| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 119380, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 2.0833333333333333e-05, | |
| "loss": 7.7261, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.1666666666666665e-05, | |
| "loss": 5.5648, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 6.25e-05, | |
| "loss": 5.0119, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 8.333333333333333e-05, | |
| "loss": 4.6599, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00010416666666666667, | |
| "loss": 4.3568, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.000125, | |
| "loss": 4.1194, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00014583333333333335, | |
| "loss": 3.8926, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00016666666666666666, | |
| "loss": 3.778, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0001875, | |
| "loss": 3.65, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00020833333333333335, | |
| "loss": 3.6165, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.00022916666666666666, | |
| "loss": 3.5523, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.3512480392306169, | |
| "eval_loss": 3.490408420562744, | |
| "eval_runtime": 8.7154, | |
| "eval_samples_per_second": 8031.783, | |
| "eval_steps_per_second": 15.719, | |
| "step": 11938 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.00025, | |
| "loss": 3.4876, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.0002708333333333333, | |
| "loss": 3.4466, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.0002916666666666667, | |
| "loss": 3.4306, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.0003125, | |
| "loss": 3.39, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.0003333333333333333, | |
| "loss": 3.3891, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.0003541666666666667, | |
| "loss": 3.367, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.000375, | |
| "loss": 3.3546, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.0003958333333333333, | |
| "loss": 3.3348, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.0004166666666666667, | |
| "loss": 3.3235, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.0004375, | |
| "loss": 3.3207, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.0004583333333333333, | |
| "loss": 3.3028, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.0004791666666666667, | |
| "loss": 3.3151, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.36783764827859605, | |
| "eval_loss": 3.319209098815918, | |
| "eval_runtime": 8.6438, | |
| "eval_samples_per_second": 8098.333, | |
| "eval_steps_per_second": 15.85, | |
| "step": 23876 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 0.0005, | |
| "loss": 3.2991, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 0.0004947578108618159, | |
| "loss": 3.3032, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 0.0004895156217236318, | |
| "loss": 3.2872, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 0.0004842734325854477, | |
| "loss": 3.2814, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 0.0004790312434472636, | |
| "loss": 3.2595, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 0.0004737890543090795, | |
| "loss": 3.2423, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 0.0004685468651708954, | |
| "loss": 3.2336, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 0.00046330467603271125, | |
| "loss": 3.2224, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 0.00045806248689452716, | |
| "loss": 3.1981, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 0.000452820297756343, | |
| "loss": 3.1808, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 0.00044757810861815897, | |
| "loss": 3.1593, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 0.0004423359194799749, | |
| "loss": 3.1526, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.3893979057591623, | |
| "eval_loss": 3.154465675354004, | |
| "eval_runtime": 8.7169, | |
| "eval_samples_per_second": 8030.369, | |
| "eval_steps_per_second": 15.717, | |
| "step": 35814 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 0.00043709373034179073, | |
| "loss": 3.1466, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 0.00043185154120360664, | |
| "loss": 3.1035, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 0.0004266093520654225, | |
| "loss": 3.0893, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 0.0004213671629272384, | |
| "loss": 3.1148, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 0.00041612497378905436, | |
| "loss": 3.0801, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 0.0004108827846508702, | |
| "loss": 3.0814, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 0.0004056405955126861, | |
| "loss": 3.0665, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 0.00040039840637450197, | |
| "loss": 3.0718, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 0.0003951562172363179, | |
| "loss": 3.0462, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 0.0003899140280981338, | |
| "loss": 3.0328, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 0.0003846718389599497, | |
| "loss": 3.0601, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 0.0003794296498217656, | |
| "loss": 3.0031, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.3971048095550437, | |
| "eval_loss": 3.0706326961517334, | |
| "eval_runtime": 8.6604, | |
| "eval_samples_per_second": 8082.758, | |
| "eval_steps_per_second": 15.819, | |
| "step": 47752 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 0.00037418746068358145, | |
| "loss": 3.0134, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 0.00036894527154539736, | |
| "loss": 3.0064, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 0.00036370308240721327, | |
| "loss": 2.9887, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 0.0003584608932690291, | |
| "loss": 2.9757, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 0.0003532187041308451, | |
| "loss": 2.9678, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 0.00034797651499266093, | |
| "loss": 2.964, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 0.00034273432585447684, | |
| "loss": 2.9642, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "learning_rate": 0.00033749213671629275, | |
| "loss": 2.9797, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 0.0003322499475781086, | |
| "loss": 2.9534, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 0.0003270077584399245, | |
| "loss": 2.9476, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 0.0003217655693017404, | |
| "loss": 2.9431, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 0.0003165233801635563, | |
| "loss": 2.9668, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.41213198432230425, | |
| "eval_loss": 2.9605636596679688, | |
| "eval_runtime": 8.7459, | |
| "eval_samples_per_second": 8003.788, | |
| "eval_steps_per_second": 15.665, | |
| "step": 59690 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 0.00031128119102537223, | |
| "loss": 2.9106, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 0.0003060390018871881, | |
| "loss": 2.9053, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 5.19, | |
| "learning_rate": 0.000300796812749004, | |
| "loss": 2.8983, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 0.00029555462361081984, | |
| "loss": 2.8828, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 5.36, | |
| "learning_rate": 0.0002903124344726358, | |
| "loss": 2.8971, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "learning_rate": 0.0002850702453344517, | |
| "loss": 2.9074, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "learning_rate": 0.00027982805619626756, | |
| "loss": 2.8792, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "learning_rate": 0.00027458586705808347, | |
| "loss": 2.8902, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 0.0002693436779198993, | |
| "loss": 2.8666, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 5.78, | |
| "learning_rate": 0.00026410148878171523, | |
| "loss": 2.8868, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 0.0002588592996435312, | |
| "loss": 2.8509, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "learning_rate": 0.00025361711050534704, | |
| "loss": 2.8548, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.4243559291065229, | |
| "eval_loss": 2.8717477321624756, | |
| "eval_runtime": 8.7188, | |
| "eval_samples_per_second": 8028.594, | |
| "eval_steps_per_second": 15.713, | |
| "step": 71628 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "learning_rate": 0.00024837492136716295, | |
| "loss": 2.8484, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "learning_rate": 0.00024313273222897883, | |
| "loss": 2.8266, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 6.2, | |
| "learning_rate": 0.0002378905430907947, | |
| "loss": 2.8247, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "learning_rate": 0.00023264835395261061, | |
| "loss": 2.8151, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 6.37, | |
| "learning_rate": 0.0002274061648144265, | |
| "loss": 2.8078, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 6.45, | |
| "learning_rate": 0.0002221639756762424, | |
| "loss": 2.8143, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "learning_rate": 0.0002169217865380583, | |
| "loss": 2.8043, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "learning_rate": 0.0002116795973998742, | |
| "loss": 2.8159, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "learning_rate": 0.00020643740826169007, | |
| "loss": 2.7825, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 6.79, | |
| "learning_rate": 0.00020119521912350598, | |
| "loss": 2.812, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 6.87, | |
| "learning_rate": 0.00019595302998532188, | |
| "loss": 2.766, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 6.95, | |
| "learning_rate": 0.00019071084084713776, | |
| "loss": 2.7686, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.4311035312390553, | |
| "eval_loss": 2.8147239685058594, | |
| "eval_runtime": 8.6579, | |
| "eval_samples_per_second": 8085.129, | |
| "eval_steps_per_second": 15.824, | |
| "step": 83566 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 0.00018546865170895367, | |
| "loss": 2.7648, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 7.12, | |
| "learning_rate": 0.00018022646257076955, | |
| "loss": 2.7609, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 0.00017498427343258543, | |
