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

9
training_logs/20260525_110326_metrics_job_496420.csv Normal file
View File

@@ -0,0 +1,9 @@
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_AgentEnvironmentTimeoutError,batch_errors/total_AgentEnvironmentTimeoutError,batch_errors/avg_DaytonaAuthenticationError,batch_errors/total_DaytonaAuthenticationError,batch_errors/avg_VerifierRuntimeError,batch_errors/total_VerifierRuntimeError,batch_errors/avg_DaytonaNotFoundError,batch_errors/total_DaytonaNotFoundError,timing/cleanup_old_checkpoints,timing/save_checkpoints,timing/save_hf_model,batch_errors/avg_DaytonaError,batch_errors/total_DaytonaError,batch_errors/avg_AgentTimeoutError,batch_errors/total_AgentTimeoutError,batch_errors/avg_ContextLengthExceededError,batch_errors/total_ContextLengthExceededError,batch_errors/avg_AgentSetupTimeoutError,batch_errors/total_AgentSetupTimeoutError,batch_errors/avg_EnvironmentStartTimeoutError,batch_errors/total_EnvironmentStartTimeoutError,batch_errors/avg_VerifierTimeoutError,batch_errors/total_VerifierTimeoutError,batch_errors/avg_OSError,batch_errors/total_OSError
0.0,0,64,512,1,0.0781,0,0.0781,653.5195,2983.9464,1.0,5734,1,1308.6167,0.2188,0.1993,0.1994,-0.0007,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0182,-0.0471,0.0,1.0,0.0,0.0159,0.4407,0.2188,5.3781,78.0601,578.2307,32.6,857.9687,279.738,0.1498,1.2614,15.3459,70.951,86.6201,8067.2067,17.8581,71.1238,7961.4669,0,19,64,512,41,63,350,5.46875,350,1.765625,113,0.109375,7.0,0.015625,1.0,,,,,,,,,,,,,,,,,
0.0,0,64,512,1,0.9844,0,0.9844,239.9746,2985.2683,1.0,7404,1,907.8881,0.0801,0.189,0.1892,-0.0003,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0065,-0.0203,0.0,1.0,0.0,0.0128,0.2031,0.0801,6.1016,78.1429,575.9431,32.9,857.9687,282.0256,0.0214,1.1741,6.3743,55.4754,61.9992,3380.5934,20.0199,55.6031,3297.3986,0,20,64,512,51,64,338,5.25,336,1.65625,106,0.25,16.0,0.015625,1.0,14.3752,21.9845,6.5064,0.015625,1.0,0.015625,1.0,,,,,,,,,,
0.0,0,64,512,2,0.5156,0,0.3906,315.1094,3154.4118,1.0,9754,1,1083.8644,0.0996,0.2996,0.2998,-0.0005,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.008,-0.032,0.0,1.0,0.0,0.0127,0.3281,0.0996,7.1946,78.3005,574.6356,33.0,857.9687,283.3331,0.028,1.3808,8.0318,63.7157,71.9046,4118.8329,18.1954,63.8445,4027.3507,0,21,64,512,36,64,375,5.8125,372,1.375,88,0.203125,13.0,,,,,,,,0.03125,2.0,0.015625,1.0,,,,,,,,
0.0,0,64,512,2,0.9375,0,0.8125,291.4688,4132.1111,1.0,9690,1,1175.4698,0.0703,0.3601,0.3603,-0.0004,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0069,-0.0247,0.0,1.0,0.0,0.0179,0.25,0.0703,7.7303,78.4548,578.4616,32.6,857.9687,279.5071,0.0229,1.429,6.5012,63.062,69.7119,5101.1025,18.1771,63.1874,5011.7831,0,22,64,512,48,64,397,6.09375,390,0.921875,59,0.125,8.0,,,0.0075,8.179,,,,0.078125,5.0,0.03125,2.0,,,,,,,,
0.0,0,64,512,2,1.0469,0,0.9375,275.9121,2933.3958,1.0,6046,1,913.748,0.0938,0.2557,0.2558,-0.0003,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0063,-0.0223,0.0,1.0,0.0,0.0135,0.2656,0.0938,8.0687,78.5605,580.3864,32.4,857.9687,277.5823,0.0178,0.9376,6.7391,56.9606,63.8352,2467.0192,19.0252,57.0779,2383.2198,0,23,64,512,40,63,411,6.40625,410,0.671875,43,0.265625,17.0,0.015625,1.0,,,,,,0.015625,1.0,,,,,,,,,,
