furina_afr_corr_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: 0.0466
• 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	0.85	200	0.0472	-0.0706
No log	1.69	400	0.0466	0.0314
0.0639	2.54	600	0.0487	-0.0414
0.0639	3.38	800	0.0468	-0.0245
0.05	4.23	1000	0.0469	nan
0.05	5.07	1200	0.0477	-0.0167
0.05	5.92	1400	0.0471	-0.0376
0.0497	6.77	1600	0.0469	0.0005
0.0497	7.61	1800	0.0463	nan
0.0495	8.46	2000	0.0466	nan

Framework versions

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