edos_taskb_llama3b_lora_newloss

This model is a fine-tuned version of meta-llama/Llama-3.2-3B on the None dataset. It achieves the following results on the evaluation set:

• eval_loss: 1.0331
• eval_accuracy: 0.5947
• eval_f1_macro: 0.5410
• eval_f1_micro: 0.5947
• eval_runtime: 2.4053
• eval_samples_per_second: 202.051
• eval_steps_per_second: 3.326
• epoch: 12.9765
• step: 700

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: 0.0003
• train_batch_size: 16
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT 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: 0.06
• num_epochs: 20
• label_smoothing_factor: 0.1

Framework versions

• PEFT 0.17.1
• Transformers 4.56.2
• Pytorch 2.8.0+cu126
• Datasets 4.1.1
• Tokenizers 0.22.0