0.0,0,64,512,2,1.0938,0,0.6562,288.5996,3682.275,1.0,12853,1,1174.4942,0.0781,0.0673,0.0674,-0.0001,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0057,-0.0049,0.0,1.0,0.0,0.0038,0.2344,0.0781,9.5992,78.8051,579.6128,32.4,857.9687,278.3559,0.0326,1.8242,7.2937,60.7161,68.1634,6306.534,19.4669,60.8368,6217.079,0,24,65,520,28,65,417,6.3538461538461535,413,0.9076923076923077,59,0.18461538461538463,12.0,,,0.0078,7.3895,,,,0.03076923076923077,2.0,0.015384615384615385,1.0,0.06153846153846154,4.0,0.015384615384615385,1.0,,,,
0.0,0,64,512,1,1.0,1,1.0,246.5586,4491.2143,1.0,12979,1,1246.6552,0.0547,0.2752,0.2754,-0.0002,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0042,-0.0133,0.0,1.0,0.0,0.0082,0.2188,0.0547,11.0213,91.3057,577.4506,32.7,857.9687,280.5181,0.0334,187.2975,10.0277,62.1765,72.3976,4522.0533,18.6719,62.3361,4243.6845,0,25,69,552,29,68,458,6.594202898550725,455,0.7391304347826086,51,0.13043478260869565,9.0,0.014492753623188406,1.0,,,5.8497,,,,,0.043478260869565216,3.0,0.028985507246376812,2.0,,,0.014492753623188406,1.0,0.014492753623188406,1.0
0.0,0,64,512,2,1.0938,0,0.6406,164.248,3096.6667,1.0,12519,1,866.242,0.0527,0.0251,0.0252,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0035,-0.0026,0.0,1.0,0.0,0.0064,0.1875,0.0527,12.0359,94.4252,576.9232,32.8,857.9687,281.0455,0.0497,1.8339,5.7861,53.1165,59.0761,6927.7034,19.1025,53.24,6847.6862,0,26,10,80,1,10,74,7.4,74,0.5,5,,,,,0.0131,8.0356,,,,,,,,,,,,,,,
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_AgentEnvironmentTimeoutError batch_errors/total_AgentEnvironmentTimeoutError batch_errors/avg_DaytonaAuthenticationError batch_errors/total_DaytonaAuthenticationError batch_errors/avg_VerifierRuntimeError batch_errors/total_VerifierRuntimeError batch_errors/avg_DaytonaNotFoundError batch_errors/total_DaytonaNotFoundError timing/cleanup_old_checkpoints timing/save_checkpoints timing/save_hf_model batch_errors/avg_DaytonaError batch_errors/total_DaytonaError batch_errors/avg_AgentTimeoutError batch_errors/total_AgentTimeoutError batch_errors/avg_ContextLengthExceededError batch_errors/total_ContextLengthExceededError batch_errors/avg_AgentSetupTimeoutError batch_errors/total_AgentSetupTimeoutError batch_errors/avg_EnvironmentStartTimeoutError batch_errors/total_EnvironmentStartTimeoutError batch_errors/avg_VerifierTimeoutError batch_errors/total_VerifierTimeoutError batch_errors/avg_OSError batch_errors/total_OSError
2 0.0 0 64 512 1 0.0781 0 0.0781 653.5195 2983.9464 1.0 5734 1 1308.6167 0.2188 0.1993 0.1994 -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 0.0182 -0.0471 0.0 1.0 0.0 0.0159 0.4407 0.2188 5.3781 78.0601 578.2307 32.6 857.9687 279.738 0.1498 1.2614 15.3459 70.951 86.6201 8067.2067 17.8581 71.1238 7961.4669 0 19 64 512 41 63 350 5.46875 350 1.765625 113 0.109375 7.0 0.015625 1.0
3 0.0 0 64 512 1 0.9844 0 0.9844 239.9746 2985.2683 1.0 7404 1 907.8881 0.0801 0.189 0.1892 -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 0.0065 -0.0203 0.0 1.0 0.0 0.0128 0.2031 0.0801 6.1016 78.1429 575.9431 32.9 857.9687 282.0256 0.0214 1.1741 6.3743 55.4754 61.9992 3380.5934 20.0199 55.6031 3297.3986 0 20 64 512 51 64 338 5.25 336 1.65625 106 0.25 16.0 0.015625 1.0 14.3752 21.9845 6.5064 0.015625 1.0 0.015625 1.0
4 0.0 0 64 512 2 0.5156 0 0.3906 315.1094 3154.4118 1.0 9754 1 1083.8644 0.0996 0.2996 0.2998 -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 0.008 -0.032 0.0 1.0 0.0 0.0127 0.3281 0.0996 7.1946 78.3005 574.6356 33.0 857.9687 283.3331 0.028 1.3808 8.0318 63.7157 71.9046 4118.8329 18.1954 63.8445 4027.3507 0 21 64 512 36 64 375 5.8125 372 1.375 88 0.203125 13.0 0.03125 2.0 0.015625 1.0
5 0.0 0 64 512 2 0.9375 0 0.8125 291.4688 4132.1111 1.0 9690 1 1175.4698 0.0703 0.3601 0.3603 -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 0.0069 -0.0247 0.0 1.0 0.0 0.0179 0.25 0.0703 7.7303 78.4548 578.4616 32.6 857.9687 279.5071 0.0229 1.429 6.5012 63.062 69.7119 5101.1025 18.1771 63.1874 5011.7831 0 22 64 512 48 64 397 6.09375 390 0.921875 59 0.125 8.0 0.0075 8.179 0.078125 5.0 0.03125 2.0
6 0.0 0 64 512 2 1.0469 0 0.9375 275.9121 2933.3958 1.0 6046 1 913.748 0.0938 0.2557 0.2558 -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 0.0063 -0.0223 0.0 1.0 0.0 0.0135 0.2656 0.0938 8.0687 78.5605 580.3864 32.4 857.9687 277.5823 0.0178 0.9376 6.7391 56.9606 63.8352 2467.0192 19.0252 57.0779 2383.2198 0 23 64 512 40 63 411 6.40625 410 0.671875 43 0.265625 17.0 0.015625 1.0 0.015625 1.0
7 0.0 0 64 512 2 1.0938 0 0.6562 288.5996 3682.275 1.0 12853 1 1174.4942 0.0781 0.0673 0.0674 -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 0.0057 -0.0049 0.0 1.0 0.0 0.0038 0.2344 0.0781 9.5992 78.8051 579.6128 32.4 857.9687 278.3559 0.0326 1.8242 7.2937 60.7161 68.1634 6306.534 19.4669 60.8368 6217.079 0 24 65 520 28 65 417 6.3538461538461535 413 0.9076923076923077 59 0.18461538461538463 12.0 0.0078 7.3895 0.03076923076923077 2.0 0.015384615384615385 1.0 0.06153846153846154 4.0 0.015384615384615385 1.0
8 0.0 0 64 512 1 1.0 1 1.0 246.5586 4491.2143 1.0 12979 1 1246.6552 0.0547 0.2752 0.2754 -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 0.0042 -0.0133 0.0 1.0 0.0 0.0082 0.2188 0.0547 11.0213 91.3057 577.4506 32.7 857.9687 280.5181 0.0334 187.2975 10.0277 62.1765 72.3976 4522.0533 18.6719 62.3361 4243.6845 0 25 69 552 29 68 458 6.594202898550725 455 0.7391304347826086 51 0.13043478260869565 9.0 0.014492753623188406 1.0 5.8497 0.043478260869565216 3.0 0.028985507246376812 2.0 0.014492753623188406 1.0 0.014492753623188406 1.0
9 0.0 0 64 512 2 1.0938 0 0.6406 164.248 3096.6667 1.0 12519 1 866.242 0.0527 0.0251 0.0252 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0035 -0.0026 0.0 1.0 0.0 0.0064 0.1875 0.0527 12.0359 94.4252 576.9232 32.8 857.9687 281.0455 0.0497 1.8339 5.7861 53.1165 59.0761 6927.7034 19.1025 53.24 6847.6862 0 26 10 80 1 10 74 7.4 74 0.5 5 0.0131 8.0356