Model: laion/a3-rl-DCAgent_selfinstruct-naive-sandboxes-2-verified-70-8B Source: Original Platform
6.3 KiB
6.3 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_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 |