[ Web Proxy ]
URL:
Viewing: https://raw.githubusercontent.com/DreamLM/Dream-Coder/main/instruct/code_eval/evalplus/eval.sh [Back]  [Original]

CUDA_VISIBLE_DEVICES=7 evalplus.evaluate --model /home/ndfl4zki/ndfl4zkiuser04/codes_posttrain/diffllm-verl/distill_warmup1epoch_reweightcart_steps64_teacher8_kept256_klbwd_algomaskgit_plus_ema0.001_ceFalse/global_step_40000 --trust_remote_code True --max_new_tokens 768 --diffusion_steps 768                   --dataset humaneval                               --backend dllm         --temperature 0.1

# CUDA_VISIBLE_DEVICES=7 evalplus.evaluate --model /home/ndfl4zki/ndfl4zkiuser04/codes_posttrain/diffllm-verl/opencoder_cleaned_allfixed_3epoch_cart_perbatchcutoff_code-608k-ctx4k_randomcutoff_lr5e-6/global_step_13438 --trust_remote_code True --max_new_tokens 768 --diffusion_steps 768                   --dataset humaneval                               --backend dllm         --temperature 0.1

# CUDA_VISIBLE_DEVICES=7 evalplus.evaluate --model /home/ndfl4zki/ndfl4zkiuser04/codes_posttrain/diffllm-verl/opencodeinstructscore5_allfixed_3epoch_cart_perbatchcutoff_code-608k-ctx4k_randomcutoff_lr5e-6/global_step_2000 --trust_remote_code True --max_new_tokens 768 --diffusion_steps 768                   --dataset humaneval                               --backend dllm         --temperature 0.1

# CUDA_VISIBLE_DEVICES=7 evalplus.evaluate --model /home/ndfl4zki/ndfl4zkiuser04/codes_posttrain/diffllm-verl/opencodeinstructscore5_allfixed_3epoch_cart_perbatchcutoff_code-608k-ctx4k_randomcutoff_lr5e-6/global_step_4321 --trust_remote_code True --max_new_tokens 768 --diffusion_steps 768                   --dataset humaneval                               --backend dllm         --temperature 0.1

# CUDA_VISIBLE_DEVICES=7 evalplus.evaluate --model /home/ndfl4zki/ndfl4zkiuser04/codes_posttrain/diffllm-verl/mixturecodev0_allfixed_3epoch_cart_perbatchcutoff_code-608k-ctx4k_randomcutoff_lr5e-6/global_step_11041 --trust_remote_code True --max_new_tokens 768 --diffusion_steps 768                   --dataset humaneval                               --backend dllm         --temperature 0.1

CUDA_VISIBLE_DEVICES=7 evalplus.evaluate --model /home/ndfl4zki/ndfl4zkiuser04/codes_posttrain/diffllm-verl/mixturecodev0_allfixed_3epoch_cart_perbatchcutoff_code-608k-ctx4k_randomcutoff_lr5e-6/global_step_22082 --trust_remote_code True --max_new_tokens 768 --diffusion_steps 768                   --dataset humaneval                               --backend dllm         --temperature 0.1

CUDA_VISIBLE_DEVICES=7 evalplus.evaluate --model /home/ndfl4zki/ndfl4zkiuser04/codes_posttrain/diffllm-verl/mixturecodev0_allfixed_3epoch_cart_perbatchcutoff_code-608k-ctx4k_randomcutoff_lr5e-6/global_step_22082 --trust_remote_code True --max_new_tokens 768 --diffusion_steps 768                   --dataset humaneval                               --backend dllm         --temperature 0.1 --alg maskgit_plus

CUDA_VISIBLE_DEVICES=7 evalplus.evaluate --model /home/ndfl4zki/ndfl4zkiuser04/codes_posttrain/diffllm-verl/mixturecodev0_allfixed_3epoch_cart_perbatchcutoff_code-608k-ctx4k_randomcutoff_lr5e-6/global_step_22082 --trust_remote_code True --max_new_tokens 768 --diffusion_steps 768                   --dataset humaneval                               --backend dllm         --temperature 0.3

CUDA_VISIBLE_DEVICES=7 evalplus.evaluate --model /home/ndfl4zki/ndfl4zkiuser04/codes_posttrain/diffllm-verl/mixturecodev0_allfixed_3epoch_cart_perbatchcutoff_code-608k-ctx4k_randomcutoff_lr5e-6/global_step_33123 --trust_remote_code True --max_new_tokens 768 --diffusion_steps 768                   --dataset humaneval                               --backend dllm         --temperature 0.1

