| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 1660, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.060350030175015085, | |
| "grad_norm": 4.037877082824707, | |
| "learning_rate": 5.76e-05, | |
| "loss": 3.1642, | |
| "mean_token_accuracy": 0.4683700659871101, | |
| "num_tokens": 161483.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12070006035003017, | |
| "grad_norm": 1.468239665031433, | |
| "learning_rate": 0.0001176, | |
| "loss": 1.5845, | |
| "mean_token_accuracy": 0.6552255868911743, | |
| "num_tokens": 294759.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.18105009052504525, | |
| "grad_norm": 0.647505521774292, | |
| "learning_rate": 0.00017759999999999998, | |
| "loss": 0.7171, | |
| "mean_token_accuracy": 0.8258614861965179, | |
| "num_tokens": 456515.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.24140012070006034, | |
| "grad_norm": 0.8074957728385925, | |
| "learning_rate": 0.0002376, | |
| "loss": 0.5756, | |
| "mean_token_accuracy": 0.8531174421310425, | |
| "num_tokens": 588873.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.30175015087507545, | |
| "grad_norm": 0.8116180896759033, | |
| "learning_rate": 0.00029759999999999997, | |
| "loss": 0.4766, | |
| "mean_token_accuracy": 0.8744671362638473, | |
| "num_tokens": 750990.0, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.3621001810500905, | |
| "grad_norm": 1.6603596210479736, | |
| "learning_rate": 0.00029997368283986634, | |
| "loss": 0.4431, | |
| "mean_token_accuracy": 0.8835952073335648, | |
| "num_tokens": 884144.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.4224502112251056, | |
| "grad_norm": 0.8336510062217712, | |
| "learning_rate": 0.0002998903096401296, | |
| "loss": 0.3611, | |
| "mean_token_accuracy": 0.9041859984397889, | |
| "num_tokens": 1046790.0, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.4828002414001207, | |
| "grad_norm": 0.987082839012146, | |
| "learning_rate": 0.0002997498664538712, | |
| "loss": 0.3448, | |
| "mean_token_accuracy": 0.9090080863237381, | |
| "num_tokens": 1180257.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5431502715751357, | |
| "grad_norm": 0.8808548450469971, | |
| "learning_rate": 0.0002995524067541326, | |
| "loss": 0.2672, | |
| "mean_token_accuracy": 0.9280223268270492, | |
| "num_tokens": 1343936.0, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.6035003017501509, | |
| "grad_norm": 1.027520775794983, | |
| "learning_rate": 0.00029929800572270793, | |
| "loss": 0.2833, | |
| "mean_token_accuracy": 0.9247983312606811, | |
| "num_tokens": 1477991.0, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.663850331925166, | |
| "grad_norm": 0.6596710085868835, | |
| "learning_rate": 0.00029898676022151893, | |
| "loss": 0.2162, | |
| "mean_token_accuracy": 0.9414234220981598, | |
| "num_tokens": 1640162.0, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.724200362100181, | |
| "grad_norm": 1.1629737615585327, | |
| "learning_rate": 0.00029861878875573505, | |
| "loss": 0.2106, | |
| "mean_token_accuracy": 0.9432486313581466, | |
| "num_tokens": 1773232.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7845503922751962, | |
| "grad_norm": 0.838697612285614, | |
| "learning_rate": 0.0002981942314286536, | |
| "loss": 0.1735, | |
| "mean_token_accuracy": 0.9535212635993957, | |
| "num_tokens": 1935668.0, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.8449004224502112, | |
| "grad_norm": 1.079795479774475, | |
| "learning_rate": 0.0002977132498883555, | |
| "loss": 0.1661, | |
| "mean_token_accuracy": 0.9547489368915558, | |
| "num_tokens": 2068608.0, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.9052504526252263, | |
| "grad_norm": 0.6005878448486328, | |
| "learning_rate": 0.0002971760272661594, | |
| "loss": 0.1547, | |
| "mean_token_accuracy": 0.959057599902153, | |
| "num_tokens": 2230863.0, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.9656004828002414, | |
| "grad_norm": 0.9613809585571289, | |
| "learning_rate": 0.00029658276810689443, | |
| "loss": 0.1472, | |
| "mean_token_accuracy": 0.9600884807109833, | |
| "num_tokens": 2363937.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.1443626582622528, | |
| "eval_mean_token_accuracy": 0.960926349098618, | |
| "eval_num_tokens": 2448118.0, | |
| "eval_runtime": 259.3789, | |
| "eval_samples_per_second": 1.423, | |
| "eval_steps_per_second": 0.713, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 1.024140012070006, | |
| "grad_norm": 0.6829183101654053, | |
| "learning_rate": 0.0002959336982910217, | |
| "loss": 0.1492, | |
| "mean_token_accuracy": 0.9617758946320445, | |
| "num_tokens": 2519362.0, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.0844900422450212, | |
| "grad_norm": 0.792141854763031, | |
| "learning_rate": 0.0002952290649486306, | |
| "loss": 0.0897, | |
| "mean_token_accuracy": 0.974867417216301, | |
| "num_tokens": 2668621.0, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.1448400724200363, | |
| "grad_norm": 0.5825597643852234, | |
| "learning_rate": 0.0002944691363653459, | |
| "loss": 0.1148, | |
| "mean_token_accuracy": 0.9691734218597412, | |
| "num_tokens": 2815906.0, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.2051901025950513, | |
| "grad_norm": 0.6245791912078857, | |
| "learning_rate": 0.0002936542018801788, | |
| "loss": 0.0923, | |
| "mean_token_accuracy": 0.9748454135656357, | |
| "num_tokens": 2964114.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.2655401327700664, | |
| "grad_norm": 0.58636873960495, | |
| "learning_rate": 0.0002927845717753632, | |
| "loss": 0.1154, | |
| "mean_token_accuracy": 0.9687699192762375, | |
| "num_tokens": 3111714.0, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 1.3258901629450814, | |
| "grad_norm": 0.8928817510604858, | |
| "learning_rate": 0.00029186057715821663, | |
| "loss": 0.0886, | |
| "mean_token_accuracy": 0.976014096736908, | |
| "num_tokens": 3258422.0, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.3862401931200965, | |
| "grad_norm": 0.5934416055679321, | |
| "learning_rate": 0.0002908825698350731, | |
| "loss": 0.0996, | |
| "mean_token_accuracy": 0.9732701396942138, | |
| "num_tokens": 3405648.0, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 1.4465902232951118, | |
| "grad_norm": 0.4363284707069397, | |
| "learning_rate": 0.00028985092217733463, | |
| "loss": 0.0679, | |
| "mean_token_accuracy": 0.9816953223943711, | |
| "num_tokens": 3553294.0, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.5069402534701268, | |
| "grad_norm": 0.6062431335449219, | |
| "learning_rate": 0.0002887660269796928, | |
| "loss": 0.1015, | |
| "mean_token_accuracy": 0.9734577733278275, | |
| "num_tokens": 3699909.0, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 1.567290283645142, | |
| "grad_norm": 0.6455872654914856, | |
| "learning_rate": 0.0002876282973105736, | |
| "loss": 0.0657, | |
| "mean_token_accuracy": 0.9815398609638214, | |
| "num_tokens": 3847893.0, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.627640313820157, | |
| "grad_norm": 0.547113835811615, | |
| "learning_rate": 0.0002864381663548645, | |
| "loss": 0.1034, | |
| "mean_token_accuracy": 0.9735846078395843, | |
| "num_tokens": 3994245.0, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 1.687990343995172, | |
| "grad_norm": 0.6483117938041687, | |
| "learning_rate": 0.0002851960872489806, | |
| "loss": 0.0634, | |
| "mean_token_accuracy": 0.9827442276477814, | |
| "num_tokens": 4144165.0, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.748340374170187, | |
| "grad_norm": 0.4899543523788452, | |
| "learning_rate": 0.00028390253290833605, | |
| "loss": 0.0942, | |
| "mean_token_accuracy": 0.9755072242021561, | |
| "num_tokens": 4291469.0, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 1.8086904043452021, | |
| "grad_norm": 0.5036582350730896, | |
| "learning_rate": 0.0002825579958472832, | |
| "loss": 0.0639, | |
| "mean_token_accuracy": 0.9823815160989762, | |
| "num_tokens": 4439415.0, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.8690404345202172, | |
| "grad_norm": 0.4868822693824768, | |
| "learning_rate": 0.00028116298799159045, | |
| "loss": 0.0787, | |
| "mean_token_accuracy": 0.9785297274589538, | |
| "num_tokens": 4587739.0, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 1.9293904646952322, | |
| "grad_norm": 0.4633966386318207, | |
| "learning_rate": 0.00027971804048352927, | |
| "loss": 0.0618, | |
| "mean_token_accuracy": 0.9832005858421325, | |
| "num_tokens": 4736249.0, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.9897404948702473, | |
| "grad_norm": 0.6208447217941284, | |
| "learning_rate": 0.0002782237034796442, | |
| "loss": 0.0665, | |
| "mean_token_accuracy": 0.9821873652935028, | |
| "num_tokens": 4875075.0, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.07273826748132706, | |
| "eval_mean_token_accuracy": 0.9805045517715247, | |
| "eval_num_tokens": 4896236.0, | |
| "eval_runtime": 259.4448, | |
| "eval_samples_per_second": 1.422, | |
| "eval_steps_per_second": 0.713, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.048280024140012, | |
| "grad_norm": 0.5759810209274292, | |
| "learning_rate": 0.0002766805459412835, | |
| "loss": 0.0716, | |
| "mean_token_accuracy": 0.9827596778722153, | |
| "num_tokens": 5028174.0, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.1086300543150274, | |
| "grad_norm": 0.4573070704936981, | |
| "learning_rate": 0.0002750891554179702, | |
| "loss": 0.0469, | |
| "mean_token_accuracy": 0.9868157178163528, | |
| "num_tokens": 5168210.0, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 2.1689800844900424, | |
| "grad_norm": 0.41777142882347107, | |
| "learning_rate": 0.000273450137823695, | |
| "loss": 0.0771, | |
| "mean_token_accuracy": 0.9796839380264282, | |
| "num_tokens": 5326702.0, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.2293301146650575, | |
| "grad_norm": 0.6522343754768372, | |
| "learning_rate": 0.00027176411720621833, | |
| "loss": 0.0467, | |
| "mean_token_accuracy": 0.9872583884000778, | |
| "num_tokens": 5467246.0, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 2.2896801448400725, | |
| "grad_norm": 0.475888729095459, | |
| "learning_rate": 0.00027003173550946665, | |
| "loss": 0.0672, | |
| "mean_token_accuracy": 0.9817777210474015, | |
| "num_tokens": 5620161.0, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.3500301750150876, | |
| "grad_norm": 0.5362425446510315, | |
| "learning_rate": 0.00026825365232911573, | |
| "loss": 0.0469, | |
| "mean_token_accuracy": 0.9871275025606155, | |
| "num_tokens": 5757651.0, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 2.4103802051901027, | |
| "grad_norm": 0.3906894326210022, | |
| "learning_rate": 0.00026643054466145294, | |
| "loss": 0.0655, | |
| "mean_token_accuracy": 0.9822571390867233, | |
| "num_tokens": 5912849.0, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.4707302353651177, | |
| "grad_norm": 0.4455728828907013, | |
| "learning_rate": 0.00026456310664561426, | |
