bert-base-greek-uncased-v1-finetuned-imdb

This model is a fine-tuned version of nlpaueb/bert-base-greek-uncased-v1 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 3.3617

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss
1.0877	1.0	45	2.9871
1.2665	2.0	90	2.9228
1.9122	3.0	135	3.1228
2.2564	4.0	180	1.6066
1.9132	5.0	225	2.6351
1.9952	6.0	270	2.2649
1.7895	7.0	315	2.3376
2.0415	8.0	360	1.9894
1.8113	9.0	405	2.2998
1.6944	10.0	450	2.1420
1.7862	11.0	495	2.7167
1.5657	12.0	540	2.5103
1.4576	13.0	585	2.0238
1.3369	14.0	630	2.5880
1.3598	15.0	675	1.8161
1.3407	16.0	720	2.4031
1.3805	17.0	765	2.2539
1.176	18.0	810	3.2901
1.1152	19.0	855	2.3024
1.0629	20.0	900	2.0823
1.1972	21.0	945	2.9957
1.1317	22.0	990	2.5360
1.0396	23.0	1035	1.6268
0.8686	24.0	1080	3.2657
1.0526	25.0	1125	3.0398
0.9023	26.0	1170	2.8197
0.9539	27.0	1215	3.1922
0.8699	28.0	1260	1.6943
0.8669	29.0	1305	2.7801
0.7893	30.0	1350	2.1385
0.7462	31.0	1395	2.2881
0.7627	32.0	1440	3.0789
0.7536	33.0	1485	2.9320
0.8317	34.0	1530	3.4081
0.6749	35.0	1575	2.7531
0.789	36.0	1620	2.9154
0.6609	37.0	1665	2.1821
0.6795	38.0	1710	2.5330
0.6408	39.0	1755	3.4374
0.6827	40.0	1800	2.3127
0.6188	41.0	1845	2.0818
0.6085	42.0	1890	2.2737
0.6978	43.0	1935	2.9629
0.6164	44.0	1980	2.5250
0.6273	45.0	2025	2.3866
0.7064	46.0	2070	2.0937
0.6561	47.0	2115	2.4984
0.7341	48.0	2160	3.1911
0.6271	49.0	2205	2.2692
0.6757	50.0	2250	2.2642

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1+cu118
• Datasets 2.13.1
• Tokenizers 0.13.3