| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0006053268765133172, | |
| "eval_steps": 500, | |
| "global_step": 100, | |
| "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": 0.0, | |
| "completions/max_length": 4095.0, | |
| "completions/max_terminated_length": 4095.0, | |
| "completions/mean_length": 1229.75, | |
| "completions/mean_terminated_length": 1229.75, | |
| "completions/min_length": 354.0, | |
| "completions/min_terminated_length": 354.0, | |
| "epoch": 6.053268765133172e-06, | |
| "grad_norm": 0.07209322590841183, | |
| "kl": 0.011932373046875, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "num_tokens": 27312.0, | |
| "reward": 0.0, | |
| "reward_std": 0.0, | |
| "rewards/avg_thinking_length_func": 73.625, | |
| "rewards/correct_answer_reward_func": 0.0, | |
| "rewards/efficient_thinking_reward_func": 0.45941640084546015, | |
| "rewards/format_reward_func": 0.987500011920929, | |
| "rewards/num_xml_reward_func": 1.03125, | |
| "rewards/tool_execution_reward_func": 0.6875, | |
| "step": 1 | |
| }, | |
| { | |
| "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, | |
| "epoch": 1.2106537530266343e-05, | |
| "grad_norm": 0.07214504525426423, | |
| "kl": 0.011932373046875, | |
| "learning_rate": 1.5000000000000002e-07, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "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, | |
| "epoch": 1.8159806295399516e-05, | |
| "grad_norm": 0.053264765218760744, | |
| "kl": 0.0120086669921875, | |
| "learning_rate": 3.0000000000000004e-07, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "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, | |
| "epoch": 2.4213075060532686e-05, | |
| "grad_norm": 0.05122123329371393, | |
| "kl": 0.01312255859375, | |
| "learning_rate": 4.5e-07, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "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": 0.0625, | |
| "completions/max_length": 2499.0, | |
| "completions/max_terminated_length": 2499.0, | |
| "completions/mean_length": 1216.875, | |
| "completions/mean_terminated_length": 1298.0, | |
| "completions/min_length": 0.0, | |
| "completions/min_terminated_length": 13.0, | |
| "epoch": 3.026634382566586e-05, | |
| "grad_norm": 1.163761459062396, | |
| "kl": 0.01102447509765625, | |
| "learning_rate": 6.000000000000001e-07, | |
| "loss": -0.0148, | |
| "num_tokens": 58482.0, | |
| "reward": 0.0473831407725811, | |
| "reward_std": 0.1895325630903244, | |
| "rewards/avg_thinking_length_func": 129.625, | |
| "rewards/correct_answer_reward_func": 0.0625, | |
| "rewards/efficient_thinking_reward_func": 0.37734568415024294, | |
| "rewards/format_reward_func": 0.9375, | |
| "rewards/num_xml_reward_func": 0.9479166269302368, | |
| "rewards/tool_execution_reward_func": 0.8125, | |
| "step": 5 | |
| }, | |
| { | |
| "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, | |
| "epoch": 3.631961259079903e-05, | |
| "grad_norm": 1.1267039287882714, | |
| "kl": 0.0118865966796875, | |
| "learning_rate": 7.5e-07, | |
| "loss": -0.0148, | |
| "step": 6 | |
| }, | |
| { | |
| "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, | |
| "epoch": 4.2372881355932206e-05, | |
| "grad_norm": 1.0659471491371402, | |
| "kl": 0.0120391845703125, | |
| "learning_rate": 9e-07, | |
| "loss": -0.0148, | |
| "step": 7 | |
| }, | |
| { | |
| "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, | |
| "epoch": 4.842615012106537e-05, | |
| "grad_norm": 1.057686209956945, | |
| "kl": 0.015655517578125, | |
| "learning_rate": 1.05e-06, | |
| "loss": -0.0148, | |
| "step": 8 | |
| }, | |
| { | |
| "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": 2692.0, | |
| "completions/max_terminated_length": 2692.0, | |
| "completions/mean_length": 1255.625, | |
| "completions/mean_terminated_length": 1255.625, | |
| "completions/min_length": 224.0, | |
| "completions/min_terminated_length": 224.0, | |
| "epoch": 5.4479418886198546e-05, | |
| "grad_norm": 1.4615219881629928, | |
| "kl": 0.030914306640625, | |
| "learning_rate": 1.2000000000000002e-06, | |
| "loss": -0.0149, | |
| "num_tokens": 86164.0, | |
| "reward": 0.16301509737968445, | |
| "reward_std": 0.29241904616355896, | |
| "rewards/avg_thinking_length_func": 80.65625, | |
| "rewards/correct_answer_reward_func": 0.25, | |
| "rewards/efficient_thinking_reward_func": 0.5424594521082594, | |
| "rewards/format_reward_func": 1.0, | |
| "rewards/num_xml_reward_func": 1.1458332538604736, | |
| "rewards/tool_execution_reward_func": 0.9375, | |
| "step": 9 | |
| }, | |
| { | |
| "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, | |
| "epoch": 6.053268765133172e-05, | |
| "grad_norm": 1.4154730974531706, | |
| "kl": 0.0540771484375, | |
| "learning_rate": 1.35e-06, | |
| "loss": -0.0149, | |
| "step": 10 | |
| }, | |
| { | |
| "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, | |
| "epoch": 6.658595641646489e-05, | |
| "grad_norm": 1.330539156016462, | |
| "kl": 0.0582275390625, | |
| "learning_rate": 1.5e-06, | |
| "loss": -0.0148, | |
| "step": 11 | |
| }, | |
| { | |
