| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 39, | |
| "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": 0.80078125, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 253.0, | |
| "completions/mean_length": 237.14453125, | |
| "completions/mean_terminated_length": 161.3529510498047, | |
| "completions/min_length": 10.0, | |
| "completions/min_terminated_length": 10.0, | |
| "entropy": 1.3392305374145508, | |
| "epoch": 0.02564102564102564, | |
| "frac_reward_zero_std": 0.2890625, | |
| "grad_norm": 0.07342787832021713, | |
| "learning_rate": 0.0, | |
| "loss": 0.0068, | |
| "num_tokens": 153643.0, | |
| "reward": 0.859375, | |
| "reward_std": 1.100690484046936, | |
| "rewards/mathematical_correctness_reward_function/mean": 0.859375, | |
| "rewards/mathematical_correctness_reward_function/std": 1.1006906032562256, | |
| "step": 1, | |
| "step_time": 86.24474567199923 | |
| }, | |
| { | |
| "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": 0.83984375, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 253.0, | |
| "completions/mean_length": 239.8671875, | |
| "completions/mean_terminated_length": 155.26828002929688, | |
| "completions/min_length": 37.0, | |
| "completions/min_terminated_length": 37.0, | |
| "entropy": 1.1771463677287102, | |
| "epoch": 0.05128205128205128, | |
| "frac_reward_zero_std": 0.3515625, | |
| "grad_norm": 0.06119547039270401, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.0204, | |
| "num_tokens": 308163.0, | |
| "reward": 0.88671875, | |
| "reward_std": 1.3041635751724243, | |
| "rewards/mathematical_correctness_reward_function/mean": 0.88671875, | |
| "rewards/mathematical_correctness_reward_function/std": 1.3041635751724243, | |
| "step": 2, | |
| "step_time": 86.508452252001 | |
| }, | |
| { | |
| "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": 0.85546875, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 253.0, | |
| "completions/mean_length": 244.81640625, | |
| "completions/mean_terminated_length": 178.6216278076172, | |
| "completions/min_length": 48.0, | |
| "completions/min_terminated_length": 48.0, | |
| "entropy": 1.1922413893043995, | |
| "epoch": 0.07692307692307693, | |
| "frac_reward_zero_std": 0.375, | |
| "grad_norm": 0.056310124695301056, | |
| "learning_rate": 5e-06, | |
| "loss": 0.0119, | |
| "num_tokens": 463868.0, | |
| "reward": 0.90234375, | |
| "reward_std": 1.124693512916565, | |
| "rewards/mathematical_correctness_reward_function/mean": 0.90234375, | |
| "rewards/mathematical_correctness_reward_function/std": 1.1246936321258545, | |
| "step": 3, | |
| "step_time": 85.8330284170006 | |
| }, | |
| { | |
| "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": 0.84765625, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 255.0, | |
| "completions/mean_length": 243.02734375, | |
| "completions/mean_terminated_length": 170.84616088867188, | |
| "completions/min_length": 82.0, | |
| "completions/min_terminated_length": 82.0, | |
| "entropy": 1.2269665226340294, | |
| "epoch": 0.10256410256410256, | |
| "frac_reward_zero_std": 0.3984375, | |
| "grad_norm": 0.05933857336640358, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.0091, | |
| "num_tokens": 619011.0, | |
| "reward": 0.91796875, | |
| "reward_std": 1.1119270324707031, | |
| "rewards/mathematical_correctness_reward_function/mean": 0.91796875, | |
| "rewards/mathematical_correctness_reward_function/std": 1.1119270324707031, | |
| "step": 4, | |
| "step_time": 85.85383133499909 | |
| }, | |
| { | |
| "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": 0.80859375, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 256.0, | |
| "completions/mean_length": 235.5390625, | |
| "completions/mean_terminated_length": 149.10203552246094, | |
| "completions/min_length": 11.0, | |
| "completions/min_terminated_length": 11.0, | |
| "entropy": 1.1289030984044075, | |
| "epoch": 0.1282051282051282, | |
| "frac_reward_zero_std": 0.3203125, | |
| "grad_norm": 0.06574889272451401, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0168, | |
| "num_tokens": 772231.0, | |
| "reward": 1.10546875, | |
| "reward_std": 1.3549507856369019, | |
| "rewards/mathematical_correctness_reward_function/mean": 1.10546875, | |
| "rewards/mathematical_correctness_reward_function/std": 1.3549507856369019, | |
| "step": 5, | |
| "step_time": 85.96325700299985 | |
| }, | |
| { | |
| "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": 0.73828125, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 256.0, | |
| "completions/mean_length": 233.44140625, | |
| "completions/mean_terminated_length": 169.80596923828125, | |
| "completions/min_length": 46.0, | |
| "completions/min_terminated_length": 46.0, | |
| "entropy": 1.2140139639377594, | |
| "epoch": 0.15384615384615385, | |
| "frac_reward_zero_std": 0.2734375, | |
| "grad_norm": 0.06448275595903397, | |
| "learning_rate": 9.979871469976197e-06, | |
| "loss": 0.0187, | |
| "num_tokens": 924882.0, | |
| "reward": 1.21875, | |
| "reward_std": 1.1127601861953735, | |
| "rewards/mathematical_correctness_reward_function/mean": 1.21875, | |
| "rewards/mathematical_correctness_reward_function/std": 1.1127601861953735, | |
| "step": 6, | |
| "step_time": 86.28028441999868 | |
| }, | |
| { | |
| "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": 0.828125, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 254.0, | |
| "completions/mean_length": 241.78515625, | |
| "completions/mean_terminated_length": 173.2954559326172, | |
| "completions/min_length": 36.0, | |
| "completions/min_terminated_length": 36.0, | |
| "entropy": 1.241826605051756, | |
| "epoch": 0.1794871794871795, | |
| "frac_reward_zero_std": 0.2421875, | |
| "grad_norm": 0.06542028486728668, | |
| "learning_rate": 9.91964794299315e-06, | |
| "loss": 0.0025, | |
| "num_tokens": 1079615.0, | |
| "reward": 1.29296875, | |
| "reward_std": 1.1359151601791382, | |
| "rewards/mathematical_correctness_reward_function/mean": 1.29296875, | |
| "rewards/mathematical_correctness_reward_function/std": 1.1359151601791382, | |
| "step": 7, | |
| "step_time": 85.96726177399978 | |
| }, | |
| { | |
| "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": 0.7578125, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 256.0, | |
| "completions/mean_length": 231.3046875, | |
| "completions/mean_terminated_length": 154.03225708007812, | |
| "completions/min_length": 44.0, | |
| "completions/min_terminated_length": 44.0, | |
| "entropy": 1.2537630051374435, | |
| "epoch": 0.20512820512820512, | |
| "frac_reward_zero_std": 0.3046875, | |
| "grad_norm": 0.06004541367292404, | |
| "learning_rate": 9.819814303479268e-06, | |
| "loss": 0.0227, | |
| "num_tokens": 1231799.0, | |
| "reward": 1.33984375, | |
| "reward_std": 1.1537383794784546, | |
| "rewards/mathematical_correctness_reward_function/mean": 1.33984375, | |
| "rewards/mathematical_correctness_reward_function/std": 1.1537383794784546, | |
| "step": 8, | |
| "step_time": 85.93508993700198 | |
| }, | |
| { | |
| "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": 0.7265625, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 250.0, | |
| "completions/mean_length": 229.26953125, | |
| "completions/mean_terminated_length": 158.24285888671875, | |
| "completions/min_length": 51.0, | |
| "completions/min_terminated_length": 51.0, | |
| "entropy": 1.1602798961102962, | |
| "epoch": 0.23076923076923078, | |
| "frac_reward_zero_std": 0.2421875, | |
| "grad_norm": 0.07147325575351715, | |
| "learning_rate": 9.681174353198687e-06, | |
| "loss": 0.0138, | |
| "num_tokens": 1383510.0, | |
| "reward": 1.62890625, | |
| "reward_std": 1.3191591501235962, | |
| "rewards/mathematical_correctness_reward_function/mean": 1.62890625, | |
| "rewards/mathematical_correctness_reward_function/std": 1.3191591501235962, | |
| "step": 9, | |
| "step_time": 86.19385715199951 | |
| }, | |
| { | |
| "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": 0.671875, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 255.0, | |
| "completions/mean_length": 222.59375, | |
| "completions/mean_terminated_length": 154.1904754638672, | |
| "completions/min_length": 49.0, | |
| "completions/min_terminated_length": 49.0, | |
| "entropy": 1.2778590954840183, | |
| "epoch": 0.2564102564102564, | |
| "frac_reward_zero_std": 0.25, | |
| "grad_norm": 0.06555230915546417, | |
| "learning_rate": 9.504844339512096e-06, | |
| "loss": -0.0007, | |
| "num_tokens": 1533384.0, | |
| "reward": 1.66015625, | |
| "reward_std": 1.3186944723129272, | |
| "rewards/mathematical_correctness_reward_function/mean": 1.66015625, | |
| "rewards/mathematical_correctness_reward_function/std": 1.3186945915222168, | |
| "step": 10, | |
| "step_time": 85.93042380499901 | |
| }, | |
| { | |
| "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": 0.66796875, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 254.0, | |
| "completions/mean_length": 219.453125, | |
| "completions/mean_terminated_length": 145.92941284179688, | |
| "completions/min_length": 38.0, | |
| "completions/min_terminated_length": 38.0, | |
| "entropy": 1.2968238294124603, | |
| "epoch": 0.28205128205128205, | |
| "frac_reward_zero_std": 0.3046875, | |
| "grad_norm": 0.0640135407447815, | |
| "learning_rate": 9.292243968009332e-06, | |
| "loss": 0.0186, | |
| "num_tokens": 1682622.0, | |
| "reward": 1.64453125, | |
| "reward_std": 1.355674147605896, | |
| "rewards/mathematical_correctness_reward_function/mean": 1.64453125, | |
| "rewards/mathematical_correctness_reward_function/std": 1.355674147605896, | |
| "step": 11, | |
| "step_time": 86.73103137099861 | |
| }, | |
| { | |
| "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": 0.70703125, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 256.0, | |
| "completions/mean_length": 227.4921875, | |
| "completions/mean_terminated_length": 158.69334411621094, | |
| "completions/min_length": 53.0, | |
| "completions/min_terminated_length": 53.0, | |
| "entropy": 1.1798847801983356, | |
| "epoch": 0.3076923076923077, | |
| "frac_reward_zero_std": 0.234375, | |
| "grad_norm": 0.06765235960483551, | |
| "learning_rate": 9.045084971874738e-06, | |
| "loss": 0.0153, | |
| "num_tokens": 1833938.0, | |
| "reward": 1.74609375, | |
| "reward_std": 1.2469509840011597, | |
| "rewards/mathematical_correctness_reward_function/mean": 1.74609375, | |
| "rewards/mathematical_correctness_reward_function/std": 1.2469509840011597, | |
| "step": 12, | |
| "step_time": 85.93055903300046 | |
| }, | |
| { | |
| "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": 0.72265625, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 255.0, | |
| "completions/mean_length": 227.6640625, | |
| "completions/mean_terminated_length": 153.8309783935547, | |
| "completions/min_length": 42.0, | |
| "completions/min_terminated_length": 42.0, | |
| "entropy": 1.0747726932168007, | |
| "epoch": 0.3333333333333333, | |
| "frac_reward_zero_std": 0.265625, | |
| "grad_norm": 0.06723812222480774, | |
| "learning_rate": 8.765357330018056e-06, | |
| "loss": 0.0142, | |
| "num_tokens": 1985174.0, | |
| "reward": 1.92578125, | |
| "reward_std": 1.4164161682128906, | |
| "rewards/mathematical_correctness_reward_function/mean": 1.92578125, | |
| "rewards/mathematical_correctness_reward_function/std": 1.4164161682128906, | |
| "step": 13, | |
| "step_time": 86.18083131499952 | |
| }, | |
| { | |
| "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": 0.671875, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 256.0, | |
| "completions/mean_length": 216.9453125, | |
| "completions/mean_terminated_length": 136.9761962890625, | |
| "completions/min_length": 19.0, | |
| "completions/min_terminated_length": 19.0, | |
| "entropy": 1.048094429075718, | |
| "epoch": 0.358974358974359, | |
| "frac_reward_zero_std": 0.2890625, | |
| "grad_norm": 0.06610685586929321, | |
| "learning_rate": 8.455313244934324e-06, | |
| "loss": 0.015, | |
| "num_tokens": 2133660.0, | |
| "reward": 1.8671875, | |
| "reward_std": 1.1740400791168213, | |
| "rewards/mathematical_correctness_reward_function/mean": 1.8671875, | |
| "rewards/mathematical_correctness_reward_function/std": 1.1740400791168213, | |
| "step": 14, | |
| "step_time": 86.0845494640007 | |
| }, | |
| { | |
| "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": 0.6171875, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 250.0, | |
| "completions/mean_length": 207.58984375, | |
| "completions/mean_terminated_length": 129.5408172607422, | |
| "completions/min_length": 39.0, | |
| "completions/min_terminated_length": 39.0, | |
| "entropy": 1.1446622498333454, | |
| "epoch": 0.38461538461538464, | |
| "frac_reward_zero_std": 0.2734375, | |
| "grad_norm": 0.07915058732032776, | |
| "learning_rate": 8.117449009293668e-06, | |
| "loss": 0.0438, | |
| "num_tokens": 2279705.0, | |
| "reward": 2.02734375, | |
| "reward_std": 1.1960861682891846, | |
| "rewards/mathematical_correctness_reward_function/mean": 2.02734375, | |
| "rewards/mathematical_correctness_reward_function/std": 1.1960861682891846, | |
| "step": 15, | |
| "step_time": 86.29595133900057 | |
| }, | |
| { | |
| "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": 0.6328125, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 252.0, | |
| "completions/mean_length": 209.8671875, | |
| "completions/mean_terminated_length": 130.3616943359375, | |
| "completions/min_length": 49.0, | |
| "completions/min_terminated_length": 49.0, | |
| "entropy": 1.0856149233877659, | |
| "epoch": 0.41025641025641024, | |
| "frac_reward_zero_std": 0.2421875, | |
| "grad_norm": 0.07183024287223816, | |
| "learning_rate": 7.754484907260513e-06, | |
| "loss": 0.0186, | |
| "num_tokens": 2426473.0, | |
| "reward": 2.00390625, | |
| "reward_std": 1.272632122039795, | |
| "rewards/mathematical_correctness_reward_function/mean": 2.00390625, | |
| "rewards/mathematical_correctness_reward_function/std": 1.272632122039795, | |
| "step": 16, | |
| "step_time": 86.06944787800421 | |
| }, | |
| { | |
| "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": 0.59375, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 249.0, | |
| "completions/mean_length": 203.3203125, | |
| "completions/mean_terminated_length": 126.3269271850586, | |
| "completions/min_length": 42.0, | |
| "completions/min_terminated_length": 42.0, | |
| "entropy": 1.1112723909318447, | |
| "epoch": 0.4358974358974359, | |
| "frac_reward_zero_std": 0.3203125, | |
| "grad_norm": 0.07727660983800888, | |
| "learning_rate": 7.369343312364994e-06, | |
| "loss": 0.0017, | |
| "num_tokens": 2571503.0, | |
| "reward": 2.3515625, | |
| "reward_std": 1.4637573957443237, | |
| "rewards/mathematical_correctness_reward_function/mean": 2.3515625, | |
| "rewards/mathematical_correctness_reward_function/std": 1.4637575149536133, | |
| "step": 17, | |
| "step_time": 86.03456121599811 | |
| }, | |
| { | |
| "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": 0.57421875, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 251.0, | |
| "completions/mean_length": 200.82421875, | |
| "completions/mean_terminated_length": 126.412841796875, | |
| "completions/min_length": 44.0, | |
| "completions/min_terminated_length": 44.0, | |
| "entropy": 1.0709168612957, | |
| "epoch": 0.46153846153846156, | |
| "frac_reward_zero_std": 0.3671875, | |
| "grad_norm": 0.07580733299255371, | |
| "learning_rate": 6.965125158269619e-06, | |
| "loss": 0.023, | |
| "num_tokens": 2716018.0, | |
| "reward": 2.24609375, | |
| "reward_std": 1.2295321226119995, | |
| "rewards/mathematical_correctness_reward_function/mean": 2.24609375, | |
| "rewards/mathematical_correctness_reward_function/std": 1.229532241821289, | |
| "step": 18, | |
| "step_time": 86.06337975900169 | |
| }, | |
| { | |
| "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": 0.5859375, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 256.0, | |
| "completions/mean_length": 203.3125, | |
| "completions/mean_terminated_length": 128.7547149658203, | |
| "completions/min_length": 46.0, | |
| "completions/min_terminated_length": 46.0, | |
| "entropy": 1.0283005349338055, | |
| "epoch": 0.48717948717948717, | |
| "frac_reward_zero_std": 0.421875, | |
| "grad_norm": 0.06546252965927124, | |
| "learning_rate": 6.545084971874738e-06, | |
| "loss": 0.0157, | |
| "num_tokens": 2861190.0, | |
| "reward": 2.3203125, | |
| "reward_std": 1.2008728981018066, | |
| "rewards/mathematical_correctness_reward_function/mean": 2.3203125, | |
| "rewards/mathematical_correctness_reward_function/std": 1.2008728981018066, | |
| "step": 19, | |
| "step_time": 86.31491269100479 | |
| }, | |
| { | |
| "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": 0.5234375, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 256.0, | |
| "completions/mean_length": 190.8125, | |
| "completions/mean_terminated_length": 119.2131118774414, | |
| "completions/min_length": 43.0, | |
| "completions/min_terminated_length": 43.0, | |
| "entropy": 1.0640101097524166, | |
| "epoch": 0.5128205128205128, | |
| "frac_reward_zero_std": 0.3359375, | |
| "grad_norm": 0.07372903823852539, | |
| "learning_rate": 6.112604669781572e-06, | |
| "loss": 0.0409, | |
| "num_tokens": 3002934.0, | |
| "reward": 2.54296875, | |
| "reward_std": 1.3038816452026367, | |
| "rewards/mathematical_correctness_reward_function/mean": 2.54296875, | |
| "rewards/mathematical_correctness_reward_function/std": 1.3038816452026367, | |
| "step": 20, | |
| "step_time": 85.70871102700039 | |
| }, | |
| { | |
| "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": 0.5546875, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 255.0, | |
| "completions/mean_length": 193.19921875, | |
| "completions/mean_terminated_length": 114.97368621826172, | |
| "completions/min_length": 44.0, | |
| "completions/min_terminated_length": 44.0, | |
| "entropy": 0.9209145903587341, | |
| "epoch": 0.5384615384615384, | |
| "frac_reward_zero_std": 0.34375, | |
| "grad_norm": 0.08010813593864441, | |
| "learning_rate": 5.671166329088278e-06, | |
| "loss": -0.0112, | |
| "num_tokens": 3145335.0, | |
| "reward": 2.375, | |
| "reward_std": 1.304592251777649, | |
| "rewards/mathematical_correctness_reward_function/mean": 2.375, | |
| "rewards/mathematical_correctness_reward_function/std": 1.304592251777649, | |
| "step": 21, | |
| "step_time": 85.71483788399382 | |
| }, | |
| { | |
| "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": 0.50390625, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 252.0, | |
| "completions/mean_length": 186.578125, | |
| "completions/mean_terminated_length": 116.06298828125, | |
| "completions/min_length": 36.0, | |
| "completions/min_terminated_length": 36.0, | |
| "entropy": 1.097434889525175, | |
| "epoch": 0.5641025641025641, | |
| "frac_reward_zero_std": 0.3359375, | |
| "grad_norm": 0.08341333270072937, | |
| "learning_rate": 5.224324151752575e-06, | |
| "loss": 0.0152, | |
| "num_tokens": 3286151.0, | |
| "reward": 2.56640625, | |
| "reward_std": 1.3675097227096558, | |
| "rewards/mathematical_correctness_reward_function/mean": 2.56640625, | |
| "rewards/mathematical_correctness_reward_function/std": 1.3675097227096558, | |
| "step": 22, | |
| "step_time": 86.00631661799889 | |
| }, | |
| { | |
| "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": 0.44921875, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 251.0, | |
| "completions/mean_length": 174.69140625, | |
| "completions/mean_terminated_length": 108.37588500976562, | |
| "completions/min_length": 35.0, | |
| "completions/min_terminated_length": 35.0, | |
| "entropy": 1.068106159567833, | |
| "epoch": 0.5897435897435898, | |
| "frac_reward_zero_std": 0.5, | |
| "grad_norm": 0.07285387814044952, | |
| "learning_rate": 4.775675848247427e-06, | |
| "loss": 0.0335, | |
| "num_tokens": 3423792.0, | |
| "reward": 2.6171875, | |
| "reward_std": 1.1105278730392456, | |
| "rewards/mathematical_correctness_reward_function/mean": 2.6171875, | |
| "rewards/mathematical_correctness_reward_function/std": 1.1105278730392456, | |
| "step": 23, | |
| "step_time": 86.11024027400526 | |
| }, | |
| { | |
| "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": 0.47265625, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 255.0, | |
| "completions/mean_length": 178.02734375, | |
| "completions/mean_terminated_length": 108.14073944091797, | |
| "completions/min_length": 40.0, | |
| "completions/min_terminated_length": 40.0, | |
| "entropy": 1.2401497773826122, | |
| "epoch": 0.6153846153846154, | |
| "frac_reward_zero_std": 0.4609375, | |
| "grad_norm": 0.0697704628109932, | |
| "learning_rate": 4.3288336709117246e-06, | |
| "loss": -0.0021, | |
| "num_tokens": 3562239.0, | |
| "reward": 2.79296875, | |
| "reward_std": 1.3862452507019043, | |
| "rewards/mathematical_correctness_reward_function/mean": 2.79296875, | |
| "rewards/mathematical_correctness_reward_function/std": 1.3862452507019043, | |
| "step": 24, | |
| "step_time": 86.22353514500355 | |
| }, | |
| { | |
| "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": 0.4765625, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 250.0, | |
| "completions/mean_length": 177.23828125, | |
| "completions/mean_terminated_length": 105.52984619140625, | |
| "completions/min_length": 44.0, | |
| "completions/min_terminated_length": 44.0, | |
| "entropy": 1.0210294723510742, | |
| "epoch": 0.6410256410256411, | |
| "frac_reward_zero_std": 0.4375, | |
| "grad_norm": 0.07643411308526993, | |
| "learning_rate": 3.887395330218429e-06, | |
| "loss": -0.0124, | |
| "num_tokens": 3700666.0, | |
| "reward": 2.6796875, | |
| "reward_std": 1.3687468767166138, | |
| "rewards/mathematical_correctness_reward_function/mean": 2.6796875, | |
| "rewards/mathematical_correctness_reward_function/std": 1.3687469959259033, | |
| "step": 25, | |
| "step_time": 85.93905450400052 | |
| }, | |
| { | |
| "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": 0.46875, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 246.0, | |
| "completions/mean_length": 168.94921875, | |
| "completions/mean_terminated_length": 92.13970947265625, | |
| "completions/min_length": 45.0, | |
| "completions/min_terminated_length": 45.0, | |
| "entropy": 1.0262951292097569, | |
| "epoch": 0.6666666666666666, | |
| "frac_reward_zero_std": 0.5, | |
| "grad_norm": 0.06944487243890762, | |
| "learning_rate": 3.4549150281252635e-06, | |
| "loss": 0.0271, | |
| "num_tokens": 3836983.0, | |
| "reward": 2.87109375, | |
| "reward_std": 1.3324694633483887, | |
| "rewards/mathematical_correctness_reward_function/mean": 2.87109375, | |
| "rewards/mathematical_correctness_reward_function/std": 1.3324694633483887, | |
| "step": 26, | |
| "step_time": 86.1643417560008 | |
| }, | |
| { | |
| "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": 0.47265625, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 242.0, | |
| "completions/mean_length": 169.29296875, | |
| "completions/mean_terminated_length": 91.57777404785156, | |
| "completions/min_length": 46.0, | |
| "completions/min_terminated_length": 46.0, | |
| "entropy": 0.9324285946786404, | |
| "epoch": 0.6923076923076923, | |
| "frac_reward_zero_std": 0.4921875, | |
| "grad_norm": 0.07685497403144836, | |
| "learning_rate": 3.0348748417303826e-06, | |
| "loss": -0.0379, | |
| "num_tokens": 3973202.0, | |
| "reward": 2.9921875, | |
| "reward_std": 1.316537857055664, | |
| "rewards/mathematical_correctness_reward_function/mean": 2.9921875, | |
| "rewards/mathematical_correctness_reward_function/std": 1.3165379762649536, | |
| "step": 27, | |
| "step_time": 85.93033944999843 | |
| }, | |
| { | |
| "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": 0.44921875, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 256.0, | |
| "completions/mean_length": 166.13671875, | |
| "completions/mean_terminated_length": 92.8439712524414, | |
| "completions/min_length": 44.0, | |
| "completions/min_terminated_length": 44.0, | |
| "entropy": 0.9749603681266308, | |
| "epoch": 0.717948717948718, | |
| "frac_reward_zero_std": 0.53125, | |
| "grad_norm": 0.07904963195323944, | |
| "learning_rate": 2.6306566876350072e-06, | |
| "loss": 0.0304, | |
| "num_tokens": 4108643.0, | |
| "reward": 2.91015625, | |
| "reward_std": 1.3618522882461548, | |
| "rewards/mathematical_correctness_reward_function/mean": 2.91015625, | |
| "rewards/mathematical_correctness_reward_function/std": 1.3618522882461548, | |
| "step": 28, | |
| "step_time": 86.1561061070006 | |
| }, | |
| { | |
| "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": 0.4765625, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 243.0, | |
| "completions/mean_length": 174.30078125, | |
| "completions/mean_terminated_length": 99.91790771484375, | |
| "completions/min_length": 38.0, | |
| "completions/min_terminated_length": 38.0, | |
| "entropy": 0.9015668518841267, | |
| "epoch": 0.7435897435897436, | |
| "frac_reward_zero_std": 0.5390625, | |
| "grad_norm": 0.0695631131529808, | |
| "learning_rate": 2.245515092739488e-06, | |
| "loss": -0.0189, | |
| "num_tokens": 4246320.0, | |
| "reward": 2.92578125, | |
| "reward_std": 1.3009647130966187, | |
| "rewards/mathematical_correctness_reward_function/mean": 2.92578125, | |
| "rewards/mathematical_correctness_reward_function/std": 1.3009647130966187, | |
| "step": 29, | |
| "step_time": 86.0680074089978 | |
| }, | |
| { | |
| "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": 0.48046875, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 252.0, | |
| "completions/mean_length": 168.703125, | |
| "completions/mean_terminated_length": 87.96992492675781, | |
| "completions/min_length": 44.0, | |
| "completions/min_terminated_length": 44.0, | |
| "entropy": 0.9284359589219093, | |
| "epoch": 0.7692307692307693, | |
| "frac_reward_zero_std": 0.5, | |
| "grad_norm": 0.07301295548677444, | |
| "learning_rate": 1.8825509907063328e-06, | |
| "loss": 0.0366, | |
| "num_tokens": 4382676.0, | |
| "reward": 2.82421875, | |
| "reward_std": 1.2665992975234985, | |
| "rewards/mathematical_correctness_reward_function/mean": 2.82421875, | |
| "rewards/mathematical_correctness_reward_function/std": 1.266599416732788, | |
| "step": 30, | |
| "step_time": 86.3119131580006 | |
| }, | |
| { | |
| "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": 0.453125, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 251.0, | |
| "completions/mean_length": 163.75, | |
| "completions/mean_terminated_length": 87.31428527832031, | |
| "completions/min_length": 42.0, | |
| "completions/min_terminated_length": 42.0, | |
| "entropy": 0.8934984058141708, | |
| "epoch": 0.7948717948717948, | |
| "frac_reward_zero_std": 0.453125, | |
| "grad_norm": 0.07767564803361893, | |
| "learning_rate": 1.544686755065677e-06, | |
| "loss": 0.011, | |
| "num_tokens": 4517750.0, | |
| "reward": 2.90234375, | |
| "reward_std": 1.398260235786438, | |
| "rewards/mathematical_correctness_reward_function/mean": 2.90234375, | |
| "rewards/mathematical_correctness_reward_function/std": 1.3982603549957275, | |
| "step": 31, | |
| "step_time": 85.92334387800292 | |
| }, | |
| { | |
| "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": 0.44140625, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 256.0, | |
| "completions/mean_length": 165.39453125, | |
| "completions/mean_terminated_length": 93.79720306396484, | |
| "completions/min_length": 44.0, | |
| "completions/min_terminated_length": 44.0, | |
| "entropy": 0.8444960452616215, | |
| "epoch": 0.8205128205128205, | |
| "frac_reward_zero_std": 0.5859375, | |
| "grad_norm": 0.06769714504480362, | |
| "learning_rate": 1.234642669981946e-06, | |
| "loss": 0.0153, | |
| "num_tokens": 4653155.0, | |
| "reward": 3.015625, | |
| "reward_std": 1.3632968664169312, | |
| "rewards/mathematical_correctness_reward_function/mean": 3.015625, | |
| "rewards/mathematical_correctness_reward_function/std": 1.3632969856262207, | |
| "step": 32, | |
| "step_time": 86.23435108699778 | |
| }, | |
| { | |
| "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": 0.4375, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 256.0, | |
| "completions/mean_length": 160.6015625, | |
| "completions/mean_terminated_length": 86.40277862548828, | |
| "completions/min_length": 41.0, | |
| "completions/min_terminated_length": 41.0, | |
| "entropy": 0.8990748878568411, | |
| "epoch": 0.8461538461538461, | |
| "frac_reward_zero_std": 0.546875, | |
| "grad_norm": 0.07534924149513245, | |
| "learning_rate": 9.549150281252633e-07, | |
| "loss": 0.0098, | |
| "num_tokens": 4787289.0, | |
| "reward": 2.84765625, | |
| "reward_std": 1.2224349975585938, | |
| "rewards/mathematical_correctness_reward_function/mean": 2.84765625, | |
| "rewards/mathematical_correctness_reward_function/std": 1.2224351167678833, | |
| "step": 33, | |
| "step_time": 85.95104637099757 | |
| }, | |
| { | |
| "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": 0.39453125, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 253.0, | |
| "completions/mean_length": 156.0546875, | |
| "completions/mean_terminated_length": 90.92903137207031, | |
| "completions/min_length": 34.0, | |
| "completions/min_terminated_length": 34.0, | |
| "entropy": 0.9421114772558212, | |
| "epoch": 0.8717948717948718, | |
| "frac_reward_zero_std": 0.625, | |
| "grad_norm": 0.06507217139005661, | |
| "learning_rate": 7.077560319906696e-07, | |
| "loss": 0.0153, | |
| "num_tokens": 4920277.0, | |
| "reward": 2.953125, | |
| "reward_std": 1.1806237697601318, | |
| "rewards/mathematical_correctness_reward_function/mean": 2.953125, | |
| "rewards/mathematical_correctness_reward_function/std": 1.1806237697601318, | |
| "step": 34, | |
| "step_time": 86.03658091100442 | |
| }, | |
| { | |
| "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": 0.4375, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 245.0, | |
| "completions/mean_length": 165.4296875, | |
| "completions/mean_terminated_length": 94.98611450195312, | |
| "completions/min_length": 3.0, | |
| "completions/min_terminated_length": 3.0, | |
| "entropy": 0.9354344457387924, | |
| "epoch": 0.8974358974358975, | |
| "frac_reward_zero_std": 0.5, | |
| "grad_norm": 0.06672986596822739, | |
| "learning_rate": 4.951556604879049e-07, | |
| "loss": -0.0051, | |
| "num_tokens": 5055601.0, | |
| "reward": 2.95703125, | |
| "reward_std": 1.3954089879989624, | |
| "rewards/mathematical_correctness_reward_function/mean": 2.95703125, | |
| "rewards/mathematical_correctness_reward_function/std": 1.3954089879989624, | |
| "step": 35, | |
| "step_time": 86.32482555100069 | |
| }, | |
| { | |
| "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": 0.42578125, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 254.0, | |
| "completions/mean_length": 159.5859375, | |
| "completions/mean_terminated_length": 88.0952377319336, | |
| "completions/min_length": 44.0, | |
| "completions/min_terminated_length": 44.0, | |
| "entropy": 1.1196487434208393, | |
| "epoch": 0.9230769230769231, | |
| "frac_reward_zero_std": 0.6640625, | |
| "grad_norm": 0.06655178964138031, | |
| "learning_rate": 3.18825646801314e-07, | |
| "loss": 0.0183, | |
| "num_tokens": 5189525.0, | |
| "reward": 2.89453125, | |
| "reward_std": 1.0177875757217407, | |
| "rewards/mathematical_correctness_reward_function/mean": 2.89453125, | |
| "rewards/mathematical_correctness_reward_function/std": 1.0177875757217407, | |
| "step": 36, | |
| "step_time": 85.99539254200317 | |
| }, | |
| { | |
| "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": 0.390625, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 248.0, | |
| "completions/mean_length": 153.83203125, | |
| "completions/mean_terminated_length": 88.3397445678711, | |
| "completions/min_length": 41.0, | |
| "completions/min_terminated_length": 41.0, | |
| "entropy": 0.86182676628232, | |
| "epoch": 0.9487179487179487, | |
| "frac_reward_zero_std": 0.4765625, | |
| "grad_norm": 0.07538075745105743, | |
| "learning_rate": 1.801856965207338e-07, | |
| "loss": 0.006, | |
| "num_tokens": 5321836.0, | |
| "reward": 2.8125, | |
| "reward_std": 1.338714599609375, | |
| "rewards/mathematical_correctness_reward_function/mean": 2.8125, | |
| "rewards/mathematical_correctness_reward_function/std": 1.338714599609375, | |
| "step": 37, | |
| "step_time": 86.28454945299382 | |
| }, | |
| { | |
| "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": 0.44921875, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 240.0, | |
| "completions/mean_length": 161.60546875, | |
| "completions/mean_terminated_length": 84.61701965332031, | |
| "completions/min_length": 47.0, | |
| "completions/min_terminated_length": 47.0, | |
| "entropy": 0.8796500340104103, | |
| "epoch": 0.9743589743589743, | |
| "frac_reward_zero_std": 0.546875, | |
| "grad_norm": 0.06645170599222183, | |
| "learning_rate": 8.035205700685167e-08, | |
| "loss": -0.0015, | |
| "num_tokens": 5456175.0, | |
| "reward": 2.91796875, | |
| "reward_std": 1.2195745706558228, | |
| "rewards/mathematical_correctness_reward_function/mean": 2.91796875, | |
| "rewards/mathematical_correctness_reward_function/std": 1.2195745706558228, | |
| "step": 38, | |
| "step_time": 85.9381635089976 | |
| }, | |
| { | |
| "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": 0.39453125, | |
| "completions/max_length": 256.0, | |
| "completions/max_terminated_length": 252.0, | |
| "completions/mean_length": 154.23828125, | |
| "completions/mean_terminated_length": 87.92903137207031, | |
| "completions/min_length": 38.0, | |
| "completions/min_terminated_length": 38.0, | |
| "entropy": 0.9763927198946476, | |
| "epoch": 1.0, | |
| "frac_reward_zero_std": 0.5390625, | |
| "grad_norm": 0.07626879215240479, | |
| "learning_rate": 2.012853002380466e-08, | |
| "loss": 0.0201, | |
| "num_tokens": 5588616.0, | |
| "reward": 2.87890625, | |
| "reward_std": 1.2291334867477417, | |
| "rewards/mathematical_correctness_reward_function/mean": 2.87890625, | |
| "rewards/mathematical_correctness_reward_function/std": 1.2291334867477417, | |
| "step": 39, | |
| "step_time": 86.1636307589979 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 39, | |
| "num_input_tokens_seen": 5588616, | |
| "num_train_epochs": 1, | |
| "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": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |