models-8k-priority-buffer-unclipped-overnight-4kbuffer-022525-step1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

• learning_rate: 8e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 596853
• distributed_type: multi-GPU
• num_devices: 8
• total_train_batch_size: 8
• total_eval_batch_size: 8
• optimizer: Use adamw_torch 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: 0.1
• num_epochs: 3

Training results

Framework versions

• PEFT 0.13.2
• Transformers 4.47.0.dev0
• Pytorch 2.4.0+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3