| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.07425283088917765, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00037126415444588826, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00037126415444588826, | |
| "eval_loss": NaN, | |
| "eval_runtime": 85.3531, | |
| "eval_samples_per_second": 53.156, | |
| "eval_steps_per_second": 13.298, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007425283088917765, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0011137924633376648, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001485056617783553, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0018563207722294413, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0022275849266753297, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 1.2882, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0025988490811212177, | |
| "grad_norm": 1.884553074836731, | |
| "learning_rate": 7e-05, | |
| "loss": 4.3348, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002970113235567106, | |
| "grad_norm": 2.009493350982666, | |
| "learning_rate": 8e-05, | |
| "loss": 4.2861, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003341377390012994, | |
| "grad_norm": 2.1323981285095215, | |
| "learning_rate": 9e-05, | |
| "loss": 4.3175, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0037126415444588825, | |
| "grad_norm": 1.962135672569275, | |
| "learning_rate": 0.0001, | |
| "loss": 4.2849, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0040839056989047705, | |
| "grad_norm": 1.8930343389511108, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 4.0676, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.004455169853350659, | |
| "grad_norm": 2.0051259994506836, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 4.1995, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004826434007796547, | |
| "grad_norm": 1.7621339559555054, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 3.7905, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005197698162242435, | |
| "grad_norm": 1.6517441272735596, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 3.6565, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.005568962316688323, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 5.1495, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005940226471134212, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0063114906255801, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.006682754780025988, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.007054018934471877, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.007425283088917765, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007796547243363653, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.008167811397809541, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.008539075552255429, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.008910339706701319, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.009281603861147207, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.009652868015593095, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.010024132170038983, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.01039539632448487, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.010766660478930759, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.011137924633376647, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.011509188787822536, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.011880452942268424, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.012251717096714312, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0126229812511602, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.012994245405606088, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.013365509560051976, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.013736773714497864, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.014108037868943754, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.014479302023389642, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.01485056617783553, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.015221830332281418, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.015593094486727306, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.015964358641173196, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.016335622795619082, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.016706886950064972, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.017078151104510858, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.017449415258956748, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.017820679413402638, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.018191943567848524, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.018563207722294413, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.018563207722294413, | |
| "eval_loss": NaN, | |
| "eval_runtime": 84.5089, | |
| "eval_samples_per_second": 53.687, | |
| "eval_steps_per_second": 13.431, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0189344718767403, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.894386393810563e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.01930573603118619, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.842005554284296e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.019677000185632076, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.788574348801675e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.020048264340077965, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.73410738492077e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.020419528494523855, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.02079079264896974, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.622126023955446e-05, | |
| "loss": 1.8059, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.02116205680341563, | |
| "grad_norm": 1.517547369003296, | |
| "learning_rate": 8.564642241456986e-05, | |
| "loss": 3.1669, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.021533320957861517, | |
| "grad_norm": 1.5346742868423462, | |
| "learning_rate": 8.506183921362443e-05, | |
| "loss": 3.1012, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.021904585112307407, | |
| "grad_norm": 1.30705726146698, | |
| "learning_rate": 8.44676704559283e-05, | |
| "loss": 2.8825, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.022275849266753293, | |
| "grad_norm": 1.4488762617111206, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 2.9703, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.022647113421199183, | |
| "grad_norm": 1.3518919944763184, | |
| "learning_rate": 8.32512286056924e-05, | |
| "loss": 2.8527, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.023018377575645073, | |
| "grad_norm": 1.0384478569030762, | |
| "learning_rate": 8.262928807620843e-05, | |
| "loss": 2.4588, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.02338964173009096, | |
| "grad_norm": 1.1018555164337158, | |
| "learning_rate": 8.199842702516583e-05, | |
| "loss": 2.6498, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.02376090588453685, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.135881792367686e-05, | |
| "loss": 4.3064, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.024132170038982735, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.024503434193428625, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.005405736415126e-05, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.02487469834787451, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.0252459625023204, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.871643313414718e-05, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.02561722665676629, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.803575286758364e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.025988490811212177, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.026359754965658067, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.66515864363997e-05, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.026731019120103953, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.594847868906076e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.027102283274549843, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.52382768867422e-05, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.02747354742899573, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.452117519152542e-05, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.02784481158344162, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.028216075737887508, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.30670581489344e-05, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.028587339892333394, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.233044034264034e-05, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.028958604046779284, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.158771761692464e-05, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.02932986820122517, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.083909302476453e-05, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.02970113235567106, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.03007239651011695, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.932495846462261e-05, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.030443660664562836, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.855986244591104e-05, