tmp-lpqm4 / evalplus_results /mbpp

58.6 MB

1 contributor

History: 3 commits

bensondccnqwc

Add files using upload-large-folder tool

d568d68 verified 11 days ago

home--work--minzijun_rl_output_2--checkpoints--verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_no_shuffle--global_step_0--actor--huggingface_vllm_temp_1.0.eval_results.json

2.01 MB

Add files using upload-large-folder tool 11 days ago
home--work--minzijun_rl_output_2--checkpoints--verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_no_shuffle--global_step_0--actor--huggingface_vllm_temp_1.0.jsonl

1.66 MB

Add files using upload-large-folder tool 11 days ago
home--work--minzijun_rl_output_2--checkpoints--verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_no_shuffle--global_step_0--actor--huggingface_vllm_temp_1.0.raw.jsonl

1.96 MB

Add files using upload-large-folder tool 11 days ago
home--work--minzijun_rl_output_2--checkpoints--verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_no_shuffle--global_step_10--actor--huggingface_vllm_temp_1.0.eval_results.json

1.8 MB

Add files using upload-large-folder tool 11 days ago
home--work--minzijun_rl_output_2--checkpoints--verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_no_shuffle--global_step_10--actor--huggingface_vllm_temp_1.0.jsonl

1.45 MB

Add files using upload-large-folder tool 11 days ago
home--work--minzijun_rl_output_2--checkpoints--verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_no_shuffle--global_step_10--actor--huggingface_vllm_temp_1.0.raw.jsonl

1.86 MB

Add files using upload-large-folder tool 11 days ago
home--work--minzijun_rl_output_2--checkpoints--verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_no_shuffle--global_step_100--actor--huggingface_vllm_temp_1.0.eval_results.json

1.86 MB

Add files using upload-large-folder tool 11 days ago
home--work--minzijun_rl_output_2--checkpoints--verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_no_shuffle--global_step_100--actor--huggingface_vllm_temp_1.0.jsonl

1.52 MB

Add files using upload-large-folder tool 11 days ago
home--work--minzijun_rl_output_2--checkpoints--verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_no_shuffle--global_step_100--actor--huggingface_vllm_temp_1.0.raw.jsonl

2.05 MB

Add files using upload-large-folder tool 11 days ago
home--work--minzijun_rl_output_2--checkpoints--verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_no_shuffle--global_step_20--actor--huggingface_vllm_temp_1.0.eval_results.json

1.8 MB

Add files using upload-large-folder tool 11 days ago
home--work--minzijun_rl_output_2--checkpoints--verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_no_shuffle--global_step_20--actor--huggingface_vllm_temp_1.0.jsonl

1.45 MB

Add files using upload-large-folder tool 11 days ago
home--work--minzijun_rl_output_2--checkpoints--verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_no_shuffle--global_step_20--actor--huggingface_vllm_temp_1.0.raw.jsonl

1.85 MB

Add files using upload-large-folder tool 11 days ago
home--work--minzijun_rl_output_2--checkpoints--verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_no_shuffle--global_step_30--actor--huggingface_vllm_temp_1.0.eval_results.json

1.78 MB

Add files using upload-large-folder tool 11 days ago
home--work--minzijun_rl_output_2--checkpoints--verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_no_shuffle--global_step_30--actor--huggingface_vllm_temp_1.0.jsonl

1.44 MB

Add files using upload-large-folder tool 11 days ago
home--work--minzijun_rl_output_2--checkpoints--verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_no_shuffle--global_step_30--actor--huggingface_vllm_temp_1.0.raw.jsonl

1.86 MB

Add files using upload-large-folder tool 11 days ago
home--work--minzijun_rl_output_2--checkpoints--verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_no_shuffle--global_step_40--actor--huggingface_vllm_temp_1.0.eval_results.json

1.82 MB

Add files using upload-large-folder tool 11 days ago
home--work--minzijun_rl_output_2--checkpoints--verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_no_shuffle--global_step_40--actor--huggingface_vllm_temp_1.0.jsonl

1.47 MB

Add files using upload-large-folder tool 11 days ago
home--work--minzijun_rl_output_2--checkpoints--verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_no_shuffle--global_step_40--actor--huggingface_vllm_temp_1.0.raw.jsonl

1.92 MB

Add files using upload-large-folder tool 11 days ago
home--work--minzijun_rl_output_2--checkpoints--verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_no_shuffle--global_step_50--actor--huggingface_vllm_temp_1.0.eval_results.json

1.83 MB

Add files using upload-large-folder tool 11 days ago
home--work--minzijun_rl_output_2--checkpoints--verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_no_shuffle--global_step_50--actor--huggingface_vllm_temp_1.0.jsonl

1.49 MB

Add files using upload-large-folder tool 11 days ago
home--work--minzijun_rl_output_2--checkpoints--verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_no_shuffle--global_step_50--actor--huggingface_vllm_temp_1.0.raw.jsonl

1.96 MB

Add files using upload-large-folder tool 11 days ago
home--work--minzijun_rl_output_2--checkpoints--verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_no_shuffle--global_step_60--actor--huggingface_vllm_temp_1.0.eval_results.json

1.86 MB

Add files using upload-large-folder tool 11 days ago
home--work--minzijun_rl_output_2--checkpoints--verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_no_shuffle--global_step_60--actor--huggingface_vllm_temp_1.0.jsonl

1.52 MB

Add files using upload-large-folder tool 11 days ago
home--work--minzijun_rl_output_2--checkpoints--verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_no_shuffle--global_step_60--actor--huggingface_vllm_temp_1.0.raw.jsonl

2.01 MB

Add files using upload-large-folder tool 11 days ago
home--work--minzijun_rl_output_2--checkpoints--verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_no_shuffle--global_step_70--actor--huggingface_vllm_temp_1.0.eval_results.json

1.87 MB

Add files using upload-large-folder tool 11 days ago
home--work--minzijun_rl_output_2--checkpoints--verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_no_shuffle--global_step_70--actor--huggingface_vllm_temp_1.0.jsonl

1.53 MB

Add files using upload-large-folder tool 11 days ago
home--work--minzijun_rl_output_2--checkpoints--verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_no_shuffle--global_step_70--actor--huggingface_vllm_temp_1.0.raw.jsonl

2.04 MB

Add files using upload-large-folder tool 11 days ago
home--work--minzijun_rl_output_2--checkpoints--verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_no_shuffle--global_step_80--actor--huggingface_vllm_temp_1.0.eval_results.json

1.86 MB

Add files using upload-large-folder tool 11 days ago
home--work--minzijun_rl_output_2--checkpoints--verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_no_shuffle--global_step_80--actor--huggingface_vllm_temp_1.0.jsonl

1.52 MB

Add files using upload-large-folder tool 11 days ago
home--work--minzijun_rl_output_2--checkpoints--verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_no_shuffle--global_step_80--actor--huggingface_vllm_temp_1.0.raw.jsonl

2.02 MB

Add files using upload-large-folder tool 11 days ago
home--work--minzijun_rl_output_2--checkpoints--verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_no_shuffle--global_step_90--actor--huggingface_vllm_temp_1.0.eval_results.json

1.88 MB

Add files using upload-large-folder tool 11 days ago
home--work--minzijun_rl_output_2--checkpoints--verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_no_shuffle--global_step_90--actor--huggingface_vllm_temp_1.0.jsonl

1.53 MB

Add files using upload-large-folder tool 11 days ago
home--work--minzijun_rl_output_2--checkpoints--verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_no_shuffle--global_step_90--actor--huggingface_vllm_temp_1.0.raw.jsonl

2.05 MB

Add files using upload-large-folder tool 11 days ago