Views
No views yet
German_Songs,German_Poems,bjoernp_ultrachat_de,OpenSchnabeltier,ultrachat_de,oasst_de,dolly_15k_de,alpaca-gpt4_de,openschnabeltier_de,evol_instruct_de,dolphin_de,booksum_de,airoboros_de & eval VAGOsolutions/MT-Bench-TrueGerman?mayflowergmbh/intel_orca_dpo_pairs_de1python src/train_bash.py --stage sft ... --finetuning_type lora --quantization_bit 4 --template alpaca --rope_scaling linear --flash_attn True --dataset_dir data --dataset German_Songs,German_Poems,bjoernp_ultrachat_de,OpenSchnabeltier,ultrachat_de,oasst_de,dolly_15k_de,alpaca-gpt4_de,openschnabeltier_de,evol_instruct_de,dolphin_de,booksum_de,airoboros_de --cutoff_len 4096 --learning_rate 5e-05 --num_train_epochs 1.0 --max_samples 100000 --per_device_train_batch_size 1 --gradient_accumulation_steps 1 --lr_scheduler_type cosine --max_grad_norm 1.0 --logging_steps 5 --save_steps 1000 --warmup_steps 0 --neftune_noise_alpha 0.5 --optim adamw_torch --upcast_layernorm True --use_llama_pro True --bf16 True --lora_rank 512 --lora_alpha 1024 --lora_dropout 0.15 --lora_target all --use_rslora True --additional_target all --create_new_adapter True --plot_loss True
2
3python src/train_bash.py --stage orpo ... --finetuning_type lora --quantization_bit 4 --template alpaca --rope_scaling linear --flash_attn True --dataset_dir data --dataset orca_dpo_de --cutoff_len 4096 --learning_rate 1e-05 --num_train_epochs 1.0 --max_samples 100000 --per_device_train_batch_size 1 --gradient_accumulation_steps 1 --lr_scheduler_type cosine --max_grad_norm 0.9 --logging_steps 5 --save_steps 250 --warmup_steps 100 --neftune_noise_alpha 0.5 --optim adamw_torch --upcast_layernorm True --use_llama_pro True --report_to none --bf16 True --lora_rank 512 --lora_alpha 1024 --lora_dropout 0.15 --use_rslora True --lora_target all --additional_target all --orpo_beta 0.1 --plot_loss True