scenario-TCR-XLMV-XCOPA-3_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: 0.4625
• F1: 0.4277

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: 48
• 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	0.4725	0.4472
No log	0.77	10	0.6932	0.4892	0.4656
No log	1.15	15	0.6932	0.4867	0.45
No log	1.54	20	0.6932	0.49	0.4584
No log	1.92	25	0.6931	0.51	0.4722
No log	2.31	30	0.6931	0.5042	0.4730
No log	2.69	35	0.6932	0.4825	0.4576
No log	3.08	40	0.6931	0.4767	0.4520
No log	3.46	45	0.6931	0.4842	0.4556
No log	3.85	50	0.6931	0.4883	0.4508
No log	4.23	55	0.6931	0.5392	0.5145
No log	4.62	60	0.6931	0.5508	0.5183
No log	5.0	65	0.6931	0.5392	0.5076
No log	5.38	70	0.6931	0.5567	0.5325
No log	5.77	75	0.6931	0.5642	0.5368
No log	6.15	80	0.6931	0.4483	0.4173
No log	6.54	85	0.6931	0.4358	0.4025
No log	6.92	90	0.6931	0.4492	0.4257
No log	7.31	95	0.6931	0.4442	0.4185
No log	7.69	100	0.6931	0.4492	0.4207
No log	8.08	105	0.6931	0.4575	0.4294
No log	8.46	110	0.6931	0.4592	0.4322
No log	8.85	115	0.6931	0.4583	0.4268
No log	9.23	120	0.6931	0.4567	0.4240
No log	9.62	125	0.6931	0.465	0.4309
No log	10.0	130	0.6931	0.5608	0.5239
No log	10.38	135	0.6931	0.5525	0.5244
No log	10.77	140	0.6931	0.5542	0.5253
No log	11.15	145	0.6931	0.5567	0.5284
No log	11.54	150	0.6931	0.5517	0.5247
No log	11.92	155	0.6931	0.5567	0.5325
No log	12.31	160	0.6931	0.5483	0.5271
No log	12.69	165	0.6931	0.5183	0.5009
No log	13.08	170	0.6931	0.5125	0.4891
No log	13.46	175	0.6931	0.4917	0.4696
No log	13.85	180	0.6931	0.4683	0.4462
No log	14.23	185	0.6931	0.4758	0.4507
No log	14.62	190	0.6931	0.515	0.4913
No log	15.0	195	0.6931	0.5242	0.5048
No log	15.38	200	0.6931	0.5208	0.4996
No log	15.77	205	0.6931	0.4567	0.4389
No log	16.15	210	0.6931	0.4492	0.4145
No log	16.54	215	0.6931	0.465	0.4309
No log	16.92	220	0.6931	0.4633	0.4270
No log	17.31	225	0.6931	0.4625	0.4277

Framework versions

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