| "loss": 0.0456, | |
| "mean_token_accuracy": 0.9875413435697555, | |
| "num_tokens": 6050687.0, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 2.5310802655401328, | |
| "grad_norm": 0.37768128514289856, | |
| "learning_rate": 0.00026265204929929413, | |
| "loss": 0.0636, | |
| "mean_token_accuracy": 0.9826168727874756, | |
| "num_tokens": 6208352.0, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.591430295715148, | |
| "grad_norm": 0.644298255443573, | |
| "learning_rate": 0.0002606981002480294, | |
| "loss": 0.0468, | |
| "mean_token_accuracy": 0.9868322855234146, | |
| "num_tokens": 6347260.0, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 2.651780325890163, | |
| "grad_norm": 0.41656455397605896, | |
| "learning_rate": 0.00025870200344815905, | |
| "loss": 0.0626, | |
| "mean_token_accuracy": 0.9830433952808381, | |
| "num_tokens": 6504918.0, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.712130356065178, | |
| "grad_norm": 0.438490092754364, | |
| "learning_rate": 0.00025666451890356674, | |
| "loss": 0.0472, | |
| "mean_token_accuracy": 0.9869848346710205, | |
| "num_tokens": 6643886.0, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 2.772480386240193, | |
| "grad_norm": 0.5694201588630676, | |
| "learning_rate": 0.0002545864223763134, | |
| "loss": 0.0619, | |
| "mean_token_accuracy": 0.9835321408510208, | |
| "num_tokens": 6799221.0, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.832830416415208, | |
| "grad_norm": 0.3199928402900696, | |
| "learning_rate": 0.00025246850509126926, | |
| "loss": 0.0428, | |
| "mean_token_accuracy": 0.9882478666305542, | |
| "num_tokens": 6937936.0, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 2.8931804465902236, | |
| "grad_norm": 0.3072766661643982, | |
| "learning_rate": 0.00025031157343485924, | |
| "loss": 0.0616, | |
| "mean_token_accuracy": 0.9832239282131195, | |
| "num_tokens": 7097502.0, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.9535304767652386, | |
| "grad_norm": 0.46456214785575867, | |
| "learning_rate": 0.000248116448648035, | |
| "loss": 0.0413, | |
| "mean_token_accuracy": 0.9884889626502991, | |
| "num_tokens": 7237082.0, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.05654008686542511, | |
| "eval_mean_token_accuracy": 0.9848334161010949, | |
| "eval_num_tokens": 7344354.0, | |
| "eval_runtime": 260.2642, | |
| "eval_samples_per_second": 1.418, | |
| "eval_steps_per_second": 0.711, | |
| "step": 1245 | |
| }, | |
| { | |
| "epoch": 3.012070006035003, | |
| "grad_norm": 0.36259251832962036, | |
| "learning_rate": 0.0002458839665135921, | |
| "loss": 0.0558, | |
| "mean_token_accuracy": 0.9843784410928943, | |
| "num_tokens": 7382070.0, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 3.0724200362100182, | |
| "grad_norm": 0.33617448806762695, | |
| "learning_rate": 0.00024361497703794942, | |
| "loss": 0.0378, | |
| "mean_token_accuracy": 0.9890254312753677, | |
| "num_tokens": 7534586.0, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 3.1327700663850333, | |
| "grad_norm": 0.25698503851890564, | |
| "learning_rate": 0.0002413103441275136, | |
| "loss": 0.0452, | |
| "mean_token_accuracy": 0.9873906564712525, | |
| "num_tokens": 7677109.0, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 3.1931200965600484, | |
| "grad_norm": 0.34490227699279785, | |
| "learning_rate": 0.00023897094525975098, | |
| "loss": 0.0411, | |
| "mean_token_accuracy": 0.9885961890220643, | |
| "num_tokens": 7831173.0, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 3.2534701267350634, | |
| "grad_norm": 0.3397490978240967, | |
| "learning_rate": 0.00023659767114909245, | |
| "loss": 0.0438, | |
| "mean_token_accuracy": 0.9878141868114472, | |
| "num_tokens": 7972828.0, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 3.3138201569100785, | |
| "grad_norm": 0.5912103056907654, | |
| "learning_rate": 0.0002341914254077985, | |
| "loss": 0.0361, | |
| "mean_token_accuracy": 0.9897723388671875, | |
| "num_tokens": 8126638.0, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 3.3741701870850935, | |
| "grad_norm": 0.3524228632450104, | |
| "learning_rate": 0.00023175312420191312, | |
| "loss": 0.0458, | |
| "mean_token_accuracy": 0.9871816504001617, | |
| "num_tokens": 8268641.0, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.4345202172601086, | |
| "grad_norm": 0.4089486598968506, | |
| "learning_rate": 0.00022928369590243834, | |
| "loss": 0.0364, | |
| "mean_token_accuracy": 0.9894253730773925, | |
| "num_tokens": 8421996.0, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 3.4948702474351236, | |
| "grad_norm": 0.32915744185447693, | |
| "learning_rate": 0.00022678408073186163, | |
| "loss": 0.0482, | |
| "mean_token_accuracy": 0.9867742687463761, | |
| "num_tokens": 8563876.0, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 3.5552202776101387, | |
| "grad_norm": 0.2799423635005951, | |
| "learning_rate": 0.0002242552304061707, | |
| "loss": 0.0391, | |
| "mean_token_accuracy": 0.9891943109035491, | |
| "num_tokens": 8716396.0, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 3.6155703077851538, | |
| "grad_norm": 0.34400495886802673, | |
| "learning_rate": 0.00022169810777249253, | |
| "loss": 0.0465, | |
| "mean_token_accuracy": 0.9871583390235901, | |
| "num_tokens": 8858385.0, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.675920337960169, | |
| "grad_norm": 0.2578590512275696, | |
| "learning_rate": 0.00021911368644249416, | |
| "loss": 0.0389, | |
| "mean_token_accuracy": 0.9889793866872787, | |
| "num_tokens": 9014977.0, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 3.736270368135184, | |
| "grad_norm": 0.4556424617767334, | |
| "learning_rate": 0.00021650295042168486, | |
| "loss": 0.0463, | |
| "mean_token_accuracy": 0.987366048693657, | |
| "num_tokens": 9157309.0, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 3.796620398310199, | |
| "grad_norm": 0.20752571523189545, | |
| "learning_rate": 0.00021386689373476087, | |
| "loss": 0.0357, | |
| "mean_token_accuracy": 0.989637770652771, | |
| "num_tokens": 9310269.0, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 3.856970428485214, | |
| "grad_norm": 0.5105423927307129, | |
| "learning_rate": 0.0002112065200471357, | |
| "loss": 0.0433, | |
| "mean_token_accuracy": 0.9879990059137345, | |
| "num_tokens": 9451742.0, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 3.9173204586602295, | |
| "grad_norm": 0.2212332934141159, | |
| "learning_rate": 0.00020852284228279925, | |
| "loss": 0.0364, | |
| "mean_token_accuracy": 0.9894431579113007, | |
| "num_tokens": 9604731.0, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 3.9776704888352445, | |
| "grad_norm": 0.23504111170768738, | |
| "learning_rate": 0.00020581688223865225, | |
| "loss": 0.0392, | |
| "mean_token_accuracy": 0.9891186225414276, | |
| "num_tokens": 9742102.0, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.04928135126829147, | |
| "eval_mean_token_accuracy": 0.9872021871644098, | |
| "eval_num_tokens": 9792472.0, | |
| "eval_runtime": 258.8897, | |
| "eval_samples_per_second": 1.425, | |
| "eval_steps_per_second": 0.715, | |
| "step": 1660 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 4150, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1969928185525258e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |