Waynehills-NLP-doogie

mimi/Waynehills-NLP-doogie

Waynehills-NLP-doogie is a machine learning model from mimi. 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

1% of all-time downloads

All-time downloads

1.1K

Public

Repo size

84.2 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin990 MB · 100%

At a glance

Library: transformers
Model type: t5
Access: Public
Created: Mar 2, 2022
Updated: Jan 6, 2022
SHA: 4e1ec489

Model card

From the Hugging Face model README

Waynehills-NLP-doogie

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

Loss: 2.9188

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
lr_scheduler_warmup_steps: 10
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
28.2167	0.06	1000	9.7030
10.4479	0.12	2000	7.5450
8.0306	0.19	3000	6.1969
6.503	0.25	4000	5.3015
5.5406	0.31	5000	4.6363
4.7299	0.38	6000	4.0431
3.9263	0.44	7000	3.6313
3.4111	0.5	8000	3.4830
3.0517	0.56	9000	3.3294
2.7524	0.62	10000	3.2077
2.5402	0.69	11000	3.1094
2.3228	0.75	12000	3.1099
2.1513	0.81	13000	3.0284
2.0418	0.88	14000	3.0155
1.8875	0.94	15000	3.0241
1.756	1.0	16000	3.0165
1.6489	1.06	17000	2.9849
1.5788	1.12	18000	2.9496
1.5368	1.19	19000	2.9500
1.4467	1.25	20000	3.0133
1.381	1.31	21000	2.9631
1.3451	1.38	22000	3.0159
1.2917	1.44	23000	2.9906
1.2605	1.5	24000	3.0006
1.2003	1.56	25000	2.9797
1.1987	1.62	26000	2.9253
1.1703	1.69	27000	3.0044
1.1474	1.75	28000	2.9216
1.0816	1.81	29000	2.9645
1.0709	1.88	30000	3.0439
1.0476	1.94	31000	3.0844
1.0645	2.0	32000	2.9434
1.0204	2.06	33000	2.9386
0.9901	2.12	34000	3.0452
0.9911	2.19	35000	2.9798
0.9706	2.25	36000	2.9919
0.9461	2.31	37000	3.0279
0.9577	2.38	38000	2.9615
0.9466	2.44	39000	2.9988
0.9486	2.5	40000	2.9133
0.9201	2.56	41000	3.0004
0.896	2.62	42000	2.9626
0.8893	2.69	43000	2.9667
0.9028	2.75	44000	2.9543
0.897	2.81	45000	2.8760
0.8664	2.88	46000	2.9894
0.8719	2.94	47000	2.8456
0.8491	3.0	48000	2.9713
0.8402	3.06	49000	2.9738
0.8484	3.12	50000	2.9361
0.8304	3.19	51000	2.8945
0.8208	3.25	52000	2.9625
0.8074	3.31	53000	3.0054
0.8226	3.38	54000	2.9405
0.8185	3.44	55000	2.9047
0.8352	3.5	56000	2.9016
0.8289	3.56	57000	2.9490
0.7918	3.62	58000	2.9621
0.8212	3.69	59000	2.9341
0.7955	3.75	60000	2.9167
0.7724	3.81	61000	2.9409
0.8169	3.88	62000	2.8925
0.7862	3.94	63000	2.9314
0.803	4.0	64000	2.9271
0.7595	4.06	65000	2.9263
0.7931	4.12	66000	2.9400
0.7759	4.19	67000	2.9501
0.7859	4.25	68000	2.9133
0.805	4.31	69000	2.8785
0.7649	4.38	70000	2.9060
0.7692	4.44	71000	2.8868
0.7692	4.5	72000	2.9045
0.7798	4.56	73000	2.8951
0.7812	4.62	74000	2.9068
0.7533	4.69	75000	2.9129
0.7527	4.75	76000	2.9157
0.7652	4.81	77000	2.9053
0.7633	4.88	78000	2.9190
0.7437	4.94	79000	2.9251
0.7653	5.0	80000	2.9188

Framework versions

Transformers 4.12.5
Pytorch 1.10.0+cu111
Datasets 1.5.0
Tokenizers 0.10.3

Library: transformers
Type: t5
Created: Mar 2, 2022
Updated: Jan 6, 2022