furina_seed42_eng_amh_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: 0.0202
• Spearman Corr: 0.7965

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	1.72	200	0.0245	0.7642
0.0761	3.45	400	0.0205	0.8068
0.0252	5.17	600	0.0201	0.8002
0.0185	6.9	800	0.0193	0.8106
0.0147	8.62	1000	0.0203	0.8017
0.0118	10.34	1200	0.0198	0.8021
0.0099	12.07	1400	0.0200	0.8029
0.0099	13.79	1600	0.0228	0.7997
0.0086	15.52	1800	0.0202	0.7982
0.0077	17.24	2000	0.0217	0.7921
0.0067	18.97	2200	0.0208	0.7985
0.0062	20.69	2400	0.0202	0.7965

Framework versions

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