furina_seed42_eng_esp_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: 0.0227
• Spearman Corr: 0.7567

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	1.61	200	0.0390	0.5403
0.0806	3.23	400	0.0258	0.7313
0.0295	4.84	600	0.0231	0.7463
0.022	6.45	800	0.0216	0.7582
0.017	8.06	1000	0.0241	0.7626
0.017	9.68	1200	0.0214	0.7723
0.0142	11.29	1400	0.0212	0.7660
0.0113	12.9	1600	0.0221	0.7655
0.0096	14.52	1800	0.0214	0.7690
0.0083	16.13	2000	0.0222	0.7595
0.0083	17.74	2200	0.0218	0.7649
0.0073	19.35	2400	0.0221	0.7600
0.0065	20.97	2600	0.0225	0.7606
0.0059	22.58	2800	0.0222	0.7574
0.0055	24.19	3000	0.0227	0.7567

Framework versions

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