| { | |
| "best_metric": 0.0698026642203331, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-200", | |
| "epoch": 0.025997660210581048, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00012998830105290525, | |
| "grad_norm": 8.895720481872559, | |
| "learning_rate": 1e-05, | |
| "loss": 1.8459, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00012998830105290525, | |
| "eval_loss": 1.0915981531143188, | |
| "eval_runtime": 1412.1497, | |
| "eval_samples_per_second": 9.175, | |
| "eval_steps_per_second": 2.294, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002599766021058105, | |
| "grad_norm": 13.155832290649414, | |
| "learning_rate": 2e-05, | |
| "loss": 2.443, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0003899649031587157, | |
| "grad_norm": 14.273755073547363, | |
| "learning_rate": 3e-05, | |
| "loss": 2.9329, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000519953204211621, | |
| "grad_norm": 16.93520736694336, | |
| "learning_rate": 4e-05, | |
| "loss": 3.3626, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0006499415052645262, | |
| "grad_norm": 11.356696128845215, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8192, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0007799298063174314, | |
| "grad_norm": 11.887849807739258, | |
| "learning_rate": 6e-05, | |
| "loss": 1.3449, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0009099181073703367, | |
| "grad_norm": 9.773666381835938, | |
| "learning_rate": 7e-05, | |
| "loss": 0.9185, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.001039906408423242, | |
| "grad_norm": 21.219711303710938, | |
| "learning_rate": 8e-05, | |
| "loss": 1.4177, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0011698947094761472, | |
| "grad_norm": 10.484102249145508, | |
| "learning_rate": 9e-05, | |
| "loss": 0.9221, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0012998830105290524, | |
| "grad_norm": 25.021635055541992, | |
| "learning_rate": 0.0001, | |
| "loss": 1.8455, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0014298713115819576, | |
| "grad_norm": 19.793079376220703, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 1.4859, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0015598596126348628, | |
| "grad_norm": 12.939811706542969, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 0.952, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0016898479136877682, | |
| "grad_norm": 16.663564682006836, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 1.0298, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0018198362147406734, | |
| "grad_norm": 12.337509155273438, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 1.119, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0019498245157935786, | |
| "grad_norm": 8.889068603515625, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 0.806, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002079812816846484, | |
| "grad_norm": 8.746395111083984, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 0.5811, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.002209801117899389, | |
| "grad_norm": 7.167966842651367, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 0.5683, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0023397894189522944, | |
| "grad_norm": 7.786585807800293, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 0.6394, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0024697777200051994, | |
| "grad_norm": 7.365955352783203, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 0.7046, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.002599766021058105, | |
| "grad_norm": 7.709902286529541, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 0.4938, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00272975432211101, | |
| "grad_norm": 9.915132522583008, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 0.942, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.002859742623163915, | |
| "grad_norm": 9.246820449829102, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 0.6803, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0029897309242168206, | |
| "grad_norm": 13.664460182189941, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 0.5407, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0031197192252697256, | |
| "grad_norm": 11.21821403503418, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 0.7522, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.003249707526322631, | |
| "grad_norm": 8.65762710571289, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 0.5756, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0033796958273755364, | |
| "grad_norm": 7.683070659637451, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 0.59, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0035096841284284414, | |
| "grad_norm": 6.744781017303467, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 0.4952, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.003639672429481347, | |
| "grad_norm": 9.178666114807129, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 0.4358, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0037696607305342518, | |
| "grad_norm": 14.2472562789917, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.5543, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.003899649031587157, | |
| "grad_norm": 7.047728061676025, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 0.6627, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004029637332640062, | |
| "grad_norm": 6.600000858306885, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 0.4999, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.004159625633692968, | |
| "grad_norm": 6.267518520355225, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 0.4127, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.004289613934745873, | |
| "grad_norm": 3.9115278720855713, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 0.2551, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.004419602235798778, | |
| "grad_norm": 3.7888052463531494, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 0.2697, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.004549590536851683, | |
| "grad_norm": 6.660991668701172, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 0.4979, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.004679578837904589, | |
| "grad_norm": 5.288132667541504, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 0.3436, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.004809567138957494, | |
| "grad_norm": 6.1838226318359375, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 0.4442, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.004939555440010399, | |
| "grad_norm": 6.035123825073242, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 0.3234, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.005069543741063305, | |
| "grad_norm": 5.086143493652344, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 0.3324, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.00519953204211621, | |
| "grad_norm": 5.471978187561035, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 0.3007, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005329520343169115, | |
| "grad_norm": 5.744053840637207, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 0.273, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.00545950864422202, | |
| "grad_norm": 11.946670532226562, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 0.1784, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.005589496945274925, | |
| "grad_norm": 7.70154333114624, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 0.4239, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.00571948524632783, | |
| "grad_norm": 5.410760879516602, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 0.4391, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.005849473547380735, | |
| "grad_norm": 4.884847164154053, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 0.3154, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.005979461848433641, | |
| "grad_norm": 5.657925128936768, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 0.3881, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.006109450149486546, | |
| "grad_norm": 3.236168622970581, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 0.2024, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.006239438450539451, | |
| "grad_norm": 4.553912162780762, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.3, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.006369426751592357, | |
| "grad_norm": 3.5105910301208496, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 0.2236, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.006499415052645262, | |
| "grad_norm": 5.97371244430542, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 0.2381, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.006499415052645262, | |
| "eval_loss": 0.2108517289161682, | |
| "eval_runtime": 1417.8328, | |
| "eval_samples_per_second": 9.139, | |
| "eval_steps_per_second": 2.285, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.006629403353698167, | |
| "grad_norm": 11.96389389038086, | |
| "learning_rate": 8.894386393810563e-05, | |
| "loss": 1.8051, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.006759391654751073, | |
| "grad_norm": 7.560161113739014, | |
| "learning_rate": 8.842005554284296e-05, | |
| "loss": 1.4103, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.006889379955803978, | |
| "grad_norm": 6.23681116104126, | |
| "learning_rate": 8.788574348801675e-05, | |
| "loss": 1.4256, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.007019368256856883, | |
| "grad_norm": 9.883326530456543, | |
| "learning_rate": 8.73410738492077e-05, | |
| "loss": 2.1999, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.007149356557909788, | |
| "grad_norm": 7.169539451599121, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 0.9196, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.007279344858962694, | |
| "grad_norm": 6.351007461547852, | |
| "learning_rate": 8.622126023955446e-05, | |
| "loss": 1.1004, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.007409333160015599, | |
| "grad_norm": 4.663862705230713, | |
| "learning_rate": 8.564642241456986e-05, | |
| "loss": 0.4545, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.0075393214610685036, | |
| "grad_norm": 5.961542129516602, | |
