semeval_taskA_model

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

• Loss: 0.3545
• Accuracy: 0.9136
• F1: 0.9132
• Precision: 0.9202
• Recall: 0.9136

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: 1e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 5
• mixed_precision_training: Native AMP
• label_smoothing_factor: 0.1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.5408	0.2541	200	0.5332	0.7773	0.7712	0.8102	0.7773
0.391	0.5083	400	0.5409	0.8140	0.8085	0.8545	0.8140
0.3775	0.7624	600	0.3763	0.8934	0.8929	0.9023	0.8934
0.33	1.0165	800	0.3793	0.8976	0.8970	0.9064	0.8976
0.3171	1.2706	1000	0.3558	0.9070	0.9066	0.9134	0.9070
0.3062	1.5248	1200	0.3388	0.9189	0.9188	0.9226	0.9189
0.2924	1.7789	1400	0.3567	0.9077	0.9073	0.9157	0.9077
0.2864	2.0330	1600	0.3545	0.9136	0.9132	0.9202	0.9136

Framework versions

• Transformers 4.45.0
• Pytorch 2.10.0+cu128
• Datasets 4.8.3
• Tokenizers 0.20.3