furina_seed42_eng_amh_hau

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

• Loss: 0.0234
• Spearman Corr: 0.7853

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	0.58	200	0.0332	0.6642
No log	1.15	400	0.0321	0.7000
No log	1.73	600	0.0304	0.7178
0.0498	2.3	800	0.0246	0.7358
0.0498	2.88	1000	0.0244	0.7339
0.0498	3.45	1200	0.0281	0.7525
0.022	4.03	1400	0.0283	0.7506
0.022	4.6	1600	0.0263	0.7552
0.022	5.18	1800	0.0317	0.7589
0.022	5.76	2000	0.0241	0.7686
0.0153	6.33	2200	0.0254	0.7715
0.0153	6.91	2400	0.0241	0.7676
0.0153	7.48	2600	0.0240	0.7688
0.0112	8.06	2800	0.0248	0.7743
0.0112	8.63	3000	0.0228	0.7737
0.0112	9.21	3200	0.0232	0.7753
0.0112	9.78	3400	0.0254	0.7730
0.0087	10.36	3600	0.0248	0.7744
0.0087	10.94	3800	0.0243	0.7716
0.0087	11.51	4000	0.0271	0.7755
0.0069	12.09	4200	0.0269	0.7833
0.0069	12.66	4400	0.0214	0.7826
0.0069	13.24	4600	0.0245	0.7811
0.0069	13.81	4800	0.0238	0.7845
0.0059	14.39	5000	0.0275	0.7861
0.0059	14.96	5200	0.0266	0.7860
0.0059	15.54	5400	0.0259	0.7865
0.005	16.12	5600	0.0253	0.7838
0.005	16.69	5800	0.0244	0.7864
0.005	17.27	6000	0.0234	0.7853

Framework versions

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