9.5 KiB
9.5 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/save_hf_model | 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_ContextLengthExceededError | batch_errors/total_ContextLengthExceededError | batch_errors/avg_InvalidChatHistory | batch_errors/total_InvalidChatHistory | batch_errors/avg_AgentTimeoutError | batch_errors/total_AgentTimeoutError | timing/cleanup_old_checkpoints | timing/save_checkpoints | batch_errors/avg_VerifierTimeoutError | batch_errors/total_VerifierTimeoutError | batch_errors/avg_DaytonaAuthenticationError | batch_errors/total_DaytonaAuthenticationError | batch_errors/avg_AgentSetupTimeoutError | batch_errors/total_AgentSetupTimeoutError | batch_errors/avg_DaytonaError | batch_errors/total_DaytonaError |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0.0 | 0 | 64 | 512 | 4 | 0.5469 | 0 | 0.25 | 4862.9727 | 4513.1443 | 5350.1168 | 31704 | 1 | 3892.5586 | 0.582 | 0.0105 | 0.1354 | -0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1296 | -0.0 | 0.0 | 1.0 | 0.0 | 0.0 | 0.6727 | 0.582 | 12.6295 | 50.548 | 561.5298 | 34.6 | 857.9675 | 296.4377 | 0.1256 | 4.65 | 69.6756 | 200.9736 | 271.0452 | 36.4673 | 4741.4969 | 23.1178 | 201.2433 | 4442.6837 | 0 | 65 | 37 | 296 | 277 | 13 | 19 | 0.40540540540540543 | 15 | 0.8918918918918919 | 33 | 0.08108108108108109 | 3.0 | ||||||||||
| 3 | 0.0 | 0 | 64 | 512 | 1 | 1.0 | 1 | 1.0 | 5066.0879 | 4639.2486 | 5299.4955 | 31799 | 1 | 5073.213 | 0.3535 | 0.0067 | 0.1205 | -0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1309 | -0.0 | 0.0 | 1.0 | 0.0 | 0.0 | 0.5 | 0.3535 | 12.7806 | 50.6748 | 627.205 | 26.9 | 857.9675 | 230.7626 | 0.0762 | 4.6149 | 37.9156 | 235.294 | 273.5463 | 605.1264 | 24.0294 | 235.5538 | 302.928 | 0 | 66 | 60 | 480 | 440 | 16 | 29 | 0.15 | 9 | 0.25 | 15 | 0.13333333333333333 | 8.0 | 42.5487 | 50.8663 | 0.18333333333333332 | 11.0 | |||||||
| 4 | 0.0 | 0 | 64 | 512 | 2 | 1.6719 | 0 | 0.9531 | 4734.041 | 5337.0905 | 4314.702 | 31845 | 1 | 3896.281 | 0.4102 | 0.0173 | 0.1281 | -0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1301 | -0.0 | 0.0 | 1.0 | 0.0 | 0.0 | 0.5156 | 0.4102 | 13.7043 | 50.7106 | 622.134 | 27.5 | 857.9675 | 235.8336 | 0.0668 | 4.5589 | 29.9015 | 188.6862 | 218.8452 | 1183.017 | 23.4914 | 188.8764 | 936.117 | 0 | 67 | 63 | 504 | 355 | 47 | 91 | 0.1111111111111111 | 7 | 0.20634920634920634 | 13 | 1.1587301587301588 | 73.0 | 0.3333333333333333 | 21.0 | 0.031746031746031744 | 2.0 | 0.5555555555555556 | 35.0 | |||||