CUDA_VISIBLE_DEVICES=7 evalplus.evaluate --model /home/ndfl4zki/ndfl4zkiuser04/codes_posttrain/diffllm-verl/lingcoder_fixlower_3epoch_cart_perbatchcutoff_code-608k-ctx4k_randomcutoff_lr5e-6/global_step_6000 --trust_remote_code True --max_new_tokens 768 --diffusion_steps 768                   --dataset humaneval                               --backend dllm         --temperature 0.1

CUDA_VISIBLE_DEVICES=7 evalplus.evaluate --model /home/ndfl4zki/ndfl4zkiuser04/codes_posttrain/diffllm-verl/mixturecodev1_fixlower_3epoch_cart_perbatchcutoff_code-608k-ctx4k_randomcutoff_bs576_cont39k_inputpad_lr5e-6/global_step_5000 --trust_remote_code True --max_new_tokens 768 --diffusion_steps 768                   --dataset humaneval                               --backend dllm         --temperature 0.1

CUDA_VISIBLE_DEVICES=7 evalplus.evaluate --model /home/ndfl4zki/ndfl4zkiuser04/codes_posttrain/diffllm-verl/lingcoder_fixlower_3epoch_cart_perbatchcutoff_code-608k-ctx4k_randomcutoff_bs576_cont39k_inputpad_lr5e-6/global_step_35548 --trust_remote_code True --max_new_tokens 768 --diffusion_steps 768                   --dataset humaneval                               --backend dllm         --temperature 0.1

CUDA_VISIBLE_DEVICES=7 evalplus.evaluate --model /home/ndfl4zki/ndfl4zkiuser04/codes_posttrain/diffllm-verl/lingcoder_fixlower_3epoch_cart_perbatchcutoff_code-608k-ctx4k_randomcutoff_bs384_lr5e-6/global_step_30000 --trust_remote_code True --max_new_tokens 768 --diffusion_steps 768                   --dataset humaneval                               --backend dllm         --temperature 0.1

CUDA_VISIBLE_DEVICES=7 evalplus.evaluate --model /home/ndfl4zki/ndfl4zkiuser04/codes_posttrain/diffllm-verl/mixturecodev1_fixlower_3epoch_cart_perbatchcutoff_code-608k-ctx4k_randomcutoff_bs576_cont39k_inputpad_lr5e-6/global_step_8794 --trust_remote_code True --max_new_tokens 768 --diffusion_steps 768                   --dataset humaneval                               --backend dllm         --temperature 0.1

CUDA_VISIBLE_DEVICES=7 evalplus.evaluate --model /home/ndfl4zki/ndfl4zkiuser04/codes_posttrain/diffllm-verl/lingcoder_fixlower_3epoch_cart_perbatchcutoff_code-608k-ctx4k_randomcutoff_bs576_cont39k_inputpad_lr5e-6/global_step_44435 --trust_remote_code True --max_new_tokens 768 --diffusion_steps 768                   --dataset humaneval                               --backend dllm         --temperature 0.1

CUDA_VISIBLE_DEVICES=7 evalplus.evaluate --model /home/ndfl4zki/ndfl4zkiuser04/codes_posttrain/diffllm-verl/mixturecodev1_fixlower_3epoch_cart_perbatchcutoff_code-608k-ctx4k_randomcutoff_bs576_cont39k_inputpad_lr5e-6/global_step_17588 --trust_remote_code True --max_new_tokens 768 --diffusion_steps 768                   --dataset humaneval                               --backend dllm         --temperature 0.1