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.030814924819008726, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.778969234612584e-05, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.031186188973454612, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.701465872208216e-05, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.0315574531279005, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.03192871728234639, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.032299981436792274, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.466250186922325e-05, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.032671245591238164, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.387014543809223e-05, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.033042509745684054, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.307399704769099e-05, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.033413773900129944, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.03378503805457583, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.147119600233758e-05, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.034156302209021716, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.066498153718735e-05, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.034527566363467606, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.985585137257401e-05, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.034898830517913496, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.90440267166055e-05, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.035270094672359385, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.035641358826805275, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.74131823855921e-05, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.03601262298125116, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6594608567103456e-05, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.03638388713569705, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.577423184847932e-05, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.03675515129014294, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.495227651252315e-05, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.03712641544458883, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03712641544458883, | |
| "eval_loss": NaN, | |
| "eval_runtime": 84.6195, | |
| "eval_samples_per_second": 53.616, | |
| "eval_steps_per_second": 13.413, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03749767959903471, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.330452921628497e-05, | |
| "loss": 0.0, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.0378689437534806, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.247918773366112e-05, | |
| "loss": 0.0, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.03824020790792649, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.165316846586541e-05, | |
| "loss": 0.0, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.03861147206237238, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.0826697238317935e-05, | |
| "loss": 0.0, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.03898273621681827, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.03935400037126415, | |
| "grad_norm": 1.0149999856948853, | |
| "learning_rate": 4.917330276168208e-05, | |
| "loss": 2.4472, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.03972526452571004, | |
| "grad_norm": 0.9319671988487244, | |
| "learning_rate": 4.834683153413459e-05, | |
| "loss": 2.2121, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.04009652868015593, | |
| "grad_norm": 0.9308563470840454, | |
| "learning_rate": 4.7520812266338885e-05, | |
| "loss": 2.3154, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.04046779283460182, | |
| "grad_norm": 0.9594351053237915, | |
| "learning_rate": 4.669547078371504e-05, | |
| "loss": 1.9862, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.04083905698904771, | |
| "grad_norm": 0.8474317789077759, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 2.3131, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.04121032114349359, | |
| "grad_norm": 0.8937053084373474, | |
| "learning_rate": 4.504772348747687e-05, | |
| "loss": 1.9905, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.04158158529793948, | |
| "grad_norm": 1.077065110206604, | |
| "learning_rate": 4.4225768151520694e-05, | |
| "loss": 2.0155, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.04195284945238537, | |
| "grad_norm": 0.8904207944869995, | |
| "learning_rate": 4.3405391432896555e-05, | |
| "loss": 2.3218, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.04232411360683126, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2586817614407895e-05, | |
| "loss": 0.0, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.04269537776127715, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.17702704859633e-05, | |
| "loss": 0.0, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.043066641915723035, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.095597328339452e-05, | |
| "loss": 0.0, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.043437906070168925, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.0144148627425993e-05, | |
| "loss": 0.0, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.043809170224614814, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.933501846281267e-05, | |
| "loss": 0.0, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.044180434379060704, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.852880399766243e-05, | |
| "loss": 0.0, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.04455169853350659, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.04492296268795248, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6926002952309016e-05, | |
| "loss": 0.0, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.045294226842398366, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.612985456190778e-05, | |
| "loss": 0.0, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.045665490996844256, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.533749813077677e-05, | |
| "loss": 0.0, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.046036755151290146, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.0, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.04640801930573603, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3765026539765834e-05, | |
| "loss": 0.0, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.04677928346018192, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.298534127791785e-05, | |
| "loss": 0.0, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.04715054761462781, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.221030765387417e-05, | |
| "loss": 0.0, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.0475218117690737, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.144013755408895e-05, | |
| "loss": 0.0, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.04789307592351959, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0675041535377405e-05, | |
| "loss": 0.0, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.04826434007796547, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.04863560423241136, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.916090697523549e-05, | |
| "loss": 0.0, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.04900686838685725, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8412282383075363e-05, | |
| "loss": 0.0, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.04937813254130314, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.766955965735968e-05, | |
| "loss": 0.0, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.04974939669574902, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.693294185106562e-05, | |
| "loss": 0.0, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.05012066085019491, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6202630348146324e-05, | |
| "loss": 0.0, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.0504919250046408, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.547882480847461e-05, | |
| "loss": 0.0, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.05086318915908669, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.476172311325783e-05, | |
| "loss": 0.0, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.05123445331353258, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.405152131093926e-05, | |
| "loss": 0.0, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.051605717467978464, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3348413563600325e-05, | |
| "loss": 0.0, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.051976981622424354, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.05234824577687024, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.196424713241637e-05, | |
| "loss": 0.0, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.05271950993131613, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.128356686585282e-05, | |
| "loss": 0.0, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.05309077408576202, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.0, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.053462038240207906, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9945942635848748e-05, | |
| "loss": 0.0, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.053833302394653795, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.928936436551661e-05, | |
| "loss": 0.0, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.054204566549099685, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8641182076323148e-05, | |
| "loss": 0.0, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.054575830703545575, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.800157297483417e-05, | |
| "loss": 0.0, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.05494709485799146, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7370711923791567e-05, | |
| "loss": 0.0, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.05531835901243735, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6748771394307585e-05, | |
| "loss": 0.0, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.05568962316688324, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.05568962316688324, | |
| "eval_loss": NaN, | |
| "eval_runtime": 84.5667, | |
| "eval_samples_per_second": 53.65, | |
| "eval_steps_per_second": 13.421, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.05606088732132913, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.553232954407171e-05, | |
| "loss": 0.0, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.056432151475775016, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4938160786375572e-05, | |
| "loss": 0.0, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.0568034156302209, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.435357758543015e-05, | |
| "loss": 0.0, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.05717467978466679, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3778739760445552e-05, | |
| "loss": 0.0, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.05754594393911268, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3213804466343421e-05, | |
| "loss": 0.0, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.05791720809355857, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2658926150792322e-05, | |
| "loss": 0.6424, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.05828847224800446, | |
| "grad_norm": 0.9106338620185852, | |
| "learning_rate": 1.2114256511983274e-05, | |
| "loss": 1.8145, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.05865973640245034, | |
| "grad_norm": 0.8052253723144531, | |
| "learning_rate": 1.157994445715706e-05, | |
| "loss": 1.8558, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.05903100055689623, | |
| "grad_norm": 0.9187486171722412, | |
| "learning_rate": 1.1056136061894384e-05, | |
| "loss": 1.9704, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.05940226471134212, | |
| "grad_norm": 0.9137905836105347, | |
| "learning_rate": 1.0542974530180327e-05, | |
| "loss": 1.9263, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.05977352886578801, | |
| "grad_norm": 0.9863153100013733, | |
| "learning_rate": 1.0040600155253765e-05, | |
| "loss": 2.1586, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.0601447930202339, | |
| "grad_norm": 0.9548128247261047, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.9655, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.06051605717467978, | |
| "grad_norm": 0.9738331437110901, | |
| "learning_rate": 9.068759265665384e-06, | |
| "loss": 2.0378, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.06088732132912567, | |
| "grad_norm": 1.0089131593704224, | |
| "learning_rate": 8.599558442598998e-06, | |
| "loss": 2.3147, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.06125858548357156, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.141676086873572e-06, | |
| "loss": 4.6648, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.06162984963801745, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.695237378953223e-06, | |
| "loss": 0.0, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.062001113792463335, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.260364370723044e-06, | |
| "loss": 0.0, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.062372377946909224, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.837175952121306e-06, | |
| "loss": 0.0, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.06274364210135512, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.425787818636131e-06, | |
| "loss": 0.0, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.063114906255801, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.026312439675552e-06, | |
| "loss": 0.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.06348617041024689, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6388590278194096e-06, | |
| "loss": 0.0, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.06385743456469278, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.263533508961827e-06, | |
| "loss": 0.0, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.06422869871913867, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.900438493352055e-06, | |
| "loss": 0.0, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.06459996287358455, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.549673247541875e-06, | |
| "loss": 0.0, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.06497122702803045, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2113336672471245e-06, | |
| "loss": 0.0, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.06534249118247633, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.885512251130763e-06, | |
| "loss": 0.0, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.06571375533692222, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5722980755146517e-06, | |
| "loss": 0.0, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.06608501949136811, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.271776770026963e-06, | |
| "loss": 0.0, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.06645628364581399, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9840304941919415e-06, | |
| "loss": 0.0, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.06682754780025989, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.06719881195470577, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 0.0, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.06757007610915167, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1982109232821178e-06, | |
| "loss": 0.0, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.06794134026359755, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.962316193157593e-06, | |
| "loss": 0.0, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.06831260441804343, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7395544861325718e-06, | |
| "loss": 0.0, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.06868386857248933, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5299867030334814e-06, | |
| "loss": 0.0, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.06905513272693521, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.333670137599713e-06, | |
| "loss": 0.0, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.06942639688138111, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1506584608200367e-06, | |
| "loss": 0.0, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.06979766103582699, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.810017062595322e-07, | |
| "loss": 0.0, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.07016892519027287, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.247462563808817e-07, | |
| "loss": 0.0, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.07054018934471877, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.819348298638839e-07, | |
| "loss": 0.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.07091145349916465, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.526064699265753e-07, | |
| "loss": 0.0, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.07128271765361055, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.367965336512403e-07, | |
| "loss": 0.0, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.07165398180805643, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3453668231809286e-07, | |
| "loss": 0.0, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.07202524596250232, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.458548727494292e-07, | |
| "loss": 0.0, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.07239651011694821, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7077534966650766e-07, | |
| "loss": 0.0, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.0727677742713941, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0931863906127327e-07, | |
| "loss": 0.0, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.07313903842583999, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.150154258476315e-08, | |
| "loss": 0.0, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.07351030258028587, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7337132953697554e-08, | |
| "loss": 0.0, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.07388156673473176, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.834750376549792e-09, | |
| "loss": 0.0, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.07425283088917765, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.07425283088917765, | |
| "eval_loss": NaN, | |
| "eval_runtime": 84.687, | |
| "eval_samples_per_second": 53.574, | |
| "eval_steps_per_second": 13.402, | |
| "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": 3 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.524891257929728e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |