furina_seed42_eng

This model is a fine-tuned version of yihongLiu/furina on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0154
• Spearman Corr: 0.8369

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: 2e-05
• 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
0.1008	2.58	200	0.0227	0.7562
0.0257	5.16	400	0.0211	0.7966
0.018	7.74	600	0.0160	0.8301
0.0117	10.32	800	0.0160	0.8281
0.0101	12.9	1000	0.0154	0.8360
0.0086	15.48	1200	0.0154	0.8367
0.007	18.06	1400	0.0150	0.8377
0.0062	20.65	1600	0.0154	0.8387
0.0059	23.23	1800	0.0155	0.8356
0.0055	25.81	2000	0.0152	0.8386
0.0052	28.39	2200	0.0154	0.8369

Framework versions

• Transformers 4.37.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1