xlm-roberta-base_lr0.001_seed42_basic_original_esp-kin-eng_train

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: 0.0383
• 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: 0.001
• 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	1.63	200	0.0388	nan
0.1383	3.27	400	0.0382	nan
0.0519	4.9	600	0.0383	nan
0.0503	6.53	800	0.0383	nan
0.0488	8.16	1000	0.0384	nan
0.0488	9.8	1200	0.0384	nan
0.0489	11.43	1400	0.0388	nan
0.0491	13.06	1600	0.0383	nan
0.0487	14.69	1800	0.0382	nan
0.0486	16.33	2000	0.0391	nan
0.0486	17.96	2200	0.0383	nan
0.0486	19.59	2400	0.0383	nan

Framework versions

• Transformers 4.37.2
• Pytorch 2.1.0+cu121
• Datasets 2.17.0
• Tokenizers 0.15.2