XMLRoberta_Dataset8kMeta

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

• Loss: 0.3777
• Accuracy: 0.9464
• F1: 0.9465

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: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	1.6260	200	0.2882	0.9243	0.9108
0.4946	3.2520	400	0.2445	0.9166	0.9073
0.1849	4.8780	600	0.2282	0.9447	0.9453
0.1256	6.5041	800	0.2781	0.9472	0.9459
0.0808	8.1301	1000	0.2434	0.9404	0.9422
0.0808	9.7561	1200	0.3441	0.9438	0.9436
0.0592	11.3821	1400	0.3017	0.9506	0.9499
0.0418	13.0081	1600	0.3410	0.9455	0.9446
0.0345	14.6341	1800	0.3515	0.9430	0.9434
0.0233	16.2602	2000	0.3690	0.9455	0.9458
0.0233	17.8862	2200	0.3746	0.9481	0.9480
0.0176	19.5122	2400	0.3777	0.9464	0.9465

Framework versions

• Transformers 4.42.4
• Pytorch 2.1.2
• Datasets 2.19.2
• Tokenizers 0.19.1