| { |
| "best_metric": 1.2029809951782227, |
| "best_model_checkpoint": "models/llama3.2-3b-sft-full/checkpoint-946", |
| "epoch": 10.0, |
| "eval_steps": 500, |
| "global_step": 4730, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0021141649048625794, |
| "grad_norm": 12.750687916050717, |
| "learning_rate": 4.228329809725159e-08, |
| "loss": 2.0313, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.10570824524312897, |
| "grad_norm": 1.6188098557526023, |
| "learning_rate": 2.1141649048625796e-06, |
| "loss": 1.8564, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.21141649048625794, |
| "grad_norm": 1.3518202018434258, |
| "learning_rate": 4.228329809725159e-06, |
| "loss": 1.5595, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.3171247357293869, |
| "grad_norm": 1.0657590959696566, |
| "learning_rate": 6.342494714587738e-06, |
| "loss": 1.4551, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.42283298097251587, |
| "grad_norm": 0.8592382874171366, |
| "learning_rate": 8.456659619450318e-06, |
| "loss": 1.3854, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.5285412262156448, |
| "grad_norm": 0.9009389463159452, |
| "learning_rate": 1.0570824524312897e-05, |
| "loss": 1.3425, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.6342494714587738, |
| "grad_norm": 1.1412749380165943, |
| "learning_rate": 1.2684989429175477e-05, |
| "loss": 1.3006, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.7399577167019028, |
| "grad_norm": 0.7983643996119608, |
| "learning_rate": 1.4799154334038057e-05, |
| "loss": 1.2744, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.8456659619450317, |
| "grad_norm": 0.8244042644021615, |
| "learning_rate": 1.6913319238900637e-05, |
| "loss": 1.2548, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.9513742071881607, |
| "grad_norm": 0.8216465876347789, |
| "learning_rate": 1.9027484143763216e-05, |
| "loss": 1.2404, |
| "step": 450 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.2400952577590942, |
| "eval_runtime": 18.7515, |
| "eval_samples_per_second": 180.785, |
| "eval_steps_per_second": 1.44, |
| "step": 473 |
| }, |
| { |
| "epoch": 1.0570824524312896, |
| "grad_norm": 0.8252930310615743, |
| "learning_rate": 1.9998014930992976e-05, |
| "loss": 1.1705, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.1627906976744187, |
| "grad_norm": 0.8757450644495188, |
| "learning_rate": 1.9983859126509827e-05, |
| "loss": 1.12, |
| "step": 550 |
| }, |
| { |
| "epoch": 1.2684989429175475, |
| "grad_norm": 0.7949433367488117, |
| "learning_rate": 1.9956111376617147e-05, |
| "loss": 1.1182, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.3742071881606766, |
| "grad_norm": 0.8258557786713708, |
| "learning_rate": 1.9914809456878166e-05, |
| "loss": 1.1182, |
| "step": 650 |
| }, |
| { |
| "epoch": 1.4799154334038054, |
| "grad_norm": 0.7933398639276036, |
| "learning_rate": 1.9860009595393798e-05, |
| "loss": 1.1038, |
| "step": 700 |
| }, |
| { |
| "epoch": 1.5856236786469344, |
| "grad_norm": 0.841899074998612, |
