6.2 KiB
6.2 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_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 |