xlm-roberta-base_ary_corr_0.0001

This model is a fine-tuned version of FacebookAI/xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0470
• Spearman Corr: 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: 0.0001
• train_batch_size: 32
• eval_batch_size: 128
• 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: 30
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Spearman Corr
No log	0.9	200	0.0462	nan
No log	1.8	400	0.0463	nan
0.0488	2.7	600	0.0481	nan
0.0488	3.6	800	0.0470	nan
0.0488	4.5	1000	0.0472	nan
0.0488	5.41	1200	0.0465	-0.0386
0.0485	6.31	1400	0.0465	-0.0268
0.0485	7.21	1600	0.0462	nan
0.0489	8.11	1800	0.0470	nan

Framework versions

• Transformers 4.37.2
• Pytorch 2.2.0+cu121
• Datasets 2.17.0
• Tokenizers 0.15.2