20230928-10-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: 0.4847
• 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
4.5116	0.46	200	0.2970	nan
3.9887	0.91	400	0.3086	4.0522
3.9101	1.37	600	0.3138	nan
3.7634	1.82	800	0.3184	3.7682
3.4413	2.28	1000	0.3977	2.9317
3.4478	2.73	1200	0.4102	nan
3.4179	3.19	1400	0.3790	3.2163
3.2165	3.64	1600	0.4435	2.7062
3.1388	4.1	1800	0.4540	2.8629
3.0987	4.56	2000	0.4509	nan
3.0614	5.01	2200	0.4894	nan
3.1399	5.47	2400	0.5337	nan
3.0387	5.92	2600	0.4667	3.0331
2.9728	6.38	2800	0.4571	nan
2.9138	6.83	3000	0.4306	2.8179
2.9157	7.29	3200	0.4520	nan
2.8103	7.74	3400	0.5	nan
2.7693	8.2	3600	0.4841	2.9349
2.8204	8.66	3800	0.4727	2.7438
2.7711	9.11	4000	0.5123	2.6654
2.7196	9.57	4200	0.4847	nan

Framework versions

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