| "learning_rate": 8.506183921362443e-05, | |
| "loss": 0.6011, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.007669309762121409, | |
| "grad_norm": 7.969834327697754, | |
| "learning_rate": 8.44676704559283e-05, | |
| "loss": 0.6682, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.007799298063174314, | |
| "grad_norm": 6.4743170738220215, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 0.6514, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.00792928636422722, | |
| "grad_norm": 6.987910270690918, | |
| "learning_rate": 8.32512286056924e-05, | |
| "loss": 0.5891, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.008059274665280124, | |
| "grad_norm": 6.665630340576172, | |
| "learning_rate": 8.262928807620843e-05, | |
| "loss": 0.4296, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.00818926296633303, | |
| "grad_norm": 8.244565963745117, | |
| "learning_rate": 8.199842702516583e-05, | |
| "loss": 0.5505, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.008319251267385936, | |
| "grad_norm": 5.804681777954102, | |
| "learning_rate": 8.135881792367686e-05, | |
| "loss": 0.4528, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.00844923956843884, | |
| "grad_norm": 9.024893760681152, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 0.8494, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.008579227869491746, | |
| "grad_norm": 9.78223991394043, | |
| "learning_rate": 8.005405736415126e-05, | |
| "loss": 0.7119, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.008709216170544652, | |
| "grad_norm": 6.717483043670654, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 0.5105, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.008839204471597556, | |
| "grad_norm": 5.113883018493652, | |
| "learning_rate": 7.871643313414718e-05, | |
| "loss": 0.5204, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.008969192772650462, | |
| "grad_norm": 4.767594814300537, | |
| "learning_rate": 7.803575286758364e-05, | |
| "loss": 0.4807, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.009099181073703366, | |
| "grad_norm": 5.869354724884033, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 0.3917, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.009229169374756272, | |
| "grad_norm": 4.560206413269043, | |
| "learning_rate": 7.66515864363997e-05, | |
| "loss": 0.4034, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.009359157675809178, | |
| "grad_norm": 6.740488052368164, | |
| "learning_rate": 7.594847868906076e-05, | |
| "loss": 0.4844, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.009489145976862082, | |
| "grad_norm": 4.010514259338379, | |
| "learning_rate": 7.52382768867422e-05, | |
| "loss": 0.3006, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.009619134277914988, | |
| "grad_norm": 10.616462707519531, | |
| "learning_rate": 7.452117519152542e-05, | |
| "loss": 0.3638, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.009749122578967893, | |
| "grad_norm": 3.899102210998535, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 0.2581, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.009879110880020798, | |
| "grad_norm": 5.232759475708008, | |
| "learning_rate": 7.30670581489344e-05, | |
| "loss": 0.4197, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.010009099181073703, | |
| "grad_norm": 3.8902716636657715, | |
| "learning_rate": 7.233044034264034e-05, | |
| "loss": 0.2863, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.01013908748212661, | |
| "grad_norm": 4.209787845611572, | |
| "learning_rate": 7.158771761692464e-05, | |
| "loss": 0.2249, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.010269075783179513, | |
| "grad_norm": 4.976950645446777, | |
| "learning_rate": 7.083909302476453e-05, | |
| "loss": 0.3716, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.01039906408423242, | |
| "grad_norm": 5.116728782653809, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 0.3137, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.010529052385285325, | |
| "grad_norm": 3.287550449371338, | |
| "learning_rate": 6.932495846462261e-05, | |
| "loss": 0.1725, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.01065904068633823, | |
| "grad_norm": 4.446608543395996, | |
| "learning_rate": 6.855986244591104e-05, | |
| "loss": 0.284, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.010789028987391135, | |
| "grad_norm": 3.303908348083496, | |
| "learning_rate": 6.778969234612584e-05, | |
| "loss": 0.1945, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.01091901728844404, | |
| "grad_norm": 7.167092800140381, | |
| "learning_rate": 6.701465872208216e-05, | |
| "loss": 0.4386, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.011049005589496945, | |
| "grad_norm": 3.590325355529785, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 0.1954, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.01117899389054985, | |
| "grad_norm": 4.736059188842773, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.5428, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.011308982191602755, | |
| "grad_norm": 6.112609386444092, | |
| "learning_rate": 6.466250186922325e-05, | |
