gpt2-finetuned-justification-v5

satyanshu404/gpt2-finetuned-justification-v5

gpt2-finetuned-justification-v5 is a machine learning model from satyanshu404. 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.

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

Downloads · 30 days

51% of all-time downloads

All-time downloads

103

Public

Parameters

301M

305 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors1.2 GB · 100%

At a glance

Library: transformers
Model type: encoder-decoder
Access: Public
Created: Apr 18, 2024
Updated: Apr 19, 2024
SHA: bc668d68

Model card

From the Hugging Face model README

gpt2-finetuned-justification-v5

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

Loss: 0.3678
Rouge1: 28.2558
Rouge2: 13.2942
Rougel: 20.5646
Rougelsum: 25.4960

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: 2
eval_batch_size: 2
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 200

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
No log	1.0	338	0.2009	31.3319	13.9488	23.6685	29.4548
0.2408	2.0	676	0.1974	29.1645	13.8230	21.7497	26.8219
0.1816	3.0	1014	0.1970	29.1922	13.8428	21.7595	26.8727
0.1816	4.0	1352	0.1976	31.8894	13.6293	23.2637	29.1353
0.1594	5.0	1690	0.1999	28.9161	13.7629	21.7786	26.6707
0.1417	6.0	2028	0.2019	26.1827	13.0883	21.6704	25.0609
0.1417	7.0	2366	0.2052	32.5679	14.4370	23.6445	29.7651
0.1287	8.0	2704	0.2093	30.4390	13.4570	22.2407	27.9234
0.1148	9.0	3042	0.2140	26.3746	13.2671	21.7004	25.0909
0.1148	10.0	3380	0.2182	30.4390	13.4570	22.2407	27.9234
0.0996	11.0	3718	0.2235	28.9954	13.7629	21.8212	26.7486
0.0918	12.0	4056	0.2292	29.6633	13.5103	21.9731	27.1570
0.0918	13.0	4394	0.2344	32.1781	13.7632	22.8996	29.0738
0.0783	14.0	4732	0.2369	27.9019	13.5715	21.1971	25.6530
0.0697	15.0	5070	0.2448	30.3482	13.6242	22.1001	27.5802
0.0697	16.0	5408	0.2478	32.2060	13.7632	22.8806	29.0774
0.0617	17.0	5746	0.2511	30.3482	13.6242	22.1001	27.5802
0.0547	18.0	6084	0.2562	30.3482	13.6242	22.1001	27.5802
0.0547	19.0	6422	0.2614	31.7077	14.1430	23.3427	29.2428
0.0486	20.0	6760	0.2619	30.3691	13.6839	22.1309	27.5877
0.0431	21.0	7098	0.2666	30.3482	13.6242	22.1001	27.5802
0.0431	22.0	7436	0.2661	32.1647	13.7632	22.8606	29.0573
0.0398	23.0	7774	0.2710	28.3033	13.7723	21.5098	26.0225
0.0356	24.0	8112	0.2743	30.3482	13.6242	22.1001	27.5802
0.0356	25.0	8450	0.2729	30.3482	13.6242	22.1001	27.5802
0.033	26.0	8788	0.2761	30.3482	13.6242	22.1001	27.5802
0.03	27.0	9126	0.2782	30.3482	13.6242	22.1001	27.5802
0.03	28.0	9464	0.2821	27.7803	13.2224	20.9152	25.2690
0.0274	29.0	9802	0.2840	27.7800	13.4113	20.6604	25.5476
0.0257	30.0	10140	0.2855	30.2852	13.6008	22.0867	27.5376
0.0257	31.0	10478	0.2878	30.3482	13.6242	22.1001	27.5802
0.0238	32.0	10816	0.2888	30.3482	13.6242	22.1001	27.5802
0.0219	33.0	11154	0.2872	30.3482	13.6242	22.1001	27.5802
0.0219	34.0	11492	0.2905	30.3482	13.6242	22.1001	27.5802
0.0211	35.0	11830	0.2926	30.2097	13.6132	22.0455	27.4601
0.0192	36.0	12168	0.2961	26.7582	13.4935	20.6488	24.7462
0.0186	37.0	12506	0.2984	26.7089	12.7390	20.4116	24.8107
0.0186	38.0	12844	0.2955	30.3482	13.6242	22.1001	27.5802
0.0175	39.0	13182	0.2985	30.3545	13.8737	22.2152	27.6296
0.017	40.0	13520	0.3025	30.3545	13.8737	22.2152	27.6296
0.017	41.0	13858	0.3038	30.5505	13.0272	21.9910	27.6810
0.0158	42.0	14196	0.3042	30.3545	13.8737	22.2152	27.6296
0.0156	43.0	14534	0.3048	26.7070	13.5119	20.6281	24.6882
0.0156	44.0	14872	0.3061	30.3440	13.8737	22.1997	27.6126
0.0147	45.0	15210	0.3081	26.7070	13.5119	20.6281	24.6882
0.0141	46.0	15548	0.3133	26.7414	13.5119	20.6325	24.7363
0.0141	47.0	15886	0.3115	30.3482	13.6242	22.1001	27.5802
0.0135	48.0	16224	0.3131	26.5987	13.0206	20.4843	24.9550
0.0131	49.0	16562	0.3142	27.9816	13.6880	21.2917	25.7438
0.0131	50.0	16900	0.3161	26.9511	13.3418	20.9442	25.0861
0.0128	51.0	17238	0.3157	26.4405	12.8498	19.8095	23.8804
0.0123	52.0	17576	0.3169	26.4482	12.8554	19.8262	23.8895
0.0123	53.0	17914	0.3162	27.4677	13.5119	21.0011	25.2709
0.0121	54.0	18252	0.3192	26.4405	12.8498	19.8095	23.8804
0.012	55.0	18590	0.3192	27.4743	13.5029	21.0202	25.2768
0.012	56.0	18928	0.3217	28.7538	13.6889	21.2448	26.2972
0.0116	57.0	19266	0.3221	30.3482	13.6242	22.1001	27.5802
0.0112	58.0	19604	0.3214	27.4677	13.5119	21.0011	25.2709
0.0112	59.0	19942	0.3256	30.3482	13.6242	22.1001	27.5802
0.011	60.0	20280	0.3246	30.3482	13.6242	22.1001	27.5802
0.0107	61.0	20618	0.3269	26.4008	12.8554	19.8262	23.8411
0.0107	62.0	20956	0.3262	30.3482	13.6242	22.1001	27.5802
0.0107	63.0	21294	0.3262	26.4405	12.8498	19.8095	23.8804
0.0104	64.0	21632	0.3313	26.4008	12.8554	19.8262	23.8411
0.0104	65.0	21970	0.3301	26.4405	12.8498	19.8095	23.8804
0.0102	66.0	22308	0.3334	27.0875	13.1212	20.9683	24.8767
0.01	67.0	22646	0.3307	27.1356	13.1167	20.9787	24.9210
0.01	68.0	22984	0.3351	26.4482	12.8554	19.8262	23.8895
0.0101	69.0	23322	0.3334	28.2990	13.2942	20.5684	25.5223
0.0098	70.0	23660	0.3337	27.4743	13.5029	21.0202	25.2768
0.0098	71.0	23998	0.3320	26.5357	12.9745	20.4634	24.8632
0.0097	72.0	24336	0.3371	26.4405	12.8498	19.8095	23.8804
0.0094	73.0	24674	0.3365	28.2536	13.2942	20.5684	25.4770
0.0096	74.0	25012	0.3334	27.4677	13.5119	21.0011	25.2709
0.0096	75.0	25350	0.3401	26.4008	12.8554	19.8262	23.8411
0.0094	76.0	25688	0.3369	27.0875	13.1212	20.9683	24.8767
0.0092	77.0	26026	0.3379	28.2558	13.2942	20.5646	25.4960
0.0092	78.0	26364	0.3402	26.4405	12.8498	19.8095	23.8804
0.0091	79.0	26702	0.3394	29.8901	13.3237	21.5272	26.8283
0.0091	80.0	27040	0.3381	20.8422	11.5482	18.3383	20.0148
0.0091	81.0	27378	0.3375	28.2558	13.2942	20.5646	25.4960
0.009	82.0	27716	0.3382	28.2536	13.2942	20.5684	25.4770
0.0088	83.0	28054	0.3393	27.4677	13.5119	21.0011	25.2709
0.0088	84.0	28392	0.3412	27.2358	13.8221	21.2686	25.1893
0.0087	85.0	28730	0.3473	26.4405	12.8498	19.8095	23.8804
0.0088	86.0	29068	0.3433	28.2902	13.2884	20.5599	25.5133
0.0088	87.0	29406	0.3433	30.3482	13.6242	22.1001	27.5802
0.0086	88.0	29744	0.3430	27.0875	13.1212	20.9683	24.8767
0.0086	89.0	30082	0.3465	30.3482	13.6242	22.1001	27.5802
0.0086	90.0	30420	0.3444	26.4611	12.8498	19.8370	23.8945
0.0085	91.0	30758	0.3480	26.4243	12.8644	19.8396	23.8598
0.0085	92.0	31096	0.3462	26.4405	12.8498	19.8095	23.8804
0.0085	93.0	31434	0.3458	30.3482	13.6242	22.1001	27.5802
0.0084	94.0	31772	0.3433	30.3482	13.6242	22.1001	27.5802
0.0084	95.0	32110	0.3468	26.4405	12.8498	19.8095	23.8804
0.0084	96.0	32448	0.3453	19.7830	7.7026	16.7373	18.8332
0.0083	97.0	32786	0.3499	21.9400	11.8071	19.0004	20.7038
0.0082	98.0	33124	0.3509	28.9561	13.0484	21.4552	26.5578
0.0082	99.0	33462	0.3493	28.2536	13.2942	20.5684	25.4770
0.0082	100.0	33800	0.3505	27.1066	13.1324	20.9784	24.8951
0.0082	101.0	34138	0.3482	27.0875	13.1212	20.9683	24.8767
0.0082	102.0	34476	0.3497	27.0875	13.1212	20.9683	24.8767
0.0082	103.0	34814	0.3517	27.0875	13.1212	20.9683	24.8767
0.0081	104.0	35152	0.3529	30.3100	13.6441	22.1010	27.5391
0.0081	105.0	35490	0.3490	26.4405	12.8498	19.8095	23.8804
0.0081	106.0	35828	0.3524	30.3282	13.6242	22.1001	27.5644
0.0079	107.0	36166	0.3514	28.2536	13.2942	20.5684	25.4770
0.0081	108.0	36504	0.3534	30.3482	13.6242	22.1001	27.5802
0.0081	109.0	36842	0.3518	28.3079	13.2884	20.5813	25.5310
0.0078	110.0	37180	0.3538	30.3482	13.6242	22.1001	27.5802
0.0079	111.0	37518	0.3567	27.2358	13.8221	21.2686	25.1893
0.0079	112.0	37856	0.3517	30.3482	13.6242	22.1001	27.5802
0.0078	113.0	38194	0.3542	27.2358	13.8221	21.2686	25.1893
0.0078	114.0	38532	0.3558	30.3482	13.6242	22.1001	27.5802
0.0078	115.0	38870	0.3571	28.3079	13.2884	20.5813	25.5310
0.0077	116.0	39208	0.3566	26.4405	12.8498	19.8095	23.8804
0.0077	117.0	39546	0.3590	27.0875	13.1212	20.9683	24.8767
0.0077	118.0	39884	0.3574	23.4456	12.1733	19.9307	22.2553
0.0076	119.0	40222	0.3563	26.4405	12.8498	19.8095	23.8804
0.0077	120.0	40560	0.3547	26.4405	12.8498	19.8095	23.8804
0.0077	121.0	40898	0.3590	26.4611	12.8498	19.8370	23.8945
0.0076	122.0	41236	0.3559	22.1818	12.0059	19.2020	20.9696
0.0076	123.0	41574	0.3529	30.3482	13.6242	22.1001	27.5802
0.0076	124.0	41912	0.3566	30.3482	13.6242	22.1001	27.5802
0.0076	125.0	42250	0.3586	26.4243	12.8644	19.8396	23.8598
0.0076	126.0	42588	0.3562	26.4405	12.8498	19.8095	23.8804
0.0076	127.0	42926	0.3594	28.2558	13.2942	20.5646	25.4960
0.0075	128.0	43264	0.3575	30.3482	13.6242	22.1001	27.5802
0.0075	129.0	43602	0.3536	30.3482	13.6242	22.1001	27.5802
0.0075	130.0	43940	0.3566	28.2536	13.2942	20.5684	25.4770
0.0074	131.0	44278	0.3591	30.3482	13.6242	22.1001	27.5802
0.0075	132.0	44616	0.3576	30.3482	13.6242	22.1001	27.5802
0.0075	133.0	44954	0.3573	26.4611	12.8498	19.8370	23.8945
0.0075	134.0	45292	0.3580	26.4008	12.8554	19.8262	23.8411
0.0075	135.0	45630	0.3584	26.4008	12.8554	19.8262	23.8411
0.0075	136.0	45968	0.3584	27.0875	13.1212	20.9683	24.8767
0.0074	137.0	46306	0.3591	30.3482	13.6242	22.1001	27.5802
0.0074	138.0	46644	0.3604	28.3079	13.2884	20.5813	25.5310
0.0074	139.0	46982	0.3624	25.6025	13.3836	19.9214	23.2847
0.0074	140.0	47320	0.3598	28.2536	13.2942	20.5684	25.4770
0.0073	141.0	47658	0.3604	26.4405	12.8498	19.8095	23.8804
0.0073	142.0	47996	0.3613	26.3898	12.8644	19.8160	23.8305
0.0074	143.0	48334	0.3614	28.2536	13.2942	20.5684	25.4770
0.0074	144.0	48672	0.3615	28.2558	13.2942	20.5646	25.4960
0.0073	145.0	49010	0.3608	28.2536	13.2942	20.5684	25.4770
0.0073	146.0	49348	0.3616	26.4405	12.8498	19.8095	23.8804
0.0072	147.0	49686	0.3652	28.9561	13.0484	21.4552	26.5578
0.0073	148.0	50024	0.3632	28.2536	13.2942	20.5684	25.4770
0.0073	149.0	50362	0.3603	27.0875	13.1212	20.9683	24.8767
0.0073	150.0	50700	0.3608	26.3919	12.8457	19.8638	23.8486
0.0072	151.0	51038	0.3614	26.3919	12.8457	19.8638	23.8486
0.0072	152.0	51376	0.3624	28.2536	13.2942	20.5684	25.4770
0.0071	153.0	51714	0.3615	26.4008	12.8554	19.8262	23.8411
0.0071	154.0	52052	0.3636	26.4405	12.8498	19.8095	23.8804
0.0071	155.0	52390	0.3646	30.3482	13.6242	22.1001	27.5802
0.0072	156.0	52728	0.3656	26.4405	12.8498	19.8095	23.8804
0.0071	157.0	53066	0.3653	26.4405	12.8498	19.8095	23.8804
0.0071	158.0	53404	0.3644	26.4405	12.8498	19.8095	23.8804
0.0071	159.0	53742	0.3648	26.4611	12.8498	19.8370	23.8945
0.0071	160.0	54080	0.3616	28.2107	13.2942	20.5662	25.4111
0.0071	161.0	54418	0.3629	28.2536	13.2942	20.5684	25.4770
0.0071	162.0	54756	0.3647	28.2558	13.2942	20.5646	25.4960
0.007	163.0	55094	0.3636	28.2558	13.2942	20.5646	25.4960
0.007	164.0	55432	0.3650	26.4405	12.8498	19.8095	23.8804
0.007	165.0	55770	0.3663	28.2558	13.2942	20.5646	25.4960
0.007	166.0	56108	0.3659	28.2558	13.2942	20.5646	25.4960
0.007	167.0	56446	0.3676	28.2558	13.2942	20.5646	25.4960
0.0069	168.0	56784	0.3659	28.2558	13.2942	20.5646	25.4960
0.0069	169.0	57122	0.3674	28.2536	13.2942	20.5684	25.4770
0.0069	170.0	57460	0.3662	26.4405	12.8498	19.8095	23.8804
0.007	171.0	57798	0.3651	26.4405	12.8498	19.8095	23.8804
0.007	172.0	58136	0.3670	26.4405	12.8498	19.8095	23.8804
0.007	173.0	58474	0.3666	26.4405	12.8498	19.8095	23.8804
0.007	174.0	58812	0.3684	26.5255	12.8696	19.9233	24.0077
0.0069	175.0	59150	0.3682	28.2902	13.2884	20.5599	25.5133
0.0069	176.0	59488	0.3681	28.3079	13.2884	20.5813	25.5310
0.0069	177.0	59826	0.3687	28.2536	13.2942	20.5684	25.4770
0.0069	178.0	60164	0.3691	28.2558	13.2942	20.5646	25.4960
0.0069	179.0	60502	0.3656	26.4008	12.8554	19.8262	23.8411
0.0069	180.0	60840	0.3664	28.2536	13.2942	20.5684	25.4770
0.0069	181.0	61178	0.3663	28.2558	13.2942	20.5646	25.4960
0.0069	182.0	61516	0.3667	28.2558	13.2942	20.5646	25.4960
0.0069	183.0	61854	0.3658	28.2558	13.2942	20.5646	25.4960
0.0069	184.0	62192	0.3671	28.2558	13.2942	20.5646	25.4960
0.0068	185.0	62530	0.3686	28.2558	13.2942	20.5646	25.4960
0.0068	186.0	62868	0.3670	28.2652	13.2942	20.5234	25.4470
0.0068	187.0	63206	0.3667	28.2558	13.2942	20.5646	25.4960
0.0068	188.0	63544	0.3669	28.2558	13.2942	20.5646	25.4960
0.0068	189.0	63882	0.3676	28.2558	13.2942	20.5646	25.4960
0.0067	190.0	64220	0.3675	28.2558	13.2942	20.5646	25.4960
0.0068	191.0	64558	0.3680	28.2558	13.2942	20.5646	25.4960
0.0068	192.0	64896	0.3681	28.2558	13.2942	20.5646	25.4960
0.007	193.0	65234	0.3675	28.2558	13.2942	20.5646	25.4960
0.0068	194.0	65572	0.3675	28.2558	13.2942	20.5646	25.4960
0.0068	195.0	65910	0.3674	28.2558	13.2942	20.5646	25.4960
0.0068	196.0	66248	0.3679	28.2558	13.2942	20.5646	25.4960
0.0068	197.0	66586	0.3678	28.2558	13.2942	20.5646	25.4960
0.0068	198.0	66924	0.3677	28.2558	13.2942	20.5646	25.4960
0.0067	199.0	67262	0.3678	28.2558	13.2942	20.5646	25.4960
0.0068	200.0	67600	0.3678	28.2558	13.2942	20.5646	25.4960

Framework versions

Transformers 4.36.2
Pytorch 2.2.2+cu121
Datasets 2.16.0
Tokenizers 0.15.2

Library: transformers
Type: encoder-decoder
Created: Apr 18, 2024
Updated: Apr 19, 2024