{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.28, "eval_steps": 500, "global_step": 160, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.05, "completions/max_length": 899.7, "completions/max_terminated_length": 834.6, "completions/mean_length": 599.55, "completions/mean_terminated_length": 580.2101257324218, "completions/min_length": 345.7, "completions/min_terminated_length": 345.7, "entropy": 0.9067775651812553, "epoch": 0.08, "frac_reward_zero_std": 0.15, "grad_norm": 2.203125, "kl": 0.034341241162474036, "learning_rate": 9.4375e-06, "loss": -0.016357305645942687, "num_tokens": 68608.0, "reward": 0.5690673828125, "reward_std": 0.5320930480957031, "rewards/JointRewardFunction/mean": 0.5690673828125, "rewards/JointRewardFunction/std": 0.5320930480957031, "step": 10, "step_time": 36.65178473630149 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.075, "completions/max_length": 915.4, "completions/max_terminated_length": 890.0, "completions/mean_length": 654.2625, "completions/mean_terminated_length": 633.4842956542968, "completions/min_length": 382.9, "completions/min_terminated_length": 382.9, "entropy": 1.2692338980734348, "epoch": 0.16, "frac_reward_zero_std": 0.175, "grad_norm": 2.0625, "kl": 0.08574351686984301, "learning_rate": 8.8125e-06, "loss": 0.011555161327123642, "num_tokens": 141593.0, "reward": 0.55255126953125, "reward_std": 0.5202917702496052, "rewards/JointRewardFunction/mean": 0.55255126953125, "rewards/JointRewardFunction/std": 0.5202917769551277, "step": 20, "step_time": 38.578124190003294 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.025, "completions/max_length": 831.7, "completions/max_terminated_length": 792.0, "completions/mean_length": 567.075, "completions/mean_terminated_length": 556.1625061035156, "completions/min_length": 353.2, "completions/min_terminated_length": 353.2, "entropy": 1.2077870965003967, "epoch": 0.24, "frac_reward_zero_std": 0.15, "grad_norm": 1.4921875, "kl": 0.07180349011905492, "learning_rate": 8.1875e-06, "loss": 0.021731069684028624, "num_tokens": 207403.0, "reward": 0.68575439453125, "reward_std": 0.4835183143615723, "rewards/JointRewardFunction/mean": 0.68575439453125, "rewards/JointRewardFunction/std": 0.48351832032203673, "step": 30, "step_time": 35.385694373202206 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.025, "completions/max_length": 899.7, "completions/max_terminated_length": 841.7, "completions/mean_length": 571.8875, "completions/mean_terminated_length": 558.7678588867187, "completions/min_length": 322.2, "completions/min_terminated_length": 322.2, "entropy": 1.0670640360563994, "epoch": 0.32, "frac_reward_zero_std": 0.15, "grad_norm": 1.0859375, "kl": 0.07311075136531145, "learning_rate": 7.5625e-06, "loss": -0.013997538387775421, "num_tokens": 273728.0, "reward": 0.74111328125, "reward_std": 0.5125789776444435, "rewards/JointRewardFunction/mean": 0.74111328125, "rewards/JointRewardFunction/std": 0.512578995525837, "step": 40, "step_time": 38.20040096230041 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.025, "completions/max_length": 842.8, "completions/max_terminated_length": 821.3, "completions/mean_length": 610.425, "completions/mean_terminated_length": 600.9160766601562, "completions/min_length": 379.3, "completions/min_terminated_length": 379.3, "entropy": 1.1711551163345575, "epoch": 0.4, "frac_reward_zero_std": 0.2, "grad_norm": 1.3203125, "kl": 0.08198881428688765, "learning_rate": 6.9375e-06, "loss": 0.0175897479057312, "num_tokens": 343392.0, "reward": 0.69986572265625, "reward_std": 0.47377224564552306, "rewards/JointRewardFunction/mean": 0.69986572265625, "rewards/JointRewardFunction/std": 0.47377225160598757, "step": 50, "step_time": 35.86526439490153 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0, "completions/max_length": 783.2, "completions/max_terminated_length": 783.2, "completions/mean_length": 560.7, "completions/mean_terminated_length": 560.7, "completions/min_length": 375.6, "completions/min_terminated_length": 375.6, "entropy": 1.1601736910641194, "epoch": 0.48, "frac_reward_zero_std": 0.15, "grad_norm": 2.0625, "kl": 0.07123464278411121, "learning_rate": 6.3125e-06, "loss": 0.005981885641813278, "num_tokens": 408588.0, "reward": 0.77021484375, "reward_std": 0.45352104529738424, "rewards/JointRewardFunction/mean": 0.77021484375, "rewards/JointRewardFunction/std": 0.4535210572183132, "step": 60, "step_time": 33.62324385899883 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0375, "completions/max_length": 859.6, "completions/max_terminated_length": 791.1, "completions/mean_length": 576.6875, "completions/mean_terminated_length": 558.1005981445312, "completions/min_length": 331.1, "completions/min_terminated_length": 331.1, "entropy": 1.0957016348838806, "epoch": 0.56, "frac_reward_zero_std": 0.225, "grad_norm": 1.578125, "kl": 0.06286744237877429, "learning_rate": 5.6875e-06, "loss": 0.02311268150806427, "num_tokens": 475179.0, "reward": 0.87257080078125, "reward_std": 0.4612266093492508, "rewards/JointRewardFunction/mean": 0.87257080078125, "rewards/JointRewardFunction/std": 0.4612266182899475, "step": 70, "step_time": 36.65166022339836 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0, "completions/max_length": 801.1, "completions/max_terminated_length": 801.1, "completions/mean_length": 529.3, "completions/mean_terminated_length": 529.3, "completions/min_length": 325.9, "completions/min_terminated_length": 325.9, "entropy": 0.9475126106292009, "epoch": 0.64, "frac_reward_zero_std": 0.175, "grad_norm": 1.6484375, "kl": 0.0728621585527435, "learning_rate": 5.0625e-06, "loss": -0.00028136512264609337, "num_tokens": 538137.0, "reward": 0.92275390625, "reward_std": 0.4701471716165543, "rewards/JointRewardFunction/mean": 0.92275390625, "rewards/JointRewardFunction/std": 0.47014717757701874, "step": 80, "step_time": 34.54745226030063 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0125, "completions/max_length": 809.0, "completions/max_terminated_length": 774.7, "completions/mean_length": 550.9125, "completions/mean_terminated_length": 544.0785736083984, "completions/min_length": 338.7, "completions/min_terminated_length": 338.7, "entropy": 0.8775507573038339, "epoch": 0.72, "frac_reward_zero_std": 0.225, "grad_norm": 1.6328125, "kl": 0.0652636706130579, "learning_rate": 4.4375e-06, "loss": 0.00958292931318283, "num_tokens": 602830.0, "reward": 0.9910400390625, "reward_std": 0.49945615530014037, "rewards/JointRewardFunction/mean": 0.9910400390625, "rewards/JointRewardFunction/std": 0.49945615530014037, "step": 90, "step_time": 34.542127643501225 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.025, "completions/max_length": 854.6, "completions/max_terminated_length": 811.1, "completions/mean_length": 556.0125, "completions/mean_terminated_length": 544.571435546875, "completions/min_length": 342.6, "completions/min_terminated_length": 342.6, "entropy": 0.9368259467184543, "epoch": 0.8, "frac_reward_zero_std": 0.1, "grad_norm": 1.5703125, "kl": 0.06576599276158959, "learning_rate": 3.8125e-06, "loss": 0.025794655084609985, "num_tokens": 667977.0, "reward": 0.95867919921875, "reward_std": 0.45399501323699953, "rewards/JointRewardFunction/mean": 0.95867919921875, "rewards/JointRewardFunction/std": 0.45399501025676725, "step": 100, "step_time": 36.289319235399674 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0, "completions/max_length": 818.4, "completions/max_terminated_length": 818.4, "completions/mean_length": 521.6875, "completions/mean_terminated_length": 521.6875, "completions/min_length": 269.7, "completions/min_terminated_length": 269.7, "entropy": 0.8984692271798849, "epoch": 0.88, "frac_reward_zero_std": 0.15, "grad_norm": 1.7578125, "kl": 0.06471977110486478, "learning_rate": 3.1875e-06, "loss": 0.011397648602724075, "num_tokens": 730256.0, "reward": 0.99234619140625, "reward_std": 0.42927705943584443, "rewards/JointRewardFunction/mean": 0.99234619140625, "rewards/JointRewardFunction/std": 0.4292770564556122, "step": 110, "step_time": 35.05004594640013 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0, "completions/max_length": 848.3, "completions/max_terminated_length": 848.3, "completions/mean_length": 537.95, "completions/mean_terminated_length": 537.95, "completions/min_length": 328.4, "completions/min_terminated_length": 328.4, "entropy": 0.886419289931655, "epoch": 0.96, "frac_reward_zero_std": 0.325, "grad_norm": 1.4609375, "kl": 0.06785837954375892, "learning_rate": 2.5625e-06, "loss": 0.01289355307817459, "num_tokens": 793664.0, "reward": 0.94119873046875, "reward_std": 0.4706839919090271, "rewards/JointRewardFunction/mean": 0.94119873046875, "rewards/JointRewardFunction/std": 0.47068399786949155, "step": 120, "step_time": 36.370545529201266 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0375, "completions/max_length": 827.7, "completions/max_terminated_length": 761.1, "completions/mean_length": 534.6625, "completions/mean_terminated_length": 516.6375061035156, "completions/min_length": 321.3, "completions/min_terminated_length": 321.3, "entropy": 0.954836780950427, "epoch": 1.04, "frac_reward_zero_std": 0.275, "grad_norm": 1.7265625, "kl": 0.06585919852368534, "learning_rate": 1.9375e-06, "loss": 0.011952327191829681, "num_tokens": 857055.0, "reward": 0.96031494140625, "reward_std": 0.44789557456970214, "rewards/JointRewardFunction/mean": 0.96031494140625, "rewards/JointRewardFunction/std": 0.44789558053016665, "step": 130, "step_time": 35.311843357800896 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.025, "completions/max_length": 826.3, "completions/max_terminated_length": 738.5, "completions/mean_length": 522.15, "completions/mean_terminated_length": 506.9553619384766, "completions/min_length": 309.7, "completions/min_terminated_length": 309.7, "entropy": 0.8662954691797495, "epoch": 1.12, "frac_reward_zero_std": 0.25, "grad_norm": 2.125, "kl": 0.07243931000120937, "learning_rate": 1.3125000000000001e-06, "loss": 0.03181460499763489, "num_tokens": 919475.0, "reward": 0.86949462890625, "reward_std": 0.5099265575408936, "rewards/JointRewardFunction/mean": 0.86949462890625, "rewards/JointRewardFunction/std": 0.5099265664815903, "step": 140, "step_time": 35.292809389702235 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0, "completions/max_length": 779.8, "completions/max_terminated_length": 779.8, "completions/mean_length": 524.8875, "completions/mean_terminated_length": 524.8875, "completions/min_length": 323.7, "completions/min_terminated_length": 323.7, "entropy": 0.9163745902478695, "epoch": 1.2, "frac_reward_zero_std": 0.325, "grad_norm": 1.3359375, "kl": 0.07890935295727104, "learning_rate": 6.875000000000001e-07, "loss": 0.0025221250951290132, "num_tokens": 982042.0, "reward": 1.10718994140625, "reward_std": 0.4580986052751541, "rewards/JointRewardFunction/mean": 1.10718994140625, "rewards/JointRewardFunction/std": 0.45809862315654754, "step": 150, "step_time": 33.446236442600274 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0125, "completions/max_length": 720.2, "completions/max_terminated_length": 691.7, "completions/mean_length": 492.3125, "completions/mean_terminated_length": 485.6000030517578, "completions/min_length": 343.0, "completions/min_terminated_length": 343.0, "entropy": 0.8506938068196177, "epoch": 1.28, "frac_reward_zero_std": 0.225, "grad_norm": 1.71875, "kl": 0.06682636064942926, "learning_rate": 6.250000000000001e-08, "loss": 0.03128217160701752, "num_tokens": 1042329.0, "reward": 0.963037109375, "reward_std": 0.4769674390554428, "rewards/JointRewardFunction/mean": 0.963037109375, "rewards/JointRewardFunction/std": 0.47696744799613955, "step": 160, "step_time": 31.293741717099692 } ], "logging_steps": 10, "max_steps": 160, "num_input_tokens_seen": 1042329, "num_train_epochs": 2, "save_steps": 10, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 0.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }