20230928-9-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: 0.5108
• Loss: nan

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
4.5519	0.46	200	0.2982	nan
4.1573	0.91	400	0.3194	nan
3.8898	1.37	600	0.3280	nan
3.7149	1.82	800	0.3765	3.2017
3.5722	2.28	1000	0.4056	nan
3.4367	2.73	1200	0.3648	3.0582
3.3854	3.19	1400	0.3741	nan
3.4153	3.64	1600	0.4019	2.8494
3.3047	4.1	1800	0.4049	2.9662
3.1112	4.56	2000	0.4419	3.0672
3.3055	5.01	2200	0.4746	2.9201
2.948	5.47	2400	0.4633	nan
2.9887	5.92	2600	0.4349	2.9944
2.9127	6.38	2800	0.4832	2.5580
2.7644	6.83	3000	0.4737	2.6597
2.8758	7.29	3200	0.4226	3.1813
2.9334	7.74	3400	0.4670	2.5154
2.7652	8.2	3600	0.4860	2.7003
2.7986	8.66	3800	0.5547	nan
2.7419	9.11	4000	0.5095	nan
2.7937	9.57	4200	0.5108	nan

Framework versions

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