| 5 | 0.0 | 0 | 64 | 512 | 3 | 2.2969 | 0 | 0.9219 | 4292.0527 | 5313.4359 | 3989.5165 | 31752 | 1 | 4965.0243 | 0.2285 | 0.0361 | 0.1284 | -0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1007 | -0.0 | 0.0 | 1.0 | 0.0 | 0.0 | 0.3594 | 0.2285 | 13.7788 | 50.7601 | 620.5532 | 27.7 | 857.9675 | 237.4144 | 0.0656 | 4.7095 | 31.3857 | 214.771 | 246.5058 | 5067.1626 | 19.1151 | 215.0541 | 4796.8269 | 0 | 68 | 61 | 488 | 276 | 57 | 125 | 0.04918032786885246 | 3 | 0.18032786885245902 | 11 | 1.8524590163934427 | 113.0 | 0.0088 | 8.3963 | 0.7868852459016393 | 48.0 | 0.03278688524590164 | 2.0 | 0.6065573770491803 | 37.0 | 0.01639344262295082 | 1.0 | |
| 6 | 0.0 | 0 | 64 | 512 | 4 | 2.0312 | 0 | 0.9844 | 2689.0547 | 4481.0945 | 2097.9143 | 16225 | 1 | 3499.4794 | 0.248 | 0.064 | 0.1772 | -0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.078 | -0.0 | 0.0 | 1.0 | 0.0 | 0.0 | 0.5 | 0.248 | 13.5363 | 50.52 | 618.4584 | 27.9 | 857.9675 | 239.5091 | 0.0562 | 2.4372 | 19.9013 | 140.6377 | 160.7959 | 2845.5649 | 19.1755 | 140.8378 | 2663.1483 | 0 | 69 | 56 | 448 | 218 | 54 | 89 | 0.125 | 7 | 0.07142857142857142 | 4 | 1.8392857142857142 | 103.0 | 2.4464285714285716 | 137.0 | 0.30357142857142855 | 17.0 | |||||||
| 7 | 0.0 | 0 | 64 | 512 | 3 | 1.8125 | 0 | 0.9531 | 1819.6953 | 3456.2381 | 1285.487 | 16720 | 1 | 2446.8912 | 0.2461 | 0.1768 | 0.2232 | -0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0662 | -0.0 | 0.0 | 1.0 | 0.0 | 0.0 | 0.5469 | 0.2461 | 13.6124 | 50.5903 | 620.05 | 27.7 | 857.9675 | 237.9175 | 0.0369 | 2.372 | 14.1649 | 102.8323 | 117.1881 | 8.0763 | 2600.3087 | 18.8825 | 102.9859 | 2461.8638 | 0 | 70 | 58 | 464 | 355 | 32 | 36 | 0.08620689655172414 | 5 | 0.13793103448275862 | 8 | 0.39655172413793105 | 23.0 | 0.0078 | 17.8975 | 1.3620689655172413 | 79.0 | 0.05172413793103448 | 3.0 | 0.017241379310344827 | 1.0 | ||
| 8 | 0.0 | 0 | 64 | 512 | 3 | 1.4375 | 0 | 0.9219 | 3140.1328 | 3793.3929 | 2632.0417 | 31776 | 1 | 3649.7812 | 0.4375 | 0.0669 | 0.1491 | -0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0942 | -0.0 | 0.0 | 1.0 | 0.0 | 0.0 | 0.6094 | 0.4375 | 13.8658 | 50.8432 | 615.5933 | 28.2 | 857.9675 | 242.3742 | 0.0646 | 4.3413 | 26.1997 | 152.3269 | 178.7983 | 1848.2381 | 19.4477 | 152.5336 | 1645.6483 | 0 | 71 | 54 | 432 | 346 | 33 | 32 | 0.1111111111111111 | 6 | 0.2222222222222222 | 12 | 0.42592592592592593 | 23.0 | 0.7962962962962963 | 43.0 | 0.018518518518518517 | 1.0 | 0.3333333333333333 | 18.0 | 0.018518518518518517 | 1.0 | |||
| 9 | 0.0 | 0 | 64 | 512 | 4 | 1.7344 | 0 | 0.9062 | 3757.4688 | 3691.0625 | 3792.253 | 31727 | 1 | 3971.7082 | 0.3438 | 0.0297 | 0.0921 | -0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1108 | -0.0 | 0.0 | 1.0 | 0.0 | 0.0 | 0.4531 | 0.3438 | 13.8605 | 50.8377 | 617.5437 | 28.0 | 857.9675 | 240.4238 | 0.0696 | 4.3975 | 27.0854 | 166.2132 | 193.5822 | 3286.0053 | 18.9345 | 166.4269 | 3069.0865 | 0 | 72 | 64 | 512 | 326 | 56 | 112 | 0.171875 | 11 | 0.1875 | 12 | 1.421875 | 91.0 | 0.008 | 82.4332 | 0.5625 | 36.0 | 0.015625 | 1.0 | 0.578125 | 37.0 | 0.015625 | 1.0 | |
| 10 | 0.0 | 0 | 64 | 512 | 4 | 1.9844 | 0 | 0.9375 | 3025.4746 | 4412.386 | 2628.2186 | 31668 | 1 | 3575.8498 | 0.2227 | 0.0329 | 0.1432 | -0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0848 | -0.0 | 0.0 | 1.0 | 0.0 | 0.0 | 0.3594 | 0.2227 | 13.8521 | 50.8289 | 615.4798 | 28.3 | 857.9675 | 242.4877 | 0.0891 | 4.3699 | 23.2891 | 149.6715 | 173.2579 | 2698.0374 | 18.0666 | 149.8792 | 2502.3368 | 0 | 73 | 60 | 480 | 337 | 49 | 48 | 0.03333333333333333 | 2 | 0.2 | 12 | 0.6166666666666667 | 37.0 | 1.4166666666666667 | 85.0 | 0.016666666666666666 | 1.0 | 0.15 | 9.0 | 0.016666666666666666 | 1.0 | |||
| 11 | 0.0 | 0 | 64 | 512 | 4 | 1.7031 | 0 | 0.9375 | 3082.4863 | 3622.4722 | 2871.1875 | 31787 | 1 | 3677.9858 | 0.2812 | 0.0609 | 0.1265 | -0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0914 | -0.0 | 0.0 | 1.0 | 0.0 | 0.0 | 0.4844 | 0.2812 | 13.8518 | 50.893 | 614.1329 | 28.4 | 857.9675 | 243.8346 | 0.0647 | 4.3386 | 23.0836 | 150.3708 | 173.7147 | 1731.4236 | 19.0162 | 150.566 | 1534.3491 | 0 | 74 | 60 | 480 | 414 | 31 | 29 | 0.06666666666666667 | 4 | 0.3 | 18 | 0.1 | 6.0 | 0.0081 | 8.0639 | 0.5666666666666667 | 34.0 | 0.016666666666666666 | 1.0 | 0.05 | 3.0 | 0.016666666666666666 | 1.0 | |
| 12 | 0.0 | 0 | 64 | 512 | 4 | 1.8281 | 1 | 1.0 | 3949.6445 | 4464.3611 | 3450.7654 | 25386 | 1 | 3103.6693 | 0.4922 | 0.0245 | 0.1625 | -0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1116 | -0.0 | 0.0 | 1.0 | 0.0 | 0.0 | 0.6406 | 0.4922 | 13.816 | 50.7961 | 612.8476 | 28.6 | 857.9675 | 245.1199 | 0.0558 | 3.786 | 27.4207 | 148.2987 | 175.969 | 5.8565 | 1591.7732 | 20.678 | 148.4921 | 1391.3251 | 0 | 75 | 61 | 488 | 446 | 18 | 27 | 0.08196721311475409 | 5 | 0.32786885245901637 | 20 | 0.2459016393442623 | 15.0 | 0.03278688524590164 | 2.0 | ||||||||
| 13 | 0.0 | 0 | 64 | 512 | 3 | 2.2344 | 2 | 1.0 | 4071.6719 | 3826.4317 | 4208.0821 | 31779 | 1 | 3359.4605 | 0.3574 | 0.0041 | 0.1367 | -0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.122 | -0.0 | 0.0 | 1.0 | 0.0 | 0.0 | 0.5312 | 0.3574 | 14.0157 | 51.0362 | 611.0781 | 28.8 | 857.9675 | 246.8895 | 0.0659 | 4.5298 | 25.7335 | 158.3383 | 184.3538 | 1915.8699 | 20.5904 | 158.5541 | 1706.3756 | 0 | 76 | 64 | 512 | 469 | 18 | 35 | 0.125 | 8 | 0.453125 | 29 | 0.046875 | 3.0 | 0.0081 | 8.0145 | 0.125 | 8.0 | 0.015625 | 1.0 | |||||
| 14 | 0.0 | 0 | 64 | 512 | 3 | 3.0 | 3 | 1.0 | 4338.9863 | 4198.9942 | 4409.1877 | 31653 | 1 | 3668.1638 | 0.334 | -0.002 | 0.0705 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1292 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 | 0.4375 | 0.334 | 14.2828 | 51.3484 | 609.1068 | 29.0 | 857.9675 | 248.8608 | 0.0664 | 4.5496 | 30.742 | 170.001 | 201.0159 | 1171.6576 | 21.017 | 170.2071 | 945.0538 | 0 | 77 | 64 | 512 | 430 | 36 | 63 | 0.640625 | 41 | 0.3125 | 20 | 0.03125 | 2.0 | 0.296875 | 19.0 | |||||||||
| 15 | 0.0 | 0 | 64 | 512 | 4 | 4.0 | 4 | 1.0 | 4903.0371 | 5346.2614 | 4811.0472 | 23634 | 1 | 4141.1011 | 0.1719 | 0.0046 | 0.11 | -0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1267 | -0.0 | 0.0 | 1.0 | 0.0 | 0.0 | 0.3438 | 0.1719 | 14.4365 | 51.4758 | 607.8784 | 29.1 | 857.9675 | 250.0891 | 0.0511 | 3.6578 | 32.3641 | 188.0312 | 220.6809 | 1996.031 | 19.1079 | 188.2653 | 1752.5626 | 0 | 78 | 93 | 744 | 701 | 23 | 38 | 0.2903225806451613 | 27 | 0.08602150537634409 | 8 | 0.0078 | 10.0346 | 0.043010752688172046 | 4.0 | 0.010752688172043012 | 1.0 | 0.03225806451612903 | 3.0 | |||||
| 16 | 0.0 | 0 | 64 | 512 | 0 | 0.0 | 0 | 0.0 | 3705.6719 | 3357.3361 | 4578.8973 | 26629 | 1 | 2424.7377 | 0.7148 | 0.0124 | 0.095 | -0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1105 | -0.0 | 0.0 | 1.0 | 0.0 | 0.0 | 0.7812 | 0.7148 | 14.4194 | 51.4582 | 606.2361 | 29.3 | 857.9675 | 251.7314 | 0.0598 | 3.8365 | 25.5076 | 130.5443 | 156.312 | 3207.1053 | 20.9174 | 130.7441 | 3026.017 | 1 | 79 | 60 | 480 | 452 | 12 | 21 | 0.1 | 6 | 0.16666666666666666 | 10 | 0.11666666666666667 | 7.0 | 0.1 | 6.0 | |||||||||
| 17 | 0.0 | 0 | 64 | 512 | 1 | 0.8281 | 0 | 0.8281 | 4801.8926 | 4507.3876 | 5101.0354 | 21141 | 1 | 3692.5927 | 0.5039 | 0.0145 | 0.122 | -0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1225 | -0.0 | 0.0 | 1.0 | 0.0 | 0.0 | 0.625 | 0.5039 | 14.3202 | 51.3997 | 605.6434 | 29.4 | 857.9675 | 252.3241 | 0.0464 | 3.3871 | 30.1146 | 181.7158 | 212.1128 | 5.9826 | 1758.6001 | 22.0893 | 181.9515 | 1521.007 | 1 | 80 | 64 | 512 | 455 | 31 | 55 | 0.078125 | 5 | 0.53125 | 34 | 0.09375 | 6.0 | 0.0078 | 11.1322 | 0.03125 | 2.0 | 0.171875 | 11.0 |