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

11
training_logs/20260525_110326_metrics_job_496421.csv Normal file
View File

@@ -0,0 +1,11 @@
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/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_DaytonaNotFoundError,batch_errors/total_DaytonaNotFoundError,batch_errors/avg_AgentTimeoutError,batch_errors/total_AgentTimeoutError,timing/cleanup_old_checkpoints,timing/save_checkpoints,timing/save_hf_model,batch_errors/avg_DaytonaError,batch_errors/total_DaytonaError,batch_errors/avg_ContextLengthExceededError,batch_errors/total_ContextLengthExceededError
0.0,0,64,512,3,0.2656,0,0.2344,621.6914,2563.8548,1.0,10562,1,1338.5955,0.2422,0.2196,0.2197,-0.0007,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0148,-0.0466,0.0,1.0,0.0,0.0201,0.4898,0.2422,7.1583,79.2762,627.8784,26.8,857.9687,230.0903,0.0496,1.7229,14.7315,75.4634,90.3725,8113.4798,18.0581,75.5904,8003.326,0,27,64,512,30,64,383,1.34375,86,5.96875,382,0.171875,11.0,0.03125,2.0,0.015625,1.0,,,,,,,
0.0,0,64,512,1,1.0,1,1.0,180.2852,3060.8,1.0,7383,1,805.1102,0.0586,0.4541,0.4545,-0.0005,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0039,-0.0311,0.0,1.0,0.0,0.0178,0.25,0.0586,7.4612,79.269,624.4182,27.2,857.9687,233.5505,0.0232,1.1905,4.8432,55.2708,60.2711,351.8545,18.7774,55.4044,271.6141,0,28,64,512,62,63,357,1.328125,85,5.53125,354,0.125,8.0,,,0.046875,3.0,8.3981,16.1295,,,,,
0.0,0,64,512,2,0.6562,0,0.3281,337.166,2777.0806,1.0,8959,1,1036.1541,0.1211,0.1954,0.1956,-0.0004,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0066,-0.0229,0.0,1.0,0.0,0.0141,0.2656,0.1211,7.748,78.3633,621.6158,27.5,857.9687,236.3529,0.0248,1.4652,6.745,58.8652,65.844,7096.5807,19.6954,59.074,7009.5751,0,29,64,512,27,64,394,1.109375,71,6.109375,391,0.296875,19.0,0.015625,1.0,0.046875,3.0,,,,,,,
0.0,0,64,512,3,1.0312,0,0.9844,217.6387,4109.1111,1.0,6682,1,963.5862,0.0527,0.0823,0.0823,-0.0001,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0039,-0.0059,0.0,1.0,0.0,0.0063,0.1875,0.0527,8.0195,78.3764,619.7124,27.8,857.9687,238.2563,0.0198,1.1139,4.882,56.4058,61.4598,2113.6889,19.3704,56.5577,2031.7437,0,30,64,512,86,62,347,0.859375,55,5.40625,346,0.359375,23.0,0.015625,1.0,0.015625,1.0,0.0098,7.9489,6.8782,,,,
0.0,0,64,512,2,0.6562,0,0.4531,504.793,3000.3256,1.0,11279,1,1347.108,0.168,0.1493,0.1494,-0.0004,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0084,-0.0258,0.0,1.0,0.0,0.0125,0.375,0.168,8.424,78.5074,623.5744,27.3,857.9687,234.3943,0.0293,1.8483,9.6408,69.6522,79.4454,5328.8946,18.0982,69.775,5229.501,0,31,64,512,53,63,402,0.59375,38,6.25,400,0.28125,18.0,0.015625,1.0,,,,,,0.015625,1.0,0.015625,1.0
0.0,0,64,512,2,1.0625,0,0.9219,344.2148,3316.5849,1.0,7996,1,1130.5575,0.1035,0.1403,0.1404,-0.0002,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0058,-0.0129,0.0,1.0,0.0,0.0071,0.2031,0.1035,8.5488,78.4227,623.5724,27.3,857.9687,234.3962,0.0352,1.2686,7.9241,64.4317,72.5126,3341.1264,18.3456,64.5529,3248.9975,0,32,64,512,91,61,363,0.609375,39,5.671875,363,0.296875,19.0,,,,,0.0095,8.5021,,,,,
0.0,0,64,512,2,0.6406,0,0.4844,463.8789,2605.3297,1.0,12112,1,1252.9052,0.1777,0.1535,0.1536,-0.0004,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0086,-0.0228,0.0,1.0,0.0,0.0137,0.3438,0.1777,9.5261,78.5966,620.8518,27.6,857.9687,237.1169,0.0312,1.9241,9.2013,67.0619,76.4287,4248.8256,18.1481,67.1959,4152.3235,0,33,64,512,47,62,386,0.828125,53,5.984375,383,0.390625,25.0,0.015625,1.0,0.015625,1.0,,,,,,0.03125,2.0
0.0,0,64,512,2,0.9531,0,0.8438,253.4688,2751.2979,1.0,5515,1,896.1226,0.0918,0.1853,0.1854,-0.0002,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0046,-0.0141,0.0,1.0,0.0,0.0094,0.1875,0.0918,9.5989,78.382,619.3303,27.8,857.9687,238.6384,0.0193,1.0688,6.365,56.4504,62.9483,3744.8018,19.1478,56.5637,3661.6347,0,34,64,512,58,63,393,0.734375,47,6.140625,393,0.21875,14.0,,,,,0.0091,7.552,,,,,
0.0,0,64,512,2,0.6562,0,0.4844,274.5176,2415.5,1.0,6569,1,839.2308,0.1133,0.1238,0.1239,-0.0002,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0051,-0.014,0.0,1.0,0.0,0.0095,0.2188,0.1133,9.9454,78.6008,617.927,28.0,857.9687,240.0417,0.0192,3.6935,5.8429,55.357,61.337,3951.6497,18.6576,55.4746,3867.9608,0,35,64,512,93,59,356,0.5625,36,5.5625,356,0.421875,27.0,,,,,,,6.1902,,,,
0.0,0,64,512,2,1.0156,0,0.7812,376.7695,2069.7527,1.0,4538,1,846.2868,0.1816,0.1047,0.1048,-0.0003,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0082,-0.0196,0.0,1.0,0.0,0.0177,0.2969,0.1816,9.9318,78.4766,616.9151,28.1,857.9687,241.0536,0.018,0.8756,7.5627,54.475,62.1755,4009.2705,18.3501,54.5945,3927.8682,0,36,2,16,0,2,15,0.5,1,7.5,15,,,,,,,0.0083,7.8228,,,,,
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/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_DaytonaNotFoundError batch_errors/total_DaytonaNotFoundError batch_errors/avg_AgentTimeoutError batch_errors/total_AgentTimeoutError timing/cleanup_old_checkpoints timing/save_checkpoints timing/save_hf_model batch_errors/avg_DaytonaError batch_errors/total_DaytonaError batch_errors/avg_ContextLengthExceededError batch_errors/total_ContextLengthExceededError
2 0.0 0 64 512 3 0.2656 0 0.2344 621.6914 2563.8548 1.0 10562 1 1338.5955 0.2422 0.2196 0.2197 -0.0007 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 0.0148 -0.0466 0.0 1.0 0.0 0.0201 0.4898 0.2422 7.1583 79.2762 627.8784 26.8 857.9687 230.0903 0.0496 1.7229 14.7315 75.4634 90.3725 8113.4798 18.0581 75.5904 8003.326 0 27 64 512 30 64 383 1.34375 86 5.96875 382 0.171875 11.0 0.03125 2.0 0.015625 1.0
3 0.0 0 64 512 1 1.0 1 1.0 180.2852 3060.8 1.0 7383 1 805.1102 0.0586 0.4541 0.4545 -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 0.0039 -0.0311 0.0 1.0 0.0 0.0178 0.25 0.0586 7.4612 79.269 624.4182 27.2 857.9687 233.5505 0.0232 1.1905 4.8432 55.2708 60.2711 351.8545 18.7774 55.4044 271.6141 0 28 64 512 62 63 357 1.328125 85 5.53125 354 0.125 8.0 0.046875 3.0 8.3981 16.1295
