gte-base-zh-finetuned-main_rev_rate

This model is a fine-tuned version of thenlper/gte-base-zh on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3443
• Accuracy: 0.0807
• F1: 0.0713

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: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.3784	1.0	85	0.3260	0.0998	0.0181
0.3258	2.0	170	0.3268	0.0913	0.0153
0.3256	3.0	255	0.3271	0.0913	0.0153
0.3255	4.0	340	0.3262	0.1040	0.0305
0.3255	5.0	425	0.3266	0.0998	0.0246
0.3248	6.0	510	0.3257	0.0955	0.0489
0.3246	7.0	595	0.3263	0.1104	0.0566
0.3233	8.0	680	0.3272	0.1062	0.0593
0.3206	9.0	765	0.3287	0.1146	0.0754
0.3171	10.0	850	0.3324	0.0977	0.0686
0.3113	11.0	935	0.3321	0.0892	0.0809
0.3021	12.0	1020	0.3357	0.0977	0.0800
0.2954	13.0	1105	0.3395	0.0828	0.0750
0.2872	14.0	1190	0.3428	0.0913	0.0803
0.2821	15.0	1275	0.3443	0.0807	0.0713

Framework versions

• Transformers 4.40.0
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1