| "loss": 0.3665, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.01143897049265566, | |
| "grad_norm": 3.9378249645233154, | |
| "learning_rate": 6.387014543809223e-05, | |
| "loss": 0.2136, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.011568958793708567, | |
| "grad_norm": 4.579885959625244, | |
| "learning_rate": 6.307399704769099e-05, | |
| "loss": 0.2942, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.01169894709476147, | |
| "grad_norm": 4.84573221206665, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 0.3229, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.011828935395814377, | |
| "grad_norm": 3.348799705505371, | |
| "learning_rate": 6.147119600233758e-05, | |
| "loss": 0.2288, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.011958923696867282, | |
| "grad_norm": 3.677680015563965, | |
| "learning_rate": 6.066498153718735e-05, | |
| "loss": 0.2188, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.012088911997920187, | |
| "grad_norm": 3.9599173069000244, | |
| "learning_rate": 5.985585137257401e-05, | |
| "loss": 0.2934, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.012218900298973092, | |
| "grad_norm": 1.8040279150009155, | |
| "learning_rate": 5.90440267166055e-05, | |
| "loss": 0.1396, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.012348888600025998, | |
| "grad_norm": 2.4542367458343506, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 0.158, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.012478876901078902, | |
| "grad_norm": 2.886835813522339, | |
| "learning_rate": 5.74131823855921e-05, | |
| "loss": 0.1485, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.012608865202131808, | |
| "grad_norm": 4.41395902633667, | |
| "learning_rate": 5.6594608567103456e-05, | |
| "loss": 0.1855, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.012738853503184714, | |
| "grad_norm": 2.9605488777160645, | |
| "learning_rate": 5.577423184847932e-05, | |
| "loss": 0.1654, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.012868841804237618, | |
| "grad_norm": 4.90177583694458, | |
| "learning_rate": 5.495227651252315e-05, | |
| "loss": 0.1931, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.012998830105290524, | |
| "grad_norm": 6.01702880859375, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 0.3606, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.012998830105290524, | |
| "eval_loss": 0.14507097005844116, | |
| "eval_runtime": 1415.1288, | |
| "eval_samples_per_second": 9.156, | |
| "eval_steps_per_second": 2.29, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01312881840634343, | |
| "grad_norm": 7.9503583908081055, | |
| "learning_rate": 5.330452921628497e-05, | |
| "loss": 1.8375, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.013258806707396334, | |
| "grad_norm": 6.233389854431152, | |
| "learning_rate": 5.247918773366112e-05, | |
| "loss": 1.3804, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.01338879500844924, | |
| "grad_norm": 4.569299697875977, | |
| "learning_rate": 5.165316846586541e-05, | |
| "loss": 1.0248, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.013518783309502146, | |
| "grad_norm": 5.200125694274902, | |
| "learning_rate": 5.0826697238317935e-05, | |
| "loss": 1.3332, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.01364877161055505, | |
| "grad_norm": 5.104859352111816, | |
| "learning_rate": 5e-05, | |
| "loss": 0.907, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.013778759911607956, | |
| "grad_norm": 3.8999855518341064, | |
| "learning_rate": 4.917330276168208e-05, | |
| "loss": 0.5831, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.01390874821266086, | |
| "grad_norm": 4.339993000030518, | |
| "learning_rate": 4.834683153413459e-05, | |
| "loss": 0.3018, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.014038736513713766, | |
| "grad_norm": 4.26090145111084, | |
| "learning_rate": 4.7520812266338885e-05, | |
| "loss": 0.4824, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.014168724814766671, | |
| "grad_norm": 6.476984024047852, | |
| "learning_rate": 4.669547078371504e-05, | |
| "loss": 0.5009, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.014298713115819576, | |
| "grad_norm": 6.847250461578369, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 0.51, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.014428701416872481, | |
| "grad_norm": 5.437959671020508, | |
| "learning_rate": 4.504772348747687e-05, | |
| "loss": 0.5212, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.014558689717925387, | |
| "grad_norm": 4.896420478820801, | |
| "learning_rate": 4.4225768151520694e-05, | |
| "loss": 0.4352, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.014688678018978291, | |
| "grad_norm": 5.313551425933838, | |
| "learning_rate": 4.3405391432896555e-05, | |
| "loss": 0.4218, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.014818666320031197, | |
| "grad_norm": 4.771443843841553, | |
| "learning_rate": 4.2586817614407895e-05, | |
| "loss": 0.3939, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.014948654621084103, | |
| "grad_norm": 3.681682825088501, | |
| "learning_rate": 4.17702704859633e-05, | |
| "loss": 0.5179, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.015078642922137007, | |
