clapAI/xlm-roberta-base-VSMEC-ep50

clapAI/phobert-base-v1-VSMEC-ep50

This model is a fine-tuned version of clapAI/phobert-base-v1-VSMEC-ep50 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.2808
• Micro F1: 63.2653
• Micro Precision: 63.2653
• Micro Recall: 63.2653
• Macro F1: 59.3649
• Macro Precision: 59.5968
• Macro Recall: 60.0346

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: 5e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• distributed_type: multi-GPU
• gradient_accumulation_steps: 4
• total_train_batch_size: 256
• optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.01
• num_epochs: 0.0

Training results

Framework versions

• Transformers 4.50.0
• Pytorch 2.4.0+cu121
• Datasets 2.15.0
• Tokenizers 0.21.1