gpt3_model

MJ199999/gpt3_model

gpt3_model is a text generation model from MJ199999. Use it when you need the model to write or continue text. It is set up for transformers.

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

Downloads · 30 days

1% of all-time downloads

All-time downloads

4.4K

Public

Repo size

33.3 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.h54.7 GB · 100%

At a glance

Task: Text Generation
Library: transformers
Model type: gpt2
Access: Public
Created: Sep 9, 2022
Updated: Sep 13, 2022
SHA: 0299e69f

Try a prompt

Spaces

Model card

From the Hugging Face model README

gpt3_model

This model is a fine-tuned version of MJ199999/gpt3_model on an unknown dataset. It achieves the following results on the evaluation set:

Train Loss: 0.4905
Train Lr: 0.0009999999
Epoch: 199

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:

optimizer: {'name': 'Adagrad', 'learning_rate': 0.0009999999, 'decay': 0.0, 'initial_accumulator_value': 0.1, 'epsilon': 1e-07}
training_precision: float32

Training results

Train Loss	Train Lr	Epoch
5.1583	0.01	0
3.9477	0.01	1
2.9332	0.01	2
2.1581	0.01	3
1.6918	0.01	4
1.3929	0.01	5
1.2062	0.01	6
1.0955	0.01	7
1.0068	0.01	8
0.9528	0.01	9
0.9051	0.01	10
0.8710	0.01	11
0.8564	0.01	12
0.8094	0.01	13
0.8143	0.01	14
0.7853	0.01	15
0.7625	0.01	16
0.7508	0.01	17
0.7449	0.01	18
0.7319	0.01	19
0.7144	0.01	20
0.7045	0.01	21
0.7029	0.01	22
0.6937	0.01	23
0.6898	0.01	24
0.6745	0.01	25
0.6767	0.01	26
0.6692	0.01	27
0.6604	0.01	28
0.6573	0.01	29
0.6524	0.01	30
0.6508	0.01	31
0.6443	0.01	32
0.6452	0.01	33
0.6371	0.01	34
0.6362	0.01	35
0.6304	0.01	36
0.6317	0.01	37
0.6270	0.01	38
0.6257	0.01	39
0.6208	0.01	40
0.6227	0.01	41
0.6154	0.01	42
0.6126	0.01	43
0.6149	0.01	44
0.6075	0.01	45
0.6084	0.01	46
0.6078	0.01	47
0.6057	0.01	48
0.6033	0.01	49
0.6040	0.01	50
0.5989	0.01	51
0.5967	0.01	52
0.5952	0.01	53
0.5911	0.01	54
0.5904	0.01	55
0.5888	0.01	56
0.5886	0.01	57
0.5883	0.01	58
0.5838	0.01	59
0.5856	0.01	60
0.5850	0.01	61
0.5801	0.01	62
0.5821	0.01	63
0.5781	0.01	64
0.5786	0.01	65
0.5835	0.01	66
0.5808	0.01	67
0.5754	0.01	68
0.5742	0.01	69
0.5733	0.01	70
0.5700	0.01	71
0.5738	0.01	72
0.5678	0.01	73
0.5695	0.01	74
0.5684	0.01	75
0.5696	0.01	76
0.5688	0.01	77
0.5648	0.01	78
0.5592	0.01	79
0.5622	0.01	80
0.5660	0.01	81
0.5636	0.01	82
0.5602	0.01	83
0.5613	0.01	84
0.5608	0.01	85
0.5589	0.01	86
0.5580	0.01	87
0.5566	0.01	88
0.5531	0.01	89
0.5571	0.01	90
0.5541	0.01	91
0.5576	0.01	92
0.5560	0.01	93
0.5517	0.01	94
0.5508	0.01	95
0.5554	0.01	96
0.5539	0.01	97
0.5493	0.01	98
0.5499	0.01	99
0.4999	0.0009999999	100
0.4981	0.0009999999	101
0.4983	0.0009999999	102
0.4984	0.0009999999	103
0.4974	0.0009999999	104
0.4957	0.0009999999	105
0.4966	0.0009999999	106
0.4975	0.0009999999	107
0.4962	0.0009999999	108
0.4932	0.0009999999	109
0.4983	0.0009999999	110
0.4937	0.0009999999	111
0.4926	0.0009999999	112
0.4944	0.0009999999	113
0.4947	0.0009999999	114
0.4953	0.0009999999	115
0.4934	0.0009999999	116
0.4929	0.0009999999	117
0.4925	0.0009999999	118
0.4948	0.0009999999	119
0.4947	0.0009999999	120
0.4936	0.0009999999	121
0.4909	0.0009999999	122
0.4960	0.0009999999	123
0.4952	0.0009999999	124
0.4923	0.0009999999	125
0.4930	0.0009999999	126
0.4942	0.0009999999	127
0.4927	0.0009999999	128
0.4917	0.0009999999	129
0.4926	0.0009999999	130
0.4927	0.0009999999	131
0.4932	0.0009999999	132
0.4925	0.0009999999	133
0.4928	0.0009999999	134
0.4936	0.0009999999	135
0.4908	0.0009999999	136
0.4936	0.0009999999	137
0.4916	0.0009999999	138
0.4906	0.0009999999	139
0.4904	0.0009999999	140
0.4920	0.0009999999	141
0.4924	0.0009999999	142
0.4902	0.0009999999	143
0.4903	0.0009999999	144
0.4903	0.0009999999	145
0.4924	0.0009999999	146
0.4889	0.0009999999	147
0.4896	0.0009999999	148
0.4919	0.0009999999	149
0.4896	0.0009999999	150
0.4906	0.0009999999	151
0.4923	0.0009999999	152
0.4899	0.0009999999	153
0.4925	0.0009999999	154
0.4901	0.0009999999	155
0.4910	0.0009999999	156
0.4904	0.0009999999	157
0.4912	0.0009999999	158
0.4937	0.0009999999	159
0.4894	0.0009999999	160
0.4913	0.0009999999	161
0.4899	0.0009999999	162
0.4894	0.0009999999	163
0.4904	0.0009999999	164
0.4900	0.0009999999	165
0.4890	0.0009999999	166
0.4919	0.0009999999	167
0.4909	0.0009999999	168
0.4891	0.0009999999	169
0.4900	0.0009999999	170
0.4910	0.0009999999	171
0.4901	0.0009999999	172
0.4914	0.0009999999	173
0.4913	0.0009999999	174
0.4897	0.0009999999	175
0.4892	0.0009999999	176
0.4929	0.0009999999	177
0.4881	0.0009999999	178
0.4920	0.0009999999	179
0.4888	0.0009999999	180
0.4901	0.0009999999	181
0.4875	0.0009999999	182
0.4930	0.0009999999	183
0.4867	0.0009999999	184
0.4890	0.0009999999	185
0.4898	0.0009999999	186
0.4880	0.0009999999	187
0.4899	0.0009999999	188
0.4881	0.0009999999	189
0.4897	0.0009999999	190
0.4876	0.0009999999	191
0.4873	0.0009999999	192
0.4901	0.0009999999	193
0.4898	0.0009999999	194
0.4898	0.0009999999	195
0.4861	0.0009999999	196
0.4878	0.0009999999	197
0.4880	0.0009999999	198
0.4905	0.0009999999	199

Framework versions

Transformers 4.21.3
TensorFlow 2.8.2
Tokenizers 0.12.1

Task: Text Generation
Library: transformers
Type: gpt2
Created: Sep 9, 2022
Updated: Sep 13, 2022