	888	1.0766	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	75.0	900	1.0761	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	76.0	912	1.0849	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	77.0	924	1.0856	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	78.0	936	1.0896	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	79.0	948	1.0952	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	80.0	960	1.0984	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	81.0	972	1.0995	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	82.0	984	1.0983	0.9612	0.844	0.9033	0.9017	5.0833
0.0089	83.0	996	1.0968	0.9612	0.844	0.9033	0.9017	5.0833
0.006	84.0	1008	1.0962	0.9612	0.844	0.9033	0.9017	5.0833
0.006	85.0	1020	1.0980	0.9612	0.844	0.9033	0.9017	5.0833
0.006	86.0	1032	1.0997	0.9612	0.844	0.9033	0.9017	5.0833
0.006	87.0	1044	1.0994	0.9612	0.844	0.9033	0.9017	5.0833
0.006	88.0	1056	1.0997	0.9612	0.844	0.9033	0.9017	5.0833
0.006	89.0	1068	1.0990	0.9612	0.844	0.9033	0.9017	5.0833
0.006	90.0	1080	1.0984	0.9612	0.844	0.9033	0.9017	5.0833
0.006	91.0	1092	1.0975	0.9612	0.844	0.9033	0.9017	5.0833
0.006	92.0	1104	1.0966	0.9612	0.844	0.9033	0.9017	5.0833
0.006	93.0	1116	1.0938	0.9612	0.844	0.9033	0.9017	5.0833
0.006	94.0	1128	1.0937	0.9612	0.844	0.9033	0.9017	5.0833
0.006	95.0	1140	1.0943	0.9612	0.844	0.9033	0.9017	5.0833
0.006	96.0	1152	1.0933	0.9612	0.844	0.9033	0.9017	5.0833
0.006	97.0	1164	1.0928	0.9612	0.844	0.9033	0.9017	5.0833
0.006	98.0	1176	1.0927	0.9612	0.844	0.9033	0.9017	5.0833
0.006	99.0	1188	1.0929	0.9612	0.844	0.9033	0.9017	5.0833
0.006	100.0	1200	1.0931	0.9612	0.844	0.9033	0.9017	5.0833

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1