20230928-3-xlm-roberta-base-new

This model is a fine-tuned version of xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:

• Accuracy: 0.5422
• Loss: 2.4161

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Accuracy	Validation Loss
4.4417	0.46	200	0.2696	nan
4.0961	0.91	400	0.3189	nan
3.7075	1.37	600	0.3422	nan
3.6918	1.82	800	0.3297	3.6692
3.7041	2.28	1000	0.4063	3.5981
3.4991	2.73	1200	0.4211	2.8302
3.3064	3.19	1400	0.4413	2.8908
3.3633	3.64	1600	0.3834	nan
3.2069	4.1	1800	0.4505	nan
3.1465	4.56	2000	0.4263	2.9270
3.1135	5.01	2200	0.4654	nan
3.0798	5.47	2400	0.4667	2.8386
3.0095	5.92	2600	0.4212	3.0044
2.9742	6.38	2800	0.4704	nan
2.968	6.83	3000	0.4883	2.3328
2.8909	7.29	3200	0.4935	nan
2.9974	7.74	3400	0.4185	nan
2.7729	8.2	3600	0.5163	2.4607
2.784	8.66	3800	0.4840	2.5350
2.7778	9.11	4000	0.5251	nan
2.7316	9.57	4200	0.5422	2.4161

Framework versions

• Transformers 4.33.3
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3