laion/a3-rl-DCAgent_code-contests-noblock-5-8B
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: laion/a3-rl-DCAgent_code-contests-noblock-5-8B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-07 12:29:36 +08:00
commit a508caa68d
55 changed files with 409528 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
training_logs/20260525_110326_metrics_job_485100.csv Normal file
View File

@@ -0,0 +1,10 @@
async/discard_rate,async/discarded_count,async/effective_batch_groups,async/effective_batch_samples,async/staleness_max,async/staleness_mean,async/staleness_min,async/staleness_ratio,generate/avg_num_tokens,generate/avg_tokens_non_zero_rewards,generate/avg_tokens_zero_rewards,generate/max_num_tokens,generate/min_num_tokens,generate/std_num_tokens,loss/avg_final_rewards,loss/avg_raw_advantages,loss/avg_raw_advantages_abs,policy/final_loss,policy/log_ratio_abs_max,policy/log_ratio_abs_mean,policy/log_ratio_abs_p99,policy/log_ratio_abs_pos00,policy/log_ratio_abs_pos10,policy/log_ratio_abs_pos20,policy/log_ratio_abs_pos30,policy/log_ratio_abs_pos40,policy/log_ratio_abs_pos50,policy/log_ratio_abs_pos60,policy/log_ratio_abs_pos70,policy/log_ratio_abs_pos80,policy/log_ratio_abs_pos90,policy/n_tokens_dp_gt_10pct,policy/n_tokens_dp_gt_1pct,policy/n_tokens_dp_gt_50pct,policy/policy_entropy,policy/policy_loss,policy/policy_lr,policy/policy_update_steps,policy/ppo_clip_ratio,policy/raw_grad_norm,reward/avg_pass_at_8,reward/avg_raw_reward,system/process_rss_gb,system/process_vms_gb,system/ram_available_gb,system/ram_percent,system/ram_total_gb,system/ram_used_gb,timing/compute_advantages_and_returns,timing/convert_to_training_input,timing/fwd_logprobs_values_reward,timing/policy_train,timing/run_training,timing/save_hf_model,timing/step,timing/sync_weights,timing/train_critic_and_policy,timing/wait_for_generation_buffer,trainer/epoch,trainer/global_step,batch_errors/total_batches,batch_errors/total_instances,batch_errors/total_successful,batch_errors/total_failed,batch_errors/total_masked,batch_errors/avg_DaytonaAuthenticationError,batch_errors/total_DaytonaAuthenticationError,batch_errors/avg_AgentEnvironmentTimeoutError,batch_errors/total_AgentEnvironmentTimeoutError,batch_errors/avg_VerifierRuntimeError,batch_errors/total_VerifierRuntimeError,batch_errors/avg_DaytonaError,batch_errors/total_DaytonaError,batch_errors/avg_DaytonaNotFoundError,batch_errors/total_DaytonaNotFoundError,timing/cleanup_old_checkpoints,timing/save_checkpoints,batch_errors/avg_AgentTimeoutError,batch_errors/total_AgentTimeoutError
0.0,0,64,512,1,0.0938,0,0.0938,412.1523,2807.8,1.0,7118,1,1116.6463,0.1465,0.2626,0.2628,-0.0005,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.017,-0.0348,0.0,1.0,0.0,0.0117,0.3276,0.1465,5.5805,78.1037,621.3371,27.6,857.9687,236.6316,0.0318,1.4004,10.3685,66.7561,77.3071,6.9408,8132.7122,17.8846,66.9061,8036.1198,0,5,64,512,17,64,376,1.6875,108,5.828125,373,0.125,8,0.046875,3.0,0.046875,3.0,,,,
0.0,0,64,512,1,0.9844,0,0.9844,122.9082,3672.5882,1.0,7301,1,700.1298,0.0332,0.4107,0.411,-0.0003,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0043,-0.016,0.0,1.0,0.0,0.0091,0.1562,0.0332,6.132,78.1099,617.5232,28.0,857.9687,240.4455,0.0258,1.1294,4.1778,49.7199,54.0518,,3465.0549,19.1569,49.8478,3390.7157,0,6,64,512,12,64,390,1.53125,98,6.078125,389,0.171875,11,,,0.015625,1.0,14.3648,22.1469,0.015625,1.0
0.0,0,64,512,2,0.1719,0,0.1406,81.3242,3428.1667,1.0,8024,1,580.4928,0.0234,0.4151,0.4154,-0.0002,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.003,-0.0109,0.0,1.0,0.0,0.0071,0.1406,0.0234,6.3622,78.2129,616.5064,28.1,857.9687,241.4623,0.022,1.147,4.0974,47.8918,52.1402,,3987.006,18.7017,48.0205,3915.0159,0,7,64,512,9,64,412,1.3125,84,6.421875,411,0.09375,6,0.015625,1.0,0.015625,1.0,,,,
0.0,0,64,512,2,0.7969,0,0.7656,53.543,2990.1111,1.0,4963,1,409.6074,0.0176,0.401,0.4013,-0.0001,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.002,-0.0074,0.0,1.0,0.0,0.0064,0.0938,0.0176,6.5256,78.4167,614.7823,28.3,857.9687,243.1863,0.0175,0.8755,3.0976,44.8012,48.0435,,6656.3028,28.5894,44.928,6578.7926,0,8,64,512,12,64,429,1.0625,68,6.640625,425,0.03125,2,0.03125,2.0,0.015625,1.0,0.0078,44.8581,0.03125,2.0
0.0,0,64,512,2,1.0156,1,1.0,83.5977,3525.1667,1.0,7387,1,595.6285,0.0234,0.2611,0.2612,-0.0001,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0032,-0.0059,0.0,1.0,0.0,0.0055,0.125,0.0234,6.8361,78.5227,617.8079,28.0,857.9687,240.1608,0.0187,1.2451,4.908,48.4858,53.5378,,1287.2347,18.8851,48.6107,1213.5661,0,9,64,512,42,64,369,1.515625,97,5.71875,366,0.03125,2,,,0.03125,2.0,,,0.046875,3.0
0.0,0,64,512,2,0.9688,0,0.5,318.5254,3871.7857,1.0,12427,1,1252.0624,0.082,0.403,0.4032,-0.0005,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0093,-0.0298,0.0,1.0,0.0,0.0096,0.2344,0.082,8.9127,78.948,613.9305,28.4,857.9687,244.0382,0.0353,1.8739,8.9165,64.647,73.728,6.0594,6403.6413,18.6729,64.7757,6309.3653,0,10,64,512,40,64,407,0.875,56,6.359375,407,0.140625,9,,,,,0.0087,8.1786,,
0.0,0,64,512,3,1.0312,1,1.0,350.1328,4469.9,1.0,31001,1,1779.2004,0.0781,0.213,0.2131,-0.0002,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.008,-0.015,0.0,1.0,0.0,0.007,0.1719,0.0781,14.811,79.299,605.6735,29.4,857.9687,252.2952,0.0625,4.1888,10.3455,76.4064,86.9738,,1527.2608,18.4561,76.5655,1417.6404,0,11,64,512,41,64,376,1.34375,86,5.828125,373,0.109375,7,0.015625,1.0,0.03125,2.0,,,0.03125,2.0
0.0,0,64,512,2,0.8125,0,0.4844,282.1934,3512.4878,1.0,12815,1,1173.8704,0.0801,0.2652,0.2654,-0.0004,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0088,-0.0229,0.0,1.0,0.0,0.0105,0.25,0.0801,14.8054,78.8495,604.8915,29.5,857.9687,253.0771,0.0379,1.7768,6.4211,60.7211,67.3241,,6140.8745,18.7329,60.8648,6053.0375,0,12,64,512,33,64,421,0.734375,47,6.546875,419,0.125,8,,,0.046875,3.0,0.008,7.973,0.03125,2.0
0.0,0,64,512,3,1.1875,1,1.0,217.332,3357.4242,1.0,6149,1,875.1285,0.0645,0.1964,0.1965,-0.0002,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0069,-0.0111,0.0,1.0,0.0,0.0056,0.2344,0.0645,15.0007,78.8141,604.7684,29.5,857.9687,253.2003,0.0234,0.9449,4.7579,55.747,60.6653,,2012.3998,19.4214,55.8837,1931.3665,0,13,19,152,22,18,102,1.368421052631579,26,5.368421052631579,102,0.10526315789473684,2,,,,,,,,
1 async/discard_rate async/discarded_count async/effective_batch_groups async/effective_batch_samples async/staleness_max async/staleness_mean async/staleness_min async/staleness_ratio generate/avg_num_tokens generate/avg_tokens_non_zero_rewards generate/avg_tokens_zero_rewards generate/max_num_tokens generate/min_num_tokens generate/std_num_tokens loss/avg_final_rewards loss/avg_raw_advantages loss/avg_raw_advantages_abs policy/final_loss policy/log_ratio_abs_max policy/log_ratio_abs_mean policy/log_ratio_abs_p99 policy/log_ratio_abs_pos00 policy/log_ratio_abs_pos10 policy/log_ratio_abs_pos20 policy/log_ratio_abs_pos30 policy/log_ratio_abs_pos40 policy/log_ratio_abs_pos50 policy/log_ratio_abs_pos60 policy/log_ratio_abs_pos70 policy/log_ratio_abs_pos80 policy/log_ratio_abs_pos90 policy/n_tokens_dp_gt_10pct policy/n_tokens_dp_gt_1pct policy/n_tokens_dp_gt_50pct policy/policy_entropy policy/policy_loss policy/policy_lr policy/policy_update_steps policy/ppo_clip_ratio policy/raw_grad_norm reward/avg_pass_at_8 reward/avg_raw_reward system/process_rss_gb system/process_vms_gb system/ram_available_gb system/ram_percent system/ram_total_gb system/ram_used_gb timing/compute_advantages_and_returns timing/convert_to_training_input timing/fwd_logprobs_values_reward timing/policy_train timing/run_training timing/save_hf_model timing/step timing/sync_weights timing/train_critic_and_policy timing/wait_for_generation_buffer trainer/epoch trainer/global_step batch_errors/total_batches batch_errors/total_instances batch_errors/total_successful batch_errors/total_failed batch_errors/total_masked batch_errors/avg_DaytonaAuthenticationError batch_errors/total_DaytonaAuthenticationError batch_errors/avg_AgentEnvironmentTimeoutError batch_errors/total_AgentEnvironmentTimeoutError batch_errors/avg_VerifierRuntimeError batch_errors/total_VerifierRuntimeError batch_errors/avg_DaytonaError batch_errors/total_DaytonaError batch_errors/avg_DaytonaNotFoundError batch_errors/total_DaytonaNotFoundError timing/cleanup_old_checkpoints timing/save_checkpoints batch_errors/avg_AgentTimeoutError batch_errors/total_AgentTimeoutError
2 0.0 0 64 512 1 0.0938 0 0.0938 412.1523 2807.8 1.0 7118 1 1116.6463 0.1465 0.2626 0.2628 -0.0005 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.017 -0.0348 0.0 1.0 0.0 0.0117 0.3276 0.1465 5.5805 78.1037 621.3371 27.6 857.9687 236.6316 0.0318 1.4004 10.3685 66.7561 77.3071 6.9408 8132.7122 17.8846 66.9061 8036.1198 0 5 64 512 17 64 376 1.6875 108 5.828125 373 0.125 8 0.046875 3.0 0.046875 3.0
3 0.0 0 64 512 1 0.9844 0 0.9844 122.9082 3672.5882 1.0 7301 1 700.1298 0.0332 0.4107 0.411 -0.0003 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0043 -0.016 0.0 1.0 0.0 0.0091 0.1562 0.0332 6.132 78.1099 617.5232 28.0 857.9687 240.4455 0.0258 1.1294 4.1778 49.7199 54.0518 3465.0549 19.1569 49.8478 3390.7157 0 6 64 512 12 64 390 1.53125 98 6.078125 389 0.171875 11 0.015625 1.0 14.3648 22.1469 0.015625 1.0
4 0.0 0 64 512 2 0.1719 0 0.1406 81.3242 3428.1667 1.0 8024 1 580.4928 0.0234 0.4151 0.4154 -0.0002 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.003 -0.0109 0.0 1.0 0.0 0.0071 0.1406 0.0234 6.3622 78.2129 616.5064 28.1 857.9687 241.4623 0.022 1.147 4.0974 47.8918 52.1402 3987.006 18.7017 48.0205 3915.0159 0 7 64 512 9 64 412 1.3125 84 6.421875 411 0.09375 6 0.015625 1.0 0.015625 1.0
5 0.0 0 64 512 2 0.7969 0 0.7656 53.543 2990.1111 1.0 4963 1 409.6074 0.0176 0.401 0.4013 -0.0001 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.002 -0.0074 0.0 1.0 0.0 0.0064 0.0938 0.0176 6.5256 78.4167 614.7823 28.3 857.9687 243.1863 0.0175 0.8755 3.0976 44.8012 48.0435 6656.3028 28.5894 44.928 6578.7926 0 8 64 512 12 64 429 1.0625 68 6.640625 425 0.03125 2 0.03125 2.0 0.015625 1.0 0.0078 44.8581 0.03125 2.0
6 0.0 0 64 512 2 1.0156 1 1.0 83.5977 3525.1667 1.0 7387 1 595.6285 0.0234 0.2611 0.2612 -0.0001 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0032 -0.0059 0.0 1.0 0.0 0.0055 0.125 0.0234 6.8361 78.5227 617.8079 28.0 857.9687 240.1608 0.0187 1.2451 4.908 48.4858 53.5378 1287.2347 18.8851 48.6107 1213.5661 0 9 64 512 42 64 369 1.515625 97 5.71875 366 0.03125 2 0.03125 2.0 0.046875 3.0
7 0.0 0 64 512 2 0.9688 0 0.5 318.5254 3871.7857 1.0 12427 1 1252.0624 0.082 0.403 0.4032 -0.0005 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0093 -0.0298 0.0 1.0 0.0 0.0096 0.2344 0.082 8.9127 78.948 613.9305 28.4 857.9687 244.0382 0.0353 1.8739 8.9165 64.647 73.728 6.0594 6403.6413 18.6729 64.7757 6309.3653 0 10 64 512 40 64 407 0.875 56 6.359375 407 0.140625 9 0.0087 8.1786
8 0.0 0 64 512 3 1.0312 1 1.0 350.1328 4469.9 1.0 31001 1 1779.2004 0.0781 0.213 0.2131 -0.0002 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.008 -0.015 0.0 1.0 0.0 0.007 0.1719 0.0781 14.811 79.299 605.6735 29.4 857.9687 252.2952 0.0625 4.1888 10.3455 76.4064 86.9738 1527.2608 18.4561 76.5655 1417.6404 0 11 64 512 41 64 376 1.34375 86 5.828125 373 0.109375 7 0.015625 1.0 0.03125 2.0 0.03125 2.0
9 0.0 0 64 512 2 0.8125 0 0.4844 282.1934 3512.4878 1.0 12815 1 1173.8704 0.0801 0.2652 0.2654 -0.0004 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0088 -0.0229 0.0 1.0 0.0 0.0105 0.25 0.0801 14.8054 78.8495 604.8915 29.5 857.9687 253.0771 0.0379 1.7768 6.4211 60.7211 67.3241 6140.8745 18.7329 60.8648 6053.0375 0 12 64 512 33 64 421 0.734375 47 6.546875 419 0.125 8 0.046875 3.0 0.008 7.973 0.03125 2.0
10 0.0 0 64 512 3 1.1875 1 1.0 217.332 3357.4242 1.0 6149 1 875.1285 0.0645 0.1964 0.1965 -0.0002 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0069 -0.0111 0.0 1.0 0.0 0.0056 0.2344 0.0645 15.0007 78.8141 604.7684 29.5 857.9687 253.2003 0.0234 0.9449 4.7579 55.747 60.6653 2012.3998 19.4214 55.8837 1931.3665 0 13 19 152 22 18 102 1.368421052631579 26 5.368421052631579 102 0.10526315789473684 2