furina_ary_loss_0.0001

This model is a fine-tuned version of yihongLiu/furina on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0489
• 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	0.0478	nan
No log	1.8	400	0.0472	nan
0.0489	2.7	600	0.0509	0.0080
0.0489	3.6	800	0.0476	nan
0.0491	4.5	1000	0.0477	nan
0.0491	5.41	1200	0.0474	nan
0.0488	6.31	1400	0.0470	nan
0.0488	7.21	1600	0.0467	nan
0.0488	8.11	1800	0.0496	nan
0.0488	9.01	2000	0.0472	nan
0.0488	9.91	2200	0.0487	0.0217
0.0486	10.81	2400	0.0472	nan
0.0486	11.71	2600	0.0484	nan
0.0484	12.61	2800	0.0490	nan
0.0484	13.51	3000	0.0469	nan
0.0485	14.41	3200	0.0489	nan

Framework versions

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