xlm-roberta-base-deepa-finetuned-panx-en

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

• Loss: 0.6775
• F1: 0.8313

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: 10
• eval_batch_size: 10
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	F1
0.4111	1.0	2000	0.3110	0.7820
0.2799	2.0	4000	0.3083	0.7873
0.2235	3.0	6000	0.3033	0.7953
0.1851	4.0	8000	0.3427	0.8028
0.1523	5.0	10000	0.3315	0.8105
0.1196	6.0	12000	0.3510	0.8055
0.0985	7.0	14000	0.4236	0.8059
0.0746	8.0	16000	0.4647	0.8199
0.0606	9.0	18000	0.4560	0.8191
0.0442	10.0	20000	0.5112	0.8164
0.0329	11.0	22000	0.5632	0.8275
0.0231	12.0	24000	0.6149	0.8280
0.0163	13.0	26000	0.6413	0.8273
0.0103	14.0	28000	0.6672	0.8284
0.0065	15.0	30000	0.6775	0.8313

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2