gpt_train_12_128

gokulsrinivasagan/gpt_train_12_128

gpt_train_12_128 is a text generation model from gokulsrinivasagan. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.

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

Downloads · 30 days

186

42% of all-time downloads

All-time downloads

443

Public

Parameters

15.4M

31 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors30.8 MB · 89%

At a glance

Task: Text Generation
Library: transformers
License: mit
Model type: gpt2
Access: Public
Created: Jul 1, 2024
Updated: Jul 2, 2024
SHA: 3c1649d1

Try a prompt

Base models

openai-community/gpt2

Datasets

gokuls/wiki_book_corpus_raw_dataset_tiny

Model card

From the Hugging Face model README

gpt_train_12_128

This model is a fine-tuned version of openai-community/gpt2 on the gokuls/wiki_book_corpus_raw_dataset_tiny dataset. It achieves the following results on the evaluation set:

Loss: 10.0781
Accuracy: 0.0781

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: 1e-05
train_batch_size: 48
eval_batch_size: 48
seed: 10
distributed_type: multi-GPU
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	Accuracy
10.8438	0.0001	1	10.8438	0.0103
10.8359	0.0001	2	10.8438	0.0103
10.8438	0.0002	3	10.8438	0.0103
10.8359	0.0003	4	10.8438	0.0103
10.8438	0.0004	5	10.8438	0.0103
10.8438	0.0004	6	10.8438	0.0103
10.8359	0.0005	7	10.8438	0.0103
10.8359	0.0006	8	10.8438	0.0103
10.8438	0.0007	9	10.8438	0.0103
10.8359	0.0007	10	10.8438	0.0103
10.8359	0.0008	11	10.8438	0.0103
10.8438	0.0009	12	10.8438	0.0103
10.8438	0.0009	13	10.8438	0.0103
10.8359	0.0010	14	10.8438	0.0103
10.8359	0.0011	15	10.8438	0.0103
10.8438	0.0012	16	10.8438	0.0103
10.8359	0.0012	17	10.8438	0.0103
10.8438	0.0013	18	10.8281	0.0113
10.8203	0.0014	19	10.8125	0.0116
10.8203	0.0015	20	10.8047	0.0117
10.8047	0.0015	21	10.7891	0.0118
10.7969	0.0016	22	10.7734	0.0118
10.7812	0.0017	23	10.7656	0.0118
10.7656	0.0017	24	10.75	0.0119
10.7578	0.0018	25	10.7344	0.0121
10.75	0.0019	26	10.7266	0.0124
10.7344	0.0020	27	10.7188	0.0131
10.7266	0.0020	28	10.7031	0.0144
10.7109	0.0021	29	10.6953	0.0165
10.7031	0.0022	30	10.6875	0.0196
10.7031	0.0023	31	10.6797	0.0236
10.6875	0.0023	32	10.6719	0.0282
10.6797	0.0024	33	10.6641	0.0330
10.6719	0.0025	34	10.6641	0.0375
10.6719	0.0025	35	10.6562	0.0409
10.6719	0.0026	36	10.6484	0.0437
10.6484	0.0027	37	10.6484	0.0461
10.6562	0.0028	38	10.6406	0.0481
10.6484	0.0028	39	10.6406	0.0498
10.6484	0.0029	40	10.6328	0.0511
10.6406	0.0030	41	10.6328	0.0521
10.6406	0.0031	42	10.625	0.0529
10.6406	0.0031	43	10.625	0.0535
10.625	0.0032	44	10.6172	0.0539
10.625	0.0033	45	10.6172	0.0542
10.625	0.0033	46	10.6172	0.0543
10.6172	0.0034	47	10.6094	0.0544
10.625	0.0035	48	10.6094	0.0545
10.6172	0.0036	49	10.6016	0.0545
10.6016	0.0036	50	10.6016	0.0545
10.6016	0.0037	51	10.6016	0.0545
10.6016	0.0038	52	10.5938	0.0546
10.6016	0.0039	53	10.5938	0.0545
10.5938	0.0039	54	10.5938	0.0545
10.6016	0.0040	55	10.5859	0.0545
10.5859	0.0041	56	10.5859	0.0545
10.6016	0.0041	57	10.5859	0.0545
10.5859	0.0042	58	10.5859	0.0546
10.5859	0.0043	59	10.5781	0.0547
10.5781	0.0044	60	10.5781	0.0548
10.5781	0.0044	61	10.5781	0.0550
10.5781	0.0045	62	10.5703	0.0553
10.5781	0.0046	63	10.5703	0.0557
10.5703	0.0046	64	10.5703	0.0561
10.5781	0.0047	65	10.5625	0.0566
10.5625	0.0048	66	10.5625	0.0570
10.5781	0.0049	67	10.5625	0.0573
10.5703	0.0049	68	10.5547	0.0575
10.5625	0.0050	69	10.5547	0.0577
10.5625	0.0051	70	10.5547	0.0578
10.5625	0.0052	71	10.5547	0.0579
10.5547	0.0052	72	10.5469	0.0580
10.5469	0.0053	73	10.5469	0.0580
10.5469	0.0054	74	10.5469	0.0580
10.5547	0.0054	75	10.5391	0.0580
10.5547	0.0055	76	10.5391	0.0580
10.5469	0.0056	77	10.5391	0.0582
10.5469	0.0057	78	10.5391	0.0582
10.5312	0.0057	79	10.5312	0.0584
10.5312	0.0058	80	10.5312	0.0586
10.5312	0.0059	81	10.5312	0.0590
10.5312	0.0060	82	10.5312	0.0593
10.5312	0.0060	83	10.5234	0.0597
10.5234	0.0061	84	10.5234	0.0600
10.5312	0.0062	85	10.5234	0.0602
10.5312	0.0062	86	10.5234	0.0603
10.5234	0.0063	87	10.5156	0.0604
10.5156	0.0064	88	10.5156	0.0605
10.5234	0.0065	89	10.5156	0.0606
10.5156	0.0065	90	10.5156	0.0606
10.5156	0.0066	91	10.5078	0.0606
10.5156	0.0067	92	10.5078	0.0605
10.5156	0.0068	93	10.5078	0.0603
10.5156	0.0068	94	10.5078	0.0602
10.5234	0.0069	95	10.5	0.0601
10.5156	0.0070	96	10.5	0.0602
10.5078	0.0070	97	10.5	0.0603
10.5	0.0071	98	10.5	0.0603
10.5078	0.0072	99	10.5	0.0604
10.5078	0.0073	100	10.4922	0.0606
10.5	0.0073	101	10.4922	0.0607
10.4922	0.0074	102	10.4922	0.0609
10.4922	0.0075	103	10.4922	0.0612
10.4844	0.0076	104	10.4844	0.0614
10.4922	0.0076	105	10.4844	0.0617
10.4922	0.0077	106	10.4844	0.0619
10.4844	0.0078	107	10.4844	0.0622
10.4922	0.0078	108	10.4766	0.0625
10.4844	0.0079	109	10.4766	0.0628
10.4766	0.0080	110	10.4766	0.0630
10.4844	0.0081	111	10.4766	0.0632
10.4766	0.0081	112	10.4766	0.0634
10.4844	0.0082	113	10.4688	0.0636
10.4766	0.0083	114	10.4688	0.0638
10.4766	0.0084	115	10.4688	0.0640
10.4844	0.0084	116	10.4688	0.0643
10.4531	0.0085	117	10.4609	0.0644
10.4609	0.0086	118	10.4609	0.0647
10.4609	0.0086	119	10.4609	0.0648
10.4688	0.0087	120	10.4609	0.0649
10.4609	0.0088	121	10.4609	0.0651
10.4609	0.0089	122	10.4531	0.0653
10.4531	0.0089	123	10.4531	0.0656
10.4531	0.0090	124	10.4531	0.0659
10.4531	0.0091	125	10.4531	0.0660
10.4531	0.0092	126	10.4453	0.0662
10.4531	0.0092	127	10.4453	0.0664
10.4453	0.0093	128	10.4453	0.0667
10.4531	0.0094	129	10.4453	0.0670
10.4375	0.0094	130	10.4453	0.0673
10.4453	0.0095	131	10.4375	0.0676
10.4375	0.0096	132	10.4375	0.0678
10.4375	0.0097	133	10.4375	0.0679
10.4297	0.0097	134	10.4375	0.0679
10.4453	0.0098	135	10.4297	0.0678
10.4375	0.0099	136	10.4297	0.0677
10.4375	0.0100	137	10.4297	0.0677
10.4219	0.0100	138	10.4297	0.0677
10.4375	0.0101	139	10.4219	0.0678
10.4297	0.0102	140	10.4219	0.0680
10.4297	0.0102	141	10.4219	0.0682
10.4219	0.0103	142	10.4219	0.0684
10.4219	0.0104	143	10.4219	0.0687
10.4219	0.0105	144	10.4141	0.0689
10.4219	0.0105	145	10.4141	0.0692
10.4141	0.0106	146	10.4141	0.0693
10.4062	0.0107	147	10.4141	0.0695
10.4141	0.0108	148	10.4062	0.0696
10.4141	0.0108	149	10.4062	0.0697
10.4219	0.0109	150	10.4062	0.0697
10.4062	0.0110	151	10.4062	0.0698
10.4141	0.0110	152	10.4062	0.0700
10.4141	0.0111	153	10.3984	0.0701
10.4219	0.0112	154	10.3984	0.0702
10.4141	0.0113	155	10.3984	0.0704
10.4062	0.0113	156	10.3984	0.0705
10.4062	0.0114	157	10.3906	0.0707
10.3906	0.0115	158	10.3906	0.0708
10.3906	0.0116	159	10.3906	0.0710
10.3984	0.0116	160	10.3906	0.0711
10.3984	0.0117	161	10.3906	0.0711
10.3906	0.0118	162	10.3828	0.0712
10.3906	0.0118	163	10.3828	0.0712
10.3906	0.0119	164	10.3828	0.0714
10.3828	0.0120	165	10.3828	0.0715
10.375	0.0121	166	10.375	0.0716
10.3828	0.0121	167	10.375	0.0717
10.3828	0.0122	168	10.375	0.0718
10.3828	0.0123	169	10.375	0.0719
10.3828	0.0124	170	10.375	0.0721
10.3672	0.0124	171	10.3672	0.0721
10.375	0.0125	172	10.3672	0.0721
10.3594	0.0126	173	10.3672	0.0721
10.375	0.0126	174	10.3672	0.0720
10.3594	0.0127	175	10.3594	0.0721
10.3672	0.0128	176	10.3594	0.0722
10.375	0.0129	177	10.3594	0.0723
10.3672	0.0129	178	10.3594	0.0726
10.3672	0.0130	179	10.3594	0.0727
10.3594	0.0131	180	10.3516	0.0728
10.3672	0.0132	181	10.3516	0.0729
10.3594	0.0132	182	10.3516	0.0730
10.3516	0.0133	183	10.3516	0.0731
10.3594	0.0134	184	10.3516	0.0732
10.3516	0.0134	185	10.3438	0.0733
10.3516	0.0135	186	10.3438	0.0733
10.3438	0.0136	187	10.3438	0.0734
10.3516	0.0137	188	10.3438	0.0734
10.3516	0.0137	189	10.3359	0.0735
10.3438	0.0138	190	10.3359	0.0735
10.3516	0.0139	191	10.3359	0.0735
10.3359	0.0139	192	10.3359	0.0737
10.3359	0.0140	193	10.3359	0.0737
10.3359	0.0141	194	10.3281	0.0736
10.3359	0.0142	195	10.3281	0.0736
10.3359	0.0142	196	10.3281	0.0736
10.3281	0.0143	197	10.3281	0.0737
10.3359	0.0144	198	10.3281	0.0738
10.3203	0.0145	199	10.3203	0.0740
10.3359	0.0145	200	10.3203	0.0741
10.3359	0.0146	201	10.3203	0.0742
10.3281	0.0147	202	10.3203	0.0743
10.3203	0.0147	203	10.3125	0.0743
10.3203	0.0148	204	10.3125	0.0743
10.3281	0.0149	205	10.3125	0.0743
10.3125	0.0150	206	10.3125	0.0741
10.3125	0.0150	207	10.3125	0.0740
10.3047	0.0151	208	10.3047	0.0740
10.3125	0.0152	209	10.3047	0.0741
10.3125	0.0153	210	10.3047	0.0742
10.3203	0.0153	211	10.3047	0.0743
10.3047	0.0154	212	10.3047	0.0744
10.3203	0.0155	213	10.2969	0.0745
10.3125	0.0155	214	10.2969	0.0747
10.3047	0.0156	215	10.2969	0.0749
10.2969	0.0157	216	10.2969	0.0750
10.3047	0.0158	217	10.2969	0.0750
10.2969	0.0158	218	10.2891	0.0749
10.2891	0.0159	219	10.2891	0.0747
10.2969	0.0160	220	10.2891	0.0744
10.2969	0.0161	221	10.2891	0.0742
10.2891	0.0161	222	10.2891	0.0741
10.2891	0.0162	223	10.2812	0.0742
10.2891	0.0163	224	10.2812	0.0743
10.2891	0.0163	225	10.2812	0.0746
10.2969	0.0164	226	10.2812	0.0748
10.2812	0.0165	227	10.2734	0.0749
10.2891	0.0166	228	10.2734	0.0750
10.2734	0.0166	229	10.2734	0.0751
10.2969	0.0167	230	10.2734	0.0750
10.2656	0.0168	231	10.2734	0.0749
10.2734	0.0169	232	10.2656	0.0747
10.2734	0.0169	233	10.2656	0.0747
10.2734	0.0170	234	10.2656	0.0746
10.2656	0.0171	235	10.2656	0.0747
10.2656	0.0171	236	10.2656	0.0748
10.2734	0.0172	237	10.2578	0.0749
10.2656	0.0173	238	10.2578	0.0752
10.2734	0.0174	239	10.2578	0.0755
10.2578	0.0174	240	10.2578	0.0756
10.2734	0.0175	241	10.2578	0.0756
10.2656	0.0176	242	10.25	0.0756
10.2578	0.0177	243	10.25	0.0756
10.2578	0.0177	244	10.25	0.0756
10.2578	0.0178	245	10.25	0.0756
10.2578	0.0179	246	10.25	0.0756
10.2578	0.0179	247	10.2422	0.0757
10.2578	0.0180	248	10.2422	0.0758
10.2422	0.0181	249	10.2422	0.0759
10.2422	0.0182	250	10.2422	0.0759
10.2422	0.0182	251	10.2422	0.0759
10.2422	0.0183	252	10.2344	0.0759
10.2422	0.0184	253	10.2344	0.0759
10.2422	0.0185	254	10.2344	0.0759
10.2422	0.0185	255	10.2344	0.0761
10.2422	0.0186	256	10.2344	0.0761
10.2422	0.0187	257	10.2266	0.0760
10.2422	0.0187	258	10.2266	0.0760
10.2344	0.0188	259	10.2266	0.0759
10.2344	0.0189	260	10.2266	0.0759
10.2266	0.0190	261	10.2266	0.0760
10.2188	0.0190	262	10.2188	0.0760
10.2266	0.0191	263	10.2188	0.0762
10.2266	0.0192	264	10.2188	0.0762
10.2188	0.0193	265	10.2188	0.0762
10.2266	0.0193	266	10.2188	0.0762
10.2188	0.0194	267	10.2109	0.0762
10.2109	0.0195	268	10.2109	0.0763
10.2109	0.0195	269	10.2109	0.0762
10.2109	0.0196	270	10.2109	0.0761
10.2188	0.0197	271	10.2109	0.0761
10.2109	0.0198	272	10.2031	0.0760
10.2188	0.0198	273	10.2031	0.0761
10.2266	0.0199	274	10.2031	0.0762
10.2188	0.0200	275	10.2031	0.0762
10.2109	0.0201	276	10.1953	0.0761
10.2109	0.0201	277	10.1953	0.0762
10.1953	0.0202	278	10.1953	0.0762
10.2031	0.0203	279	10.1953	0.0763
10.2188	0.0203	280	10.1953	0.0765
10.1953	0.0204	281	10.1875	0.0766
10.1953	0.0205	282	10.1875	0.0767
10.2031	0.0206	283	10.1875	0.0767
10.1797	0.0206	284	10.1875	0.0766
10.1953	0.0207	285	10.1875	0.0765
10.1953	0.0208	286	10.1797	0.0764
10.1875	0.0209	287	10.1797	0.0764
10.1953	0.0209	288	10.1797	0.0765
10.1875	0.0210	289	10.1797	0.0765
10.1875	0.0211	290	10.1797	0.0768
10.1797	0.0211	291	10.1719	0.0770
10.1719	0.0212	292	10.1719	0.0771
10.1719	0.0213	293	10.1719	0.0772
10.1797	0.0214	294	10.1719	0.0773
10.1797	0.0214	295	10.1719	0.0773
10.1641	0.0215	296	10.1641	0.0773
10.1719	0.0216	297	10.1641	0.0773
10.1719	0.0217	298	10.1641	0.0773
10.1719	0.0217	299	10.1641	0.0773
10.1719	0.0218	300	10.1641	0.0773
10.1641	0.0219	301	10.1641	0.0773
10.1562	0.0219	302	10.1562	0.0772
10.1719	0.0220	303	10.1562	0.0771
10.1562	0.0221	304	10.1562	0.0772
10.1641	0.0222	305	10.1562	0.0773
10.1562	0.0222	306	10.1484	0.0773
10.1641	0.0223	307	10.1484	0.0773
10.1719	0.0224	308	10.1484	0.0775
10.1562	0.0224	309	10.1484	0.0775
10.1719	0.0225	310	10.1484	0.0775
10.1562	0.0226	311	10.1406	0.0774
10.1562	0.0227	312	10.1406	0.0774
10.1562	0.0227	313	10.1406	0.0773
10.1406	0.0228	314	10.1406	0.0774
10.1406	0.0229	315	10.1406	0.0774
10.1406	0.0230	316	10.1406	0.0774
10.1328	0.0230	317	10.1328	0.0775
10.1484	0.0231	318	10.1328	0.0775
10.1328	0.0232	319	10.1328	0.0775
10.1328	0.0232	320	10.1328	0.0775
10.125	0.0233	321	10.1328	0.0775
10.1406	0.0234	322	10.125	0.0776
10.1328	0.0235	323	10.125	0.0777
10.125	0.0235	324	10.125	0.0778
10.125	0.0236	325	10.125	0.0777
10.125	0.0237	326	10.125	0.0777
10.1328	0.0238	327	10.1172	0.0777
10.1172	0.0238	328	10.1172	0.0777
10.1172	0.0239	329	10.1172	0.0777
10.125	0.0240	330	10.1172	0.0778
10.1094	0.0240	331	10.1172	0.0778
10.1094	0.0241	332	10.1094	0.0777
10.1094	0.0242	333	10.1094	0.0776
10.1172	0.0243	334	10.1094	0.0775
10.125	0.0243	335	10.1094	0.0774
10.1172	0.0244	336	10.1094	0.0772
10.1016	0.0245	337	10.1016	0.0771
10.1094	0.0246	338	10.1016	0.0773
10.1172	0.0246	339	10.1016	0.0775
10.1094	0.0247	340	10.1016	0.0777
10.1172	0.0248	341	10.1016	0.0778
10.0938	0.0248	342	10.0938	0.0779
10.1016	0.0249	343	10.0938	0.0780
10.0938	0.0250	344	10.0938	0.0780
10.0938	0.0251	345	10.0938	0.0780
10.1016	0.0251	346	10.0938	0.0781
10.1094	0.0252	347	10.0859	0.0780
10.0938	0.0253	348	10.0859	0.0780
10.0938	0.0254	349	10.0859	0.0780
10.0859	0.0254	350	10.0859	0.0779
10.0859	0.0255	351	10.0859	0.0780
10.0938	0.0256	352	10.0781	0.0781

Framework versions

Transformers 4.41.2
Pytorch 2.1.0a0+32f93b1
Datasets 2.20.0
Tokenizers 0.19.1

Task: Text Generation
Library: transformers
Type: gpt2
License: mit
Created: Jul 1, 2024
Updated: Jul 2, 2024