Modelpublic

thrunlab/t5-base_cola_dense_sp0_ar0

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face

0likes8downloads

Model Card

t5-basecoladensesp0ar0

This model is a fine-tuned version of t5-base on the glue dataset. It achieves the following results on the evaluation set:

—Loss: 4.9143
—Accuracy: 0.0

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: 5e-05
—trainbatchsize: 32
—evalbatchsize: 64
—seed: 1
—optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
—lrschedulertype: linear
—lrschedulerwarmup_steps: 20
—num_epochs: 6

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.5646	0.09	25	0.6556	0.6913
0.6392	0.19	50	0.5933	0.6913
0.5668	0.28	75	0.5673	0.6913
0.4777	0.37	100	0.5130	0.7872
0.4982	0.47	125	0.5462	0.7987
0.515	0.56	150	0.4918	0.8025
0.5279	0.65	175	0.4923	0.7900
0.4246	0.75	200	0.5310	0.7958
0.4437	0.84	225	0.4455	0.8159
0.4251	0.93	250	0.4847	0.8111
0.2875	1.03	275	0.5152	0.8102
0.3736	1.12	300	0.5038	0.8130
0.3489	1.21	325	0.4612	0.8159
0.3729	1.31	350	0.5098	0.8102
0.3574	1.4	375	0.5389	0.8121
0.3897	1.49	400	0.4788	0.8130
0.3785	1.59	425	0.4827	0.8150
0.4429	1.68	450	0.5501	0.8063
0.3893	1.77	475	0.4393	0.8245
0.3531	1.87	500	0.4769	0.8255
0.3853	1.96	525	0.4711	0.8284
0.3173	2.05	550	0.5262	0.8226
0.3102	2.15	575	0.5084	0.8284
0.3236	2.24	600	0.5517	0.8293
0.2618	2.33	625	0.5825	0.8322

Framework versions

—Transformers 4.33.2
—Pytorch 2.0.1+cu117
—Datasets 2.14.5
—Tokenizers 0.11.6