laion/a3-rl-DCAgent_selfinstruct-naive-sandboxes-2-verified-70-8B
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_selfinstruct-naive-sandboxes-2-verified-70-8B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-07 10:27:18 +08:00
commit 3e52217125
33 changed files with 226712 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
training_logs/20260604_123153_metrics_job_567548.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/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_RewardFileNotFoundError,batch_errors/total_RewardFileNotFoundError,timing/cleanup_old_checkpoints,timing/save_checkpoints,batch_errors/avg_DaytonaValidationError,batch_errors/total_DaytonaValidationError,batch_errors/avg_ContextLengthExceededError,batch_errors/total_ContextLengthExceededError,batch_errors/avg_RuntimeError,batch_errors/total_RuntimeError,batch_errors/avg_DaytonaError,batch_errors/total_DaytonaError,batch_errors/avg_AgentTimeoutError,batch_errors/total_AgentTimeoutError,batch_errors/avg_VerifierTimeoutError,batch_errors/total_VerifierTimeoutError,timing/save_hf_model,batch_errors/avg_VerifierOutputParseError,batch_errors/total_VerifierOutputParseError,batch_errors/avg_DaytonaNotFoundError,batch_errors/total_DaytonaNotFoundError
0.0,0,64,512,0,0.0,0,0.0,3631.0469,3316.3012,3953.2569,25303,1,3243.0733,0.5059,-0.0087,0.0861,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.154,-0.0,0.0,1.0,0.0,0.0146,0.625,0.5059,10.7936,50.364,633.8085,26.1,857.9676,224.1591,0.1114,3.6373,28.9658,151.5911,180.8148,1358.0963,18.6186,151.7373,1155.0253,0,1,121,968,939,6,29,0.30578512396694213,37,,,,,,,,,,,,,,,,,,,
0.0,0,64,512,1,0.7969,0,0.7969,4822.3672,4358.4062,5286.3281,25740,1,3816.7518,0.5,-0.0131,0.1439,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1522,0.0,0.0,1.0,0.0,0.0203,0.6719,0.5,11.4775,50.4393,624.6882,27.2,857.9676,233.2794,0.0519,4.284,32.9178,189.316,222.548,833.5217,19.8811,189.578,586.8065,0,2,58,464,439,5,25,0.43103448275862066,25,38.5904,48.4066,,,,,,,,,,,,,,,,,
0.0,0,64,512,2,1.3438,0,0.875,6234.4707,5933.786,6452.138,29898,1,5603.3019,0.4199,0.0118,0.1815,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1483,0.0,0.0,1.0,0.0,0.019,0.5938,0.4199,13.2484,50.647,630.5422,26.5,857.9676,227.4254,0.0614,4.581,59.1585,286.7886,346.2501,703.0723,19.4633,287.0298,332.7757,0,3,62,496,461,8,28,0.2903225806451613,18,,,0.11290322580645161,7.0,0.16129032258064516,10.0,,,,,,,,,,,,,
0.0,0,64,512,3,1.7031,0,0.8438,6754.2012,6667.6059,6828.2464,30918,1,6199.201,0.4609,-0.0051,0.1719,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1546,0.0,0.0,1.0,0.0,0.0208,0.6406,0.4609,13.3757,50.8519,626.7498,26.9,857.9676,231.2178,0.0647,4.8313,51.8113,299.0531,351.1909,923.9643,19.7377,299.3145,548.2019,0,4,54,432,310,24,117,1.4259259259259258,77,0.0067,11.238,0.018518518518518517,1.0,1.0555555555555556,57.0,0.018518518518518517,1.0,0.07407407407407407,4.0,0.018518518518518517,1.0,0.05555555555555555,3.0,,,,,
0.0,0,64,512,4,2.6406,1,1.0,6037.8184,7489.2791,5303.55,31319,1,7148.2511,0.3359,0.0173,0.1494,-0.0001,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1177,-0.0041,0.0,1.0,0.0,0.0141,0.4531,0.3359,13.5831,51.1094,624.3487,27.2,857.9676,233.6189,0.0632,4.8082,51.5733,303.1749,355.0612,609.8127,19.9157,303.4245,230.0243,0,5,58,464,389,20,75,0.3793103448275862,22,,,,,1.0,58.0,,,,,0.05172413793103448,3.0,,,7.5975,0.13793103448275862,8.0,,
0.0,0,64,512,5,3.0469,1,1.0,6446.5898,7161.3189,6042.2324,31463,1,6726.1259,0.3613,0.0237,0.1225,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1422,-0.0,0.0,1.0,0.0,0.0174,0.5,0.3613,14.5126,51.5042,634.199,26.1,857.9676,223.7686,0.0641,4.8218,47.3073,311.2799,358.8908,528.5257,19.4415,311.5191,145.3683,0,6,55,440,378,14,46,0.2909090909090909,16,0.0069,9.3271,,,0.43636363636363634,24.0,,,0.10909090909090909,6.0,0.03636363636363636,2.0,0.14545454545454545,8.0,,,,0.14545454545454545,8.0
0.0,0,64,512,6,2.8438,1,1.0,5989.127,6446.3918,5759.824,30379,1,5927.6954,0.334,0.0071,0.2061,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1469,-0.0028,0.0,1.0,0.0,0.0169,0.4844,0.334,14.6947,51.7031,630.6147,26.5,857.9676,227.3529,0.0656,4.6023,46.2763,268.8931,315.4526,589.5032,20.6408,269.1104,248.8046,0,7,53,424,336,15,87,1.3018867924528301,69,,,,,0.4339622641509434,23.0,0.018867924528301886,1.0,0.018867924528301886,1.0,0.03773584905660377,2.0,,,,,,,
0.0,0,64,512,7,2.8125,0,0.9375,5809.7773,6972.8086,5007.5545,30602,1,6322.6044,0.4082,0.0127,0.1764,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1395,-0.0,0.0,1.0,0.0,0.0182,0.5312,0.4082,14.9265,51.8948,629.9464,26.6,857.9676,228.0212,0.0612,5.115,50.7488,301.5099,352.5549,605.9063,19.7309,301.7446,228.5022,0,8,60,480,417,18,63,0.3,18,0.0077,9.0045,,,0.6333333333333333,38.0,,,,,0.11666666666666667,7.0,,,,,,,
0.0,0,64,512,7,2.9688,0,0.9688,5550.0059,5062.7014,5740.6902,27434,1,5458.1306,0.2812,0.0007,0.1828,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.147,0.0,0.0,1.0,0.0,0.0205,0.4844,0.2812,14.893,51.924,626.8531,26.9,857.9676,231.1145,0.0634,4.1708,43.4535,247.6858,291.4212,687.7597,19.8574,247.9039,372.3071,0,9,57,456,384,18,70,0.5789473684210527,33,,,,,0.6491228070175439,37.0,,,,,0.10526315789473684,6.0,0.12280701754385964,7.0,,,,,
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_RewardFileNotFoundError batch_errors/total_RewardFileNotFoundError timing/cleanup_old_checkpoints timing/save_checkpoints batch_errors/avg_DaytonaValidationError batch_errors/total_DaytonaValidationError batch_errors/avg_ContextLengthExceededError batch_errors/total_ContextLengthExceededError batch_errors/avg_RuntimeError batch_errors/total_RuntimeError batch_errors/avg_DaytonaError batch_errors/total_DaytonaError batch_errors/avg_AgentTimeoutError batch_errors/total_AgentTimeoutError batch_errors/avg_VerifierTimeoutError batch_errors/total_VerifierTimeoutError timing/save_hf_model batch_errors/avg_VerifierOutputParseError batch_errors/total_VerifierOutputParseError batch_errors/avg_DaytonaNotFoundError batch_errors/total_DaytonaNotFoundError
2 0.0 0 64 512 0 0.0 0 0.0 3631.0469 3316.3012 3953.2569 25303 1 3243.0733 0.5059 -0.0087 0.0861 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.154 -0.0 0.0 1.0 0.0 0.0146 0.625 0.5059 10.7936 50.364 633.8085 26.1 857.9676 224.1591 0.1114 3.6373 28.9658 151.5911 180.8148 1358.0963 18.6186 151.7373 1155.0253 0 1 121 968 939 6 29 0.30578512396694213 37
3 0.0 0 64 512 1 0.7969 0 0.7969 4822.3672 4358.4062 5286.3281 25740 1 3816.7518 0.5 -0.0131 0.1439 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1522 0.0 0.0 1.0 0.0 0.0203 0.6719 0.5 11.4775 50.4393 624.6882 27.2 857.9676 233.2794 0.0519 4.284 32.9178 189.316 222.548 833.5217 19.8811 189.578 586.8065 0 2 58 464 439 5 25 0.43103448275862066 25 38.5904 48.4066
4 0.0 0 64 512 2 1.3438 0 0.875 6234.4707 5933.786 6452.138 29898 1 5603.3019 0.4199 0.0118 0.1815 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1483 0.0 0.0 1.0 0.0 0.019 0.5938 0.4199 13.2484 50.647 630.5422 26.5 857.9676 227.4254 0.0614 4.581 59.1585 286.7886 346.2501 703.0723 19.4633 287.0298 332.7757 0 3 62 496 461 8 28 0.2903225806451613 18 0.11290322580645161 7.0 0.16129032258064516 10.0
5 0.0 0 64 512 3 1.7031 0 0.8438 6754.2012 6667.6059 6828.2464 30918 1 6199.201 0.4609 -0.0051 0.1719 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1546 0.0 0.0 1.0 0.0 0.0208 0.6406 0.4609 13.3757 50.8519 626.7498 26.9 857.9676 231.2178 0.0647 4.8313 51.8113 299.0531 351.1909 923.9643 19.7377 299.3145 548.2019 0 4 54 432 310 24 117 1.4259259259259258 77 0.0067 11.238 0.018518518518518517 1.0 1.0555555555555556 57.0 0.018518518518518517 1.0 0.07407407407407407 4.0 0.018518518518518517 1.0 0.05555555555555555 3.0
6 0.0 0 64 512 4 2.6406 1 1.0 6037.8184 7489.2791 5303.55 31319 1 7148.2511 0.3359 0.0173 0.1494 -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 0.1177 -0.0041 0.0 1.0 0.0 0.0141 0.4531 0.3359 13.5831 51.1094 624.3487 27.2 857.9676 233.6189 0.0632 4.8082 51.5733 303.1749 355.0612 609.8127 19.9157 303.4245 230.0243 0 5 58 464 389 20 75 0.3793103448275862 22 1.0 58.0 0.05172413793103448 3.0 7.5975 0.13793103448275862 8.0
7 0.0 0 64 512 5 3.0469 1 1.0 6446.5898 7161.3189 6042.2324 31463 1 6726.1259 0.3613 0.0237 0.1225 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1422 -0.0 0.0 1.0 0.0 0.0174 0.5 0.3613 14.5126 51.5042 634.199 26.1 857.9676 223.7686 0.0641 4.8218 47.3073 311.2799 358.8908 528.5257 19.4415 311.5191 145.3683 0 6 55 440 378 14 46 0.2909090909090909 16 0.0069 9.3271 0.43636363636363634 24.0 0.10909090909090909 6.0 0.03636363636363636 2.0 0.14545454545454545 8.0 0.14545454545454545 8.0
8 0.0 0 64 512 6 2.8438 1 1.0 5989.127 6446.3918 5759.824 30379 1 5927.6954 0.334 0.0071 0.2061 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1469 -0.0028 0.0 1.0 0.0 0.0169 0.4844 0.334 14.6947 51.7031 630.6147 26.5 857.9676 227.3529 0.0656 4.6023 46.2763 268.8931 315.4526 589.5032 20.6408 269.1104 248.8046 0 7 53 424 336 15 87 1.3018867924528301 69 0.4339622641509434 23.0 0.018867924528301886 1.0 0.018867924528301886 1.0 0.03773584905660377 2.0
9 0.0 0 64 512 7 2.8125 0 0.9375 5809.7773 6972.8086 5007.5545 30602 1 6322.6044 0.4082 0.0127 0.1764 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1395 -0.0 0.0 1.0 0.0 0.0182 0.5312 0.4082 14.9265 51.8948 629.9464 26.6 857.9676 228.0212 0.0612 5.115 50.7488 301.5099 352.5549 605.9063 19.7309 301.7446 228.5022 0 8 60 480 417 18 63 0.3 18 0.0077 9.0045 0.6333333333333333 38.0 0.11666666666666667 7.0
10 0.0 0 64 512 7 2.9688 0 0.9688 5550.0059 5062.7014 5740.6902 27434 1 5458.1306 0.2812 0.0007 0.1828 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.147 0.0 0.0 1.0 0.0 0.0205 0.4844 0.2812 14.893 51.924 626.8531 26.9 857.9676 231.1145 0.0634 4.1708 43.4535 247.6858 291.4212 687.7597 19.8574 247.9039 372.3071 0 9 57 456 384 18 70 0.5789473684210527 33 0.6491228070175439 37.0 0.10526315789473684 6.0 0.12280701754385964 7.0