| { | |
| "best_metric": 0.00010527808626648039, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-150", | |
| "epoch": 0.8800880088008801, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0044004400440044, | |
| "grad_norm": 0.12771454453468323, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0426, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0044004400440044, | |
| "eval_loss": 0.4005989134311676, | |
| "eval_runtime": 26.5958, | |
| "eval_samples_per_second": 14.401, | |
| "eval_steps_per_second": 3.61, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0088008800880088, | |
| "grad_norm": 0.1674533635377884, | |
| "learning_rate": 2e-05, | |
| "loss": 0.062, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.013201320132013201, | |
| "grad_norm": 0.2129768431186676, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0726, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0176017601760176, | |
| "grad_norm": 0.21180090308189392, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0685, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.022002200220022004, | |
| "grad_norm": 0.20727582275867462, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0579, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.026402640264026403, | |
| "grad_norm": 0.1735854595899582, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0498, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.030803080308030802, | |
| "grad_norm": 0.13483098149299622, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0363, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0352035203520352, | |
| "grad_norm": 0.18715985119342804, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0242, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.039603960396039604, | |
| "grad_norm": 0.08055658638477325, | |
| "learning_rate": 9e-05, | |
| "loss": 0.006, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04400440044004401, | |
| "grad_norm": 0.054394036531448364, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0043, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0484048404840484, | |
| "grad_norm": 0.010181427001953125, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 0.0003, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.052805280528052806, | |
| "grad_norm": 0.024874452501535416, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 0.0007, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05720572057205721, | |
| "grad_norm": 0.002741459058597684, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 0.0001, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.061606160616061605, | |
| "grad_norm": 0.02060742676258087, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 0.0005, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.066006600660066, | |
| "grad_norm": 0.031613726168870926, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 0.0006, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0704070407040704, | |
| "grad_norm": 0.18244582414627075, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 0.0012, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0748074807480748, | |
| "grad_norm": 0.1566692590713501, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 0.0053, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.07920792079207921, | |
| "grad_norm": 0.03750842064619064, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 0.0007, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08360836083608361, | |
| "grad_norm": 0.042819686233997345, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 0.0007, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.08800880088008801, | |
| "grad_norm": 1.0322291851043701, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 0.0157, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0924092409240924, | |
| "grad_norm": 0.01983068324625492, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 0.0003, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0968096809680968, | |
| "grad_norm": 0.716315746307373, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 0.0147, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.10121012101210121, | |
| "grad_norm": 0.11902855336666107, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 0.0019, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.10561056105610561, | |
| "grad_norm": 0.23638315498828888, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 0.0029, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.11001100110011001, | |
| "grad_norm": 1.6142650842666626, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 0.0185, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11441144114411442, | |
| "grad_norm": 5.675965309143066, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 0.0331, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1188118811881188, | |
| "grad_norm": 0.5444292426109314, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 0.0054, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.12321232123212321, | |
| "grad_norm": 0.26792553067207336, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 0.0008, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.1276127612761276, | |
| "grad_norm": 0.8868173956871033, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0055, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.132013201320132, | |
| "grad_norm": 1.2971628904342651, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 0.0052, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13641364136413642, | |
| "grad_norm": 0.9248525500297546, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 0.0025, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.1408140814081408, | |
| "grad_norm": 0.09059440344572067, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 0.0006, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.14521452145214522, | |
| "grad_norm": 0.36796489357948303, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 0.0005, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1496149614961496, | |
| "grad_norm": 0.01746664009988308, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 0.0004, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.15401540154015403, | |
| "grad_norm": 0.005237877834588289, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 0.0002, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.15841584158415842, | |
| "grad_norm": 0.005986074451357126, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 0.0002, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1628162816281628, | |
| "grad_norm": 0.016195502132177353, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 0.0003, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.16721672167216722, | |
| "grad_norm": 0.46905526518821716, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 0.0013, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.1716171617161716, | |
| "grad_norm": 0.01955334283411503, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 0.0004, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.17601760176017603, | |
| "grad_norm": 0.00414010277017951, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 0.0001, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.18041804180418042, | |
| "grad_norm": 0.030733508989214897, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 0.0003, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.1848184818481848, | |
| "grad_norm": 0.008328596130013466, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 0.0002, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.18921892189218922, | |
| "grad_norm": 0.5453759431838989, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 0.006, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1936193619361936, | |
| "grad_norm": 0.06769367307424545, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 0.0004, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.19801980198019803, | |
| "grad_norm": 0.03878987208008766, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 0.0007, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.20242024202420242, | |
| "grad_norm": 0.2882028818130493, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 0.0085, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2068206820682068, | |
| "grad_norm": 0.004409385845065117, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 0.0001, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.21122112211221122, | |
| "grad_norm": 0.037853118032217026, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0006, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.2156215621562156, | |
| "grad_norm": 2.1406216621398926, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 0.0147, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.22002200220022003, | |
| "grad_norm": 0.07293225824832916, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 0.0007, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.22002200220022003, | |
| "eval_loss": 0.004681536927819252, | |
| "eval_runtime": 27.0797, | |
| "eval_samples_per_second": 14.143, | |
| "eval_steps_per_second": 3.545, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.22442244224422442, | |
| "grad_norm": 0.0517556257545948, | |
| "learning_rate": 8.894386393810563e-05, | |
| "loss": 0.0012, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.22882288228822883, | |
| "grad_norm": 0.04808424413204193, | |
| "learning_rate": 8.842005554284296e-05, | |
| "loss": 0.001, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.23322332233223322, | |
| "grad_norm": 0.007223631255328655, | |
| "learning_rate": 8.788574348801675e-05, | |
| "loss": 0.0001, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.2376237623762376, | |
| "grad_norm": 0.025885717943310738, | |
| "learning_rate": 8.73410738492077e-05, | |
| "loss": 0.0003, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.24202420242024203, | |
| "grad_norm": 0.005397991742938757, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 0.0001, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.24642464246424642, | |
| "grad_norm": 0.01347585953772068, | |
| "learning_rate": 8.622126023955446e-05, | |
| "loss": 0.0001, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.2508250825082508, | |
| "grad_norm": 0.0014133111108094454, | |
| "learning_rate": 8.564642241456986e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.2552255225522552, | |
| "grad_norm": 0.15845124423503876, | |
| "learning_rate": 8.506183921362443e-05, | |
| "loss": 0.0073, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.25962596259625964, | |
| "grad_norm": 0.02083076536655426, | |
| "learning_rate": 8.44676704559283e-05, | |
| "loss": 0.0047, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.264026402640264, | |
| "grad_norm": 0.005129943136125803, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 0.0001, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2684268426842684, | |