| "learning_rate": 1.9791786396254126e-05, |
| "loss": 1.1021, |
| "step": 750 |
| }, |
| { |
| "epoch": 1.6913319238900635, |
| "grad_norm": 0.7846336500672028, |
| "learning_rate": 1.971023273797303e-05, |
| "loss": 1.1144, |
| "step": 800 |
| }, |
| { |
| "epoch": 1.7970401691331923, |
| "grad_norm": 0.8229424691925108, |
| "learning_rate": 1.961545964704409e-05, |
| "loss": 1.1026, |
| "step": 850 |
| }, |
| { |
| "epoch": 1.9027484143763214, |
| "grad_norm": 0.7508672417042123, |
| "learning_rate": 1.950759614679005e-05, |
| "loss": 1.0999, |
| "step": 900 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 1.2029809951782227, |
| "eval_runtime": 18.6697, |
| "eval_samples_per_second": 181.578, |
| "eval_steps_per_second": 1.446, |
| "step": 946 |
| }, |
| { |
| "epoch": 2.0084566596194504, |
| "grad_norm": 1.1731388344496063, |
| "learning_rate": 1.9386789081711465e-05, |
| "loss": 1.0829, |
| "step": 950 |
| }, |
| { |
| "epoch": 2.1141649048625792, |
| "grad_norm": 0.8445527906517972, |
| "learning_rate": 1.9253202917573813e-05, |
| "loss": 0.8792, |
| "step": 1000 |
| }, |
| { |
| "epoch": 2.219873150105708, |
| "grad_norm": 0.8760066547012747, |
| "learning_rate": 1.910701951750511e-05, |
| "loss": 0.8858, |
| "step": 1050 |
| }, |
| { |
| "epoch": 2.3255813953488373, |
| "grad_norm": 0.8556944230458313, |
| "learning_rate": 1.894843789440892e-05, |
| "loss": 0.8963, |
| "step": 1100 |
| }, |
| { |
| "epoch": 2.431289640591966, |
| "grad_norm": 0.9640553709381205, |
| "learning_rate": 1.8777673940029783e-05, |
| "loss": 0.8986, |
| "step": 1150 |
| }, |
| { |
| "epoch": 2.536997885835095, |
| "grad_norm": 0.8627140770648074, |
| "learning_rate": 1.8594960131039935e-05, |
| "loss": 0.8938, |
| "step": 1200 |
| }, |
| { |
| "epoch": 2.6427061310782243, |
| "grad_norm": 0.9535715556479282, |
| "learning_rate": 1.8400545212547452e-05, |
| "loss": 0.8955, |
| "step": 1250 |
| }, |
| { |
| "epoch": 2.748414376321353, |
| "grad_norm": 0.8552691365971952, |
| "learning_rate": 1.819469385945664e-05, |
| "loss": 0.9014, |
| "step": 1300 |
| }, |
| { |
| "epoch": 2.854122621564482, |
| "grad_norm": 0.8665945027227095, |
| "learning_rate": 1.7977686316141757e-05, |
| "loss": 0.8947, |
| "step": 1350 |
| }, |
| { |
| "epoch": 2.9598308668076108, |
| "grad_norm": 0.9619834334611845, |
| "learning_rate": 1.7749818014924612e-05, |
| "loss": 0.9009, |
| "step": 1400 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 1.2264167070388794, |
| "eval_runtime": 18.611, |
| "eval_samples_per_second": 182.15, |
| "eval_steps_per_second": 1.451, |
| "step": 1419 |
| }, |
| { |
| "epoch": 3.06553911205074, |
| "grad_norm": 1.0859362155871017, |
| "learning_rate": 1.7511399173875326e-05, |
| "loss": 0.7572, |
| "step": 1450 |
| }, |
| { |
| "epoch": 3.171247357293869, |
| "grad_norm": 4.277266247206096, |
| "learning_rate": 1.7262754374483997e-05, |
| "loss": 0.667, |
| "step": 1500 |
| }, |
| { |
| "epoch": 3.276955602536998, |
| "grad_norm": 1.0657798474808275, |
| "learning_rate": 1.7004222119778044e-05, |
