furina_seed42_eng_kin_amh_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: 0.0154
• Spearman Corr: 0.8112

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	1.95	200	0.0239	0.7162
0.0881	3.9	400	0.0177	0.7990
0.0228	5.85	600	0.0167	0.8089
0.0168	7.8	800	0.0153	0.8124
0.0127	9.76	1000	0.0168	0.8121
0.0102	11.71	1200	0.0157	0.8114
0.0085	13.66	1400	0.0154	0.8122
0.0073	15.61	1600	0.0156	0.8132
0.0068	17.56	1800	0.0152	0.8097
0.0061	19.51	2000	0.0158	0.8094
0.0055	21.46	2200	0.0155	0.8098
0.005	23.41	2400	0.0152	0.8113
0.005	25.37	2600	0.0152	0.8099
0.0046	27.32	2800	0.0153	0.8113
0.0044	29.27	3000	0.0154	0.8112

Framework versions

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