6.4 KiB
6.4 KiB
| 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 | batch_errors/avg_AgentSetupTimeoutError | batch_errors/total_AgentSetupTimeoutError | batch_errors/avg_VerifierTimeoutError | batch_errors/total_VerifierTimeoutError | batch_errors/avg_DaytonaError | batch_errors/total_DaytonaError | batch_errors/avg_ContextLengthExceededError | batch_errors/total_ContextLengthExceededError | timing/save_hf_model | batch_errors/avg_AgentTimeoutError | batch_errors/total_AgentTimeoutError |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0.0 | 0 | 64 | 512 | 1 | 0.0156 | 0 | 0.0156 | 513.5391 | 2625.2 | 1.0 | 26236 | 1 | 1588.8893 | 0.1953 | 0.1608 | 0.1609 | -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 | 0.0083 | -0.0291 | 0.0 | 1.0 | 0.0 | 0.0178 | 0.4444 | 0.1953 | 12.0642 | 78.6154 | 606.7097 | 29.3 | 857.9687 | 251.259 | 0.1923 | 3.5931 | 15.4184 | 73.4268 | 89.2021 | 8145.718 | 17.602 | 73.591 | 8035.3206 | 0 | 37 | 64 | 512 | 40 | 63 | 367 | 5.734375 | 367 | 1.46875 | 94 | 0.15625 | 10 | 0.015625 | 1.0 | |||||||||||||
| 3 | 0.0 | 0 | 64 | 512 | 1 | 0.9844 | 0 | 0.9844 | 256.4102 | 3270.25 | 1.0 | 8312 | 1 | 1017.874 | 0.0781 | 0.3646 | 0.3647 | -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 | 0.0034 | -0.0217 | 0.0 | 1.0 | 0.0 | 0.0125 | 0.2344 | 0.0781 | 12.0077 | 78.1334 | 605.2178 | 29.5 | 857.9687 | 252.7509 | 0.0239 | 1.3387 | 7.0582 | 59.3834 | 66.5873 | 3328.8664 | 18.4202 | 59.5048 | 3242.5172 | 0 | 38 | 64 | 512 | 86 | 64 | 312 | 4.828125 | 309 | 1.0 | 64 | 0.5625 | 36 | 0.09375 | 6.0 | 11.4426 | 19.0624 | 0.078125 | 5.0 | 0.046875 | 3.0 | 0.015625 | 1.0 | 0.03125 | 2.0 | |||
| 4 | 0.0 | 0 | 64 | 512 | 2 | 0.7656 | 0 | 0.5312 | 408.6738 | 2428.0814 | 1.0 | 8101 | 1 | 1031.8913 | 0.168 | 0.3035 | 0.3037 | -0.0008 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0079 | -0.0498 | 0.0 | 1.0 | 0.0 | 0.0244 | 0.4375 | 0.168 | 13.3047 | 91.9354 | 606.3735 | 29.3 | 857.9687 | 251.5952 | 0.0241 | 1.2992 | 6.9572 | 60.9637 | 68.0737 | 6397.0696 | 17.4018 | 61.092 | 6310.2938 | 0 | 39 | 68 | 544 | 61 | 67 | 381 | 5.573529411764706 | 379 | 1.1764705882352942 | 80 | 0.25 | 17 | 0.014705882352941176 | 1.0 | 0.058823529411764705 | 4.0 | 0.014705882352941176 | 1.0 | 0.014705882352941176 | 1.0 | |||||||
| 5 | 0.0 | 0 | 64 | 512 | 3 | 1.2344 | 0 | 0.9688 | 383.9883 | 3215.5902 | 1.0 | 9054 | 1 | 1172.8826 | 0.1191 | 0.181 | 0.1811 | -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 | 0.0055 | -0.0256 | 0.0 | 1.0 | 0.0 | 0.0197 | 0.3281 | 0.1191 | 14.0406 | 92.0868 | 605.7397 | 29.4 | 857.9687 | 252.229 | 0.0354 | 1.6468 | 7.3746 | 62.4563 | 69.9967 | 5420.0066 | 17.7311 | 62.5862 | 5330.6236 | 0 | 40 | 64 | 512 | 64 | 64 | 399 | 6.234375 | 399 | 0.546875 | 35 | 0.203125 | 13 | 0.015625 | 1.0 | 0.0079 | 8.9118 | 6.6659 | ||||||||||
| 6 | 0.0 | 0 | 64 | 512 | 4 | 1.0781 | 0 | 0.8281 | 315.2949 | 2596.4677 | 1.0 | 6019 | 1 | 911.6647 | 0.1211 | 0.075 | 0.0751 | -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 | 0.006 | -0.0107 | 0.0 | 1.0 | 0.0 | 0.01 | 0.2812 | 0.1211 | 14.3649 | 92.0377 | 605.8729 | 29.4 | 857.9687 | 252.0958 | 0.0196 | 1.2515 | 6.8124 | 57.2361 | 64.2337 | 2226.1873 | 17.7717 | 57.4013 | 2142.928 | 0 | 41 | 60 | 480 | 76 | 57 | 352 | 5.866666666666666 | 352 | 0.55 | 33 | 0.3 | 18 | 0.016666666666666666 | 1.0 | |||||||||||||
| 7 | 0.0 | 0 | 64 | 512 | 2 | 1.1562 | 0 | 0.8594 | 350.4609 | 2294.8974 | 1.0 | 6096 | 1 | 918.4495 | 0.1523 | 0.156 | 0.1561 | -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 | 0.007 | -0.0193 | 0.0 | 1.0 | 0.0 | 0.0108 | 0.3281 | 0.1523 | 16.0237 | 92.0465 | 604.1669 | 29.6 | 857.9687 | 253.8018 | 0.0281 | 1.007 | 6.8732 | 58.1443 | 65.1695 | 4730.9187 | 18.9548 | 58.2679 | 4645.7861 | 0 | 42 | 65 | 520 | 117 | 60 | 320 | 4.923076923076923 | 320 | 0.7846153846153846 | 51 | 0.4461538461538462 | 29 | 0.03076923076923077 | 2.0 | 0.0079 | 7.5503 | 0.015384615384615385 | 1.0 | |||||||||
| 8 | 0.0 | 0 | 64 | 512 | 3 | 1.1562 | 0 | 0.8594 | 506.7285 | 2214.1026 | 1.0 | 9784 | 1 | 1181.084 | 0.2285 | 0.1962 | 0.1963 | -0.0006 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0097 | -0.0374 | 0.0 | 1.0 | 0.0 | 0.02 | 0.4688 | 0.2285 | 16.5446 | 92.2373 | 608.1587 | 29.1 | 857.9687 | 249.81 | 0.0281 | 1.6023 | 8.6365 | 65.3044 | 74.2194 | 3828.8954 | 19.3517 | 65.5544 | 3733.7211 | 0 | 43 | 63 | 504 | 57 | 63 | 380 | 6.0 | 378 | 0.7619047619047619 | 48 | 0.2857142857142857 | 18 | 0.015873015873015872 | 1.0 | 0.031746031746031744 | 2.0 | |||||||||||
| 9 | 0.0 | 0 | 64 | 512 | 3 | 1.2812 | 0 | 0.875 | 384.8477 | 3448.8947 | 1.0 | 11922 | 1 | 1321.23 | 0.1113 | 0.1286 | 0.1287 | -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 | 0.0052 | -0.0139 | 0.0 | 1.0 | 0.0 | 0.0125 | 0.2656 | 0.1113 | 16.9448 | 92.2662 | 606.6965 | 29.3 | 857.9687 | 251.2722 | 0.0323 | 1.7789 | 8.0712 | 63.9146 | 72.1439 | 4075.9496 | 19.0722 | 64.0401 | 3982.9522 | 0 | 44 | 67 | 536 | 61 | 66 | 393 | 5.82089552238806 | 390 | 0.7761194029850746 | 52 | 0.43283582089552236 | 29 | 0.014925373134328358 | 1.0 | 0.0083 | 7.3633 | 0.014925373134328358 | 1.0 | 0.029850746268656716 | 2.0 | |||||||
| 10 | 0.0 | 0 | 64 | 512 | 3 | 1.0625 | 0 | 0.7344 | 289.7832 | 2550.2586 | 1.0 | 9971 | 1 | 1016.4986 | 0.1133 | 0.148 | 0.1481 | -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 | 0.0047 | -0.0191 | 0.0 | 1.0 | 0.0 | 0.0151 | 0.2344 | 0.1133 | 17.2552 | 92.2487 | 605.9093 | 29.4 | 857.9687 | 252.0594 | 0.0283 | 2.2306 | 6.986 | 57.0132 | 64.3289 | 4079.3376 | 19.0583 | 57.3142 | 3993.7175 | 0 | 45 | 18 | 144 | 27 | 18 | 97 | 5.333333333333333 | 96 | 0.6111111111111112 | 11 | 0.5 | 9 | 5.9741 | 0.05555555555555555 | 1.0 |