furina_hau_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: 0.0469
• 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	0.95	200	0.0478	nan
No log	1.91	400	0.0499	nan
0.0448	2.86	600	0.0468	nan
0.0448	3.82	800	0.0471	-0.0064
0.045	4.77	1000	0.0477	nan
0.045	5.73	1200	0.0468	nan
0.0448	6.68	1400	0.0490	nan
0.0448	7.64	1600	0.0471	nan
0.0447	8.59	1800	0.0472	nan
0.0447	9.55	2000	0.0478	nan
0.0448	10.5	2200	0.0469	nan

Framework versions

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