scenario-TCR-XLMV-XCOPA-6_data-xcopa_all

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

• Loss: 0.6931
• Accuracy: 0.5083
• F1: 0.4627

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
• train_batch_size: 32
• eval_batch_size: 32
• seed: 341241
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 500

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	0.38	5	0.6931	0.5133	0.4904
No log	0.77	10	0.6931	0.5542	0.5344
No log	1.15	15	0.6931	0.5358	0.5093
No log	1.54	20	0.6931	0.5508	0.5373
No log	1.92	25	0.6931	0.5033	0.4716
No log	2.31	30	0.6931	0.53	0.5261
No log	2.69	35	0.6931	0.5383	0.5257
No log	3.08	40	0.6931	0.5308	0.5159
No log	3.46	45	0.6931	0.4933	0.4856
No log	3.85	50	0.6931	0.5308	0.5233
No log	4.23	55	0.6931	0.5517	0.5410
No log	4.62	60	0.6931	0.5625	0.5570
No log	5.0	65	0.6931	0.5433	0.5308
No log	5.38	70	0.6931	0.53	0.5236
No log	5.77	75	0.6931	0.5267	0.5103
No log	6.15	80	0.6931	0.5308	0.4987
No log	6.54	85	0.6931	0.5017	0.4889
No log	6.92	90	0.6931	0.5267	0.5009
No log	7.31	95	0.6931	0.5367	0.5062
No log	7.69	100	0.6931	0.5133	0.4859
No log	8.08	105	0.6931	0.4817	0.4610
No log	8.46	110	0.6932	0.5	0.4854
No log	8.85	115	0.6931	0.4992	0.4788
No log	9.23	120	0.6931	0.5	0.4881
No log	9.62	125	0.6931	0.5042	0.4884
No log	10.0	130	0.6931	0.5025	0.4936
No log	10.38	135	0.6931	0.4908	0.4764
No log	10.77	140	0.6931	0.4942	0.4816
No log	11.15	145	0.6932	0.5033	0.4532
No log	11.54	150	0.6931	0.525	0.4732
No log	11.92	155	0.6931	0.53	0.4946
No log	12.31	160	0.6931	0.5192	0.4489
No log	12.69	165	0.6931	0.5225	0.4729
No log	13.08	170	0.6931	0.5117	0.4624
No log	13.46	175	0.6931	0.5383	0.4851
No log	13.85	180	0.6931	0.5208	0.4691
No log	14.23	185	0.6931	0.5258	0.4717
No log	14.62	190	0.6931	0.5417	0.4860
No log	15.0	195	0.6931	0.5233	0.4838
No log	15.38	200	0.6931	0.5258	0.4851
No log	15.77	205	0.6931	0.5392	0.4931
No log	16.15	210	0.6931	0.5083	0.4627

Framework versions

• Transformers 4.33.3
• Pytorch 2.1.1+cu121
• Datasets 2.14.5
• Tokenizers 0.13.3