| "loss": 0.6762, |
| "step": 1550 |
| }, |
| { |
| "epoch": 3.382663847780127, |
| "grad_norm": 1.1532443588160448, |
| "learning_rate": 1.673615437348693e-05, |
| "loss": 0.6818, |
| "step": 1600 |
| }, |
| { |
| "epoch": 3.488372093023256, |
| "grad_norm": 1.027155281075861, |
| "learning_rate": 1.6458916080881566e-05, |
| "loss": 0.6855, |
| "step": 1650 |
| }, |
| { |
| "epoch": 3.5940803382663846, |
| "grad_norm": 1.1083716056629094, |
| "learning_rate": 1.6172884671940753e-05, |
| "loss": 0.6812, |
| "step": 1700 |
| }, |
| { |
| "epoch": 3.699788583509514, |
| "grad_norm": 1.0062825632251786, |
| "learning_rate": 1.587844954752106e-05, |
| "loss": 0.6883, |
| "step": 1750 |
| }, |
| { |
| "epoch": 3.8054968287526427, |
| "grad_norm": 1.07000970987697, |
| "learning_rate": 1.557601154922964e-05, |
| "loss": 0.6893, |
| "step": 1800 |
| }, |
| { |
| "epoch": 3.9112050739957716, |
| "grad_norm": 1.0384275987977813, |
| "learning_rate": 1.5265982413721662e-05, |
| "loss": 0.6876, |
| "step": 1850 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 1.2967802286148071, |
| "eval_runtime": 18.6163, |
| "eval_samples_per_second": 182.098, |
| "eval_steps_per_second": 1.45, |
| "step": 1892 |
| }, |
| { |
| "epoch": 4.016913319238901, |
| "grad_norm": 1.3109377397084605, |
| "learning_rate": 1.494878421216539e-05, |
| "loss": 0.6596, |
| "step": 1900 |
| }, |
| { |
| "epoch": 4.12262156448203, |
| "grad_norm": 1.2688929301953065, |
| "learning_rate": 1.4624848775637845e-05, |
| "loss": 0.4741, |
| "step": 1950 |
| }, |
| { |
| "epoch": 4.2283298097251585, |
| "grad_norm": 1.1894927227873353, |
| "learning_rate": 1.4294617107233504e-05, |
| "loss": 0.4744, |
| "step": 2000 |
| }, |
| { |
| "epoch": 4.334038054968287, |
| "grad_norm": 1.2032936700401937, |
| "learning_rate": 1.3958538781686194e-05, |
| "loss": 0.4805, |
| "step": 2050 |
| }, |
| { |
| "epoch": 4.439746300211416, |
| "grad_norm": 1.3185879928970223, |
| "learning_rate": 1.3617071333321705e-05, |
| "loss": 0.4826, |
| "step": 2100 |
| }, |
| { |
| "epoch": 4.545454545454545, |
| "grad_norm": 1.209922790479991, |
| "learning_rate": 1.3270679633174219e-05, |
| "loss": 0.4839, |
| "step": 2150 |
| }, |
| { |
| "epoch": 4.651162790697675, |
| "grad_norm": 1.242791543340292, |
| "learning_rate": 1.2919835256114639e-05, |
| "loss": 0.4885, |
| "step": 2200 |
| }, |
| { |
| "epoch": 4.7568710359408035, |
| "grad_norm": 1.201986398108636, |
| "learning_rate": 1.2565015838852364e-05, |
| "loss": 0.4871, |
| "step": 2250 |
| }, |
| { |
| "epoch": 4.862579281183932, |
| "grad_norm": 1.2360526015797055, |
| "learning_rate": 1.2206704429684504e-05, |
| "loss": 0.4846, |
| "step": 2300 |
| }, |
| { |
| "epoch": 4.968287526427061, |
| "grad_norm": 1.1786633423072006, |
| "learning_rate": 1.1845388830877826e-05, |
| "loss": 0.4893, |
| "step": 2350 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 1.4134972095489502, |
| "eval_runtime": 18.68, |
| "eval_samples_per_second": 181.478, |
| "eval_steps_per_second": 1.445, |
| "step": 2365 |
| }, |
| { |
| "epoch": 5.07399577167019, |
| "grad_norm": 1.2309864025937378, |
| "learning_rate": 1.1481560934578686e-05, |
| "loss": 0.3702, |
| "step": 2400 |
| }, |
| { |
| "epoch": 5.179704016913319, |
| "grad_norm": 1.2786650363864003, |
| "learning_rate": 1.1115716053155003e-05, |
| "loss": 0.3218, |
| "step": 2450 |
| }, |
| { |
| "epoch": 5.2854122621564485, |
| "grad_norm": 1.2330334913778382, |
| "learning_rate": 1.0748352244882008e-05, |
| "loss": 0.3265, |
| "step": 2500 |
| }, |
| { |
| "epoch": 5.391120507399577, |
| "grad_norm": 1.2643477957547729, |
| "learning_rate": 1.0379969635889705e-05, |
| "loss": 0.3295, |
| "step": 2550 |
| }, |
| { |
| "epoch": 5.496828752642706, |
| "grad_norm": 1.281027075874609, |
| "learning_rate": 1.0011069739295196e-05, |
| "loss": 0.3263, |
| "step": 2600 |
| }, |
| { |
| "epoch": 5.602536997885835, |
| "grad_norm": 1.22994140794609, |
| "learning_rate": 9.642154772446763e-06, |
| "loss": 0.3289, |
| "step": 2650 |
| }, |
| { |
| "epoch": 5.708245243128964, |
| "grad_norm": 1.3028039578218702, |
| "learning_rate": 9.273726973209203e-06, |
| "loss": 0.3284, |
| "step": 2700 |
| }, |
| { |
| "epoch": 5.813953488372093, |
| "grad_norm": 1.2532248232758287, |
| "learning_rate": 8.906287916221259e-06, |
| "loss": 0.3308, |
| "step": 2750 |
| }, |
| { |
| "epoch": 5.9196617336152215, |
| "grad_norm": 1.3100012552937503, |
| "learning_rate": 8.540337830055927e-06, |
| "loss": 0.3315, |
| "step": 2800 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 1.5860239267349243, |
| "eval_runtime": 18.5094, |
| "eval_samples_per_second": 183.151, |
| "eval_steps_per_second": 1.459, |
| "step": 2838 |
| }, |
| { |
| "epoch": 6.025369978858351, |
| "grad_norm": 1.4354000732242087, |
| "learning_rate": 8.176374916213325e-06, |
| "loss": 0.3032, |
| "step": 2850 |
| }, |
| { |
| "epoch": 6.13107822410148, |
| "grad_norm": 1.1648180451771042, |
| "learning_rate": 7.814894670873171e-06, |
| "loss": 0.2141, |
| "step": 2900 |
| }, |
| { |
| "epoch": 6.236786469344609, |
| "grad_norm": 1.1884819713548493, |
| "learning_rate": 7.456389210330289e-06, |
| "loss": 0.2153, |
| "step": 2950 |
| }, |
| { |
| "epoch": 6.342494714587738, |
| "grad_norm": 1.2643468298433007, |
| "learning_rate": 7.101346601031416e-06, |
| "loss": 0.2153, |
| "step": 3000 |
| }, |
| { |
| "epoch": 6.4482029598308666, |
| "grad_norm": 1.2064695562383054, |
| "learning_rate": 6.750250195125509e-06, |
| "loss": 0.2188, |
| "step": 3050 |
| }, |
| { |
| "epoch": 6.553911205073996, |
| "grad_norm": 1.2016268195975075, |
| "learning_rate": 6.4035779724320115e-06, |
| "loss": 0.2171, |
| "step": 3100 |
| }, |
| { |
| "epoch": 6.659619450317125, |
| "grad_norm": 1.2411099570397714, |
| "learning_rate": 6.061801889722952e-06, |
| "loss": 0.2162, |
| "step": 3150 |
| }, |
| { |
| "epoch": 6.765327695560254, |
| "grad_norm": 1.2392777259407999, |
| "learning_rate": 5.725387238204831e-06, |
| "loss": 0.215, |
| "step": 3200 |
| }, |
| { |
| "epoch": 6.871035940803383, |
| "grad_norm": 1.1740909434133877, |
| "learning_rate": 5.394792010074907e-06, |
| "loss": 0.2166, |
| "step": 3250 |
| }, |
| { |
| "epoch": 6.976744186046512, |
| "grad_norm": 1.2762193770401755, |
| "learning_rate": 5.0704662750142875e-06, |
| "loss": 0.2165, |
| "step": 3300 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_loss": 1.802822470664978, |
| "eval_runtime": 18.5091, |
| "eval_samples_per_second": 183.153, |
| "eval_steps_per_second": 1.459, |
| "step": 3311 |
| }, |
| { |
| "epoch": 7.08245243128964, |
| "grad_norm": 1.0526386037599447, |
| "learning_rate": 4.752851567466723e-06, |
| "loss": 0.1594, |
| "step": 3350 |
| }, |
| { |
| "epoch": 7.188160676532769, |
| "grad_norm": 1.147178748636373, |
| "learning_rate": 4.442380285537152e-06, |
| "loss": 0.1424, |
| "step": 3400 |
| }, |
| { |
| "epoch": 7.293868921775898, |
| "grad_norm": 1.0933846169501016, |
| "learning_rate": 4.1394751023283985e-06, |
| "loss": 0.1429, |
| "step": 3450 |
| }, |
| { |
| "epoch": 7.399577167019028, |
| "grad_norm": 1.1027491437777261, |
| "learning_rate": 3.844548390517433e-06, |
| "loss": 0.1446, |
| "step": 3500 |
| }, |
| { |
| "epoch": 7.505285412262157, |
| "grad_norm": 1.17228307610312, |
| "learning_rate": 3.5580016609545076e-06, |
| "loss": 0.1472, |
| "step": 3550 |
| }, |
| { |
| "epoch": 7.6109936575052854, |
| "grad_norm": 1.1469564201071871, |
| "learning_rate": 3.280225016049543e-06, |
| "loss": 0.1444, |
| "step": 3600 |
| }, |
| { |
| "epoch": 7.716701902748414, |
| "grad_norm": 1.1481692114896938, |
| "learning_rate": 3.011596618689825e-06, |
| "loss": 0.1442, |
| "step": 3650 |
| }, |
| { |
| "epoch": 7.822410147991543, |
| "grad_norm": 1.0576784331195976, |
| "learning_rate": 2.7524821774121158e-06, |
| "loss": 0.1432, |
| "step": 3700 |
| }, |
| { |
| "epoch": 7.928118393234672, |
| "grad_norm": 1.017768412790375, |
| "learning_rate": 2.5032344485299886e-06, |
| "loss": 0.1444, |
| "step": 3750 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 2.0527853965759277, |
| "eval_runtime": 18.5305, |
| "eval_samples_per_second": 182.942, |
| "eval_steps_per_second": 1.457, |
| "step": 3784 |
| }, |
| { |
| "epoch": 8.033826638477802, |
| "grad_norm": 0.8182949486515412, |
| "learning_rate": 2.2641927558942135e-06, |
| "loss": 0.1304, |
| "step": 3800 |
| }, |
| { |
| "epoch": 8.13953488372093, |
| "grad_norm": 0.8622437048349989, |
| "learning_rate": 2.0356825289400185e-06, |
| "loss": 0.1036, |
| "step": 3850 |
| }, |
| { |
| "epoch": 8.24524312896406, |
| "grad_norm": 0.7861265978157033, |
| "learning_rate": 1.818014859650068e-06, |
| "loss": 0.1028, |
| "step": 3900 |
| }, |
| { |
| "epoch": 8.350951374207188, |
| "grad_norm": 0.8194211537002656, |
| "learning_rate": 1.6114860790363351e-06, |
| "loss": 0.1032, |
| "step": 3950 |
| }, |
| { |
| "epoch": 8.456659619450317, |
| "grad_norm": 0.8182271224247505, |
| "learning_rate": 1.4163773537174653e-06, |
| "loss": 0.1032, |
| "step": 4000 |
| }, |
| { |
| "epoch": 8.562367864693446, |
| "grad_norm": 0.8307023639288861, |
| "learning_rate": 1.2329543031407953e-06, |
| "loss": 0.1036, |
| "step": 4050 |
| }, |
| { |
| "epoch": 8.668076109936575, |
| "grad_norm": 0.8784936190909071, |
| "learning_rate": 1.0614666379701732e-06, |
| "loss": 0.1023, |
| "step": 4100 |
| }, |
| { |
| "epoch": 8.773784355179703, |
| "grad_norm": 0.81990506328911, |
| "learning_rate": 9.021478201318846e-07, |
| "loss": 0.1036, |
| "step": 4150 |
| }, |
| { |
| "epoch": 8.879492600422832, |
| "grad_norm": 1.2592556041877936, |
| "learning_rate": 7.552147449814573e-07, |
| "loss": 0.1044, |
| "step": 4200 |
| }, |
| { |
| "epoch": 8.985200845665961, |
| "grad_norm": 0.7975519834622627, |
| "learning_rate": 6.20867446024066e-07, |
| "loss": 0.1032, |
| "step": 4250 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_loss": 2.279863119125366, |
| "eval_runtime": 18.5289, |
| "eval_samples_per_second": 182.957, |
| "eval_steps_per_second": 1.457, |
| "step": 4257 |
| }, |
| { |
| "epoch": 9.090909090909092, |
| "grad_norm": 0.7603748072458637, |
| "learning_rate": 4.992888225905467e-07, |
| "loss": 0.0893, |
| "step": 4300 |
| }, |
| { |
| "epoch": 9.19661733615222, |
| "grad_norm": 0.7495366875123604, |
| "learning_rate": 3.906443908397017e-07, |
| "loss": 0.0873, |
| "step": 4350 |
| }, |
| { |
| "epoch": 9.30232558139535, |
| "grad_norm": 0.7691079659468273, |
| "learning_rate": 2.9508205842594727e-07, |
| "loss": 0.0871, |
| "step": 4400 |
| }, |
| { |
| "epoch": 9.408033826638478, |
| "grad_norm": 0.6348077284451538, |
| "learning_rate": 2.127319231390168e-07, |
| "loss": 0.0877, |
| "step": 4450 |
| }, |
| { |
| "epoch": 9.513742071881607, |
| "grad_norm": 0.6760109276931042, |
| "learning_rate": 1.4370609578987948e-07, |
| "loss": 0.0875, |
| "step": 4500 |
| }, |
| { |
| "epoch": 9.619450317124736, |
| "grad_norm": 0.6725906544777629, |
| "learning_rate": 8.809854758399017e-08, |
| "loss": 0.087, |
| "step": 4550 |
| }, |
| { |
| "epoch": 9.725158562367865, |
| "grad_norm": 0.6525914332864488, |
| "learning_rate": 4.5984982189636316e-08, |
| "loss": 0.0865, |
| "step": 4600 |
| }, |
| { |
| "epoch": 9.830866807610994, |
| "grad_norm": 0.6640786754191882, |
| "learning_rate": 1.7422732675583808e-08, |
| "loss": 0.0888, |
| "step": 4650 |
| }, |
| { |
| "epoch": 9.936575052854122, |
| "grad_norm": 0.6669826671643079, |
| "learning_rate": 2.4506834582960213e-09, |
| "loss": 0.0879, |
| "step": 4700 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_loss": 2.3936548233032227, |
| "eval_runtime": 18.4489, |
| "eval_samples_per_second": 183.751, |
| "eval_steps_per_second": 1.464, |
| "step": 4730 |
| }, |
| { |
| "epoch": 10.0, |
| "step": 4730, |
| "total_flos": 651355949629440.0, |
| "train_loss": 0.5446855222952038, |
| "train_runtime": 13348.3684, |
| "train_samples_per_second": 45.308, |
| "train_steps_per_second": 0.354 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 4730, |
| "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": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 651355949629440.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
