my_awesome_billsum_model_82

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: 0.2651
• Rouge1: 0.9769
• Rouge2: 0.8861
• Rougel: 0.9414
• Rougelsum: 0.9398
• Gen Len: 4.9583

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	0.1788	0.9675	0.8359	0.9136	0.9111	4.9792
No log	2.0	24	0.1578	0.9706	0.8564	0.9219	0.9199	5.0
No log	3.0	36	0.1606	0.974	0.8654	0.9317	0.9307	4.9375
No log	4.0	48	0.1720	0.9769	0.8861	0.9414	0.9398	4.9583
No log	5.0	60	0.1800	0.9769	0.8861	0.9414	0.9398	4.9583
No log	6.0	72	0.1871	0.9769	0.8861	0.9414	0.9398	4.9583
No log	7.0	84	0.1840	0.974	0.8654	0.9317	0.9307	4.9375
No log	8.0	96	0.1802	0.9769	0.8861	0.9414	0.9398	4.9583
No log	9.0	108	0.1672	0.9769	0.8861	0.9414	0.9398	4.9583
No log	10.0	120	0.1875	0.9769	0.8861	0.9414	0.9398	4.9583
No log	11.0	132	0.2060	0.9728	0.8655	0.9285	0.927	4.9792
No log	12.0	144	0.2068	0.9728	0.8655	0.9285	0.927	4.9792
No log	13.0	156	0.2064	0.9769	0.8861	0.9414	0.9398	4.9583
No log	14.0	168	0.2066	0.9769	0.8861	0.9414	0.9398	4.9583
No log	15.0	180	0.1867	0.9769	0.8861	0.9414	0.9398	4.9583
No log	16.0	192	0.1947	0.974	0.8654	0.9317	0.9307	4.9375
No log	17.0	204	0.1979	0.9769	0.8861	0.9414	0.9398	4.9583
No log	18.0	216	0.1971	0.9769	0.8861	0.9414	0.9398	4.9583
No log	19.0	228	0.1865	0.9769	0.8861	0.9414	0.9398	4.9583
No log	20.0	240	0.1757	0.9769	0.8861	0.9414	0.9398	4.9583
No log	21.0	252	0.1735	0.9769	0.8861	0.9414	0.9398	4.9583
No log	22.0	264	0.1846	0.9769	0.8861	0.9414	0.9398	4.9583
No log	23.0	276	0.2039	0.9769	0.8861	0.9414	0.9398	4.9583
No log	24.0	288	0.2251	0.9769	0.8861	0.9414	0.9398	4.9583
No log	25.0	300	0.2272	0.9769	0.8861	0.9414	0.9398	4.9583
No log	26.0	312	0.2165	0.9769	0.8861	0.9414	0.9398	4.9583
No log	27.0	324	0.2202	0.9769	0.8861	0.9414	0.9398	4.9583
No log	28.0	336	0.2166	0.9769	0.8861	0.9414	0.9398	4.9583
No log	29.0	348	0.2151	0.9769	0.8861	0.9414	0.9398	4.9583
No log	30.0	360	0.2151	0.9769	0.8861	0.9414	0.9398	4.9583
No log	31.0	372	0.2136	0.9769	0.8861	0.9414	0.9398	4.9583
No log	32.0	384	0.2206	0.9769	0.8861	0.9414	0.9398	4.9583
No log	33.0	396	0.2233	0.9769	0.8861	0.9414	0.9398	4.9583
No log	34.0	408	0.2220	0.9769	0.8861	0.9414	0.9398	4.9583
No log	35.0	420	0.2263	0.9769	0.8861	0.9414	0.9398	4.9583
No log	36.0	432	0.2298	0.9769	0.8861	0.9414	0.9398	4.9583
No log	37.0	444	0.2413	0.9769	0.8861	0.9414	0.9398	4.9583
No log	38.0	456	0.2407	0.9769	0.8861	0.9414	0.9398	4.9583
No log	39.0	468	0.2407	0.9769	0.8861	0.9414	0.9398	4.9583
No log	40.0	480	0.2420	0.9769	0.8861	0.9414	0.9398	4.9583
No log	41.0	492	0.2424	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	42.0	504	0.2442	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	43.0	516	0.2466	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	44.0	528	0.2416	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	45.0	540	0.2442	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	46.0	552	0.2457	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	47.0	564	0.2383	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	48.0	576	0.2481	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	49.0	588	0.2512	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	50.0	600	0.2510	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	51.0	612	0.2516	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	52.0	624	0.2491	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	53.0	636	0.2480	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	54.0	648	0.2493	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	55.0	660	0.2417	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	56.0	672	0.2320	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	57.0	684	0.2270	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	58.0	696	0.2351	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	59.0	708	0.2414	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	60.0	720	0.2490	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	61.0	732	0.2489	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	62.0	744	0.2496	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	63.0	756	0.2505	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	64.0	768	0.2515	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	65.0	780	0.2511	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	66.0	792	0.2521	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	67.0	804	0.2530	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	68.0	816	0.2536	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	69.0	828	0.2535	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	70.0	840	0.2575	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	71.0	852	0.2593	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	72.0	864	0.2588	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	73.0	876	0.2654	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	74.0	888	0.2622	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	75.0	900	0.2597	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	76.0	912	0.2586	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	77.0	924	0.2566	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	78.0	936	0.2554	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	79.0	948	0.2560	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	80.0	960	0.2582	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	81.0	972	0.2614	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	82.0	984	0.2652	0.9769	0.8861	0.9414	0.9398	4.9583
0.0483	83.0	996	0.2685	0.9769	0.8861	0.9414	0.9398	4.9583
0.0231	84.0	1008	0.2696	0.9769	0.8861	0.9414	0.9398	4.9583
0.0231	85.0	1020	0.2700	0.9769	0.8861	0.9414	0.9398	4.9583
0.0231	86.0	1032	0.2715	0.9769	0.8861	0.9414	0.9398	4.9583
0.0231	87.0	1044	0.2697	0.9769	0.8861	0.9414	0.9398	4.9583
0.0231	88.0	1056	0.2692	0.9769	0.8861	0.9414	0.9398	4.9583
0.0231	89.0	1068	0.2666	0.9769	0.8861	0.9414	0.9398	4.9583
0.0231	90.0	1080	0.2666	0.9769	0.8861	0.9414	0.9398	4.9583
0.0231	91.0	1092	0.2671	0.9769	0.8861	0.9414	0.9398	4.9583
0.0231	92.0	1104	0.2665	0.9769	0.8861	0.9414	0.9398	4.9583
0.0231	93.0	1116	0.2655	0.9769	0.8861	0.9414	0.9398	4.9583
0.0231	94.0	1128	0.2646	0.9769	0.8861	0.9414	0.9398	4.9583
0.0231	95.0	1140	0.2652	0.9769	0.8861	0.9414	0.9398	4.9583
0.0231	96.0	1152	0.2656	0.9769	0.8861	0.9414	0.9398	4.9583
0.0231	97.0	1164	0.2657	0.9769	0.8861	0.9414	0.9398	4.9583
0.0231	98.0	1176	0.2656	0.9769	0.8861	0.9414	0.9398	4.9583
0.0231	99.0	1188	0.2654	0.9769	0.8861	0.9414	0.9398	4.9583
0.0231	100.0	1200	0.2651	0.9769	0.8861	0.9414	0.9398	4.9583

Framework versions

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