furina_seed42_eng_amh_esp_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: 0.0215
• Spearman Corr: 0.7964

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	1.76	200	0.0220	0.7121
0.0794	3.52	400	0.0219	0.7836
0.0236	5.29	600	0.0310	0.7932
0.0176	7.05	800	0.0201	0.7950
0.0136	8.81	1000	0.0218	0.7973
0.0113	10.57	1200	0.0211	0.7975
0.0097	12.33	1400	0.0238	0.7996
0.008	14.1	1600	0.0228	0.8032
0.008	15.86	1800	0.0239	0.8028
0.0071	17.62	2000	0.0232	0.8007
0.0063	19.38	2200	0.0224	0.7948
0.0058	21.15	2400	0.0215	0.7964

Framework versions

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