scenario-TCR-XLMV-XCOPA-4_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: 0.5008
• F1: 0.4628

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: 4824
• 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	0.6932	0.4642	0.4462
No log	0.77	10	0.6932	0.485	0.4560
No log	1.15	15	0.6932	0.4992	0.4551
No log	1.54	20	0.6932	0.4983	0.4467
No log	1.92	25	0.6932	0.4958	0.4444
No log	2.31	30	0.6932	0.5075	0.4661
No log	2.69	35	0.6931	0.5042	0.4625
No log	3.08	40	0.6931	0.4967	0.4597
No log	3.46	45	0.6931	0.4908	0.4636
No log	3.85	50	0.6932	0.5008	0.4647
No log	4.23	55	0.6931	0.5067	0.4752
No log	4.62	60	0.6931	0.5033	0.4688
No log	5.0	65	0.6932	0.4875	0.4524
No log	5.38	70	0.6932	0.4517	0.4156
No log	5.77	75	0.6932	0.4667	0.4286
No log	6.15	80	0.6932	0.4683	0.4334
No log	6.54	85	0.6932	0.47	0.4382
No log	6.92	90	0.6932	0.4692	0.4437
No log	7.31	95	0.6931	0.4967	0.4766
No log	7.69	100	0.6931	0.53	0.5138
No log	8.08	105	0.6931	0.4858	0.4686
No log	8.46	110	0.6932	0.4767	0.4452
No log	8.85	115	0.6931	0.4617	0.4353
No log	9.23	120	0.6931	0.4683	0.4433
No log	9.62	125	0.6931	0.4717	0.4429
No log	10.0	130	0.6931	0.4858	0.4630
No log	10.38	135	0.6931	0.4983	0.4872
No log	10.77	140	0.6931	0.4958	0.4771
No log	11.15	145	0.6931	0.5108	0.4846
No log	11.54	150	0.6931	0.5075	0.4784
No log	11.92	155	0.6931	0.5267	0.4883
No log	12.31	160	0.6931	0.5142	0.4809
No log	12.69	165	0.6931	0.5108	0.4873
No log	13.08	170	0.6931	0.5075	0.4829
No log	13.46	175	0.6931	0.5042	0.4758
No log	13.85	180	0.6931	0.4825	0.4567
No log	14.23	185	0.6931	0.4625	0.4337
No log	14.62	190	0.6931	0.4783	0.4528
No log	15.0	195	0.6931	0.4767	0.4510
No log	15.38	200	0.6931	0.4675	0.4370
No log	15.77	205	0.6931	0.4675	0.4370
No log	16.15	210	0.6931	0.465	0.4368
No log	16.54	215	0.6931	0.4792	0.4522
No log	16.92	220	0.6931	0.4875	0.4591
No log	17.31	225	0.6931	0.4892	0.4628
No log	17.69	230	0.6931	0.4933	0.4591
No log	18.08	235	0.6931	0.5325	0.4978
No log	18.46	240	0.6931	0.5192	0.4750
No log	18.85	245	0.6931	0.5142	0.4836
No log	19.23	250	0.6931	0.5008	0.4628

Framework versions

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