t5-v1_1-base-fce-e8-b16

jeremyvictor/t5-v1_1-base-fce-e8-b16

t5-v1_1-base-fce-e8-b16 is a machine learning model from jeremyvictor. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

10% of all-time downloads

All-time downloads

313

Public

Repo size

67.4 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin990 MB · 100%

At a glance

Library: transformers
License: apache-2.0
Model type: t5
Access: Public
Created: Jul 16, 2023
Updated: Jul 16, 2023
SHA: f1cf05b3

Model card

From the Hugging Face model README

t5-v1_1-base-fce-e8-b16

This model is a fine-tuned version of google/t5-v1_1-base on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.3409
Rouge1: 87.1583
Rouge2: 79.8003
Rougel: 86.6556
Rougelsum: 86.6858
Gen Len: 14.8987

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: 0.001
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Adafactor
lr_scheduler_type: linear
num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
3.9063	0.06	100	0.8111	27.4937	22.9629	27.3015	27.2771	7.4286
0.7836	0.11	200	0.5104	85.4419	76.9583	84.8358	84.8509	15.0488
0.6368	0.17	300	0.4682	86.2542	77.5212	85.6688	85.6923	14.8298
0.5924	0.23	400	0.4734	86.4845	78.0506	85.9059	85.9008	14.8352
0.5694	0.28	500	0.4081	86.352	78.0709	85.8245	85.8281	14.8585
0.5335	0.34	600	0.4179	86.5893	78.4175	86.0693	86.0625	14.8745
0.5246	0.4	700	0.3990	86.4139	78.4306	85.9523	85.9443	14.8617
0.504	0.45	800	0.4233	86.7504	78.7906	86.2416	86.2447	14.8759
0.4818	0.51	900	0.4008	86.7978	78.8187	86.2413	86.2432	14.8699
0.4756	0.56	1000	0.4028	86.9123	79.0247	86.3563	86.3635	14.8640
0.4772	0.62	1100	0.3789	86.5028	78.5736	85.9794	85.9983	14.8717
0.4638	0.68	1200	0.3818	86.6276	78.7383	86.084	86.0903	14.9124
0.4614	0.73	1300	0.3839	86.8128	79.2001	86.3591	86.3519	14.8695
0.4326	0.79	1400	0.3751	86.9302	79.3511	86.4188	86.4311	14.9019
0.4485	0.85	1500	0.3654	86.6862	79.0433	86.1832	86.1872	14.9206
0.4187	0.9	1600	0.3823	86.9451	79.2758	86.4628	86.4724	14.8795
0.4218	0.96	1700	0.3696	86.9051	79.1393	86.3682	86.3627	14.9220
0.3812	1.02	1800	0.3699	87.0233	79.4507	86.513	86.5154	14.8873
0.3116	1.07	1900	0.3763	86.9293	79.2058	86.4356	86.4445	14.8918
0.3237	1.13	2000	0.3740	87.0449	79.4088	86.5157	86.5319	14.8918
0.3071	1.19	2100	0.3690	86.5698	78.4408	85.9993	86.0409	14.9069
0.3072	1.24	2200	0.3646	86.9336	79.334	86.4284	86.4303	14.8918
0.2953	1.3	2300	0.3750	86.7437	78.949	86.2131	86.202	14.8909
0.308	1.35	2400	0.3613	86.792	79.2179	86.2832	86.2934	14.8923
0.3132	1.41	2500	0.3528	86.7653	79.0525	86.2258	86.2357	14.9110
