| { | |
| "best_metric": 0.05233228579163551, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 1.9975031210986267, | |
| "eval_steps": 25, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.019975031210986267, | |
| "grad_norm": 32.32381057739258, | |
| "learning_rate": 2e-05, | |
| "loss": 6.6435, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.019975031210986267, | |
| "eval_loss": 6.483519554138184, | |
| "eval_runtime": 6.8225, | |
| "eval_samples_per_second": 98.791, | |
| "eval_steps_per_second": 6.303, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.039950062421972535, | |
| "grad_norm": 32.88056182861328, | |
| "learning_rate": 4e-05, | |
| "loss": 6.6757, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0599250936329588, | |
| "grad_norm": 31.19997787475586, | |
| "learning_rate": 6e-05, | |
| "loss": 6.4156, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.07990012484394507, | |
| "grad_norm": 23.896907806396484, | |
| "learning_rate": 8e-05, | |
| "loss": 5.0024, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.09987515605493133, | |
| "grad_norm": 13.470758438110352, | |
| "learning_rate": 0.0001, | |
| "loss": 3.1743, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1198501872659176, | |
| "grad_norm": 9.408984184265137, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 2.0651, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.13982521847690388, | |
| "grad_norm": 9.622489929199219, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 1.413, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.15980024968789014, | |
| "grad_norm": 6.5332932472229, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 0.7076, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1797752808988764, | |
| "grad_norm": 2.7348451614379883, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 0.307, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.19975031210986266, | |
| "grad_norm": 1.4920560121536255, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 0.1333, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.21972534332084895, | |
| "grad_norm": 0.7912208437919617, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 0.0924, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2397003745318352, | |
| "grad_norm": 0.4346309304237366, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 0.0483, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2596754057428215, | |
| "grad_norm": 1.192466139793396, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 0.0972, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.27965043695380776, | |
| "grad_norm": 1.9299390316009521, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 0.1222, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.299625468164794, | |
| "grad_norm": 0.6965848207473755, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 0.0805, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3196004993757803, | |
| "grad_norm": 0.9696741700172424, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 0.096, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.33957553058676654, | |
| "grad_norm": 0.6358460187911987, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 0.0818, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3595505617977528, | |
| "grad_norm": 0.5815155506134033, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 0.0761, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.37952559300873906, | |
| "grad_norm": 0.6561976671218872, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 0.0709, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.3995006242197253, | |
| "grad_norm": 1.2013440132141113, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 0.1275, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.41947565543071164, | |
| "grad_norm": 0.5312557816505432, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 0.0696, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.4394506866416979, | |
| "grad_norm": 0.39881420135498047, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 0.0519, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.45942571785268416, | |
| "grad_norm": 0.38855546712875366, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 0.0509, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.4794007490636704, | |
| "grad_norm": 0.5084037780761719, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0526, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.4993757802746567, | |
| "grad_norm": 0.36609482765197754, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 0.0417, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4993757802746567, | |
| "eval_loss": 0.07570720463991165, | |
| "eval_runtime": 6.8153, | |
| "eval_samples_per_second": 98.895, | |
| "eval_steps_per_second": 6.309, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.519350811485643, | |
| "grad_norm": 1.0404666662216187, | |
| "learning_rate": 8.842005554284296e-05, | |
| "loss": 0.1171, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.5393258426966292, | |
| "grad_norm": 0.6350396871566772, | |
| "learning_rate": 8.73410738492077e-05, | |
| "loss": 0.0752, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5593008739076155, | |
| "grad_norm": 0.5021554827690125, | |
| "learning_rate": 8.622126023955446e-05, | |
| "loss": 0.0646, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.5792759051186017, | |
| "grad_norm": 0.7377936244010925, | |
| "learning_rate": 8.506183921362443e-05, | |
| "loss": 0.0745, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.599250936329588, | |
| "grad_norm": 0.5337192416191101, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 0.0594, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6192259675405742, | |
| "grad_norm": 0.5033006072044373, | |
| "learning_rate": 8.262928807620843e-05, | |
| "loss": 0.0501, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.6392009987515606, | |
| "grad_norm": 0.4639797806739807, | |
| "learning_rate": 8.135881792367686e-05, | |
| "loss": 0.0591, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.6591760299625468, | |
| "grad_norm": 0.47012022137641907, | |
| "learning_rate": 8.005405736415126e-05, | |
| "loss": 0.0583, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.6791510611735331, | |
| "grad_norm": 0.40740257501602173, | |
| "learning_rate": 7.871643313414718e-05, | |
| "loss": 0.0393, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.6991260923845194, | |
| "grad_norm": 0.4334827959537506, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 0.0694, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.7191011235955056, | |
| "grad_norm": 0.34927257895469666, | |
| "learning_rate": 7.594847868906076e-05, | |
| "loss": 0.0407, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.7390761548064919, | |
| "grad_norm": 0.3759843707084656, | |
| "learning_rate": 7.452117519152542e-05, | |
| "loss": 0.0333, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.7590511860174781, | |
| "grad_norm": 0.3167741596698761, | |
| "learning_rate": 7.30670581489344e-05, | |
| "loss": 0.0618, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.7790262172284644, | |
| "grad_norm": 1.1636722087860107, | |
| "learning_rate": 7.158771761692464e-05, | |
| "loss": 0.1346, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.7990012484394506, | |
| "grad_norm": 0.699979305267334, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 0.0876, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.818976279650437, | |
| "grad_norm": 0.5671290755271912, | |
| "learning_rate": 6.855986244591104e-05, | |
| "loss": 0.0756, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.8389513108614233, | |
| "grad_norm": 0.3836475908756256, | |
| "learning_rate": 6.701465872208216e-05, | |
| "loss": 0.0673, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.8589263420724095, | |
| "grad_norm": 0.3973909020423889, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0461, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.8789013732833958, | |
| "grad_norm": 0.41587159037590027, | |
| "learning_rate": 6.387014543809223e-05, | |
| "loss": 0.0576, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.898876404494382, | |
| "grad_norm": 0.47783681750297546, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 0.0507, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.9188514357053683, | |
| "grad_norm": 0.5148672461509705, | |
| "learning_rate": 6.066498153718735e-05, | |
| "loss": 0.0676, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.9388264669163545, | |
| "grad_norm": 0.5991238355636597, | |
| "learning_rate": 5.90440267166055e-05, | |
| "loss": 0.0565, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.9588014981273408, | |
| "grad_norm": 0.5729100704193115, | |
| "learning_rate": 5.74131823855921e-05, | |
| "loss": 0.0693, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.978776529338327, | |
| "grad_norm": 0.46636906266212463, | |
| "learning_rate": 5.577423184847932e-05, | |
| "loss": 0.0614, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.9987515605493134, | |
| "grad_norm": 0.3745470643043518, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 0.0263, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.9987515605493134, | |
| "eval_loss": 0.05686701834201813, | |
| "eval_runtime": 6.7983, | |
| "eval_samples_per_second": 99.142, | |
| "eval_steps_per_second": 6.325, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.0187265917602997, | |
| "grad_norm": 0.6444295048713684, | |
| "learning_rate": 5.247918773366112e-05, | |
| "loss": 0.0721, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.038701622971286, | |
| "grad_norm": 0.356772780418396, | |
| "learning_rate": 5.0826697238317935e-05, | |
| "loss": 0.0615, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.058676654182272, | |
| "grad_norm": 0.42914852499961853, | |
| "learning_rate": 4.917330276168208e-05, | |
| "loss": 0.0448, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 1.0786516853932584, | |
| "grad_norm": 0.45043033361434937, | |
| "learning_rate": 4.7520812266338885e-05, | |
| "loss": 0.0495, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.0986267166042447, | |
| "grad_norm": 0.3365642726421356, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 0.0594, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.118601747815231, | |
| "grad_norm": 0.2681638300418854, | |
| "learning_rate": 4.4225768151520694e-05, | |
| "loss": 0.0334, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.1385767790262173, | |
| "grad_norm": 0.38356465101242065, | |
| "learning_rate": 4.2586817614407895e-05, | |
| "loss": 0.0523, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 1.1585518102372034, | |
| "grad_norm": 0.40522027015686035, | |
| "learning_rate": 4.095597328339452e-05, | |
| "loss": 0.0413, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.1785268414481898, | |
| "grad_norm": 0.22131456434726715, | |
| "learning_rate": 3.933501846281267e-05, | |
| "loss": 0.0239, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 1.198501872659176, | |
| "grad_norm": 0.3389541208744049, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 0.0372, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.2184769038701624, | |
| "grad_norm": 0.29863250255584717, | |
| "learning_rate": 3.612985456190778e-05, | |
| "loss": 0.0212, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 1.2384519350811485, | |
| "grad_norm": 0.22949916124343872, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.0169, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.2584269662921348, | |
| "grad_norm": 0.28763681650161743, | |
| "learning_rate": 3.298534127791785e-05, | |
| "loss": 0.0261, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.2784019975031211, | |
| "grad_norm": 0.37180131673812866, | |
| "learning_rate": 3.144013755408895e-05, | |
| "loss": 0.0322, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.2983770287141074, | |
| "grad_norm": 0.3311071991920471, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 0.0346, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.3183520599250937, | |
| "grad_norm": 0.3131641149520874, | |
| "learning_rate": 2.8412282383075363e-05, | |
| "loss": 0.0391, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.3383270911360798, | |
| "grad_norm": 0.3434888422489166, | |
| "learning_rate": 2.693294185106562e-05, | |
| "loss": 0.0433, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 1.3583021223470662, | |
| "grad_norm": 0.35058820247650146, | |
| "learning_rate": 2.547882480847461e-05, | |
| "loss": 0.0353, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.3782771535580525, | |
| "grad_norm": 0.23418645560741425, | |
| "learning_rate": 2.405152131093926e-05, | |
| "loss": 0.0217, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.3982521847690386, | |
| "grad_norm": 0.2888217866420746, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 0.0274, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.4182272159800249, | |
| "grad_norm": 0.39486294984817505, | |
| "learning_rate": 2.128356686585282e-05, | |
| "loss": 0.0554, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 1.4382022471910112, | |
| "grad_norm": 0.23438122868537903, | |
| "learning_rate": 1.9945942635848748e-05, | |
| "loss": 0.0198, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.4581772784019975, | |
| "grad_norm": 0.29288169741630554, | |
| "learning_rate": 1.8641182076323148e-05, | |
| "loss": 0.0312, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.4781523096129838, | |
| "grad_norm": 0.23595376312732697, | |
| "learning_rate": 1.7370711923791567e-05, | |
| "loss": 0.0211, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.4981273408239701, | |
| "grad_norm": 0.3430394232273102, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 0.0217, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.4981273408239701, | |
| "eval_loss": 0.05315978825092316, | |
| "eval_runtime": 6.797, | |
| "eval_samples_per_second": 99.162, | |
| "eval_steps_per_second": 6.326, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.5181023720349565, | |
| "grad_norm": 0.392977237701416, | |
| "learning_rate": 1.4938160786375572e-05, | |
| "loss": 0.0447, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.5380774032459426, | |
| "grad_norm": 0.2741864323616028, | |
| "learning_rate": 1.3778739760445552e-05, | |
| "loss": 0.0361, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.5580524344569289, | |
| "grad_norm": 0.27243152260780334, | |
| "learning_rate": 1.2658926150792322e-05, | |
| "loss": 0.0274, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.578027465667915, | |
| "grad_norm": 0.40270382165908813, | |
| "learning_rate": 1.157994445715706e-05, | |
| "loss": 0.0542, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 1.5980024968789013, | |
| "grad_norm": 0.22019416093826294, | |
| "learning_rate": 1.0542974530180327e-05, | |
| "loss": 0.0271, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.6179775280898876, | |
| "grad_norm": 0.3104560077190399, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0328, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.637952559300874, | |
| "grad_norm": 0.2330722212791443, | |
| "learning_rate": 8.599558442598998e-06, | |
| "loss": 0.0335, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.6579275905118602, | |
| "grad_norm": 0.28479820489883423, | |
| "learning_rate": 7.695237378953223e-06, | |
| "loss": 0.0329, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 1.6779026217228465, | |
| "grad_norm": 0.28051578998565674, | |
| "learning_rate": 6.837175952121306e-06, | |
| "loss": 0.0266, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.6978776529338329, | |
| "grad_norm": 0.23817192018032074, | |
| "learning_rate": 6.026312439675552e-06, | |
| "loss": 0.024, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.717852684144819, | |
| "grad_norm": 0.2637062966823578, | |
| "learning_rate": 5.263533508961827e-06, | |
| "loss": 0.0312, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.7378277153558053, | |
| "grad_norm": 0.263805627822876, | |
| "learning_rate": 4.549673247541875e-06, | |
| "loss": 0.0224, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.7578027465667914, | |
| "grad_norm": 0.24613410234451294, | |
| "learning_rate": 3.885512251130763e-06, | |
| "loss": 0.0316, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.3555324971675873, | |
| "learning_rate": 3.271776770026963e-06, | |
| "loss": 0.0366, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.797752808988764, | |
| "grad_norm": 0.3043622374534607, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 0.0401, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.8177278401997503, | |
| "grad_norm": 0.46414047479629517, | |
| "learning_rate": 2.1982109232821178e-06, | |
| "loss": 0.0492, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.8377028714107366, | |
| "grad_norm": 0.287507027387619, | |
| "learning_rate": 1.7395544861325718e-06, | |
| "loss": 0.0219, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.857677902621723, | |
| "grad_norm": 0.3227818012237549, | |
| "learning_rate": 1.333670137599713e-06, | |
| "loss": 0.0388, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.8776529338327093, | |
| "grad_norm": 0.397909015417099, | |
| "learning_rate": 9.810017062595322e-07, | |
| "loss": 0.047, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.8976279650436954, | |
| "grad_norm": 0.4243538975715637, | |
| "learning_rate": 6.819348298638839e-07, | |
| "loss": 0.0484, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.9176029962546817, | |
| "grad_norm": 0.26352471113204956, | |
| "learning_rate": 4.367965336512403e-07, | |
| "loss": 0.0285, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.9375780274656678, | |
| "grad_norm": 0.26268190145492554, | |
| "learning_rate": 2.458548727494292e-07, | |
| "loss": 0.0279, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.957553058676654, | |
| "grad_norm": 0.2822859585285187, | |
| "learning_rate": 1.0931863906127327e-07, | |
| "loss": 0.0192, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.9775280898876404, | |
| "grad_norm": 0.30654722452163696, | |
| "learning_rate": 2.7337132953697554e-08, | |
| "loss": 0.0183, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.9975031210986267, | |
| "grad_norm": 0.28469908237457275, | |
| "learning_rate": 0.0, | |
| "loss": 0.0287, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.9975031210986267, | |
| "eval_loss": 0.05233228579163551, | |
| "eval_runtime": 6.8792, | |
| "eval_samples_per_second": 97.977, | |
| "eval_steps_per_second": 6.251, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": 4.238145415544832e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |