| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.997867803837953, | |
| "eval_steps": 500, | |
| "global_step": 117, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 900.6354370117188, | |
| "epoch": 0.008528784648187633, | |
| "grad_norm": 0.1047119145669114, | |
| "kl": 0.0, | |
| "learning_rate": 8.333333333333333e-08, | |
| "loss": 0.0344, | |
| "reward": 0.6380208432674408, | |
| "reward_std": 0.28531794250011444, | |
| "rewards/accuracy_reward": 0.2187500037252903, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4192708432674408, | |
| "step": 1 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 854.7135620117188, | |
| "epoch": 0.017057569296375266, | |
| "grad_norm": 0.11530117442986747, | |
| "kl": 0.0, | |
| "learning_rate": 1.6666666666666665e-07, | |
| "loss": 0.0351, | |
| "reward": 0.657552108168602, | |
| "reward_std": 0.2899518311023712, | |
| "rewards/accuracy_reward": 0.2291666679084301, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4283854216337204, | |
| "step": 2 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 867.5573272705078, | |
| "epoch": 0.0255863539445629, | |
| "grad_norm": 0.09623548443000227, | |
| "kl": 3.0338764190673828e-05, | |
| "learning_rate": 2.5e-07, | |
| "loss": 0.029, | |
| "reward": 0.6757812649011612, | |
| "reward_std": 0.2807866409420967, | |
| "rewards/accuracy_reward": 0.2656250037252903, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4101562649011612, | |
| "step": 3 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 865.0468902587891, | |
| "epoch": 0.03411513859275053, | |
| "grad_norm": 0.09387745574548279, | |
| "kl": 3.224611282348633e-05, | |
| "learning_rate": 3.333333333333333e-07, | |
| "loss": 0.0195, | |
| "reward": 0.680989608168602, | |
| "reward_std": 0.22749873250722885, | |
| "rewards/accuracy_reward": 0.260416679084301, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.420572929084301, | |
| "step": 4 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 874.0833435058594, | |
| "epoch": 0.042643923240938165, | |
| "grad_norm": 0.1040483701911719, | |
| "kl": 2.8252601623535156e-05, | |
| "learning_rate": 4.1666666666666667e-07, | |
| "loss": 0.0295, | |
| "reward": 0.6484375149011612, | |
| "reward_std": 0.2922288328409195, | |
| "rewards/accuracy_reward": 0.2447916716337204, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4036458432674408, | |
| "step": 5 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 920.4948120117188, | |
| "epoch": 0.0511727078891258, | |
| "grad_norm": 0.09263733090394395, | |
| "kl": 2.6434659957885742e-05, | |
| "learning_rate": 5e-07, | |
| "loss": 0.0181, | |
| "reward": 0.6367187649011612, | |
| "reward_std": 0.2526780068874359, | |
| "rewards/accuracy_reward": 0.2395833395421505, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.397135429084301, | |
| "step": 6 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 909.1666870117188, | |
| "epoch": 0.05970149253731343, | |
| "grad_norm": 0.09754843712930072, | |
| "kl": 2.7477741241455078e-05, | |
| "learning_rate": 5.833333333333334e-07, | |
| "loss": 0.022, | |
| "reward": 0.6119791865348816, | |
| "reward_std": 0.24693656712770462, | |
| "rewards/accuracy_reward": 0.2083333358168602, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4036458432674408, | |
| "step": 7 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 882.6093902587891, | |
| "epoch": 0.06823027718550106, | |
| "grad_norm": 0.10698220402492142, | |
| "kl": 2.574920654296875e-05, | |
| "learning_rate": 6.666666666666666e-07, | |
| "loss": 0.0338, | |
| "reward": 0.6354166716337204, | |
| "reward_std": 0.3055984266102314, | |
| "rewards/accuracy_reward": 0.2291666716337204, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4062500074505806, | |
| "step": 8 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 861.4166870117188, | |
| "epoch": 0.0767590618336887, | |
| "grad_norm": 0.09175606026484463, | |
| "kl": 2.2083520889282227e-05, | |
| "learning_rate": 7.5e-07, | |
| "loss": 0.0218, | |
| "reward": 0.6914062649011612, | |
| "reward_std": 0.26398611813783646, | |
| "rewards/accuracy_reward": 0.2656250111758709, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4257812574505806, | |
| "step": 9 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 888.0052337646484, | |
| "epoch": 0.08528784648187633, | |
| "grad_norm": 0.09578445324972125, | |
| "kl": 2.3156404495239258e-05, | |
| "learning_rate": 8.333333333333333e-07, | |
| "loss": 0.0237, | |
| "reward": 0.6328125149011612, | |
| "reward_std": 0.27884968370199203, | |
| "rewards/accuracy_reward": 0.2343750074505806, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.3984375149011612, | |
| "step": 10 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 865.5312652587891, | |
| "epoch": 0.09381663113006397, | |
| "grad_norm": 0.10709658440221362, | |
| "kl": 3.358721733093262e-05, | |
| "learning_rate": 9.166666666666665e-07, | |
| "loss": 0.0318, | |
| "reward": 0.6562500149011612, | |
| "reward_std": 0.2637302502989769, | |
| "rewards/accuracy_reward": 0.2239583395421505, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4322916716337204, | |
| "step": 11 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 879.6406402587891, | |
| "epoch": 0.1023454157782516, | |
| "grad_norm": 0.09755874874639302, | |
| "kl": 1.6964972019195557e-05, | |
| "learning_rate": 1e-06, | |
| "loss": 0.0353, | |
| "reward": 0.6054687649011612, | |
| "reward_std": 0.2676795497536659, | |
| "rewards/accuracy_reward": 0.1875000074505806, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4179687574505806, | |
| "step": 12 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 856.1145935058594, | |
| "epoch": 0.11087420042643924, | |
| "grad_norm": 0.1022905864478667, | |
| "kl": 1.7881393432617188e-05, | |
| "learning_rate": 9.997985945275765e-07, | |
| "loss": 0.0314, | |
| "reward": 0.7460937649011612, | |
| "reward_std": 0.3503185026347637, | |
| "rewards/accuracy_reward": 0.3125000111758709, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4335937574505806, | |
| "step": 13 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 895.6614837646484, | |
| "epoch": 0.11940298507462686, | |
| "grad_norm": 0.11059533170338177, | |
| "kl": 1.1781696230173111e-05, | |
| "learning_rate": 9.991945583954808e-07, | |
| "loss": 0.0385, | |
| "reward": 0.6666666865348816, | |
| "reward_std": 0.24441985040903091, | |
| "rewards/accuracy_reward": 0.2708333469927311, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.3958333358168602, | |
| "step": 14 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 843.5208587646484, | |
| "epoch": 0.1279317697228145, | |
| "grad_norm": 0.11109902149091894, | |
| "kl": 2.9981136322021484e-05, | |
| "learning_rate": 9.981884322978574e-07, | |
| "loss": 0.0477, | |
| "reward": 0.7187500149011612, | |
| "reward_std": 0.2864153981208801, | |
| "rewards/accuracy_reward": 0.2864583432674408, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.432291679084301, | |
| "step": 15 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 924.8593902587891, | |
| "epoch": 0.13646055437100213, | |
| "grad_norm": 0.09376562642210598, | |
| "kl": 1.5351921319961548e-05, | |
| "learning_rate": 9.967811168538266e-07, | |
| "loss": 0.0178, | |
| "reward": 0.5690104365348816, | |
| "reward_std": 0.22629111260175705, | |
| "rewards/accuracy_reward": 0.18750000651925802, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.3815104216337204, | |
| "step": 16 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 827.0781402587891, | |
| "epoch": 0.14498933901918976, | |
| "grad_norm": 0.11928251247397695, | |
| "kl": 5.745887756347656e-05, | |
| "learning_rate": 9.949738718013078e-07, | |
| "loss": 0.0386, | |
| "reward": 0.716145858168602, | |
| "reward_std": 0.29323747754096985, | |
| "rewards/accuracy_reward": 0.2864583432674408, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4296875074505806, | |
| "step": 17 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 862.7968902587891, | |
| "epoch": 0.1535181236673774, | |
| "grad_norm": 0.11764742163599885, | |
| "kl": 8.106231689453125e-05, | |
| "learning_rate": 9.927683148693833e-07, | |
| "loss": 0.0377, | |
| "reward": 0.7369791865348816, | |
| "reward_std": 0.3344801068305969, | |
| "rewards/accuracy_reward": 0.2968750074505806, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4401041865348816, | |
| "step": 18 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 856.0833587646484, | |
| "epoch": 0.16204690831556504, | |
| "grad_norm": 0.11626948639680061, | |
| "kl": 0.00013709068298339844, | |
| "learning_rate": 9.901664203302124e-07, | |
| "loss": 0.0244, | |
| "reward": 0.7330729514360428, | |
| "reward_std": 0.3556398004293442, | |
| "rewards/accuracy_reward": 0.3072916753590107, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4257812574505806, | |
| "step": 19 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 888.3593902587891, | |
| "epoch": 0.17057569296375266, | |
| "grad_norm": 0.10593013667421312, | |
| "kl": 0.00017189979553222656, | |
| "learning_rate": 9.871705172317903e-07, | |
| "loss": 0.0252, | |
| "reward": 0.7122395932674408, | |
| "reward_std": 0.28121476620435715, | |
| "rewards/accuracy_reward": 0.2968750074505806, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4153645932674408, | |
| "step": 20 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 868.9479370117188, | |
| "epoch": 0.1791044776119403, | |
| "grad_norm": 0.09140054371357058, | |
| "kl": 0.00022101402282714844, | |
| "learning_rate": 9.83783287313134e-07, | |
| "loss": 0.0317, | |
| "reward": 0.6679687798023224, | |
| "reward_std": 0.2439953126013279, | |
| "rewards/accuracy_reward": 0.2604166716337204, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4075520932674408, | |
| "step": 21 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 900.4635620117188, | |
| "epoch": 0.18763326226012794, | |
| "grad_norm": 0.08631101274786548, | |
| "kl": 0.00023651123046875, | |
| "learning_rate": 9.800077626037633e-07, | |
| "loss": 0.0196, | |
| "reward": 0.6588541865348816, | |
| "reward_std": 0.23990928381681442, | |
| "rewards/accuracy_reward": 0.2812500149011612, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.3776041865348816, | |
| "step": 22 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 836.4635620117188, | |
| "epoch": 0.19616204690831557, | |
| "grad_norm": 0.12476489606118728, | |
| "kl": 0.00028514862060546875, | |
| "learning_rate": 9.758473227096238e-07, | |
| "loss": 0.0465, | |
| "reward": 0.7604166865348816, | |
| "reward_std": 0.2827945090830326, | |
| "rewards/accuracy_reward": 0.3333333507180214, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4270833432674408, | |
| "step": 23 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 811.2135620117188, | |
| "epoch": 0.2046908315565032, | |
| "grad_norm": 0.12350610547282559, | |
| "kl": 0.0004482269287109375, | |
| "learning_rate": 9.713056917878816e-07, | |
| "loss": 0.0395, | |
| "reward": 0.8072917014360428, | |
| "reward_std": 0.3758667781949043, | |
| "rewards/accuracy_reward": 0.3385416716337204, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4687500074505806, | |
| "step": 24 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 811.0156555175781, | |
| "epoch": 0.21321961620469082, | |
| "grad_norm": 0.14395478117486019, | |
| "kl": 0.0006284713745117188, | |
| "learning_rate": 9.663869352132985e-07, | |
| "loss": 0.0595, | |
| "reward": 0.8359375149011612, | |
| "reward_std": 0.3746277466416359, | |
| "rewards/accuracy_reward": 0.3750000074505806, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4609375223517418, | |
| "step": 25 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 832.7031555175781, | |
| "epoch": 0.22174840085287847, | |
| "grad_norm": 0.10763270448685561, | |
| "kl": 0.0009222030639648438, | |
| "learning_rate": 9.610954559391704e-07, | |
| "loss": 0.0286, | |
| "reward": 0.7890625149011612, | |
| "reward_std": 0.33439672738313675, | |
| "rewards/accuracy_reward": 0.3541666753590107, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4348958432674408, | |
| "step": 26 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 860.2031402587891, | |
| "epoch": 0.2302771855010661, | |
| "grad_norm": 0.10404844467911575, | |
| "kl": 0.0011348724365234375, | |
| "learning_rate": 9.554359905560885e-07, | |
| "loss": 0.032, | |
| "reward": 0.7096354365348816, | |
| "reward_std": 0.2931777909398079, | |
| "rewards/accuracy_reward": 0.2708333395421505, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4388020932674408, | |
| "step": 27 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 856.5833435058594, | |
| "epoch": 0.23880597014925373, | |
| "grad_norm": 0.10123739483013773, | |
| "kl": 0.0012950897216796875, | |
| "learning_rate": 9.494136050520494e-07, | |
| "loss": 0.0261, | |
| "reward": 0.770833358168602, | |
| "reward_std": 0.2946149371564388, | |
| "rewards/accuracy_reward": 0.3489583358168602, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4218750074505806, | |
| "step": 28 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 832.2500152587891, | |
| "epoch": 0.24733475479744135, | |
| "grad_norm": 0.13065337957291293, | |
| "kl": 0.002017974853515625, | |
| "learning_rate": 9.430336902777083e-07, | |
| "loss": 0.0503, | |
| "reward": 0.7187500149011612, | |
| "reward_std": 0.3128848895430565, | |
| "rewards/accuracy_reward": 0.2864583395421505, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.432291679084301, | |
| "step": 29 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 826.4166717529297, | |
| "epoch": 0.255863539445629, | |
| "grad_norm": 0.09823806495804126, | |
| "kl": 0.002166748046875, | |
| "learning_rate": 9.363019571208397e-07, | |
| "loss": 0.0395, | |
| "reward": 0.805989608168602, | |
| "reward_std": 0.2694031372666359, | |
| "rewards/accuracy_reward": 0.3541666716337204, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4518229216337204, | |
| "step": 30 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 824.8229370117188, | |
| "epoch": 0.26439232409381663, | |
| "grad_norm": 0.1203001703483411, | |
| "kl": 0.0022106170654296875, | |
| "learning_rate": 9.292244313943176e-07, | |
| "loss": 0.0293, | |
| "reward": 0.8437500149011612, | |
| "reward_std": 0.32543642818927765, | |
| "rewards/accuracy_reward": 0.385416679084301, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4583333432674408, | |
| "step": 31 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 841.8854370117188, | |
| "epoch": 0.27292110874200426, | |
| "grad_norm": 0.10358406145081914, | |
| "kl": 0.001796722412109375, | |
| "learning_rate": 9.218074484421977e-07, | |
| "loss": 0.0164, | |
| "reward": 0.7604166865348816, | |
| "reward_std": 0.2593543827533722, | |
| "rewards/accuracy_reward": 0.3489583432674408, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4114583432674408, | |
| "step": 32 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 856.7708587646484, | |
| "epoch": 0.2814498933901919, | |
| "grad_norm": 0.11364346236817396, | |
| "kl": 0.002414703369140625, | |
| "learning_rate": 9.140576474687263e-07, | |
| "loss": 0.0434, | |
| "reward": 0.759114608168602, | |
| "reward_std": 0.33615656197071075, | |
| "rewards/accuracy_reward": 0.3385416753590107, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4205729216337204, | |
| "step": 33 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 834.5104370117188, | |
| "epoch": 0.2899786780383795, | |
| "grad_norm": 0.10166028684229766, | |
| "kl": 0.002529144287109375, | |
| "learning_rate": 9.059819655953535e-07, | |
| "loss": 0.0331, | |
| "reward": 0.856770858168602, | |
| "reward_std": 0.3039211444556713, | |
| "rewards/accuracy_reward": 0.40625, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4505208507180214, | |
| "step": 34 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 859.5260620117188, | |
| "epoch": 0.29850746268656714, | |
| "grad_norm": 0.0979984277638273, | |
| "kl": 0.0023040771484375, | |
| "learning_rate": 8.975876316510698e-07, | |
| "loss": 0.0098, | |
| "reward": 0.7213541865348816, | |
| "reward_std": 0.2962498851120472, | |
| "rewards/accuracy_reward": 0.3020833395421505, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4192708432674408, | |
| "step": 35 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 841.4010620117188, | |
| "epoch": 0.3070362473347548, | |
| "grad_norm": 0.10990186241167772, | |
| "kl": 0.0025806427001953125, | |
| "learning_rate": 8.88882159701625e-07, | |
| "loss": 0.0398, | |
| "reward": 0.8007812649011612, | |
| "reward_std": 0.24869437888264656, | |
| "rewards/accuracy_reward": 0.3593750074505806, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4414062574505806, | |
| "step": 36 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 850.8958587646484, | |
| "epoch": 0.31556503198294245, | |
| "grad_norm": 0.10162456866935911, | |
| "kl": 0.0020751953125, | |
| "learning_rate": 8.798733423234219e-07, | |
| "loss": 0.0196, | |
| "reward": 0.7513020932674408, | |
| "reward_std": 0.3161752223968506, | |
| "rewards/accuracy_reward": 0.322916679084301, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4283854365348816, | |
| "step": 37 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 807.6198120117188, | |
| "epoch": 0.32409381663113007, | |
| "grad_norm": 0.12462007815073382, | |
| "kl": 0.0030517578125, | |
| "learning_rate": 8.705692436281051e-07, | |
| "loss": 0.0275, | |
| "reward": 0.9049479365348816, | |
| "reward_std": 0.34908805042505264, | |
| "rewards/accuracy_reward": 0.4427083432674408, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4622395858168602, | |
| "step": 38 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 816.0625152587891, | |
| "epoch": 0.3326226012793177, | |
| "grad_norm": 0.11104231541623208, | |
| "kl": 0.0030975341796875, | |
| "learning_rate": 8.609781920440891e-07, | |
| "loss": 0.0297, | |
| "reward": 0.8593750298023224, | |
| "reward_std": 0.32317084819078445, | |
| "rewards/accuracy_reward": 0.4114583432674408, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.447916679084301, | |
| "step": 39 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 796.3020935058594, | |
| "epoch": 0.3411513859275053, | |
| "grad_norm": 0.13610346328647868, | |
| "kl": 0.003070831298828125, | |
| "learning_rate": 8.511087728614862e-07, | |
| "loss": 0.0483, | |
| "reward": 0.8750000447034836, | |
| "reward_std": 0.3504873104393482, | |
| "rewards/accuracy_reward": 0.4218750223517418, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4531250223517418, | |
| "step": 40 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 854.9479370117188, | |
| "epoch": 0.34968017057569295, | |
| "grad_norm": 0.11242226065429707, | |
| "kl": 0.00298309326171875, | |
| "learning_rate": 8.409698205471098e-07, | |
| "loss": 0.0346, | |
| "reward": 0.782552108168602, | |
| "reward_std": 0.2810005471110344, | |
| "rewards/accuracy_reward": 0.3802083432674408, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4023437574505806, | |
| "step": 41 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 839.5417022705078, | |
| "epoch": 0.3582089552238806, | |
| "grad_norm": 0.11122225109397199, | |
| "kl": 0.00334930419921875, | |
| "learning_rate": 8.305704108364301e-07, | |
| "loss": 0.0317, | |
| "reward": 0.8046875298023224, | |
| "reward_std": 0.3338276296854019, | |
| "rewards/accuracy_reward": 0.3645833432674408, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4401041716337204, | |
| "step": 42 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 789.2448120117188, | |
| "epoch": 0.36673773987206826, | |
| "grad_norm": 0.11097398896150926, | |
| "kl": 0.003635406494140625, | |
| "learning_rate": 8.199198526095611e-07, | |
| "loss": 0.0402, | |
| "reward": 0.9713541716337204, | |
| "reward_std": 0.3105647638440132, | |
| "rewards/accuracy_reward": 0.5052083432674408, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4661458432674408, | |
| "step": 43 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 793.0000152587891, | |
| "epoch": 0.3752665245202559, | |
| "grad_norm": 0.09575318819337564, | |
| "kl": 0.0031280517578125, | |
| "learning_rate": 8.090276795585531e-07, | |
| "loss": 0.0245, | |
| "reward": 0.8854167014360428, | |
| "reward_std": 0.22198471054434776, | |
| "rewards/accuracy_reward": 0.4270833507180214, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4583333432674408, | |
| "step": 44 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 811.1510620117188, | |
| "epoch": 0.3837953091684435, | |
| "grad_norm": 0.10911023519160144, | |
| "kl": 0.00479888916015625, | |
| "learning_rate": 7.979036416534461e-07, | |
| "loss": 0.0284, | |
| "reward": 0.825520858168602, | |
| "reward_std": 0.26300477609038353, | |
| "rewards/accuracy_reward": 0.3854166716337204, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4401041716337204, | |
| "step": 45 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 811.3385620117188, | |
| "epoch": 0.39232409381663114, | |
| "grad_norm": 0.11175922770281452, | |
| "kl": 0.00440216064453125, | |
| "learning_rate": 7.86557696414727e-07, | |
| "loss": 0.0308, | |
| "reward": 0.8281250149011612, | |
| "reward_std": 0.3059505745768547, | |
| "rewards/accuracy_reward": 0.3802083432674408, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.447916679084301, | |
| "step": 46 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 836.9531555175781, | |
| "epoch": 0.40085287846481876, | |
| "grad_norm": 0.10892804200516466, | |
| "kl": 0.003810882568359375, | |
| "learning_rate": 7.75e-07, | |
| "loss": 0.0193, | |
| "reward": 0.7630208432674408, | |
| "reward_std": 0.2446611113846302, | |
| "rewards/accuracy_reward": 0.3333333432674408, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4296875074505806, | |
| "step": 47 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 785.0364837646484, | |
| "epoch": 0.4093816631130064, | |
| "grad_norm": 0.10448799382228237, | |
| "kl": 0.0042266845703125, | |
| "learning_rate": 7.632408981128493e-07, | |
| "loss": 0.0443, | |
| "reward": 0.9244792014360428, | |
| "reward_std": 0.2805204316973686, | |
| "rewards/accuracy_reward": 0.4583333432674408, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4661458507180214, | |
| "step": 48 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 824.7917022705078, | |
| "epoch": 0.417910447761194, | |
| "grad_norm": 0.1194917798835356, | |
| "kl": 0.00485992431640625, | |
| "learning_rate": 7.512909167420346e-07, | |
| "loss": 0.0244, | |
| "reward": 0.8111979365348816, | |
| "reward_std": 0.3343728110194206, | |
| "rewards/accuracy_reward": 0.3750000074505806, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4361979216337204, | |
| "step": 49 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 803.1718902587891, | |
| "epoch": 0.42643923240938164, | |
| "grad_norm": 0.1182071034035621, | |
| "kl": 0.004547119140625, | |
| "learning_rate": 7.391607527393044e-07, | |
| "loss": 0.0209, | |
| "reward": 0.7460937649011612, | |
| "reward_std": 0.22397059574723244, | |
| "rewards/accuracy_reward": 0.3281250111758709, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4179687649011612, | |
| "step": 50 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 840.7708587646484, | |
| "epoch": 0.4349680170575693, | |
| "grad_norm": 0.12153276862962169, | |
| "kl": 0.005279541015625, | |
| "learning_rate": 7.268612642442656e-07, | |
| "loss": 0.0388, | |
| "reward": 0.7747395932674408, | |
| "reward_std": 0.29431235045194626, | |
| "rewards/accuracy_reward": 0.3281250074505806, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4466145932674408, | |
| "step": 51 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 810.8437805175781, | |
| "epoch": 0.44349680170575695, | |
| "grad_norm": 0.10677125711269464, | |
| "kl": 0.005016326904296875, | |
| "learning_rate": 7.144034609648778e-07, | |
| "loss": 0.0308, | |
| "reward": 0.9335937798023224, | |
| "reward_std": 0.2992444187402725, | |
| "rewards/accuracy_reward": 0.447916679084301, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4856770932674408, | |
| "step": 52 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 850.2135620117188, | |
| "epoch": 0.4520255863539446, | |
| "grad_norm": 0.09689246162817927, | |
| "kl": 0.004337310791015625, | |
| "learning_rate": 7.017984943222735e-07, | |
| "loss": 0.0339, | |
| "reward": 0.8098958730697632, | |
| "reward_std": 0.24391771852970123, | |
| "rewards/accuracy_reward": 0.385416679084301, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.424479179084301, | |
| "step": 53 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 801.6250152587891, | |
| "epoch": 0.4605543710021322, | |
| "grad_norm": 0.1110145602964871, | |
| "kl": 0.00634002685546875, | |
| "learning_rate": 6.890576474687263e-07, | |
| "loss": 0.0443, | |
| "reward": 0.8710937649011612, | |
| "reward_std": 0.2881768085062504, | |
| "rewards/accuracy_reward": 0.4166666865348816, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4544270932674408, | |
| "step": 54 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 793.8750152587891, | |
| "epoch": 0.4690831556503198, | |
| "grad_norm": 0.11287919842468197, | |
| "kl": 0.00574493408203125, | |
| "learning_rate": 6.761923251877012e-07, | |
| "loss": 0.0196, | |
| "reward": 0.9309895932674408, | |
| "reward_std": 0.252448420971632, | |
| "rewards/accuracy_reward": 0.4531250074505806, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4778645932674408, | |
| "step": 55 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 822.9062652587891, | |
| "epoch": 0.47761194029850745, | |
| "grad_norm": 0.10712880691483767, | |
| "kl": 0.0055999755859375, | |
| "learning_rate": 6.632140436850289e-07, | |
| "loss": 0.0347, | |
| "reward": 0.8632812798023224, | |
| "reward_std": 0.2900092527270317, | |
| "rewards/accuracy_reward": 0.4010416716337204, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4622395932674408, | |
| "step": 56 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 841.6718902587891, | |
| "epoch": 0.4861407249466951, | |
| "grad_norm": 0.11360218470340229, | |
| "kl": 0.00505828857421875, | |
| "learning_rate": 6.501344202803414e-07, | |
| "loss": 0.0278, | |
| "reward": 0.8776041865348816, | |
| "reward_std": 0.2797526493668556, | |
| "rewards/accuracy_reward": 0.4270833358168602, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4505208432674408, | |
| "step": 57 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 786.0885620117188, | |
| "epoch": 0.4946695095948827, | |
| "grad_norm": 0.09660671347801546, | |
| "kl": 0.00525665283203125, | |
| "learning_rate": 6.36965163007999e-07, | |
| "loss": 0.0177, | |
| "reward": 0.9049479365348816, | |
| "reward_std": 0.2301800586283207, | |
| "rewards/accuracy_reward": 0.447916679084301, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4570312649011612, | |
| "step": 58 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 865.3593902587891, | |
| "epoch": 0.5031982942430704, | |
| "grad_norm": 0.10774282361431926, | |
| "kl": 0.0062103271484375, | |
| "learning_rate": 6.23718060136812e-07, | |
| "loss": 0.0291, | |
| "reward": 0.8606770932674408, | |
| "reward_std": 0.3248429372906685, | |
| "rewards/accuracy_reward": 0.4114583507180214, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4492187649011612, | |
| "step": 59 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 851.3437805175781, | |
| "epoch": 0.511727078891258, | |
| "grad_norm": 0.10751507893398955, | |
| "kl": 0.0060577392578125, | |
| "learning_rate": 6.10404969617945e-07, | |
| "loss": 0.0275, | |
| "reward": 0.7994791865348816, | |
| "reward_std": 0.2524433769285679, | |
| "rewards/accuracy_reward": 0.3750000074505806, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4244791716337204, | |
| "step": 60 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 839.1146087646484, | |
| "epoch": 0.5202558635394456, | |
| "grad_norm": 0.11847979500014862, | |
| "kl": 0.00791168212890625, | |
| "learning_rate": 5.97037808470444e-07, | |
| "loss": 0.047, | |
| "reward": 0.8437500149011612, | |
| "reward_std": 0.27961887419223785, | |
| "rewards/accuracy_reward": 0.3906250149011612, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4531250149011612, | |
| "step": 61 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 772.3385620117188, | |
| "epoch": 0.5287846481876333, | |
| "grad_norm": 0.1316610193310866, | |
| "kl": 0.006988525390625, | |
| "learning_rate": 5.836285421138909e-07, | |
| "loss": 0.0523, | |
| "reward": 0.8984375298023224, | |
| "reward_std": 0.24485836923122406, | |
| "rewards/accuracy_reward": 0.3958333432674408, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.5026041939854622, | |
| "step": 62 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 814.2760620117188, | |
| "epoch": 0.5373134328358209, | |
| "grad_norm": 0.11592047451693034, | |
| "kl": 0.0073089599609375, | |
| "learning_rate": 5.701891736577317e-07, | |
| "loss": 0.0358, | |
| "reward": 0.813802108168602, | |
| "reward_std": 0.2582968771457672, | |
| "rewards/accuracy_reward": 0.3645833432674408, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4492187649011612, | |
| "step": 63 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 769.1250305175781, | |
| "epoch": 0.5458422174840085, | |
| "grad_norm": 0.13152164686975176, | |
| "kl": 0.0075531005859375, | |
| "learning_rate": 5.567317331568686e-07, | |
| "loss": 0.0389, | |
| "reward": 0.9752604514360428, | |
| "reward_std": 0.3396269455552101, | |
| "rewards/accuracy_reward": 0.479166679084301, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4960937649011612, | |
| "step": 64 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 833.2187652587891, | |
| "epoch": 0.5543710021321961, | |
| "grad_norm": 0.11640227796478432, | |
| "kl": 0.0069122314453125, | |
| "learning_rate": 5.432682668431314e-07, | |
| "loss": 0.0338, | |
| "reward": 0.8502604514360428, | |
| "reward_std": 0.2958378382027149, | |
| "rewards/accuracy_reward": 0.4062500074505806, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4440104216337204, | |
| "step": 65 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 786.2864837646484, | |
| "epoch": 0.5628997867803838, | |
| "grad_norm": 0.14642542124355792, | |
| "kl": 0.0079498291015625, | |
| "learning_rate": 5.298108263422685e-07, | |
| "loss": 0.0443, | |
| "reward": 1.0013021379709244, | |
| "reward_std": 0.37428252026438713, | |
| "rewards/accuracy_reward": 0.510416679084301, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.490885429084301, | |
| "step": 66 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 799.9896087646484, | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 0.13169692017238832, | |
| "kl": 0.00823211669921875, | |
| "learning_rate": 5.163714578861091e-07, | |
| "loss": 0.0526, | |
| "reward": 0.8997395932674408, | |
| "reward_std": 0.33160682767629623, | |
| "rewards/accuracy_reward": 0.4010416865348816, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4986979439854622, | |
| "step": 67 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 857.1354370117188, | |
| "epoch": 0.579957356076759, | |
| "grad_norm": 0.1069980915235563, | |
| "kl": 0.007354736328125, | |
| "learning_rate": 5.02962191529556e-07, | |
| "loss": 0.0278, | |
| "reward": 0.7916666865348816, | |
| "reward_std": 0.2258782833814621, | |
| "rewards/accuracy_reward": 0.3541666753590107, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4375000149011612, | |
| "step": 68 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 865.6406402587891, | |
| "epoch": 0.5884861407249466, | |
| "grad_norm": 0.10309499954991647, | |
| "kl": 0.0067901611328125, | |
| "learning_rate": 4.895950303820552e-07, | |
| "loss": 0.0296, | |
| "reward": 0.774739608168602, | |
| "reward_std": 0.2874305471777916, | |
| "rewards/accuracy_reward": 0.3437500074505806, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4309895932674408, | |
| "step": 69 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 821.2344055175781, | |
| "epoch": 0.5970149253731343, | |
| "grad_norm": 0.13248930196397823, | |
| "kl": 0.00777435302734375, | |
| "learning_rate": 4.76281939863188e-07, | |
| "loss": 0.0537, | |
| "reward": 0.9023437798023224, | |
| "reward_std": 0.3311818540096283, | |
| "rewards/accuracy_reward": 0.4270833432674408, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.475260429084301, | |
| "step": 70 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 810.8177337646484, | |
| "epoch": 0.605543710021322, | |
| "grad_norm": 0.11529960531868733, | |
| "kl": 0.008636474609375, | |
| "learning_rate": 4.6303483699200105e-07, | |
| "loss": 0.0261, | |
| "reward": 0.9192708730697632, | |
| "reward_std": 0.3068869337439537, | |
| "rewards/accuracy_reward": 0.4531250149011612, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4661458358168602, | |
| "step": 71 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 801.1770935058594, | |
| "epoch": 0.6140724946695096, | |
| "grad_norm": 0.11755133653830964, | |
| "kl": 0.010284423828125, | |
| "learning_rate": 4.4986557971965856e-07, | |
| "loss": 0.0391, | |
| "reward": 0.8359375298023224, | |
| "reward_std": 0.2929926961660385, | |
| "rewards/accuracy_reward": 0.3697916753590107, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4661458432674408, | |
| "step": 72 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 786.2500305175781, | |
| "epoch": 0.6226012793176973, | |
| "grad_norm": 0.14898312092719013, | |
| "kl": 0.00911712646484375, | |
| "learning_rate": 4.367859563149712e-07, | |
| "loss": 0.0556, | |
| "reward": 0.962239608168602, | |
| "reward_std": 0.3554273024201393, | |
| "rewards/accuracy_reward": 0.463541679084301, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4986979365348816, | |
| "step": 73 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 840.5000305175781, | |
| "epoch": 0.6311300639658849, | |
| "grad_norm": 0.1084603067680966, | |
| "kl": 0.0075225830078125, | |
| "learning_rate": 4.2380767481229884e-07, | |
| "loss": 0.0177, | |
| "reward": 0.9062500298023224, | |
| "reward_std": 0.2926729619503021, | |
| "rewards/accuracy_reward": 0.4427083358168602, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4635416865348816, | |
| "step": 74 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 793.2135772705078, | |
| "epoch": 0.6396588486140725, | |
| "grad_norm": 0.11707168848017023, | |
| "kl": 0.00870513916015625, | |
| "learning_rate": 4.1094235253127374e-07, | |
| "loss": 0.0225, | |
| "reward": 0.971354216337204, | |
| "reward_std": 0.28287459164857864, | |
| "rewards/accuracy_reward": 0.4739583507180214, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.497395858168602, | |
| "step": 75 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 790.9062652587891, | |
| "epoch": 0.6481876332622601, | |
| "grad_norm": 0.11531067175734634, | |
| "kl": 0.0094451904296875, | |
| "learning_rate": 3.982015056777265e-07, | |
| "loss": 0.0297, | |
| "reward": 0.9557291865348816, | |
| "reward_std": 0.25578880310058594, | |
| "rewards/accuracy_reward": 0.4843750149011612, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4713541865348816, | |
| "step": 76 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 768.7239685058594, | |
| "epoch": 0.6567164179104478, | |
| "grad_norm": 0.1320106685409761, | |
| "kl": 0.0102386474609375, | |
| "learning_rate": 3.855965390351222e-07, | |
| "loss": 0.0417, | |
| "reward": 0.962239608168602, | |
| "reward_std": 0.2732561454176903, | |
| "rewards/accuracy_reward": 0.4635416716337204, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.498697929084301, | |
| "step": 77 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 781.3489685058594, | |
| "epoch": 0.6652452025586354, | |
| "grad_norm": 0.1344780448279913, | |
| "kl": 0.00832366943359375, | |
| "learning_rate": 3.731387357557344e-07, | |
| "loss": 0.0452, | |
| "reward": 1.0169271230697632, | |
| "reward_std": 0.35733717679977417, | |
| "rewards/accuracy_reward": 0.5000000149011612, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.5169271007180214, | |
| "step": 78 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 799.0677185058594, | |
| "epoch": 0.673773987206823, | |
| "grad_norm": 0.12035730419810114, | |
| "kl": 0.00931549072265625, | |
| "learning_rate": 3.608392472606956e-07, | |
| "loss": 0.044, | |
| "reward": 0.9049479365348816, | |
| "reward_std": 0.32109028846025467, | |
| "rewards/accuracy_reward": 0.4375000074505806, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.467447929084301, | |
| "step": 79 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 868.9323120117188, | |
| "epoch": 0.6823027718550106, | |
| "grad_norm": 0.10803684448437832, | |
| "kl": 0.00897979736328125, | |
| "learning_rate": 3.4870908325796527e-07, | |
| "loss": 0.0308, | |
| "reward": 0.774739608168602, | |
| "reward_std": 0.28679391369223595, | |
| "rewards/accuracy_reward": 0.3437500074505806, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4309895858168602, | |
| "step": 80 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 830.3906402587891, | |
| "epoch": 0.6908315565031983, | |
| "grad_norm": 0.11935680801330077, | |
| "kl": 0.00799560546875, | |
| "learning_rate": 3.367591018871506e-07, | |
| "loss": 0.0304, | |
| "reward": 0.9270833730697632, | |
| "reward_std": 0.3459775671362877, | |
| "rewards/accuracy_reward": 0.4375000074505806, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4895833432674408, | |
| "step": 81 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 804.4531555175781, | |
| "epoch": 0.6993603411513859, | |
| "grad_norm": 0.13609643645529676, | |
| "kl": 0.00872802734375, | |
| "learning_rate": 3.250000000000001e-07, | |
| "loss": 0.0571, | |
| "reward": 0.8867187649011612, | |
| "reward_std": 0.33319345116615295, | |
| "rewards/accuracy_reward": 0.401041679084301, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4856770932674408, | |
| "step": 82 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 777.0416870117188, | |
| "epoch": 0.7078891257995735, | |
| "grad_norm": 0.13067073463194692, | |
| "kl": 0.00905609130859375, | |
| "learning_rate": 3.1344230358527284e-07, | |
| "loss": 0.0374, | |
| "reward": 1.033854216337204, | |
| "reward_std": 0.3256627693772316, | |
| "rewards/accuracy_reward": 0.5, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.5338541865348816, | |
| "step": 83 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 805.9896087646484, | |
| "epoch": 0.7164179104477612, | |
| "grad_norm": 0.14281987226405615, | |
| "kl": 0.0091705322265625, | |
| "learning_rate": 3.020963583465539e-07, | |
| "loss": 0.0382, | |
| "reward": 0.9401041716337204, | |
| "reward_std": 0.2688889801502228, | |
| "rewards/accuracy_reward": 0.4375000074505806, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.502604179084301, | |
| "step": 84 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 861.2500152587891, | |
| "epoch": 0.7249466950959488, | |
| "grad_norm": 0.11279936057889765, | |
| "kl": 0.008758544921875, | |
| "learning_rate": 2.9097232044144696e-07, | |
| "loss": 0.0312, | |
| "reward": 0.8671875149011612, | |
| "reward_std": 0.31369951367378235, | |
| "rewards/accuracy_reward": 0.3958333432674408, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.471354179084301, | |
| "step": 85 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 816.1562652587891, | |
| "epoch": 0.7334754797441365, | |
| "grad_norm": 0.10042567088503304, | |
| "kl": 0.0089874267578125, | |
| "learning_rate": 2.8008014739043884e-07, | |
| "loss": 0.0312, | |
| "reward": 0.7968750149011612, | |
| "reward_std": 0.28011347353458405, | |
| "rewards/accuracy_reward": 0.3593750074505806, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4375000074505806, | |
| "step": 86 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 815.0521087646484, | |
| "epoch": 0.7420042643923241, | |
| "grad_norm": 0.14295156229246506, | |
| "kl": 0.0097198486328125, | |
| "learning_rate": 2.6942958916356994e-07, | |
| "loss": 0.0584, | |
| "reward": 0.8971354514360428, | |
| "reward_std": 0.3291558399796486, | |
| "rewards/accuracy_reward": 0.416666679084301, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4804687574505806, | |
| "step": 87 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 801.5260772705078, | |
| "epoch": 0.7505330490405118, | |
| "grad_norm": 0.11305321904987985, | |
| "kl": 0.0097808837890625, | |
| "learning_rate": 2.5903017945289017e-07, | |
| "loss": 0.0148, | |
| "reward": 0.9322916716337204, | |
| "reward_std": 0.24261895567178726, | |
| "rewards/accuracy_reward": 0.447916679084301, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4843750223517418, | |
| "step": 88 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 803.7083435058594, | |
| "epoch": 0.7590618336886994, | |
| "grad_norm": 0.11745643059040382, | |
| "kl": 0.0095367431640625, | |
| "learning_rate": 2.488912271385139e-07, | |
| "loss": 0.0416, | |
| "reward": 0.9973958730697632, | |
| "reward_std": 0.31152600049972534, | |
| "rewards/accuracy_reward": 0.5000000149011612, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4973958432674408, | |
| "step": 89 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 793.3125152587891, | |
| "epoch": 0.767590618336887, | |
| "grad_norm": 0.12149395755942659, | |
| "kl": 0.0098876953125, | |
| "learning_rate": 2.390218079559109e-07, | |
| "loss": 0.0244, | |
| "reward": 1.0351562798023224, | |
| "reward_std": 0.30135782063007355, | |
| "rewards/accuracy_reward": 0.5364583507180214, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4986979365348816, | |
| "step": 90 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 832.4114685058594, | |
| "epoch": 0.7761194029850746, | |
| "grad_norm": 0.1284291053033323, | |
| "kl": 0.01007080078125, | |
| "learning_rate": 2.294307563718949e-07, | |
| "loss": 0.0419, | |
| "reward": 0.845052108168602, | |
| "reward_std": 0.24289947375655174, | |
| "rewards/accuracy_reward": 0.385416679084301, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.459635429084301, | |
| "step": 91 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 810.6875152587891, | |
| "epoch": 0.7846481876332623, | |
| "grad_norm": 0.12108019651078701, | |
| "kl": 0.0109405517578125, | |
| "learning_rate": 2.2012665767657823e-07, | |
| "loss": 0.0228, | |
| "reward": 0.8593750298023224, | |
| "reward_std": 0.2939864583313465, | |
| "rewards/accuracy_reward": 0.3802083432674408, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.479166679084301, | |
| "step": 92 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 816.0833435058594, | |
| "epoch": 0.7931769722814499, | |
| "grad_norm": 0.1248794400539759, | |
| "kl": 0.0101318359375, | |
| "learning_rate": 2.1111784029837509e-07, | |
| "loss": 0.0366, | |
| "reward": 0.8750000149011612, | |
| "reward_std": 0.3214331939816475, | |
| "rewards/accuracy_reward": 0.3750000149011612, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.5000000223517418, | |
| "step": 93 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 759.9219055175781, | |
| "epoch": 0.8017057569296375, | |
| "grad_norm": 0.14143793722100087, | |
| "kl": 0.010162353515625, | |
| "learning_rate": 2.0241236834893028e-07, | |
| "loss": 0.0446, | |
| "reward": 1.0013021230697632, | |
| "reward_std": 0.30526329576969147, | |
| "rewards/accuracy_reward": 0.4947916865348816, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.5065104365348816, | |
| "step": 94 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 800.8021087646484, | |
| "epoch": 0.8102345415778252, | |
| "grad_norm": 0.1243853221942541, | |
| "kl": 0.010223388671875, | |
| "learning_rate": 1.9401803440464654e-07, | |
| "loss": 0.0342, | |
| "reward": 0.958333358168602, | |
| "reward_std": 0.2869706079363823, | |
| "rewards/accuracy_reward": 0.4427083507180214, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.5156250223517418, | |
| "step": 95 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 803.5104370117188, | |
| "epoch": 0.8187633262260128, | |
| "grad_norm": 0.1306441755839297, | |
| "kl": 0.0102386474609375, | |
| "learning_rate": 1.8594235253127372e-07, | |
| "loss": 0.0602, | |
| "reward": 0.9882812649011612, | |
| "reward_std": 0.2958815321326256, | |
| "rewards/accuracy_reward": 0.4895833432674408, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4986979365348816, | |
| "step": 96 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 812.1979370117188, | |
| "epoch": 0.8272921108742004, | |
| "grad_norm": 0.12020848008929602, | |
| "kl": 0.0102691650390625, | |
| "learning_rate": 1.7819255155780238e-07, | |
| "loss": 0.0299, | |
| "reward": 0.8619791865348816, | |
| "reward_std": 0.3012324385344982, | |
| "rewards/accuracy_reward": 0.3906250149011612, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4713541865348816, | |
| "step": 97 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 868.9895935058594, | |
| "epoch": 0.835820895522388, | |
| "grad_norm": 0.11268918840030598, | |
| "kl": 0.0112152099609375, | |
| "learning_rate": 1.7077556860568238e-07, | |
| "loss": 0.0146, | |
| "reward": 0.7968750149011612, | |
| "reward_std": 0.2770479694008827, | |
| "rewards/accuracy_reward": 0.3645833432674408, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.432291679084301, | |
| "step": 98 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 817.0625305175781, | |
| "epoch": 0.8443496801705757, | |
| "grad_norm": 0.11763553136010904, | |
| "kl": 0.01142120361328125, | |
| "learning_rate": 1.6369804287916025e-07, | |
| "loss": 0.0342, | |
| "reward": 0.860677108168602, | |
| "reward_std": 0.2829681634902954, | |
| "rewards/accuracy_reward": 0.4062500074505806, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4544270932674408, | |
| "step": 99 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 791.9791717529297, | |
| "epoch": 0.8528784648187633, | |
| "grad_norm": 0.12058635085867997, | |
| "kl": 0.0102996826171875, | |
| "learning_rate": 1.5696630972229166e-07, | |
| "loss": 0.0342, | |
| "reward": 0.927083358168602, | |
| "reward_std": 0.3461384028196335, | |
| "rewards/accuracy_reward": 0.4270833432674408, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.5000000223517418, | |
| "step": 100 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 787.3594055175781, | |
| "epoch": 0.8614072494669509, | |
| "grad_norm": 0.13223369624098508, | |
| "kl": 0.0110626220703125, | |
| "learning_rate": 1.5058639494795067e-07, | |
| "loss": 0.0514, | |
| "reward": 0.9804687947034836, | |
| "reward_std": 0.33672135323286057, | |
| "rewards/accuracy_reward": 0.4375000149011612, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.5429687723517418, | |
| "step": 101 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 781.0364837646484, | |
| "epoch": 0.8699360341151386, | |
| "grad_norm": 0.12924436581025062, | |
| "kl": 0.0109710693359375, | |
| "learning_rate": 1.4456400944391144e-07, | |
| "loss": 0.0326, | |
| "reward": 0.971354216337204, | |
| "reward_std": 0.35067974030971527, | |
| "rewards/accuracy_reward": 0.4791666939854622, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4921875223517418, | |
| "step": 102 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 815.4792022705078, | |
| "epoch": 0.8784648187633263, | |
| "grad_norm": 0.12735565071518637, | |
| "kl": 0.0097808837890625, | |
| "learning_rate": 1.3890454406082956e-07, | |
| "loss": 0.0469, | |
| "reward": 0.9609375298023224, | |
| "reward_std": 0.31679093837738037, | |
| "rewards/accuracy_reward": 0.4583333432674408, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.5026041865348816, | |
| "step": 103 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 820.6198120117188, | |
| "epoch": 0.8869936034115139, | |
| "grad_norm": 0.11515316700594094, | |
| "kl": 0.0109100341796875, | |
| "learning_rate": 1.3361306478670148e-07, | |
| "loss": 0.0367, | |
| "reward": 0.9244792014360428, | |
| "reward_std": 0.25151925161480904, | |
| "rewards/accuracy_reward": 0.4270833432674408, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.497395858168602, | |
| "step": 104 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 759.3281555175781, | |
| "epoch": 0.8955223880597015, | |
| "grad_norm": 0.14319190866589507, | |
| "kl": 0.0105133056640625, | |
| "learning_rate": 1.2869430821211826e-07, | |
| "loss": 0.0298, | |
| "reward": 0.9596354514360428, | |
| "reward_std": 0.2728368118405342, | |
| "rewards/accuracy_reward": 0.4583333507180214, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.501302108168602, | |
| "step": 105 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 818.6614837646484, | |
| "epoch": 0.9040511727078892, | |
| "grad_norm": 0.10985275674671954, | |
| "kl": 0.0103302001953125, | |
| "learning_rate": 1.2415267729037608e-07, | |
| "loss": 0.0311, | |
| "reward": 0.8710937649011612, | |
| "reward_std": 0.2647658996284008, | |
| "rewards/accuracy_reward": 0.4010416865348816, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4700521007180214, | |
| "step": 106 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 775.0625152587891, | |
| "epoch": 0.9125799573560768, | |
| "grad_norm": 0.1272726543004608, | |
| "kl": 0.0119171142578125, | |
| "learning_rate": 1.1999223739623666e-07, | |
| "loss": 0.0317, | |
| "reward": 0.9244791865348816, | |
| "reward_std": 0.2937668412923813, | |
| "rewards/accuracy_reward": 0.432291679084301, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4921875149011612, | |
| "step": 107 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 792.1979370117188, | |
| "epoch": 0.9211087420042644, | |
| "grad_norm": 0.1363433345784819, | |
| "kl": 0.0108795166015625, | |
| "learning_rate": 1.1621671268686605e-07, | |
| "loss": 0.0482, | |
| "reward": 0.950520858168602, | |
| "reward_std": 0.2951006144285202, | |
| "rewards/accuracy_reward": 0.4427083432674408, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.5078125149011612, | |
| "step": 108 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 840.5989837646484, | |
| "epoch": 0.929637526652452, | |
| "grad_norm": 0.11723986953897444, | |
| "kl": 0.0102691650390625, | |
| "learning_rate": 1.1282948276820962e-07, | |
| "loss": 0.0323, | |
| "reward": 0.903645858168602, | |
| "reward_std": 0.31709685176610947, | |
| "rewards/accuracy_reward": 0.4114583432674408, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4921875223517418, | |
| "step": 109 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 785.3125, | |
| "epoch": 0.9381663113006397, | |
| "grad_norm": 0.1303189109965419, | |
| "kl": 0.0109100341796875, | |
| "learning_rate": 1.0983357966978745e-07, | |
| "loss": 0.0299, | |
| "reward": 0.973958358168602, | |
| "reward_std": 0.3055407963693142, | |
| "rewards/accuracy_reward": 0.4479166865348816, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.526041679084301, | |
| "step": 110 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 812.7916870117188, | |
| "epoch": 0.9466950959488273, | |
| "grad_norm": 0.13474852991113115, | |
| "kl": 0.011871337890625, | |
| "learning_rate": 1.0723168513061665e-07, | |
| "loss": 0.0379, | |
| "reward": 0.864583358168602, | |
| "reward_std": 0.2699150890111923, | |
| "rewards/accuracy_reward": 0.3906250149011612, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4739583432674408, | |
| "step": 111 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 828.9948120117188, | |
| "epoch": 0.9552238805970149, | |
| "grad_norm": 0.15444917838378422, | |
| "kl": 0.0113677978515625, | |
| "learning_rate": 1.0502612819869216e-07, | |
| "loss": 0.056, | |
| "reward": 0.9531250149011612, | |
| "reward_std": 0.40493085235357285, | |
| "rewards/accuracy_reward": 0.4375000223517418, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.5156250149011612, | |
| "step": 112 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 758.9791870117188, | |
| "epoch": 0.9637526652452025, | |
| "grad_norm": 0.11394166249687963, | |
| "kl": 0.0107421875, | |
| "learning_rate": 1.032188831461732e-07, | |
| "loss": 0.0172, | |
| "reward": 1.0195312649011612, | |
| "reward_std": 0.23920952156186104, | |
| "rewards/accuracy_reward": 0.5260416865348816, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4934895932674408, | |
| "step": 113 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 835.1614685058594, | |
| "epoch": 0.9722814498933902, | |
| "grad_norm": 0.14157333655394927, | |
| "kl": 0.0106353759765625, | |
| "learning_rate": 1.0181156770214242e-07, | |
| "loss": 0.0532, | |
| "reward": 0.8906250149011612, | |
| "reward_std": 0.344898097217083, | |
| "rewards/accuracy_reward": 0.4010416753590107, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4895833507180214, | |
| "step": 114 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 784.8802337646484, | |
| "epoch": 0.9808102345415778, | |
| "grad_norm": 0.12045891162749811, | |
| "kl": 0.0106201171875, | |
| "learning_rate": 1.0080544160451918e-07, | |
| "loss": 0.0387, | |
| "reward": 0.9531250149011612, | |
| "reward_std": 0.3491218537092209, | |
| "rewards/accuracy_reward": 0.4479166865348816, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.5052083507180214, | |
| "step": 115 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 826.1719055175781, | |
| "epoch": 0.9893390191897654, | |
| "grad_norm": 0.1211356758875429, | |
| "kl": 0.01165771484375, | |
| "learning_rate": 1.002014054724235e-07, | |
| "loss": 0.0394, | |
| "reward": 0.9440104514360428, | |
| "reward_std": 0.30041512846946716, | |
| "rewards/accuracy_reward": 0.4583333432674408, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4856770932674408, | |
| "step": 116 | |
| }, | |
| { | |
| "clip_ratio": 0.0, | |
| "completion_length": 895.8125152587891, | |
| "epoch": 0.997867803837953, | |
| "grad_norm": 0.14489529140501242, | |
| "kl": 0.009857177734375, | |
| "learning_rate": 1e-07, | |
| "loss": 0.054, | |
| "reward": 0.9101562649011612, | |
| "reward_std": 0.3278352990746498, | |
| "rewards/accuracy_reward": 0.416666679084301, | |
| "rewards/format_reward": 0.0, | |
| "rewards/tag_count_reward": 0.4934896007180214, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.997867803837953, | |
| "step": 117, | |
| "total_flos": 0.0, | |
| "train_loss": 0.03437558454899197, | |
| "train_runtime": 4123.9479, | |
| "train_samples_per_second": 1.819, | |
| "train_steps_per_second": 0.028 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 117, | |
| "num_input_tokens_seen": 0, | |
| "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 | |
| } | |