| "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, | |
| "epoch": 7.263922518159807e-05, | |
| "grad_norm": 1.152360438708297, | |
| "kl": 0.1031494140625, | |
| "learning_rate": 1.65e-06, | |
| "loss": -0.0147, | |
| "step": 12 | |
| }, | |
| { | |
| "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": 2962.0, | |
| "completions/max_terminated_length": 2962.0, | |
| "completions/mean_length": 1276.4375, | |
| "completions/mean_terminated_length": 1276.4375, | |
| "completions/min_length": 13.0, | |
| "completions/min_terminated_length": 13.0, | |
| "epoch": 7.869249394673124e-05, | |
| "grad_norm": 0.6615289048669231, | |
| "kl": 0.1724853515625, | |
| "learning_rate": 1.8e-06, | |
| "loss": 0.0005, | |
| "num_tokens": 114191.0, | |
| "reward": 0.0, | |
| "reward_std": 0.0, | |
| "rewards/avg_thinking_length_func": 127.6875, | |
| "rewards/correct_answer_reward_func": 0.0, | |
| "rewards/efficient_thinking_reward_func": 0.3556471644759768, | |
| "rewards/format_reward_func": 0.949999988079071, | |
| "rewards/num_xml_reward_func": 0.875, | |
| "rewards/tool_execution_reward_func": 0.75, | |
| "step": 13 | |
| }, | |
| { | |
| "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, | |
| "epoch": 8.474576271186441e-05, | |
| "grad_norm": 0.12138546214366204, | |
| "kl": 0.147705078125, | |
| "learning_rate": 1.95e-06, | |
| "loss": 0.0004, | |
| "step": 14 | |
| }, | |
| { | |
| "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, | |
| "epoch": 9.079903147699757e-05, | |
| "grad_norm": 0.09332769954040936, | |
| "kl": 0.1591796875, | |
| "learning_rate": 2.1e-06, | |
| "loss": 0.0004, | |
| "step": 15 | |
| }, | |
| { | |
| "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, | |
| "epoch": 9.685230024213075e-05, | |
| "grad_norm": 0.07716503221980582, | |
| "kl": 0.162109375, | |
| "learning_rate": 2.25e-06, | |
| "loss": 0.0004, | |
| "step": 16 | |
| }, | |
| { | |
| "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": 0.0625, | |
| "completions/max_length": 2705.0, | |
| "completions/max_terminated_length": 2705.0, | |
| "completions/mean_length": 1008.3125, | |
| "completions/mean_terminated_length": 1075.5333333333333, | |
| "completions/min_length": 0.0, | |
| "completions/min_terminated_length": 302.0, | |
| "epoch": 0.00010290556900726392, | |
| "grad_norm": 0.9574173404984538, | |
| "kl": 0.200439453125, | |
| "learning_rate": 2.4000000000000003e-06, | |
| "loss": -0.0132, | |
| "num_tokens": 142012.0, | |
| "reward": 0.2393198013305664, | |
| "reward_std": 0.32144659757614136, | |
| "rewards/avg_thinking_length_func": 90.72916412353516, | |
| "rewards/correct_answer_reward_func": 0.375, | |
| "rewards/efficient_thinking_reward_func": 0.4970963413018923, | |
| "rewards/format_reward_func": 0.9937499761581421, | |
| "rewards/num_xml_reward_func": 1.1197916269302368, | |
| "rewards/tool_execution_reward_func": 0.75, | |
| "step": 17 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.00010895883777239709, | |
| "grad_norm": 0.828846190744325, | |
| "kl": 0.23681640625, | |
| "learning_rate": 2.55e-06, | |
| "loss": -0.0131, | |
| "step": 18 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.00011501210653753027, | |
| "grad_norm": 1.0886098363962515, | |
| "kl": 0.34619140625, | |
| "learning_rate": 2.7e-06, | |
| "loss": -0.0128, | |
| "step": 19 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.00012106537530266344, | |
| "grad_norm": 0.6602921666981004, | |
| "kl": 0.31396484375, | |
| "learning_rate": 2.85e-06, | |
| "loss": -0.0129, | |
| "step": 20 | |
| }, | |
| { | |
| "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": 0.0625, | |
| "completions/max_length": 2584.0, | |
| "completions/max_terminated_length": 2584.0, | |
| "completions/mean_length": 1127.125, | |
| "completions/mean_terminated_length": 1202.2666666666667, | |
| "completions/min_length": 0.0, | |
| "completions/min_terminated_length": 13.0, | |
| "epoch": 0.0001271186440677966, | |
| "grad_norm": 0.29632542403765916, | |
| "kl": 0.54736328125, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0011, | |
| "num_tokens": 171746.0, | |
| "reward": 0.0, | |
| "reward_std": 0.0, | |
| "rewards/avg_thinking_length_func": 147.97500610351562, | |
| "rewards/correct_answer_reward_func": 0.0, | |
| "rewards/efficient_thinking_reward_func": 0.5322939489765828, | |
| "rewards/format_reward_func": 0.9375, | |
| "rewards/num_xml_reward_func": 1.0625, | |
| "rewards/tool_execution_reward_func": 0.800000011920929, | |
| "step": 21 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.00013317191283292979, | |
| "grad_norm": 0.1030784592698183, | |
| "kl": 0.60009765625, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0011, | |
| "step": 22 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.00013922518159806296, | |
| "grad_norm": 0.06720833154961504, | |
| "kl": 0.615234375, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0011, | |
| "step": 23 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.00014527845036319613, | |
| "grad_norm": 0.06007920361540232, | |
