ft_sharegpt_top20pct_M1_LST_Qwen3_8B_rawfull_17langs_20260315_232435_en2xx_xx2en_merged_shuffled_cutoff8192_20260421_131718

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

• learning_rate: 1e-05
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 8
• total_train_batch_size: 128
• total_eval_batch_size: 32
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine_with_min_lr
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 1.0

Training results

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu128
• Datasets 3.6.0
• Tokenizers 0.22.0