ruadapt_qwen2.5_3B_darulm_unigram_128000_full_lr2e4_bs256

• Loss: 2.7895
• Accuracy: 0.4654

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

• learning_rate: 0.0002
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• distributed_type: multi-GPU
• num_devices: 64
• gradient_accumulation_steps: 2
• total_train_batch_size: 256
• total_eval_batch_size: 128
• optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 100
• num_epochs: 1.0

Training results

Framework versions

• Transformers 4.37.2
• Pytorch 2.3.0a0+6ddf5cf85e.nv24.04
• Datasets 2.18.0
• Tokenizers 0.15.2