xlm-roberta-base_eng_loss_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: 0.0465
• 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	1.33	200	0.0465	nan
0.0469	2.66	400	0.0466	nan
0.0471	3.99	600	0.0467	nan
0.0471	5.32	800	0.0462	nan
0.0471	6.64	1000	0.0462	nan
0.0471	7.97	1200	0.0463	nan
0.0471	9.3	1400	0.0476	nan
0.047	10.63	1600	0.0461	nan
0.0469	11.96	1800	0.0468	nan
0.0469	13.29	2000	0.0464	0.0242
0.047	14.62	2200	0.0471	-0.0375
0.0467	15.95	2400	0.0465	nan

Framework versions

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