furina_seed42_eng_kin_hau_basic_2e-05

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

• Loss: 0.0261
• Spearman Corr: 0.7485

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	1.59	200	0.0355	0.6099
0.0837	3.19	400	0.0284	0.7050
0.0265	4.78	600	0.0265	0.7290
0.0202	6.37	800	0.0257	0.7317
0.0153	7.97	1000	0.0252	0.7333
0.0153	9.56	1200	0.0254	0.7464
0.0126	11.16	1400	0.0243	0.7483
0.0109	12.75	1600	0.0254	0.7467
0.009	14.34	1800	0.0253	0.7463
0.0081	15.94	2000	0.0259	0.7450
0.0081	17.53	2200	0.0258	0.7454
0.0072	19.12	2400	0.0249	0.7474
0.0066	20.72	2600	0.0264	0.7453
0.0061	22.31	2800	0.0252	0.7463
0.0057	23.9	3000	0.0261	0.7485

Framework versions

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