| "loss": 2.7306, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 7.29, | |
| "learning_rate": 0.00016974208429440136, | |
| "loss": 2.718, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "learning_rate": 0.00016449989515621724, | |
| "loss": 2.7218, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 7.46, | |
| "learning_rate": 0.00015925770601803312, | |
| "loss": 2.7624, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 7.54, | |
| "learning_rate": 0.00015401551687984903, | |
| "loss": 2.7478, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 7.62, | |
| "learning_rate": 0.0001487733277416649, | |
| "loss": 2.7372, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "learning_rate": 0.00014353113860348082, | |
| "loss": 2.7467, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 7.79, | |
| "learning_rate": 0.00013828894946529672, | |
| "loss": 2.7205, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 7.87, | |
| "learning_rate": 0.0001330467603271126, | |
| "loss": 2.7269, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "learning_rate": 0.00012780457118892848, | |
| "loss": 2.7195, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.4389084267882209, | |
| "eval_loss": 2.7656898498535156, | |
| "eval_runtime": 8.6162, | |
| "eval_samples_per_second": 8124.227, | |
| "eval_steps_per_second": 15.9, | |
| "step": 95504 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "learning_rate": 0.0001225623820507444, | |
| "loss": 2.7004, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 8.13, | |
| "learning_rate": 0.00011732019291256028, | |
| "loss": 2.7043, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 8.21, | |
| "learning_rate": 0.00011207800377437619, | |
| "loss": 2.7322, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 8.29, | |
| "learning_rate": 0.00010683581463619207, | |
| "loss": 2.6874, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 8.38, | |
| "learning_rate": 0.00010159362549800798, | |
| "loss": 2.6771, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 8.46, | |
| "learning_rate": 9.635143635982387e-05, | |
| "loss": 2.6827, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 8.54, | |
| "learning_rate": 9.110924722163975e-05, | |
| "loss": 2.6756, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 8.63, | |
| "learning_rate": 8.586705808345566e-05, | |
| "loss": 2.6575, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 8.71, | |
| "learning_rate": 8.062486894527155e-05, | |
| "loss": 2.669, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 7.538267980708744e-05, | |
| "loss": 2.6623, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 8.88, | |
| "learning_rate": 7.014049066890334e-05, | |
| "loss": 2.6518, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "learning_rate": 6.489830153071923e-05, | |
| "loss": 2.6659, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.4483279917760174, | |
| "eval_loss": 2.710298538208008, | |
| "eval_runtime": 8.5942, | |
| "eval_samples_per_second": 8145.024, | |
| "eval_steps_per_second": 15.941, | |
| "step": 107442 | |
| }, | |
| { | |
| "epoch": 9.05, | |
| "learning_rate": 5.965611239253512e-05, | |
| "loss": 2.6505, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 9.13, | |
| "learning_rate": 5.441392325435102e-05, | |
| "loss": 2.6367, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 9.21, | |
| "learning_rate": 4.917173411616691e-05, | |
| "loss": 2.6232, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "learning_rate": 4.3929544977982805e-05, | |
| "loss": 2.6453, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "learning_rate": 3.8687355839798705e-05, | |
| "loss": 2.6565, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 3.344516670161459e-05, | |
| "loss": 2.6244, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 9.55, | |
| "learning_rate": 2.820297756343049e-05, | |
| "loss": 2.6429, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 9.63, | |
| "learning_rate": 2.2960788425246382e-05, | |
| "loss": 2.6117, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 9.72, | |
| "learning_rate": 1.771859928706228e-05, | |
| "loss": 2.6289, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 9.8, | |
| "learning_rate": 1.2476410148878172e-05, | |
| "loss": 2.6174, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 9.88, | |
| "learning_rate": 7.234221010694066e-06, | |
| "loss": 2.6142, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 9.97, | |
| "learning_rate": 1.99203187250996e-06, | |
| "loss": 2.6254, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.4510256799878438, | |
| "eval_loss": 2.699005126953125, | |
| "eval_runtime": 8.5626, | |
| "eval_samples_per_second": 8175.05, | |
| "eval_steps_per_second": 16.0, | |
| "step": 119380 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 119380, | |
| "total_flos": 6556448698096128.0, | |
| "train_loss": 3.079910436302079, | |
| "train_runtime": 7252.3341, | |
| "train_samples_per_second": 1053.439, | |
| "train_steps_per_second": 16.461 | |
| } | |
| ], | |
| "logging_steps": 1000, | |
| "max_steps": 119380, | |
| "num_train_epochs": 10, | |
| "save_steps": 2000, | |
| "total_flos": 6556448698096128.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |