furina_seed42_eng_basic_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: 0.0264
• Spearman Corr: 0.7658

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
0.0829	2.33	200	0.0263	0.1504
0.0419	4.65	400	0.0243	0.7133
0.0205	6.98	600	0.0234	0.7782
0.012	9.3	800	0.0398	0.7527
0.0081	11.63	1000	0.0276	0.7545
0.0051	13.95	1200	0.0326	0.7530
0.0047	16.28	1400	0.0268	0.7556
0.0039	18.6	1600	0.0271	0.7627
0.0037	20.93	1800	0.0204	0.7698
0.0033	23.26	2000	0.0264	0.7606
0.0029	25.58	2200	0.0268	0.7685
0.0025	27.91	2400	0.0264	0.7658

Framework versions

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