furina_seed42_eng_kin_hau_basic

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

• Loss: 0.0273
• Spearman Corr: 0.8040

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
No log	1.77	200	0.0339	0.7391
0.0845	3.54	400	0.0337	0.7909
0.0273	5.31	600	0.0228	0.8081
0.0199	7.08	800	0.0229	0.8163
0.0152	8.85	1000	0.0241	0.8102
0.0123	10.62	1200	0.0278	0.8168
0.0102	12.39	1400	0.0282	0.8072
0.0087	14.16	1600	0.0210	0.8108
0.008	15.93	1800	0.0234	0.8106
0.008	17.7	2000	0.0278	0.8059
0.0069	19.47	2200	0.0308	0.8107
0.0063	21.24	2400	0.0257	0.8127
0.0057	23.01	2600	0.0257	0.8095
0.0055	24.78	2800	0.0250	0.8077
0.0051	26.55	3000	0.0252	0.8055
0.005	28.32	3200	0.0273	0.8040

Framework versions

• Transformers 4.37.2
• Pytorch 2.1.0+cu121
• Datasets 2.17.0
• Tokenizers 0.15.1