0.3141	1.47	2600	0.3494	86.8884	79.2484	86.3719	86.3622	14.9069
0.3095	1.52	2700	0.3539	87.0166	79.5218	86.5167	86.5248	14.8905
0.3274	1.58	2800	0.3599	87.2104	79.7277	86.7135	86.7127	14.8854
0.312	1.64	2900	0.3536	86.8926	79.2971	86.3699	86.3666	14.8886
0.3134	1.69	3000	0.3518	87.0884	79.5848	86.5877	86.6005	14.9028
0.3012	1.75	3100	0.3573	86.3559	78.1413	85.8416	85.8479	14.8763
0.311	1.81	3200	0.3467	86.9837	79.4983	86.4827	86.4981	14.8937
0.303	1.86	3300	0.3422	86.9232	79.3542	86.4098	86.4427	14.9032
0.304	1.92	3400	0.3409	87.1583	79.8003	86.6556	86.6858	14.8987
0.2934	1.98	3500	0.3485	87.0529	79.6491	86.5825	86.6003	14.9000
0.247	2.03	3600	0.3586	87.0147	79.6418	86.5126	86.5339	14.9042
0.193	2.09	3700	0.3667	86.9326	79.4481	86.4675	86.4709	14.9128
0.195	2.14	3800	0.3673	86.8892	79.3638	86.3717	86.3866	14.9210
0.19	2.2	3900	0.3670	86.8789	79.4677	86.3925	86.3892	14.9023
0.2033	2.26	4000	0.3600	86.9004	79.5211	86.4043	86.407	14.9042
0.1969	2.31	4100	0.3587	87.0403	79.7208	86.5257	86.5245	14.8978
0.2035	2.37	4200	0.3630	86.8793	79.4667	86.3931	86.3875	14.8895
0.2162	2.43	4300	0.3722	86.78	79.3367	86.2742	86.2812	14.9083
0.1984	2.48	4400	0.3573	86.7248	79.2577	86.218	86.2139	14.8918
0.2058	2.54	4500	0.3617	86.6452	79.1422	86.1701	86.1838	14.8909
0.2161	2.6	4600	0.3554	86.8574	79.5476	86.3982	86.4095	14.9283
0.215	2.65	4700	0.3583	86.8873	79.5265	86.4039	86.3996	14.8923
0.2048	2.71	4800	0.3535	86.8465	79.3852	86.3446	86.344	14.8978
0.2099	2.77	4900	0.3601	86.8952	79.4424	86.3888	86.387	14.8868
0.2149	2.82	5000	0.3603	86.7871	79.2397	86.297	86.3004	14.8850
0.2251	2.88	5100	0.3448	86.9477	79.6744	86.4984	86.4911	14.9133
0.2048	2.93	5200	0.3522	86.8843	79.37	86.3702	86.3668	14.8955
0.2099	2.99	5300	0.3459	86.7938	79.2104	86.3027	86.3169	14.9137
0.1377	3.05	5400	0.4000	86.9855	79.4184	86.438	86.4375	14.9110
0.1369	3.1	5500	0.3848	86.8338	79.2098	86.2885	86.3028	14.9019
0.1357	3.16	5600	0.3914	86.7061	79.2474	86.2247	86.2237	14.9105
0.1263	3.22	5700	0.3864	86.7128	79.1103	86.2121	86.2166	14.9137
0.135	3.27	5800	0.3929	86.8134	79.4572	86.3608	86.3683	14.9124
0.1361	3.33	5900	0.3828	86.9149	79.4756	86.4152	86.3959	14.8959
0.1286	3.39	6000	0.3849	86.8025	79.3645	86.3215	86.3204	14.8996
0.1335	3.44	6100	0.3793	86.7591	79.2887	86.2778	86.2765	14.9105
0.1278	3.5	6200	0.3938	86.8352	79.4161	86.3282	86.3376	14.9169
0.1346	3.56	6300	0.3943	86.9637	79.6404	86.4753	86.4718	14.8978
0.1421	3.61	6400	0.3799	86.8445	79.4133	86.3271	86.3206	14.9151
0.1398	3.67	6500	0.3923	86.9793	79.6847	86.4935	86.4889	14.9174
0.1359	3.72	6600	0.3912	86.9095	79.3593	86.4296	86.4506	14.8959
0.1444	3.78	6700	0.3741	86.8498	79.3141	86.3586	86.3681	14.8909
0.1351	3.84	6800	0.3840	87.223	79.825	86.7127	86.7371	14.8877
0.1325	3.89	6900	0.3816	87.148	79.8102	86.6405	86.6511	14.9133
0.1315	3.95	7000	0.3796	86.7778	79.3782	86.3057	86.2939	14.9005
0.1332	4.01	7100	0.3962	87.0238	79.6621	86.5384	86.5306	14.8996
0.0834	4.06	7200	0.4271	86.9999	79.7076	86.4981	86.5026	14.9014
0.088	4.12	7300	0.4176	86.9193	79.4698	86.4085	86.4171	14.9128
0.0897	4.18	7400	0.4109	86.9287	79.5866	86.4541	86.4474	14.9037
0.0908	4.23	7500	0.4109	87.1272	79.7632	86.6206	86.6176	14.9133
0.0895	4.29	7600	0.4114	87.0107	79.7349	86.4873	86.4754	14.9023
0.0856	4.35	7700	0.4242	87.0115	79.6387	86.4786	86.49	14.8982
0.0852	4.4	7800	0.4271	86.9943	79.6717	86.5126	86.5026	14.9019
0.0919	4.46	7900	0.4216	86.9903	79.67	86.512	86.5085	14.8937
0.0907	4.51	8000	0.4180	87.0323	79.7092	86.5391	86.5343	14.8978
0.0889	4.57	8100	0.4276	86.9813	79.6367	86.4697	86.4724	14.9115
0.0907	4.63	8200	0.4209	87.0149	79.5637	86.5028	86.5059	14.9092
0.0966	4.68	8300	0.4064	86.9685	79.4665	86.4393	86.4523	14.9010
0.088	4.74	8400	0.4234	86.9921	79.5729	86.4977	86.5067	14.8800
0.0897	4.8	8500	0.4117	87.0727	79.7094	86.5465	86.5482	14.9014
0.0924	4.85	8600	0.4056	86.8789	79.409	86.3689	86.3672	14.9083
0.0916	4.91	8700	0.4127	86.8645	79.4195	86.3814	86.3729	14.8982
0.0908	4.97	8800	0.4054	86.9146	79.4138	86.4022	86.399	14.9000
0.078	5.02	8900	0.4403	87.0178	79.6166	86.5112	86.505	14.9078
0.0583	5.08	9000	0.4400	86.9828	79.649	86.4913	86.4962	14.9064
0.057	5.14	9100	0.4637	87.0435	79.6446	86.5464	86.5252	14.9037
0.0581	5.19	9200	0.4617	87.017	79.6255	86.5004	86.4907	14.9069
0.0562	5.25	9300	0.4521	86.8638	79.479	86.3298	86.338	14.9096
0.0588	5.3	9400	0.4472	86.9719	79.5608	86.4751	86.4798	14.9073
0.0571	5.36	9500	0.4472	87.0325	79.6355	86.5154	86.5278	14.9073
0.0589	5.42	9600	0.4580	87.1556	79.8992	86.627	86.6372	14.9064
0.057	5.47	9700	0.4527	87.0033	79.6457	86.4846	86.5031	14.9101
0.0595	5.53	9800	0.4538	87.0419	79.6632	86.5261	86.5434	14.9055
0.062	5.59	9900	0.4518	87.0581	79.6818	86.54	86.551	14.9005
0.0568	5.64	10000	0.4549	87.1255	79.8908	86.6143	86.6255	14.9042
0.0572	5.7	10100	0.4557	86.9927	79.5946	86.4726	86.4953	14.9023
0.0603	5.76	10200	0.4493	87.0665	79.7469	86.58	86.5934	14.8932
0.0604	5.81	10300	0.4533	87.0864	79.7039	86.5871	86.5851	14.9042
0.0564	5.87	10400	0.4653	87.082	79.766	86.5835	86.5775	14.9055
0.0579	5.93	10500	0.4677	86.9805	79.5068	86.4708	86.4744	14.8882
0.0582	5.98	10600	0.4607	86.9273	79.3762	86.4228	86.4225	14.9119
0.0454	6.04	10700	0.4917	87.038	79.6146	86.5363	86.533	14.9156
0.0399	6.09	10800	0.4986	87.0026	79.5481	86.4992	86.4924	14.9042
0.0367	6.15	10900	0.5115	87.13	79.7506	86.6082	86.621	14.9055
0.0405	6.21	11000	0.5084	87.0768	79.6986	86.5541	86.5403	14.9083
0.0386	6.26	11100	0.5092	87.1376	79.7442	86.5937	86.5767	14.8996
0.0382	6.32	11200	0.5063	87.0779	79.7205	86.561	86.5546	14.8982
0.0431	6.38	11300	0.4950	87.0998	79.7699	86.5882	86.5916	14.9028
0.0388	6.43	11400	0.5098	87.1711	79.8707	86.6425	86.6409	14.9023
0.041	6.49	11500	0.4911	87.1742	79.8319	86.6434	86.6522	14.9005
0.0379	6.55	11600	0.5023	87.2258	79.9175	86.7019	86.7018	14.9010
0.0383	6.6	11700	0.5078	87.0913	79.7547	86.5767	86.5826	14.9046
0.0387	6.66	11800	0.5111	87.1913	79.9592	86.6805	86.6742	14.9060
0.0362	6.72	11900	0.5125	87.0096	79.6639	86.5037	86.5039	14.9124
0.0343	6.77	12000	0.5210	87.0657	79.7384	86.5621	86.5561	14.9110
0.0401	6.83	12100	0.5110	87.1338	79.8537	86.6368	86.6271	14.9124
0.0353	6.88	12200	0.5169	87.082	79.756	86.5771	86.5718	14.9073
0.0384	6.94	12300	0.4998	87.1211	79.8474	86.6016	86.6065	14.9078
0.0395	7.0	12400	0.5184	87.1621	79.8793	86.6411	86.648	14.9064
0.0243	7.05	12500	0.5387	87.1588	79.8545	86.6464	86.6627	14.9019
0.0283	7.11	12600	0.5384	87.1909	79.8888	86.6567	86.6698	14.9042
0.026	7.17	12700	0.5459	87.1782	79.7991	86.6373	86.6507	14.9028
0.0303	7.22	12800	0.5301	87.1014	79.7321	86.5581	86.5743	14.9014
0.0252	7.28	12900	0.5481	87.0907	79.6948	86.5306	86.5474	14.9069
0.0273	7.34	13000	0.5469	87.0971	79.6697	86.5392	86.558	14.8987
0.0249	7.39	13100	0.5462	87.095	79.6904	86.5559	86.566	14.9037
0.0246	7.45	13200	0.5553	87.0964	79.6834	86.5572	86.5607	14.9055
0.0286	7.51	13300	0.5501	87.0933	79.7177	86.5579	86.5582	14.9092
0.0234	7.56	13400	0.5550	87.1266	79.7546	86.5833	86.5855	14.9087
0.0263	7.62	13500	0.5570	87.0957	79.6859	86.5608	86.5584	14.9064
0.0238	7.67	13600	0.5630	87.1368	79.7487	86.6036	86.6031	14.9032
0.0258	7.73	13700	0.5598	87.1527	79.7481	86.622	86.6153	14.9055
0.0249	7.79	13800	0.5649	87.15	79.7419	86.6106	86.6056	14.9046
0.0272	7.84	13900	0.5616	87.1439	79.7597	86.6085	86.6081	14.9042
0.0261	7.9	14000	0.5596	87.1359	79.7696	86.6081	86.6024	14.9051
0.0233	7.96	14100	0.5611	87.1367	79.7636	86.6112	86.6019	14.9046

Framework versions

Transformers 4.30.1
Pytorch 1.11.0a0+b6df043
Datasets 2.12.0
Tokenizers 0.13.3

Library: transformers
Type: t5
License: apache-2.0
Created: Jul 16, 2023
Updated: Jul 16, 2023