furina_seed42_eng_basic_5e-06

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

• Loss: 0.0179
• Spearman Corr: 0.7914

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: 5e-06
• 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
0.1741	2.33	200	0.0321	0.1668
0.0715	4.65	400	0.0148	0.7067
0.0342	6.98	600	0.0191	0.7501
0.0281	9.3	800	0.0140	0.7591
0.0247	11.63	1000	0.0130	0.7711
0.0201	13.95	1200	0.0171	0.7764
0.019	16.28	1400	0.0161	0.7852
0.0178	18.6	1600	0.0146	0.7903
0.017	20.93	1800	0.0201	0.7889
0.0163	23.26	2000	0.0183	0.7923
0.0159	25.58	2200	0.0180	0.7907
0.0153	27.91	2400	0.0179	0.7914

Framework versions

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