| "grad_norm": 4.138582229614258, | |
| "learning_rate": 4.095597328339452e-05, | |
| "loss": 0.3389, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.015208631223189913, | |
| "grad_norm": 4.465811252593994, | |
| "learning_rate": 4.0144148627425993e-05, | |
| "loss": 0.4372, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.015338619524242819, | |
| "grad_norm": 4.707912445068359, | |
| "learning_rate": 3.933501846281267e-05, | |
| "loss": 0.4408, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.015468607825295723, | |
| "grad_norm": 4.273300647735596, | |
| "learning_rate": 3.852880399766243e-05, | |
| "loss": 0.4049, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.015598596126348629, | |
| "grad_norm": 3.297325849533081, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 0.2983, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.015728584427401535, | |
| "grad_norm": 3.599745035171509, | |
| "learning_rate": 3.6926002952309016e-05, | |
| "loss": 0.332, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.01585857272845444, | |
| "grad_norm": 3.2352163791656494, | |
| "learning_rate": 3.612985456190778e-05, | |
| "loss": 0.2846, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.015988561029507343, | |
| "grad_norm": 5.459647178649902, | |
| "learning_rate": 3.533749813077677e-05, | |
| "loss": 0.3044, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.01611854933056025, | |
| "grad_norm": 3.7283079624176025, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.2579, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.016248537631613155, | |
| "grad_norm": 2.8069612979888916, | |
| "learning_rate": 3.3765026539765834e-05, | |
| "loss": 0.2671, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.01637852593266606, | |
| "grad_norm": 3.1048874855041504, | |
| "learning_rate": 3.298534127791785e-05, | |
| "loss": 0.1552, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.016508514233718966, | |
| "grad_norm": 4.251136779785156, | |
| "learning_rate": 3.221030765387417e-05, | |
| "loss": 0.2977, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.016638502534771872, | |
| "grad_norm": 5.176329135894775, | |
| "learning_rate": 3.144013755408895e-05, | |
| "loss": 0.2595, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.016768490835824774, | |
| "grad_norm": 4.689629554748535, | |
| "learning_rate": 3.0675041535377405e-05, | |
| "loss": 0.3759, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.01689847913687768, | |
| "grad_norm": 3.1052284240722656, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 0.1697, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.017028467437930586, | |
| "grad_norm": 4.357040882110596, | |
| "learning_rate": 2.916090697523549e-05, | |
| "loss": 0.2108, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.017158455738983492, | |
| "grad_norm": 5.174962520599365, | |
| "learning_rate": 2.8412282383075363e-05, | |
| "loss": 0.2725, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.017288444040036398, | |
| "grad_norm": 4.341920375823975, | |
| "learning_rate": 2.766955965735968e-05, | |
| "loss": 0.1915, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.017418432341089304, | |
| "grad_norm": 4.376591682434082, | |
| "learning_rate": 2.693294185106562e-05, | |
| "loss": 0.2614, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.017548420642142206, | |
| "grad_norm": 3.130718231201172, | |
| "learning_rate": 2.6202630348146324e-05, | |
| "loss": 0.1921, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.017678408943195112, | |
| "grad_norm": 2.5387256145477295, | |
| "learning_rate": 2.547882480847461e-05, | |
| "loss": 0.1437, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.017808397244248018, | |
| "grad_norm": 4.208658695220947, | |
| "learning_rate": 2.476172311325783e-05, | |
| "loss": 0.2688, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.017938385545300924, | |
| "grad_norm": 2.6489620208740234, | |
| "learning_rate": 2.405152131093926e-05, | |
| "loss": 0.2148, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.01806837384635383, | |
| "grad_norm": 4.43926477432251, | |
| "learning_rate": 2.3348413563600325e-05, | |
| "loss": 0.2774, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.018198362147406732, | |
| "grad_norm": 2.5864620208740234, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 0.159, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.018328350448459638, | |
| "grad_norm": 4.264463424682617, | |
| "learning_rate": 2.196424713241637e-05, | |
| "loss": 0.321, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.018458338749512544, | |
| "grad_norm": 5.146592140197754, | |
| "learning_rate": 2.128356686585282e-05, | |
| "loss": 0.18, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.01858832705056545, | |
| "grad_norm": 3.3703808784484863, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.1344, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.018718315351618355, | |
| "grad_norm": 1.4023449420928955, | |
| "learning_rate": 1.9945942635848748e-05, | |
| "loss": 0.063, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.01884830365267126, | |
| "grad_norm": 3.0542232990264893, | |
| "learning_rate": 1.928936436551661e-05, | |
| "loss": 0.16, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.018978291953724163, | |
| "grad_norm": 2.733213424682617, | |
| "learning_rate": 1.8641182076323148e-05, | |
| "loss": 0.1332, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.01910828025477707, | |
| "grad_norm": 2.248521327972412, | |
| "learning_rate": 1.800157297483417e-05, | |
| "loss": 0.1503, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.019238268555829975, | |
| "grad_norm": 3.6398096084594727, | |
| "learning_rate": 1.7370711923791567e-05, | |
| "loss": 0.2957, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.01936825685688288, | |
| "grad_norm": 2.906625747680664, | |
| "learning_rate": 1.6748771394307585e-05, | |
| "loss": 0.1492, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.019498245157935787, | |
| "grad_norm": 2.7944815158843994, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 0.1233, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.019498245157935787, | |
| "eval_loss": 0.11835423856973648, | |
| "eval_runtime": 1419.5313, | |
| "eval_samples_per_second": 9.128, | |
| "eval_steps_per_second": 2.282, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.019628233458988693, | |
| "grad_norm": 5.7533440589904785, | |
| "learning_rate": 1.553232954407171e-05, | |
| "loss": 1.2347, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.019758221760041595, | |
| "grad_norm": 5.189516544342041, | |
| "learning_rate": 1.4938160786375572e-05, | |
| "loss": 1.2582, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.0198882100610945, | |
| "grad_norm": 5.34510612487793, | |
| "learning_rate": 1.435357758543015e-05, | |
| "loss": 1.307, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.020018198362147407, | |
| "grad_norm": 5.2588043212890625, | |
| "learning_rate": 1.3778739760445552e-05, | |
| "loss": 1.1249, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.020148186663200313, | |
| "grad_norm": 7.321238994598389, | |
| "learning_rate": 1.3213804466343421e-05, | |
| "loss": 0.8712, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.02027817496425322, | |
| "grad_norm": 4.537265300750732, | |
| "learning_rate": 1.2658926150792322e-05, | |
| "loss": 0.5625, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.02040816326530612, | |
| "grad_norm": 3.4912362098693848, | |
| "learning_rate": 1.2114256511983274e-05, | |
| "loss": 0.408, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.020538151566359027, | |
| "grad_norm": 3.847301483154297, | |
| "learning_rate": 1.157994445715706e-05, | |
| "loss": 0.4588, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.020668139867411933, | |
| "grad_norm": 8.650979995727539, | |
| "learning_rate": 1.1056136061894384e-05, | |
| "loss": 0.4644, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.02079812816846484, | |
| "grad_norm": 11.216106414794922, | |
| "learning_rate": 1.0542974530180327e-05, | |
| "loss": 0.5373, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.020928116469517744, | |
| "grad_norm": 9.541360855102539, | |
| "learning_rate": 1.0040600155253765e-05, | |
| "loss": 0.3775, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.02105810477057065, | |
| "grad_norm": 5.9185686111450195, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.3445, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.021188093071623552, | |
| "grad_norm": 4.697037220001221, | |
| "learning_rate": 9.068759265665384e-06, | |
| "loss": 0.2805, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.02131808137267646, | |
| "grad_norm": 5.3230485916137695, | |
| "learning_rate": 8.599558442598998e-06, | |
| "loss": 0.5409, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.021448069673729364, | |
| "grad_norm": 4.811458110809326, | |
| "learning_rate": 8.141676086873572e-06, | |
| "loss": 0.3386, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.02157805797478227, | |
| "grad_norm": 7.939873695373535, | |
| "learning_rate": 7.695237378953223e-06, | |
| "loss": 0.324, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.021708046275835176, | |
| "grad_norm": 4.232122421264648, | |
| "learning_rate": 7.260364370723044e-06, | |
| "loss": 0.3584, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.02183803457688808, | |
| "grad_norm": 4.569654941558838, | |
| "learning_rate": 6.837175952121306e-06, | |
| "loss": 0.3538, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.021968022877940984, | |
| "grad_norm": 4.851064682006836, | |
| "learning_rate": 6.425787818636131e-06, | |
| "loss": 0.3865, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.02209801117899389, | |
| "grad_norm": 4.279152870178223, | |
| "learning_rate": 6.026312439675552e-06, | |
| "loss": 0.4051, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.022227999480046796, | |
| "grad_norm": 4.414910316467285, | |
| "learning_rate": 5.6388590278194096e-06, | |
| "loss": 0.3067, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.0223579877810997, | |
| "grad_norm": 5.755686283111572, | |
| "learning_rate": 5.263533508961827e-06, | |
| "loss": 0.2625, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.022487976082152607, | |
| "grad_norm": 3.9747025966644287, | |
| "learning_rate": 4.900438493352055e-06, | |
| "loss": 0.2678, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.02261796438320551, | |
| "grad_norm": 4.925014495849609, | |
| "learning_rate": 4.549673247541875e-06, | |
| "loss": 0.4446, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.022747952684258416, | |
| "grad_norm": 3.8584940433502197, | |
| "learning_rate": 4.2113336672471245e-06, | |
| "loss": 0.2705, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.02287794098531132, | |
| "grad_norm": 6.217220783233643, | |
| "learning_rate": 3.885512251130763e-06, | |
| "loss": 0.2744, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.023007929286364227, | |
| "grad_norm": 3.975886106491089, | |
| "learning_rate": 3.5722980755146517e-06, | |
| "loss": 0.1502, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.023137917587417133, | |
| "grad_norm": 3.1045374870300293, | |
| "learning_rate": 3.271776770026963e-06, | |
| "loss": 0.1656, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.02326790588847004, | |
| "grad_norm": 3.4880239963531494, | |
| "learning_rate": 2.9840304941919415e-06, | |
| "loss": 0.1164, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.02339789418952294, | |
| "grad_norm": 2.9001333713531494, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 0.1343, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.023527882490575847, | |
| "grad_norm": 2.706907033920288, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 0.1605, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.023657870791628753, | |
| "grad_norm": 2.9197463989257812, | |
| "learning_rate": 2.1982109232821178e-06, | |
| "loss": 0.1823, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.02378785909268166, | |
| "grad_norm": 2.654012441635132, | |
| "learning_rate": 1.962316193157593e-06, | |
| "loss": 0.1404, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.023917847393734565, | |
| "grad_norm": 2.891735792160034, | |
| "learning_rate": 1.7395544861325718e-06, | |
| "loss": 0.1778, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.02404783569478747, | |
| "grad_norm": 2.2459590435028076, | |
| "learning_rate": 1.5299867030334814e-06, | |
| "loss": 0.1375, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.024177823995840373, | |
| "grad_norm": 4.118468761444092, | |
| "learning_rate": 1.333670137599713e-06, | |
| "loss": 0.2924, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.02430781229689328, | |
| "grad_norm": 2.8520309925079346, | |
| "learning_rate": 1.1506584608200367e-06, | |
| "loss": 0.1181, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.024437800597946185, | |
| "grad_norm": 3.3957877159118652, | |
| "learning_rate": 9.810017062595322e-07, | |
| "loss": 0.1221, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.02456778889899909, | |
| "grad_norm": 3.7786142826080322, | |
| "learning_rate": 8.247462563808817e-07, | |
| "loss": 0.1115, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.024697777200051996, | |
| "grad_norm": 3.0048716068267822, | |
| "learning_rate": 6.819348298638839e-07, | |
| "loss": 0.2042, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.024827765501104902, | |
| "grad_norm": 2.7258095741271973, | |
| "learning_rate": 5.526064699265753e-07, | |
| "loss": 0.1736, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.024957753802157805, | |
| "grad_norm": 2.4716155529022217, | |
| "learning_rate": 4.367965336512403e-07, | |
| "loss": 0.1401, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.02508774210321071, | |
| "grad_norm": 5.744486331939697, | |
| "learning_rate": 3.3453668231809286e-07, | |
| "loss": 0.3324, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.025217730404263616, | |
| "grad_norm": 1.9319515228271484, | |
| "learning_rate": 2.458548727494292e-07, | |
| "loss": 0.1337, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.025347718705316522, | |
| "grad_norm": 1.988318681716919, | |
| "learning_rate": 1.7077534966650766e-07, | |
| "loss": 0.1646, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.025477707006369428, | |
| "grad_norm": 2.43589448928833, | |
| "learning_rate": 1.0931863906127327e-07, | |
| "loss": 0.0924, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.02560769530742233, | |
| "grad_norm": 2.2786128520965576, | |
| "learning_rate": 6.150154258476315e-08, | |
| "loss": 0.1111, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.025737683608475236, | |
| "grad_norm": 2.1147823333740234, | |
| "learning_rate": 2.7337132953697554e-08, | |
| "loss": 0.1388, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.025867671909528142, | |
| "grad_norm": 1.7648025751113892, | |
| "learning_rate": 6.834750376549792e-09, | |
| "loss": 0.0861, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.025997660210581048, | |
| "grad_norm": 1.70954167842865, | |
| "learning_rate": 0.0, | |
| "loss": 0.1374, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.025997660210581048, | |
| "eval_loss": 0.0698026642203331, | |
| "eval_runtime": 1418.5099, | |
| "eval_samples_per_second": 9.134, | |
| "eval_steps_per_second": 2.284, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.123153154615542e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |