Modelpublic

dahe827/xlnet-base-cased-airlines-news-multi-label-7-actions

sourceHugging Facemitupdated 2y agoView on Hugging Face

0likes14downloads

Model Card

xlnet-base-cased-airlines-news-multi-label-7-actions

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

—Loss: 0.2151
—F1: 0.9188
—Jaccard: 0.6316

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: 0.0001
—trainbatchsize: 32
—evalbatchsize: 32
—seed: 42
—optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
—lrschedulertype: linear
—lrschedulerwarmup_steps: 150
—num_epochs: 45

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Jaccard
No log	1.0	57	0.4002	0.8330	0.4071
No log	2.0	114	0.3221	0.8443	0.4115
No log	3.0	171	0.2836	0.8703	0.4565
No log	4.0	228	0.2654	0.8731	0.4786
No log	5.0	285	0.2478	0.8825	0.5288
No log	6.0	342	0.2410	0.8925	0.5395
No log	7.0	399	0.2337	0.8990	0.5830
No log	8.0	456	0.2313	0.8997	0.5586
0.3113	9.0	513	0.2287	0.8974	0.5579
0.3113	10.0	570	0.2242	0.9037	0.6080
0.3113	11.0	627	0.2215	0.9036	0.5911
0.3113	12.0	684	0.2209	0.9072	0.5977
0.3113	13.0	741	0.2192	0.9093	0.6169
0.3113	14.0	798	0.2193	0.9076	0.6125
0.3113	15.0	855	0.2206	0.9067	0.6257
0.3113	16.0	912	0.2166	0.9121	0.6265
0.3113	17.0	969	0.2151	0.9188	0.6316
0.2282	18.0	1026	0.2143	0.9107	0.6279
0.2282	19.0	1083	0.2132	0.9105	0.6346
0.2282	20.0	1140	0.2132	0.9106	0.6279
0.2282	21.0	1197	0.2174	0.9122	0.6243
0.2282	22.0	1254	0.2161	0.9139	0.6221
0.2282	23.0	1311	0.2127	0.9119	0.6287
0.2282	24.0	1368	0.2129	0.9119	0.6353
0.2282	25.0	1425	0.2112	0.9147	0.6324
0.2282	26.0	1482	0.2122	0.9129	0.6386
0.2142	27.0	1539	0.2126	0.9146	0.6272
0.2142	28.0	1596	0.2114	0.9144	0.6331
0.2142	29.0	1653	0.2109	0.9159	0.6434
0.2142	30.0	1710	0.2102	0.9165	0.6479
0.2142	31.0	1767	0.2120	0.9114	0.6397
0.2142	32.0	1824	0.2110	0.9125	0.6405
0.2142	33.0	1881	0.2111	0.9093	0.625
0.2142	34.0	1938	0.2110	0.9109	0.6243
0.2142	35.0	1995	0.2111	0.9110	0.6324
0.2084	36.0	2052	0.2127	0.9141	0.6394
0.2084	37.0	2109	0.2112	0.9098	0.6265
0.2084	38.0	2166	0.2109	0.9112	0.6309
0.2084	39.0	2223	0.2109	0.9137	0.6405
0.2084	40.0	2280	0.2111	0.9122	0.6346
0.2084	41.0	2337	0.2111	0.9111	0.6368
0.2084	42.0	2394	0.2113	0.9099	0.6279
0.2084	43.0	2451	0.2112	0.9105	0.6324
0.2054	44.0	2508	0.2111	0.9105	0.6287
0.2054	45.0	2565	0.2110	0.9089	0.6221

Framework versions

—Transformers 4.41.1
—Pytorch 2.3.0+cu121
—Datasets 2.19.1
—Tokenizers 0.19.1