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

8
training_logs/20260525_110326_metrics_job_485101.csv Normal file
View File

@@ -0,0 +1,8 @@
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_DaytonaNotFoundError,batch_errors/total_DaytonaNotFoundError,batch_errors/avg_DaytonaError,batch_errors/total_DaytonaError,batch_errors/avg_VerifierRuntimeError,batch_errors/total_VerifierRuntimeError,batch_errors/avg_AgentTimeoutError,batch_errors/total_AgentTimeoutError,timing/cleanup_old_checkpoints,timing/save_checkpoints,timing/save_hf_model
0.0,0,64,512,1,0.0312,0,0.0312,331.7969,2689.381,1.0,5793,1,965.9963,0.123,0.2187,0.2189,-0.0004,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0119,-0.0249,0.0,1.0,0.0,0.0124,0.2742,0.123,5.3837,78.0531,602.3064,29.8,857.9687,255.6623,0.1194,1.0144,12.9162,57.498,70.6558,8113.5248,18.1367,57.6196,8023.7177,0,13,64,512,19,64,381,1.5625,100,5.890625,377,0.015625,1.0,0.015625,1.0,0.171875,11,0.046875,3.0,,,
0.0,0,64,512,1,0.9062,0,0.9062,97.1699,2592.5263,1.0,5692,1,535.645,0.0371,0.4498,0.4501,-0.0002,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0041,-0.0146,0.0,1.0,0.0,0.0075,0.125,0.0371,5.7223,78.1088,599.2325,30.2,857.9687,258.7362,0.0198,0.9137,4.3069,44.4851,48.9503,6886.3196,18.478,44.6233,6817.976,0,14,64,512,61,64,351,1.34375,86,5.25,336,,,0.046875,3.0,0.21875,14,0.1875,12.0,24.0683,41.284,
0.0,0,64,512,2,1.0469,1,1.0,393.2031,3292.9344,1.0,10838,1,1198.2489,0.1191,0.2169,0.2171,-0.0005,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0124,-0.0307,0.0,1.0,0.0,0.0123,0.375,0.1191,7.4045,78.2452,598.44,30.2,857.9687,259.5287,0.0315,1.6347,7.3081,63.1214,70.5896,791.9402,18.239,63.2496,701.4743,0,15,64,512,61,63,356,1.296875,83,5.53125,354,,,0.015625,1.0,0.1875,12,0.015625,1.0,,,6.9084
0.0,0,64,512,2,1.5625,0,0.7812,346.5215,2901.1148,1.0,13177,1,1177.6427,0.1191,0.2065,0.2066,-0.0003,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0113,-0.0216,0.0,1.0,0.0,0.0089,0.3125,0.1191,8.5541,78.4775,596.4595,30.5,857.9687,261.5092,0.0308,1.904,7.6796,61.4263,69.2639,6575.7601,17.4986,61.5532,6487.0923,0,16,64,512,47,64,359,1.515625,97,5.53125,354,0.0625,4.0,,,0.078125,5,0.078125,5.0,0.0085,7.7753,
0.0,0,64,512,3,1.0625,1,1.0,314.8184,3419.617,1.0,7961,1,1092.2585,0.0918,0.359,0.3591,-0.0005,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0084,-0.0295,0.0,1.0,0.0,0.0108,0.25,0.0918,8.6535,78.4467,598.0707,30.3,857.9687,259.898,0.0216,1.2139,6.2721,60.5518,66.9689,920.1572,17.1829,60.6749,834.7893,0,17,64,512,36,64,404,1.0625,68,6.265625,401,0.03125,2.0,0.015625,1.0,0.03125,2,0.03125,2.0,,,
0.0,0,64,512,2,1.2031,0,0.6094,245.1484,3473.3333,1.0,11370,1,999.9222,0.0703,0.1244,0.1245,-0.0002,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0063,-0.0109,0.0,1.0,0.0,0.0061,0.2344,0.0703,9.0319,78.7547,600.501,30.0,857.9687,257.4677,0.029,1.7294,5.1895,52.9781,58.3217,6610.6145,17.2028,53.1029,6533.3592,0,18,64,512,53,63,421,0.5,32,6.484375,415,0.015625,1.0,0.03125,2.0,0.078125,5,0.0625,4.0,0.0079,7.9661,
0.0,0,64,512,1,1.0,1,1.0,321.1836,3094.0943,1.0,8352,1,1061.5795,0.1035,0.0722,0.0722,-0.0001,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0086,-0.007,0.0,1.0,0.0,0.0041,0.2812,0.1035,9.3094,78.7746,599.7432,30.1,857.9687,258.2255,0.0369,1.3938,6.5872,58.4137,65.1632,1357.7171,17.8468,58.5387,1273.3116,0,19,25,200,21,25,158,0.68,17,6.32,158,,,,,0.16,4,,,,,
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_DaytonaNotFoundError batch_errors/total_DaytonaNotFoundError batch_errors/avg_DaytonaError batch_errors/total_DaytonaError batch_errors/avg_VerifierRuntimeError batch_errors/total_VerifierRuntimeError batch_errors/avg_AgentTimeoutError batch_errors/total_AgentTimeoutError timing/cleanup_old_checkpoints timing/save_checkpoints timing/save_hf_model
2 0.0 0 64 512 1 0.0312 0 0.0312 331.7969 2689.381 1.0 5793 1 965.9963 0.123 0.2187 0.2189 -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 0.0119 -0.0249 0.0 1.0 0.0 0.0124 0.2742 0.123 5.3837 78.0531 602.3064 29.8 857.9687 255.6623 0.1194 1.0144 12.9162 57.498 70.6558 8113.5248 18.1367 57.6196 8023.7177 0 13 64 512 19 64 381 1.5625 100 5.890625 377 0.015625 1.0 0.015625 1.0 0.171875 11 0.046875 3.0
3 0.0 0 64 512 1 0.9062 0 0.9062 97.1699 2592.5263 1.0 5692 1 535.645 0.0371 0.4498 0.4501 -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 0.0041 -0.0146 0.0 1.0 0.0 0.0075 0.125 0.0371 5.7223 78.1088 599.2325 30.2 857.9687 258.7362 0.0198 0.9137 4.3069 44.4851 48.9503 6886.3196 18.478 44.6233 6817.976 0 14 64 512 61 64 351 1.34375 86 5.25 336 0.046875 3.0 0.21875 14 0.1875 12.0 24.0683 41.284
4 0.0 0 64 512 2 1.0469 1 1.0 393.2031 3292.9344 1.0 10838 1 1198.2489 0.1191 0.2169 0.2171 -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 0.0124 -0.0307 0.0 1.0 0.0 0.0123 0.375 0.1191 7.4045 78.2452 598.44 30.2 857.9687 259.5287 0.0315 1.6347 7.3081 63.1214 70.5896 791.9402 18.239 63.2496 701.4743 0 15 64 512 61 63 356 1.296875 83 5.53125 354 0.015625 1.0 0.1875 12 0.015625 1.0 6.9084
5 0.0 0 64 512 2 1.5625 0 0.7812 346.5215 2901.1148 1.0 13177 1 1177.6427 0.1191 0.2065 0.2066 -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 0.0113 -0.0216 0.0 1.0 0.0 0.0089 0.3125 0.1191 8.5541 78.4775 596.4595 30.5 857.9687 261.5092 0.0308 1.904 7.6796 61.4263 69.2639 6575.7601 17.4986 61.5532 6487.0923 0 16 64 512 47 64 359 1.515625 97 5.53125 354 0.0625 4.0 0.078125 5 0.078125 5.0 0.0085 7.7753
6 0.0 0 64 512 3 1.0625 1 1.0 314.8184 3419.617 1.0 7961 1 1092.2585 0.0918 0.359 0.3591 -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 0.0084 -0.0295 0.0 1.0 0.0 0.0108 0.25 0.0918 8.6535 78.4467 598.0707 30.3 857.9687 259.898 0.0216 1.2139 6.2721 60.5518 66.9689 920.1572 17.1829 60.6749 834.7893 0 17 64 512 36 64 404 1.0625 68 6.265625 401 0.03125 2.0 0.015625 1.0 0.03125 2 0.03125 2.0
7 0.0 0 64 512 2 1.2031 0 0.6094 245.1484 3473.3333 1.0 11370 1 999.9222 0.0703 0.1244 0.1245 -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 0.0063 -0.0109 0.0 1.0 0.0 0.0061 0.2344 0.0703 9.0319 78.7547 600.501 30.0 857.9687 257.4677 0.029 1.7294 5.1895 52.9781 58.3217 6610.6145 17.2028 53.1029 6533.3592 0 18 64 512 53 63 421 0.5 32 6.484375 415 0.015625 1.0 0.03125 2.0 0.078125 5 0.0625 4.0 0.0079 7.9661
8 0.0 0 64 512 1 1.0 1 1.0 321.1836 3094.0943 1.0 8352 1 1061.5795 0.1035 0.0722 0.0722 -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 0.0086 -0.007 0.0 1.0 0.0 0.0041 0.2812 0.1035 9.3094 78.7746 599.7432 30.1 857.9687 258.2255 0.0369 1.3938 6.5872 58.4137 65.1632 1357.7171 17.8468 58.5387 1273.3116 0 19 25 200 21 25 158 0.68 17 6.32 158 0.16 4