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,generate/tis/aligned_tokens,generate/tis/alignment_fail_count,generate/tis/exact_match_fraction,generate/tis/lcs_fallback_fraction,generate/tis/lcs_fallback_messages,generate/tis/unaligned_fraction,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,policy/rollout_train_prob_diff_mean,policy/rollout_train_prob_diff_std,policy/tis/imp_ratio_capped_fraction,policy/tis/imp_ratio_mean,policy/tis/log_ratio_abs_mean,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/cleanup_old_checkpoints,timing/compute_advantages_and_returns,timing/convert_to_training_input,timing/fwd_logprobs_values_reward,timing/policy_train,timing/run_training,timing/save_checkpoints,timing/step,timing/sync_weights,timing/train_critic_and_policy,timing/wait_for_generation_buffer,tis/batch_skipped_no_logprobs,tis/skipped_fraction,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
0.0,0,64,512,0,0.0,0,0.0,5398.6328,5080.3033,6405.3821,29926,1,4304.197,1804094.0,67.0,0.9671,0.0,0.0,0.0329,0.7598,-0.0083,0.1003,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.2266,0.0,0.0,1.0,0.0,0.0,29312150.0,39173644288.0,0.0,0.9936,0.0159,0.8281,0.7598,14.693,50.618,592.3261,31.0,857.9675,265.6414,12.0401,0.1573,5.8422,43.0002,211.2987,254.6735,20.1839,1584.7922,22.6728,211.5154,1301.6032,0.0,0.0,1,82,16,128,128,0,0