| "kl": 0.5869140625, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0011, | |
| "step": 24 | |
| }, | |
| { | |
| "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": 0.125, | |
| "completions/max_length": 2784.0, | |
| "completions/max_terminated_length": 2784.0, | |
| "completions/mean_length": 1101.5625, | |
| "completions/mean_terminated_length": 1258.9285714285713, | |
| "completions/min_length": 0.0, | |
| "completions/min_terminated_length": 307.0, | |
| "epoch": 0.0001513317191283293, | |
| "grad_norm": 89.19553783212066, | |
| "kl": 9.30859375, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0237, | |
| "num_tokens": 205155.0, | |
| "reward": -0.10851632058620453, | |
| "reward_std": 0.300925612449646, | |
| "rewards/avg_thinking_length_func": 73.3125, | |
| "rewards/correct_answer_reward_func": 0.25, | |
| "rewards/efficient_thinking_reward_func": 0.5233806335786315, | |
| "rewards/format_reward_func": 1.0, | |
| "rewards/num_xml_reward_func": 1.0416666269302368, | |
| "rewards/tool_execution_reward_func": 0.9375, | |
| "step": 25 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.00015738498789346248, | |
| "grad_norm": 2.0573920189308668, | |
| "kl": 0.83154296875, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0012, | |
| "step": 26 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.00016343825665859565, | |
| "grad_norm": 0.8432081368048696, | |
| "kl": 0.5546875, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0004, | |
| "step": 27 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.00016949152542372882, | |
| "grad_norm": 1.8587603334809846, | |
| "kl": 0.546875, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0003, | |
| "step": 28 | |
| }, | |
| { | |
| "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": 2871.0, | |
| "completions/max_terminated_length": 2871.0, | |
| "completions/mean_length": 1893.9375, | |
| "completions/mean_terminated_length": 1893.9375, | |
| "completions/min_length": 1204.0, | |
| "completions/min_terminated_length": 1204.0, | |
| "epoch": 0.000175544794188862, | |
| "grad_norm": 64.92072887185255, | |
| "kl": 8.59521484375, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0227, | |
| "num_tokens": 243062.0, | |
| "reward": 0.03321200609207153, | |
| "reward_std": 0.13284802436828613, | |
| "rewards/avg_thinking_length_func": 282.96875, | |
| "rewards/correct_answer_reward_func": 0.0625, | |
| "rewards/efficient_thinking_reward_func": 0.4781555664530499, | |
| "rewards/format_reward_func": 1.0, | |
| "rewards/num_xml_reward_func": 1.2395832538604736, | |
| "rewards/tool_execution_reward_func": 1.125, | |
| "step": 29 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.00018159806295399514, | |
| "grad_norm": 23076.53534131984, | |
| "kl": 46.0673828125, | |
| "learning_rate": 3e-06, | |
| "loss": 0.3029, | |
| "step": 30 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.00018765133171912832, | |
| "grad_norm": 6.2253448587216, | |
| "kl": 0.97314453125, | |
| "learning_rate": 3e-06, | |
| "loss": -0.0007, | |
| "step": 31 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.0001937046004842615, | |
| "grad_norm": 3.6768029356119563, | |
| "kl": 0.62109375, | |
| "learning_rate": 3e-06, | |
| "loss": -0.0015, | |
| "step": 32 | |
| }, | |
| { | |
| "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": 0.0625, | |
| "completions/max_length": 2817.0, | |
| "completions/max_terminated_length": 2817.0, | |
| "completions/mean_length": 1192.4375, | |
| "completions/mean_terminated_length": 1271.9333333333334, | |
| "completions/min_length": 0.0, | |
| "completions/min_terminated_length": 323.0, | |
| "epoch": 0.00019975786924939466, | |
| "grad_norm": 3.7035403316845934, | |
| "kl": 1.03271484375, | |
| "learning_rate": 3e-06, | |
| "loss": -0.0039, | |
| "num_tokens": 273829.0, | |
| "reward": 0.09496757388114929, | |
| "reward_std": 0.41386595368385315, | |
| "rewards/avg_thinking_length_func": 69.1875, | |
| "rewards/correct_answer_reward_func": 0.4375, | |
| "rewards/efficient_thinking_reward_func": 0.4750871147644119, | |
| "rewards/format_reward_func": 1.0, | |
| "rewards/num_xml_reward_func": 0.9479166269302368, | |
| "rewards/tool_execution_reward_func": 0.9375, | |
| "step": 33 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.00020581113801452784, | |
| "grad_norm": 1.6964420133725846, | |
| "kl": 0.6962890625, | |
| "learning_rate": 3e-06, | |
| "loss": -0.0055, | |
| "step": 34 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.000211864406779661, | |
| "grad_norm": 1.2613994802405568, | |
| "kl": 0.7099609375, | |
| "learning_rate": 3e-06, | |
| "loss": -0.0054, | |
| "step": 35 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.00021791767554479418, | |
| "grad_norm": 1.4140209746173513, | |
| "kl": 0.7392578125, | |
| "learning_rate": 3e-06, | |
| "loss": -0.0051, | |
| "step": 36 | |
| }, | |
| { | |
| "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": 0.0625, | |
| "completions/max_length": 3204.0, | |
| "completions/max_terminated_length": 3204.0, | |
| "completions/mean_length": 1571.1875, | |
| "completions/mean_terminated_length": 1675.9333333333334, | |
| "completions/min_length": 0.0, | |
| "completions/min_terminated_length": 511.0, | |
| "epoch": 0.00022397094430992736, | |
| "grad_norm": 53596994705358.31, | |
| "kl": 3710857740297.5625, | |
| "learning_rate": 3e-06, | |
| "loss": 10334783488.0, | |
| "num_tokens": 310668.0, | |
| "reward": -0.043196823447942734, | |
| "reward_std": 0.17278729379177094, | |
| "rewards/avg_thinking_length_func": 162.5625, | |
| "rewards/correct_answer_reward_func": 0.0625, | |
| "rewards/efficient_thinking_reward_func": 0.3250826003494903, | |
| "rewards/format_reward_func": 0.987500011920929, | |
| "rewards/num_xml_reward_func": 0.875, | |
| "rewards/tool_execution_reward_func": 0.9375, | |
| "step": 37 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.00023002421307506053, | |
| "grad_norm": 84771335.30009712, | |
| "kl": 2411058.75, | |
| "learning_rate": 3e-06, | |
| "loss": 6696.0161, | |
| "step": 38 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.0002360774818401937, | |
| "grad_norm": 3632.7359114591427, | |
| "kl": 133.154296875, | |
| "learning_rate": 3e-06, | |
| "loss": 0.82, | |
| "step": 39 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.00024213075060532688, | |
| "grad_norm": 42.64315100889087, | |
| "kl": 3.703125, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0345, | |
| "step": 40 | |
| }, | |
| { | |
| "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": 0.0625, | |
| "completions/max_length": 2535.0, | |
| "completions/max_terminated_length": 2535.0, | |
| "completions/mean_length": 1004.0625, | |
| "completions/mean_terminated_length": 1071.0, | |
| "completions/min_length": 0.0, | |
| "completions/min_terminated_length": 277.0, | |
| "epoch": 0.00024818401937046, | |
| "grad_norm": 0.3830041877799282, | |
| "kl": 0.59814453125, | |
| "learning_rate": 3e-06, | |
| "loss": -0.0042, | |
| "num_tokens": 338421.0, | |
| "reward": 0.0777856633067131, | |
| "reward_std": 0.305923730134964, | |
| "rewards/avg_thinking_length_func": 89.21875, | |
| "rewards/correct_answer_reward_func": 0.3125, | |
| "rewards/efficient_thinking_reward_func": 0.49057807654986807, | |
| "rewards/format_reward_func": 1.0, | |
| "rewards/num_xml_reward_func": 1.0104166269302368, | |
| "rewards/tool_execution_reward_func": 0.8125, | |
| "step": 41 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.0002542372881355932, | |
| "grad_norm": 0.26752404691559056, | |
| "kl": 0.572265625, | |
| "learning_rate": 3e-06, | |
| "loss": -0.0043, | |
| "step": 42 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.00026029055690072637, | |
| "grad_norm": 0.24396627644436175, | |
| "kl": 0.59033203125, | |
| "learning_rate": 3e-06, | |
| "loss": -0.0043, | |
| "step": 43 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.00026634382566585957, | |
| "grad_norm": 0.2219905360560463, | |
| "kl": 0.5869140625, | |
| "learning_rate": 3e-06, | |
| "loss": -0.0043, | |
| "step": 44 | |
| }, | |
| { | |
| "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": 2556.0, | |
| "completions/max_terminated_length": 2556.0, | |
| "completions/mean_length": 1469.9375, | |
| "completions/mean_terminated_length": 1469.9375, | |
| "completions/min_length": 806.0, | |
| "completions/min_terminated_length": 806.0, | |
| "epoch": 0.0002723970944309927, | |
| "grad_norm": 0.3505513257767094, | |
| "kl": 0.515625, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0017, | |
| "num_tokens": 369544.0, | |
| "reward": 0.0, | |
| "reward_std": 0.0, | |
| "rewards/avg_thinking_length_func": 145.875, | |
| "rewards/correct_answer_reward_func": 0.0, | |
| "rewards/efficient_thinking_reward_func": 0.3200705292271429, | |
| "rewards/format_reward_func": 0.9937499761581421, | |
| "rewards/num_xml_reward_func": 0.875, | |
| "rewards/tool_execution_reward_func": 0.875, | |
| "step": 45 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.0002784503631961259, | |
| "grad_norm": 0.1358254536364525, | |
| "kl": 0.48291015625, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0016, | |
| "step": 46 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.00028450363196125906, | |
| "grad_norm": 0.04953296360188178, | |
| "kl": 0.46240234375, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0016, | |
| "step": 47 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.00029055690072639226, | |
| "grad_norm": 0.04556158513173327, | |
| "kl": 0.458984375, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0015, | |
| "step": 48 | |
| }, | |
| { | |
| "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": 1418.0, | |
| "completions/max_terminated_length": 1418.0, | |
| "completions/mean_length": 1150.0625, | |
| "completions/mean_terminated_length": 1150.0625, | |
| "completions/min_length": 281.0, | |
| "completions/min_terminated_length": 281.0, | |
| "epoch": 0.0002966101694915254, | |
| "grad_norm": 24.523298976288224, | |
| "kl": 4.013671875, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0174, | |
| "num_tokens": 395537.0, | |
| "reward": 0.09051951766014099, | |
| "reward_std": 0.40777578949928284, | |
| "rewards/avg_thinking_length_func": 90.625, | |
| "rewards/correct_answer_reward_func": 0.4375, | |
| "rewards/efficient_thinking_reward_func": 0.6560945998667584, | |
| "rewards/format_reward_func": 1.0, | |
| "rewards/num_xml_reward_func": 1.1875, | |
| "rewards/tool_execution_reward_func": 0.9375, | |
| "step": 49 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.0003026634382566586, | |
| "grad_norm": 1.1088188455815937, | |
| "kl": 1.0966796875, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0085, | |
| "step": 50 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.00030871670702179176, | |
| "grad_norm": 0.8246471166001736, | |
| "kl": 0.998046875, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0081, | |
| "step": 51 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.00031476997578692496, | |
| "grad_norm": 0.7444859388030179, | |
| "kl": 0.927734375, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0079, | |
| "step": 52 | |
| }, | |
| { | |
| "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": 3603.0, | |
| "completions/max_terminated_length": 3603.0, | |
| "completions/mean_length": 1481.75, | |
| "completions/mean_terminated_length": 1481.75, | |
| "completions/min_length": 938.0, | |
| "completions/min_terminated_length": 938.0, | |
| "epoch": 0.0003208232445520581, | |
| "grad_norm": 0.6560467591027961, | |
| "kl": 0.72265625, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0026, | |
| "num_tokens": 426849.0, | |
| "reward": 0.0, | |
| "reward_std": 0.0, | |
| "rewards/avg_thinking_length_func": 110.40625, | |
| "rewards/correct_answer_reward_func": 0.0, | |
| "rewards/efficient_thinking_reward_func": 0.5525294297041425, | |
| "rewards/format_reward_func": 0.9697916507720947, | |
| "rewards/num_xml_reward_func": 0.9583333730697632, | |
| "rewards/tool_execution_reward_func": 0.875, | |
| "step": 53 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.0003268765133171913, | |
| "grad_norm": 0.9054808017375268, | |
| "kl": 0.7802734375, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0027, | |
| "step": 54 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.00033292978208232445, | |
| "grad_norm": 0.2664167272731428, | |
| "kl": 0.6806640625, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0024, | |
| "step": 55 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.00033898305084745765, | |
| "grad_norm": 0.06723837861451398, | |
| "kl": 0.6181640625, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0022, | |
| "step": 56 | |
| }, | |
| { | |
| "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": 3084.0, | |
| "completions/max_terminated_length": 3084.0, | |
| "completions/mean_length": 1275.125, | |
| "completions/mean_terminated_length": 1275.125, | |
| "completions/min_length": 239.0, | |
| "completions/min_terminated_length": 239.0, | |
| "epoch": 0.0003450363196125908, | |
| "grad_norm": 18149.022369023623, | |
| "kl": 436.88671875, | |
| "learning_rate": 3e-06, | |
| "loss": 2.4098, | |
| "num_tokens": 454843.0, | |
| "reward": 0.06402035802602768, | |
| "reward_std": 0.3948812782764435, | |
| "rewards/avg_thinking_length_func": 72.0, | |
| "rewards/correct_answer_reward_func": 0.375, | |
| "rewards/efficient_thinking_reward_func": 0.5193150989217454, | |
| "rewards/format_reward_func": 0.9791666865348816, | |
| "rewards/num_xml_reward_func": 1.046875, | |
| "rewards/tool_execution_reward_func": 0.875, | |
| "step": 57 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.000351089588377724, | |
| "grad_norm": 130.24455511173358, | |
| "kl": 25.609375, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0696, | |
| "step": 58 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.00035714285714285714, | |
| "grad_norm": 6.994583625280491, | |
| "kl": 3.1640625, | |
| "learning_rate": 3e-06, | |
| "loss": -0.0064, | |
| "step": 59 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.0003631961259079903, | |
| "grad_norm": 1.0257205408467853, | |
| "kl": 1.396484375, | |
| "learning_rate": 3e-06, | |
| "loss": -0.0124, | |
| "step": 60 | |
| }, | |
| { | |
| "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": 0.0625, | |
| "completions/max_length": 3353.0, | |
| "completions/max_terminated_length": 3353.0, | |
| "completions/mean_length": 1478.4375, | |
| "completions/mean_terminated_length": 1577.0, | |
| "completions/min_length": 0.0, | |
| "completions/min_terminated_length": 13.0, | |
| "epoch": 0.0003692493946731235, | |
| "grad_norm": 0.39241037722147315, | |
| "kl": 0.7880859375, | |
| "learning_rate": 3e-06, | |
| "loss": -0.0248, | |
| "num_tokens": 490198.0, | |
| "reward": 0.004050910472869873, | |
| "reward_std": 0.2644372284412384, | |
| "rewards/avg_thinking_length_func": 157.6770782470703, | |
| "rewards/correct_answer_reward_func": 0.125, | |
| "rewards/efficient_thinking_reward_func": 0.5676122758117079, | |
| "rewards/format_reward_func": 0.9004167318344116, | |
| "rewards/num_xml_reward_func": 0.96875, | |
| "rewards/tool_execution_reward_func": 0.9375, | |
| "step": 61 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.00037530266343825664, | |
| "grad_norm": 0.33115302407577757, | |
| "kl": 0.78515625, | |
| "learning_rate": 3e-06, | |
| "loss": -0.0248, | |
| "step": 62 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.00038135593220338984, | |
| "grad_norm": 0.25505560853744225, | |
| "kl": 0.798828125, | |
| "learning_rate": 3e-06, | |
| "loss": -0.0248, | |
| "step": 63 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.000387409200968523, | |
| "grad_norm": 0.2102809253373098, | |
| "kl": 0.828125, | |
| "learning_rate": 3e-06, | |
| "loss": -0.0248, | |
| "step": 64 | |
| }, | |
| { | |
| "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": 0.0625, | |
| "completions/max_length": 2543.0, | |
| "completions/max_terminated_length": 2543.0, | |
| "completions/mean_length": 1185.3125, | |
| "completions/mean_terminated_length": 1264.3333333333333, | |
| "completions/min_length": 0.0, | |
| "completions/min_terminated_length": 213.0, | |
| "epoch": 0.0003934624697336562, | |
| "grad_norm": 0.8562023922194224, | |
| "kl": 1.2021484375, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0037, | |
| "num_tokens": 520851.0, | |
| "reward": 0.0788969099521637, | |
| "reward_std": 0.2156054973602295, | |
| "rewards/avg_thinking_length_func": 114.40625, | |
| "rewards/correct_answer_reward_func": 0.125, | |
| "rewards/efficient_thinking_reward_func": 0.7406251293101025, | |
| "rewards/format_reward_func": 0.9466667175292969, | |
| "rewards/num_xml_reward_func": 1.0520833730697632, | |
| "rewards/tool_execution_reward_func": 0.875, | |
| "step": 65 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.00039951573849878933, | |
| "grad_norm": 0.2046311200261111, | |
| "kl": 1.0009765625, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0031, | |
| "step": 66 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.00040556900726392253, | |
| "grad_norm": 0.1947907245304449, | |
| "kl": 0.9833984375, | |
| "learning_rate": 3e-06, | |
| "loss": 0.003, | |
| "step": 67 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.0004116222760290557, | |
| "grad_norm": 0.19275059130452188, | |
| "kl": 0.9736328125, | |
| "learning_rate": 3e-06, | |
| "loss": 0.003, | |
| "step": 68 | |
| }, | |
| { | |
| "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": 3362.0, | |
| "completions/max_terminated_length": 3362.0, | |
| "completions/mean_length": 1588.1875, | |
| "completions/mean_terminated_length": 1588.1875, | |
| "completions/min_length": 252.0, | |
| "completions/min_terminated_length": 252.0, | |
| "epoch": 0.0004176755447941889, | |
| "grad_norm": 0.8366730039548783, | |
| "kl": 0.8349609375, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0219, | |
| "num_tokens": 553866.0, | |
| "reward": -0.043196823447942734, | |
| "reward_std": 0.17278729379177094, | |
| "rewards/avg_thinking_length_func": 197.28125, | |
| "rewards/correct_answer_reward_func": 0.0625, | |
| "rewards/efficient_thinking_reward_func": 0.6236665630221623, | |
| "rewards/format_reward_func": 0.984375, | |
| "rewards/num_xml_reward_func": 1.375, | |
| "rewards/tool_execution_reward_func": 1.0625, | |
| "step": 69 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.000423728813559322, | |
| "grad_norm": 0.9243760422793489, | |
| "kl": 0.8310546875, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0219, | |
| "step": 70 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.0004297820823244552, | |
| "grad_norm": 2.5683071328894296, | |
| "kl": 0.947265625, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0226, | |
| "step": 71 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.00043583535108958837, | |
| "grad_norm": 8580.97667222067, | |
| "kl": 167.6015625, | |
| "learning_rate": 3e-06, | |
| "loss": 1.3871, | |
| "step": 72 | |
| }, | |
| { | |
| "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": 2605.0, | |
| "completions/max_terminated_length": 2605.0, | |
| "completions/mean_length": 1085.4375, | |
| "completions/mean_terminated_length": 1085.4375, | |
| "completions/min_length": 243.0, | |
| "completions/min_terminated_length": 243.0, | |
| "epoch": 0.00044188861985472157, | |
| "grad_norm": 2.698763686067543, | |
| "kl": 1.203125, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0159, | |
| "num_tokens": 578825.0, | |
| "reward": 0.13226403295993805, | |
| "reward_std": 0.32802054286003113, | |
| "rewards/avg_thinking_length_func": 51.78125, | |
| "rewards/correct_answer_reward_func": 0.4375, | |
| "rewards/efficient_thinking_reward_func": 0.4221610379909578, | |
| "rewards/format_reward_func": 1.0, | |
| "rewards/num_xml_reward_func": 1.1979166269302368, | |
| "rewards/tool_execution_reward_func": 0.8125, | |
| "step": 73 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.0004479418886198547, | |
| "grad_norm": 0.4428441474501145, | |
| "kl": 0.9765625, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0152, | |
| "step": 74 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.0004539951573849879, | |
| "grad_norm": 0.4303895229040926, | |
| "kl": 0.9765625, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0152, | |
| "step": 75 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.00046004842615012106, | |
| "grad_norm": 14.390819598577476, | |
| "kl": 2.109375, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0187, | |
| "step": 76 | |
| }, | |
| { | |
| "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": 2957.0, | |
| "completions/max_terminated_length": 2957.0, | |
| "completions/mean_length": 1399.0625, | |
| "completions/mean_terminated_length": 1399.0625, | |
| "completions/min_length": 568.0, | |
| "completions/min_terminated_length": 568.0, | |
| "epoch": 0.00046610169491525426, | |
| "grad_norm": 4189.702981431435, | |
| "kl": 92.814453125, | |
| "learning_rate": 3e-06, | |
| "loss": 0.6434, | |
| "num_tokens": 608814.0, | |
| "reward": 0.044644102454185486, | |
| "reward_std": 0.17857640981674194, | |
| "rewards/avg_thinking_length_func": 100.25, | |
| "rewards/correct_answer_reward_func": 0.0625, | |
| "rewards/efficient_thinking_reward_func": 0.4614093326791774, | |
| "rewards/format_reward_func": 0.981249988079071, | |
| "rewards/num_xml_reward_func": 1.2708332538604736, | |
| "rewards/tool_execution_reward_func": 0.875, | |
| "step": 77 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.0004721549636803874, | |
| "grad_norm": 99.00548055580344, | |
| "kl": 14.109375, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0301, | |
| "step": 78 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.00047820823244552055, | |
| "grad_norm": 5.827885456645575, | |
| "kl": 2.306640625, | |
| "learning_rate": 3e-06, | |
| "loss": -0.005, | |
| "step": 79 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.00048426150121065375, | |
| "grad_norm": 1.393289989818607, | |
| "kl": 1.1181640625, | |
| "learning_rate": 3e-06, | |
| "loss": -0.0072, | |
| "step": 80 | |
| }, | |
| { | |
| "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": 0.0625, | |
| "completions/max_length": 2912.0, | |
| "completions/max_terminated_length": 2912.0, | |
| "completions/mean_length": 1180.6875, | |
| "completions/mean_terminated_length": 1259.4, | |
| "completions/min_length": 0.0, | |
| "completions/min_terminated_length": 318.0, | |
| "epoch": 0.000490314769975787, | |
| "grad_norm": 15.423239339093648, | |
| "kl": 3.791015625, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0403, | |
| "num_tokens": 639393.0, | |
| "reward": 0.12507787346839905, | |
| "reward_std": 0.42275041341781616, | |
| "rewards/avg_thinking_length_func": 77.41666412353516, | |
| "rewards/correct_answer_reward_func": 0.5, | |
| "rewards/efficient_thinking_reward_func": 0.5368496096788951, | |
| "rewards/format_reward_func": 0.9825000166893005, | |
| "rewards/num_xml_reward_func": 1.09375, | |
| "rewards/tool_execution_reward_func": 0.9375, | |
| "step": 81 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.00049636803874092, | |
| "grad_norm": 2.262950442352818, | |
| "kl": 1.6640625, | |
| "learning_rate": 3e-06, | |
| "loss": 0.032, | |
| "step": 82 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.0005024213075060532, | |
| "grad_norm": 1.1984612569756452, | |
| "kl": 1.18359375, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0306, | |
| "step": 83 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.0005084745762711864, | |
| "grad_norm": 2.42271341300058, | |
| "kl": 1.287109375, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0313, | |
| "step": 84 | |
| }, | |
| { | |
| "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": 0.125, | |
| "completions/max_length": 2703.0, | |
| "completions/max_terminated_length": 2703.0, | |
| "completions/mean_length": 1237.0, | |
| "completions/mean_terminated_length": 1413.7142857142858, | |
| "completions/min_length": 0.0, | |
| "completions/min_terminated_length": 744.0, | |
| "epoch": 0.0005145278450363196, | |
| "grad_norm": 0.18115764428552125, | |
| "kl": 0.751953125, | |
| "learning_rate": 3e-06, | |
| "loss": -0.0039, | |
| "num_tokens": 674981.0, | |
| "reward": 0.03594072163105011, | |
| "reward_std": 0.14376287162303925, | |
| "rewards/avg_thinking_length_func": 100.3125, | |
| "rewards/correct_answer_reward_func": 0.0625, | |
| "rewards/efficient_thinking_reward_func": 0.6207628181651339, | |
| "rewards/format_reward_func": 0.96875, | |
| "rewards/num_xml_reward_func": 1.3270833492279053, | |
| "rewards/tool_execution_reward_func": 0.9375, | |
| "step": 85 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.0005205811138014527, | |
| "grad_norm": 0.1563801639696718, | |
| "kl": 0.7373046875, | |
| "learning_rate": 3e-06, | |
| "loss": -0.004, | |
| "step": 86 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.0005266343825665859, | |
| "grad_norm": 0.1436249859111408, | |
| "kl": 0.73046875, | |
| "learning_rate": 3e-06, | |
| "loss": -0.004, | |
| "step": 87 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.0005326876513317191, | |
| "grad_norm": 0.1274894764193074, | |
| "kl": 0.724609375, | |
| "learning_rate": 3e-06, | |
| "loss": -0.004, | |
| "step": 88 | |
| }, | |
| { | |
| "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": 2842.0, | |
| "completions/max_terminated_length": 2842.0, | |
| "completions/mean_length": 1241.375, | |
| "completions/mean_terminated_length": 1241.375, | |
| "completions/min_length": 230.0, | |
| "completions/min_terminated_length": 230.0, | |
| "epoch": 0.0005387409200968523, | |
| "grad_norm": 5.853699967839861, | |
| "kl": 1.76171875, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0202, | |
| "num_tokens": 702435.0, | |
| "reward": 0.18937985599040985, | |
| "reward_std": 0.26354894042015076, | |
| "rewards/avg_thinking_length_func": 74.375, | |
| "rewards/correct_answer_reward_func": 0.375, | |
| "rewards/efficient_thinking_reward_func": 0.485505122320828, | |
| "rewards/format_reward_func": 0.9916666746139526, | |
| "rewards/num_xml_reward_func": 1.3125, | |
| "rewards/tool_execution_reward_func": 0.8125, | |
| "step": 89 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.0005447941888619854, | |
| "grad_norm": 1.095172664109551, | |
| "kl": 1.482421875, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0181, | |
| "step": 90 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.0005508474576271186, | |
| "grad_norm": 0.42798964827778446, | |
| "kl": 1.3359375, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0174, | |
| "step": 91 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.0005569007263922518, | |
| "grad_norm": 0.4252584937775968, | |
| "kl": 1.2265625, | |
| "learning_rate": 3e-06, | |
| "loss": 0.017, | |
| "step": 92 | |
| }, | |
| { | |
| "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": 0.125, | |
| "completions/max_length": 2607.0, | |
| "completions/max_terminated_length": 2607.0, | |
| "completions/mean_length": 1312.6875, | |
| "completions/mean_terminated_length": 1500.2142857142858, | |
| "completions/min_length": 0.0, | |
| "completions/min_terminated_length": 442.0, | |
| "epoch": 0.000562953995157385, | |
| "grad_norm": 1.1205239401676392, | |
| "kl": 1.189453125, | |
| "learning_rate": 3e-06, | |
| "loss": -0.0069, | |
| "num_tokens": 739234.0, | |
| "reward": 0.033249590545892715, | |
| "reward_std": 0.13299836218357086, | |
| "rewards/avg_thinking_length_func": 151.1875, | |
| "rewards/correct_answer_reward_func": 0.0625, | |
| "rewards/efficient_thinking_reward_func": 0.4546527628842526, | |
| "rewards/format_reward_func": 0.9666666984558105, | |
| "rewards/num_xml_reward_func": 1.2395833730697632, | |
| "rewards/tool_execution_reward_func": 0.9375, | |
| "step": 93 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.0005690072639225181, | |
| "grad_norm": 0.6129371822076389, | |
| "kl": 1.0341796875, | |
| "learning_rate": 3e-06, | |
| "loss": -0.0072, | |
| "step": 94 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.0005750605326876513, | |
| "grad_norm": 0.30285345268245273, | |
| "kl": 0.8857421875, | |
| "learning_rate": 3e-06, | |
| "loss": -0.0076, | |
| "step": 95 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.0005811138014527845, | |
| "grad_norm": 0.2502782554540184, | |
| "kl": 0.798828125, | |
| "learning_rate": 3e-06, | |
| "loss": -0.0079, | |
| "step": 96 | |
| }, | |
| { | |
| "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": 2939.0, | |
| "completions/max_terminated_length": 2939.0, | |
| "completions/mean_length": 1035.125, | |
| "completions/mean_terminated_length": 1035.125, | |
| "completions/min_length": 169.0, | |
| "completions/min_terminated_length": 169.0, | |
| "epoch": 0.0005871670702179177, | |
| "grad_norm": 5.13582049228313, | |
| "kl": 2.056640625, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0147, | |
| "num_tokens": 763388.0, | |
| "reward": 0.18276317417621613, | |
| "reward_std": 0.3562992513179779, | |
| "rewards/avg_thinking_length_func": 61.21875, | |
| "rewards/correct_answer_reward_func": 0.5, | |
| "rewards/efficient_thinking_reward_func": 0.4562464008188011, | |
| "rewards/format_reward_func": 1.0, | |
| "rewards/num_xml_reward_func": 1.2916666269302368, | |
| "rewards/tool_execution_reward_func": 0.75, | |
| "step": 97 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.0005932203389830508, | |
| "grad_norm": 0.8360603719298867, | |
| "kl": 1.5234375, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0126, | |
| "step": 98 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.000599273607748184, | |
| "grad_norm": 0.47398212103799814, | |
| "kl": 1.265625, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0117, | |
| "step": 99 | |
| }, | |
| { | |
| "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, | |
| "epoch": 0.0006053268765133172, | |
| "grad_norm": 0.4824867513848336, | |
| "kl": 1.189453125, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0115, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 2000, | |
| "num_input_tokens_seen": 763388, | |
| "num_train_epochs": 1, | |
| "save_steps": 20, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |