layai/syn-news-dict

dict

This model is a fine-tuned version of /juice2/scr2/laya/Meta-Llama-3-8B on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.9098
• Accuracy: 0.7301

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: 40
• eval_batch_size: 40
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 160
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.7964	1.0560	500	1.9098	0.7301
0.2989	2.1119	1000	1.9240	0.7473

Framework versions

• Transformers 4.45.0.dev0
• Pytorch 2.3.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1