CUDA_VISIBLE_DEVICES=4 evalplus.evaluate --model /home/ndfl4zki/ndfl4zkiuser04/codes_posttrain/diffllm-verl/ckpts/lingcoder_fixlower_3epoch_cart_randomcutoff_code-960k-ctx4k_bs576_inputpad_lr5e-6/global_step_26652 --trust_remote_code True --max_new_tokens 768 --diffusion_steps 768 --dataset humaneval --backend dllm --temperature 0.1
CUDA_VISIBLE_DEVICES=5 evalplus.evaluate --model /home/ndfl4zki/ndfl4zkiuser04/codes_posttrain/diffllm-verl/ckpts/mixturecodev2_cart_randomcutoff_code-960k-ctx4k_bs288_wd0.1_ct_inputpad_lr2e-6/global_step_5000 --trust_remote_code True --max_new_tokens 768 --diffusion_steps 768 --dataset humaneval --backend dllm --temperature 0.1
CUDA_VISIBLE_DEVICES=6 evalplus.evaluate --model /home/ndfl4zki/ndfl4zkiuser04/codes_posttrain/diffllm-verl/ckpts/mixturecodev2_cart_randomcutoff_code-960k-ctx4k_bs288_wd0.1_ct_inputpad_lr2e-6/global_step_10000 --trust_remote_code True --max_new_tokens 768 --diffusion_steps 768 --dataset humaneval --backend dllm --temperature 0.1
CUDA_VISIBLE_DEVICES=7 evalplus.evaluate --model /home/ndfl4zki/ndfl4zkiuser04/codes_posttrain/diffllm-verl/ckpts/mixturecodev2_cart_randomcutoff_code-960k-ctx4k_bs288_wd0.1_ct_inputpad_lr2e-6/global_step_15000 --trust_remote_code True --max_new_tokens 768 --diffusion_steps 768 --dataset humaneval --backend dllm --temperature 0.1

CUDA_VISIBLE_DEVICES=4 evalplus.evaluate --model /home/ndfl4zki/ndfl4zkiuser04/codes_posttrain/diffllm-verl/ckpts/mixturecodev2_cart_randomcutoff_code-960k-ctx4k_bs288_wd0.1_ct_inputpad_lr2e-6/global_step_20000 --trust_remote_code True --max_new_tokens 768 --diffusion_steps 768 --dataset humaneval --backend dllm --temperature 0.1
CUDA_VISIBLE_DEVICES=5 evalplus.evaluate --model /home/ndfl4zki/ndfl4zkiuser04/codes_posttrain/diffllm-verl/ckpts/mixturecodev2_cart_randomcutoff_code-960k-ctx4k_bs288_wd0.1_ct_inputpad_lr2e-6/global_step_25000 --trust_remote_code True --max_new_tokens 768 --diffusion_steps 768 --dataset humaneval --backend dllm --temperature 0.1
CUDA_VISIBLE_DEVICES=6 evalplus.evaluate --model /home/ndfl4zki/ndfl4zkiuser04/codes_posttrain/diffllm-verl/ckpts/mixturecodev2_cart_randomcutoff_code-960k-ctx4k_bs288_wd0.1_ct_inputpad_lr2e-6/global_step_18226 --trust_remote_code True --max_new_tokens 768 --diffusion_steps 768 --dataset humaneval --backend dllm --temperature 0.1

CUDA_VISIBLE_DEVICES=3 evalplus.evaluate --model /home/ndfl4zki/ndfl4zkiuser04/codes_posttrain/diffllm-verl/ckpts/lingcoder_fixlower_3epoch_cart_perbatchcutoff_code-608k-ctx4k_randomcutoff_bs384_lr5e-6/global_step_39993 --trust_remote_code True --max_new_tokens 768 --diffusion_steps 768                   --dataset humaneval                               --backend dllm         --temperature 0.1
CUDA_VISIBLE_DEVICES=5 evalplus.evaluate --model ~/ckpts/rl/diff-rl/lcb_reslen256_lr1e-7_bs48_cartp0.1/global_step_90/actor/huggingface --trust_remote_code True --max_new_tokens 768 --diffusion_steps 768 --dataset humaneval --backend dllm --temperature 0.1
CUDA_VISIBLE_DEVICES=2 evalplus.evaluate --model Dream-org/Dream-v0-Instruct-7B --trust_remote_code True --max_new_tokens 768 --diffusion_steps 768 --dataset humaneval --backend dllm --temperature 0.1

CUDA_VISIBLE_DEVICES=4 evalplus.evaluate --model /home/ndfl4zki/ndfl4zkiuser04/codes_posttrain/diffllm-verl/mixturev3_cart_perbatchcutoff_code-608k-ctx4k_randomcutoff_bs576_cont2_inputpad_lr5e-6/global_step_3469 --trust_remote_code True --max_new_tokens 768 --diffusion_steps 768 --dataset humaneval --backend dllm --temperature 0.1
CUDA_VISIBLE_DEVICES=4 evalplus.evaluate --model /home/ndfl4zki/ndfl4zkiuser04/codes_posttrain/diffllm-verl/mixturev3_cart_perbatchcutoff_code-608k-ctx4k_randomcutoff_bs576_cont2_inputpad_lr5e-6/global_step_6938 --trust_remote_code True --max_new_tokens 768 --diffusion_steps 768 --dataset humaneval --backend dllm --temperature 0.1

Web Proxy Viewer  |  New URL  |  Original Page