4 0.0 0 64 512 2 0.6562 0 0.3281 337.166 2777.0806 1.0 8959 1 1036.1541 0.1211 0.1954 0.1956 -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 0.0066 -0.0229 0.0 1.0 0.0 0.0141 0.2656 0.1211 7.748 78.3633 621.6158 27.5 857.9687 236.3529 0.0248 1.4652 6.745 58.8652 65.844 7096.5807 19.6954 59.074 7009.5751 0 29 64 512 27 64 394 1.109375 71 6.109375 391 0.296875 19.0 0.015625 1.0 0.046875 3.0
5 0.0 0 64 512 3 1.0312 0 0.9844 217.6387 4109.1111 1.0 6682 1 963.5862 0.0527 0.0823 0.0823 -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 0.0039 -0.0059 0.0 1.0 0.0 0.0063 0.1875 0.0527 8.0195 78.3764 619.7124 27.8 857.9687 238.2563 0.0198 1.1139 4.882 56.4058 61.4598 2113.6889 19.3704 56.5577 2031.7437 0 30 64 512 86 62 347 0.859375 55 5.40625 346 0.359375 23.0 0.015625 1.0 0.015625 1.0 0.0098 7.9489 6.8782
6 0.0 0 64 512 2 0.6562 0 0.4531 504.793 3000.3256 1.0 11279 1 1347.108 0.168 0.1493 0.1494 -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 0.0084 -0.0258 0.0 1.0 0.0 0.0125 0.375 0.168 8.424 78.5074 623.5744 27.3 857.9687 234.3943 0.0293 1.8483 9.6408 69.6522 79.4454 5328.8946 18.0982 69.775 5229.501 0 31 64 512 53 63 402 0.59375 38 6.25 400 0.28125 18.0 0.015625 1.0 0.015625 1.0 0.015625 1.0
7 0.0 0 64 512 2 1.0625 0 0.9219 344.2148 3316.5849 1.0 7996 1 1130.5575 0.1035 0.1403 0.1404 -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 0.0058 -0.0129 0.0 1.0 0.0 0.0071 0.2031 0.1035 8.5488 78.4227 623.5724 27.3 857.9687 234.3962 0.0352 1.2686 7.9241 64.4317 72.5126 3341.1264 18.3456 64.5529 3248.9975 0 32 64 512 91 61 363 0.609375 39 5.671875 363 0.296875 19.0 0.0095 8.5021
8 0.0 0 64 512 2 0.6406 0 0.4844 463.8789 2605.3297 1.0 12112 1 1252.9052 0.1777 0.1535 0.1536 -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 0.0086 -0.0228 0.0 1.0 0.0 0.0137 0.3438 0.1777 9.5261 78.5966 620.8518 27.6 857.9687 237.1169 0.0312 1.9241 9.2013 67.0619 76.4287 4248.8256 18.1481 67.1959 4152.3235 0 33 64 512 47 62 386 0.828125 53 5.984375 383 0.390625 25.0 0.015625 1.0 0.015625 1.0 0.03125 2.0
9 0.0 0 64 512 2 0.9531 0 0.8438 253.4688 2751.2979 1.0 5515 1 896.1226 0.0918 0.1853 0.1854 -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 0.0046 -0.0141 0.0 1.0 0.0 0.0094 0.1875 0.0918 9.5989 78.382 619.3303 27.8 857.9687 238.6384 0.0193 1.0688 6.365 56.4504 62.9483 3744.8018 19.1478 56.5637 3661.6347 0 34 64 512 58 63 393 0.734375 47 6.140625 393 0.21875 14.0 0.0091 7.552
10 0.0 0 64 512 2 0.6562 0 0.4844 274.5176 2415.5 1.0 6569 1 839.2308 0.1133 0.1238 0.1239 -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 0.0051 -0.014 0.0 1.0 0.0 0.0095 0.2188 0.1133 9.9454 78.6008 617.927 28.0 857.9687 240.0417 0.0192 3.6935 5.8429 55.357 61.337 3951.6497 18.6576 55.4746 3867.9608 0 35 64 512 93 59 356 0.5625 36 5.5625 356 0.421875 27.0 6.1902
11 0.0 0 64 512 2 1.0156 0 0.7812 376.7695 2069.7527 1.0 4538 1 846.2868 0.1816 0.1047 0.1048 -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 0.0082 -0.0196 0.0 1.0 0.0 0.0177 0.2969 0.1816 9.9318 78.4766 616.9151 28.1 857.9687 241.0536 0.018 0.8756 7.5627 54.475 62.1755 4009.2705 18.3501 54.5945 3927.8682 0 36 2 16 0 2 15 0.5 1 7.5 15 0.0083 7.8228