| "grad_norm": 0.0006734408671036363, | |
| "learning_rate": 8.32512286056924e-05, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.27282728272827284, | |
| "grad_norm": 0.0014560576528310776, | |
| "learning_rate": 8.262928807620843e-05, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.27722772277227725, | |
| "grad_norm": 0.04228012636303902, | |
| "learning_rate": 8.199842702516583e-05, | |
| "loss": 0.0001, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.2816281628162816, | |
| "grad_norm": 0.0012700504157692194, | |
| "learning_rate": 8.135881792367686e-05, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.28602860286028603, | |
| "grad_norm": 0.0008805114193819463, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.29042904290429045, | |
| "grad_norm": 0.0020040771923959255, | |
| "learning_rate": 8.005405736415126e-05, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.2948294829482948, | |
| "grad_norm": 0.001436033402569592, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.2992299229922992, | |
| "grad_norm": 0.05818886682391167, | |
| "learning_rate": 7.871643313414718e-05, | |
| "loss": 0.0004, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.30363036303630364, | |
| "grad_norm": 0.00826526153832674, | |
| "learning_rate": 7.803575286758364e-05, | |
| "loss": 0.0001, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.30803080308030806, | |
| "grad_norm": 0.004249353427439928, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 0.0001, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.3124312431243124, | |
| "grad_norm": 0.0024739697109907866, | |
| "learning_rate": 7.66515864363997e-05, | |
| "loss": 0.0001, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.31683168316831684, | |
| "grad_norm": 0.014817255549132824, | |
| "learning_rate": 7.594847868906076e-05, | |
| "loss": 0.0002, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.32123212321232125, | |
| "grad_norm": 0.04050708934664726, | |
| "learning_rate": 7.52382768867422e-05, | |
| "loss": 0.0002, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.3256325632563256, | |
| "grad_norm": 0.14514382183551788, | |
| "learning_rate": 7.452117519152542e-05, | |
| "loss": 0.0013, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.33003300330033003, | |
| "grad_norm": 0.006615113001316786, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 0.0001, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.33443344334433445, | |
| "grad_norm": 0.0007390982354991138, | |
| "learning_rate": 7.30670581489344e-05, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.3388338833883388, | |
| "grad_norm": 0.002446439117193222, | |
| "learning_rate": 7.233044034264034e-05, | |
| "loss": 0.0001, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.3432343234323432, | |
| "grad_norm": 0.002361354883760214, | |
| "learning_rate": 7.158771761692464e-05, | |
| "loss": 0.0001, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.34763476347634764, | |
| "grad_norm": 0.002348387148231268, | |
| "learning_rate": 7.083909302476453e-05, | |
| "loss": 0.0001, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.35203520352035206, | |
| "grad_norm": 0.0021446961909532547, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 0.0001, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.3564356435643564, | |
| "grad_norm": 0.002954555442556739, | |
| "learning_rate": 6.932495846462261e-05, | |
| "loss": 0.0001, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.36083608360836084, | |
| "grad_norm": 0.0016349947545677423, | |
| "learning_rate": 6.855986244591104e-05, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.36523652365236525, | |
| "grad_norm": 0.0034120974596589804, | |
| "learning_rate": 6.778969234612584e-05, | |
| "loss": 0.0001, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.3696369636963696, | |
| "grad_norm": 0.002268855692818761, | |
| "learning_rate": 6.701465872208216e-05, | |
| "loss": 0.0001, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.37403740374037403, | |
| "grad_norm": 0.00328146037645638, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 0.0001, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.37843784378437845, | |
| "grad_norm": 0.0033682214561849833, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.38283828382838286, | |
| "grad_norm": 0.001991323195397854, | |
| "learning_rate": 6.466250186922325e-05, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.3872387238723872, | |
| "grad_norm": 0.0033785931300371885, | |
| "learning_rate": 6.387014543809223e-05, | |
| "loss": 0.0001, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.39163916391639164, | |
| "grad_norm": 0.002204329939559102, | |
| "learning_rate": 6.307399704769099e-05, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.39603960396039606, | |
| "grad_norm": 0.03163732588291168, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 0.0004, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.4004400440044004, | |
| "grad_norm": 0.0045194183476269245, | |
| "learning_rate": 6.147119600233758e-05, | |
| "loss": 0.0001, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.40484048404840484, | |
| "grad_norm": 0.02233019843697548, | |
| "learning_rate": 6.066498153718735e-05, | |
| "loss": 0.0003, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.40924092409240925, | |
| "grad_norm": 0.0032185649033635855, | |
| "learning_rate": 5.985585137257401e-05, | |
| "loss": 0.0001, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.4136413641364136, | |
| "grad_norm": 0.010241584852337837, | |
| "learning_rate": 5.90440267166055e-05, | |
| "loss": 0.0001, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.41804180418041803, | |
| "grad_norm": 0.056131426244974136, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 0.0005, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.42244224422442245, | |
| "grad_norm": 0.2798404395580292, | |
| "learning_rate": 5.74131823855921e-05, | |
| "loss": 0.0014, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.42684268426842686, | |
| "grad_norm": 0.05619452893733978, | |
| "learning_rate": 5.6594608567103456e-05, | |
| "loss": 0.0006, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.4312431243124312, | |
| "grad_norm": 0.01462170947343111, | |
| "learning_rate": 5.577423184847932e-05, | |
| "loss": 0.0002, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.43564356435643564, | |
| "grad_norm": 0.19371579587459564, | |
| "learning_rate": 5.495227651252315e-05, | |
| "loss": 0.0016, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.44004400440044006, | |
| "grad_norm": 0.007606116123497486, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 0.0001, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.44004400440044006, | |
| "eval_loss": 0.0002134703245246783, | |
| "eval_runtime": 27.0459, | |
| "eval_samples_per_second": 14.161, | |
| "eval_steps_per_second": 3.55, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 0.028686359524726868, | |
| "learning_rate": 5.330452921628497e-05, | |
| "loss": 0.0002, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.44884488448844884, | |
| "grad_norm": 0.00039603031473234296, | |
| "learning_rate": 5.247918773366112e-05, | |
| "loss": 0.0, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.45324532453245325, | |
| "grad_norm": 0.0035085747949779034, | |
| "learning_rate": 5.165316846586541e-05, | |
| "loss": 0.0, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.45764576457645767, | |
| "grad_norm": 0.06442967802286148, | |
| "learning_rate": 5.0826697238317935e-05, | |
| "loss": 0.0012, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.46204620462046203, | |
| "grad_norm": 0.014701965264976025, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0003, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.46644664466446645, | |
| "grad_norm": 0.0005143084563314915, | |
| "learning_rate": 4.917330276168208e-05, | |
| "loss": 0.0, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.47084708470847086, | |
| "grad_norm": 0.0055423094891011715, | |
| "learning_rate": 4.834683153413459e-05, | |
| "loss": 0.0001, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.4752475247524752, | |
| "grad_norm": 0.04162374883890152, | |
| "learning_rate": 4.7520812266338885e-05, | |
| "loss": 0.0001, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.47964796479647964, | |
| "grad_norm": 0.00013863068306818604, | |
| "learning_rate": 4.669547078371504e-05, | |
| "loss": 0.0, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.48404840484048406, | |
| "grad_norm": 0.0002098706318065524, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 0.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.4884488448844885, | |
| "grad_norm": 0.0002865023852791637, | |
| "learning_rate": 4.504772348747687e-05, | |
| "loss": 0.0, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.49284928492849284, | |
| "grad_norm": 0.00010739878052845597, | |
| "learning_rate": 4.4225768151520694e-05, | |
| "loss": 0.0, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.49724972497249725, | |
| "grad_norm": 0.0002565592003520578, | |
| "learning_rate": 4.3405391432896555e-05, | |
| "loss": 0.0, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.5016501650165016, | |
| "grad_norm": 0.000523771217558533, | |
| "learning_rate": 4.2586817614407895e-05, | |
| "loss": 0.0, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.506050605060506, | |
| "grad_norm": 0.00040572145371697843, | |
| "learning_rate": 4.17702704859633e-05, | |
| "loss": 0.0, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.5104510451045104, | |
| "grad_norm": 0.0008220706367865205, | |
| "learning_rate": 4.095597328339452e-05, | |
| "loss": 0.0, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.5148514851485149, | |
| "grad_norm": 0.00047265394823625684, | |
| "learning_rate": 4.0144148627425993e-05, | |
| "loss": 0.0, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.5192519251925193, | |
| "grad_norm": 0.008099446073174477, | |
| "learning_rate": 3.933501846281267e-05, | |
| "loss": 0.0, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.5236523652365237, | |
| "grad_norm": 0.00020315141591709107, | |
| "learning_rate": 3.852880399766243e-05, | |
| "loss": 0.0, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.528052805280528, | |
| "grad_norm": 0.11890555918216705, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 0.0018, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.5324532453245324, | |
| "grad_norm": 0.0033121719025075436, | |
| "learning_rate": 3.6926002952309016e-05, | |
| "loss": 0.0, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.5368536853685368, | |
| "grad_norm": 0.12536010146141052, | |
| "learning_rate": 3.612985456190778e-05, | |
| "loss": 0.0016, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.5412541254125413, | |
| "grad_norm": 0.004900174215435982, | |
| "learning_rate": 3.533749813077677e-05, | |
| "loss": 0.0, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.5456545654565457, | |
| "grad_norm": 0.0516606941819191, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.0008, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.5500550055005501, | |
| "grad_norm": 0.001469736802391708, | |
| "learning_rate": 3.3765026539765834e-05, | |
| "loss": 0.0, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.5544554455445545, | |
| "grad_norm": 0.0003152410499751568, | |
| "learning_rate": 3.298534127791785e-05, | |
| "loss": 0.0, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.5588558855885588, | |
| "grad_norm": 0.07094491273164749, | |
| "learning_rate": 3.221030765387417e-05, | |
| "loss": 0.0002, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.5632563256325632, | |
| "grad_norm": 0.0002319741470273584, | |
| "learning_rate": 3.144013755408895e-05, | |
| "loss": 0.0, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.5676567656765676, | |
| "grad_norm": 0.00016111215518321842, | |
| "learning_rate": 3.0675041535377405e-05, | |
| "loss": 0.0, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.5720572057205721, | |
| "grad_norm": 0.0022377546411007643, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5764576457645765, | |
| "grad_norm": 0.00019582318782340735, | |
| "learning_rate": 2.916090697523549e-05, | |
| "loss": 0.0, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.5808580858085809, | |
| "grad_norm": 0.00011543017899384722, | |
| "learning_rate": 2.8412282383075363e-05, | |
| "loss": 0.0, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.5852585258525853, | |
| "grad_norm": 0.0004567111609503627, | |
| "learning_rate": 2.766955965735968e-05, | |
| "loss": 0.0, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.5896589658965896, | |
| "grad_norm": 0.00046952450065873563, | |
| "learning_rate": 2.693294185106562e-05, | |
| "loss": 0.0, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.594059405940594, | |
| "grad_norm": 0.00011668720981106162, | |
| "learning_rate": 2.6202630348146324e-05, | |
| "loss": 0.0, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.5984598459845984, | |
| "grad_norm": 0.00031584527459926903, | |
| "learning_rate": 2.547882480847461e-05, | |
| "loss": 0.0, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.6028602860286029, | |
| "grad_norm": 0.00011703503696480766, | |
| "learning_rate": 2.476172311325783e-05, | |
| "loss": 0.0, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.6072607260726073, | |
| "grad_norm": 0.0003631680738180876, | |
| "learning_rate": 2.405152131093926e-05, | |
| "loss": 0.0, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.6116611661166117, | |
| "grad_norm": 0.00011544793233042583, | |
| "learning_rate": 2.3348413563600325e-05, | |
| "loss": 0.0, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.6160616061606161, | |
| "grad_norm": 0.00012302027607802302, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.6204620462046204, | |
| "grad_norm": 0.0001410643308190629, | |
| "learning_rate": 2.196424713241637e-05, | |
| "loss": 0.0, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.6248624862486248, | |
| "grad_norm": 0.00011864223779411986, | |
| "learning_rate": 2.128356686585282e-05, | |
| "loss": 0.0, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.6292629262926293, | |
| "grad_norm": 0.00015806937881279737, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.0, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.6336633663366337, | |
| "grad_norm": 0.00018578377785161138, | |
| "learning_rate": 1.9945942635848748e-05, | |
| "loss": 0.0, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.6380638063806381, | |
| "grad_norm": 0.05664031207561493, | |
| "learning_rate": 1.928936436551661e-05, | |
| "loss": 0.0004, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.6424642464246425, | |
| "grad_norm": 0.00017318692698609084, | |
| "learning_rate": 1.8641182076323148e-05, | |
| "loss": 0.0, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.6468646864686468, | |
| "grad_norm": 0.0009654519381001592, | |
| "learning_rate": 1.800157297483417e-05, | |
| "loss": 0.0, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.6512651265126512, | |
| "grad_norm": 0.0026648039929568768, | |
| "learning_rate": 1.7370711923791567e-05, | |
| "loss": 0.0, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.6556655665566556, | |
| "grad_norm": 0.000252189434831962, | |
| "learning_rate": 1.6748771394307585e-05, | |
| "loss": 0.0, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.6600660066006601, | |
| "grad_norm": 0.00020123129070270807, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6600660066006601, | |
| "eval_loss": 0.00010527808626648039, | |
| "eval_runtime": 27.0236, | |
| "eval_samples_per_second": 14.173, | |
| "eval_steps_per_second": 3.552, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6644664466446645, | |
| "grad_norm": 0.0077056908048689365, | |
| "learning_rate": 1.553232954407171e-05, | |
| "loss": 0.0016, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.6688668866886689, | |
| "grad_norm": 0.0005785844987258315, | |
| "learning_rate": 1.4938160786375572e-05, | |
| "loss": 0.0, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.6732673267326733, | |
| "grad_norm": 0.020315540954470634, | |
| "learning_rate": 1.435357758543015e-05, | |
| "loss": 0.0005, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.6776677667766776, | |
| "grad_norm": 0.0021794300992041826, | |
| "learning_rate": 1.3778739760445552e-05, | |
| "loss": 0.0, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.682068206820682, | |
| "grad_norm": 0.03600750118494034, | |
| "learning_rate": 1.3213804466343421e-05, | |
| "loss": 0.0004, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.6864686468646864, | |
| "grad_norm": 0.0006952560506761074, | |
| "learning_rate": 1.2658926150792322e-05, | |
| "loss": 0.0, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.6908690869086909, | |
| "grad_norm": 0.12142467498779297, | |
| "learning_rate": 1.2114256511983274e-05, | |
| "loss": 0.0022, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.6952695269526953, | |
| "grad_norm": 0.04297574982047081, | |
| "learning_rate": 1.157994445715706e-05, | |
| "loss": 0.0015, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.6996699669966997, | |
| "grad_norm": 0.00041042795055545866, | |
| "learning_rate": 1.1056136061894384e-05, | |
| "loss": 0.0, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.7040704070407041, | |
| "grad_norm": 0.000730111263692379, | |
| "learning_rate": 1.0542974530180327e-05, | |
| "loss": 0.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.7084708470847084, | |
| "grad_norm": 9.697436325950548e-05, | |
| "learning_rate": 1.0040600155253765e-05, | |
| "loss": 0.0, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.7128712871287128, | |
| "grad_norm": 0.00011400500807212666, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.7172717271727173, | |
| "grad_norm": 0.002222096547484398, | |
| "learning_rate": 9.068759265665384e-06, | |
| "loss": 0.0, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.7216721672167217, | |
| "grad_norm": 0.00013305660104379058, | |
| "learning_rate": 8.599558442598998e-06, | |
| "loss": 0.0, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.7260726072607261, | |
| "grad_norm": 0.0007609356543980539, | |
| "learning_rate": 8.141676086873572e-06, | |
| "loss": 0.0, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.7304730473047305, | |
| "grad_norm": 0.00014448395813815296, | |
| "learning_rate": 7.695237378953223e-06, | |
| "loss": 0.0, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.7348734873487349, | |
| "grad_norm": 9.054927795659751e-05, | |
| "learning_rate": 7.260364370723044e-06, | |
| "loss": 0.0, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.7392739273927392, | |
| "grad_norm": 0.15017244219779968, | |
| "learning_rate": 6.837175952121306e-06, | |
| "loss": 0.002, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.7436743674367436, | |
| "grad_norm": 0.002310999669134617, | |
| "learning_rate": 6.425787818636131e-06, | |
| "loss": 0.0, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.7480748074807481, | |
| "grad_norm": 0.0015457016415894032, | |
| "learning_rate": 6.026312439675552e-06, | |
| "loss": 0.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.7524752475247525, | |
| "grad_norm": 0.0009740770328789949, | |
| "learning_rate": 5.6388590278194096e-06, | |
| "loss": 0.0, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.7568756875687569, | |
| "grad_norm": 0.0009460056899115443, | |
| "learning_rate": 5.263533508961827e-06, | |
| "loss": 0.0, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.7612761276127613, | |
| "grad_norm": 0.0009794700890779495, | |
| "learning_rate": 4.900438493352055e-06, | |
| "loss": 0.0, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.7656765676567657, | |
| "grad_norm": 0.02345697022974491, | |
| "learning_rate": 4.549673247541875e-06, | |
| "loss": 0.0001, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.77007700770077, | |
| "grad_norm": 0.00010123919491888955, | |
| "learning_rate": 4.2113336672471245e-06, | |
| "loss": 0.0, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.7744774477447744, | |
| "grad_norm": 0.00011137992987642065, | |
| "learning_rate": 3.885512251130763e-06, | |
| "loss": 0.0, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.7788778877887789, | |
| "grad_norm": 0.00018668893608264625, | |
| "learning_rate": 3.5722980755146517e-06, | |
| "loss": 0.0, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.7832783278327833, | |
| "grad_norm": 0.0004606316506396979, | |
| "learning_rate": 3.271776770026963e-06, | |
| "loss": 0.0, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.7876787678767877, | |
| "grad_norm": 0.0003202547668479383, | |
| "learning_rate": 2.9840304941919415e-06, | |
| "loss": 0.0, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.7920792079207921, | |
| "grad_norm": 0.0002549044438637793, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.7964796479647965, | |
| "grad_norm": 9.19110607355833e-05, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 0.0, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.8008800880088008, | |
| "grad_norm": 0.00020243048493284732, | |
| "learning_rate": 2.1982109232821178e-06, | |
| "loss": 0.0, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.8052805280528053, | |
| "grad_norm": 0.00010552083404036239, | |
| "learning_rate": 1.962316193157593e-06, | |
| "loss": 0.0, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.8096809680968097, | |
| "grad_norm": 9.792312630452216e-05, | |
| "learning_rate": 1.7395544861325718e-06, | |
| "loss": 0.0, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.8140814081408141, | |
| "grad_norm": 0.0009077927097678185, | |
| "learning_rate": 1.5299867030334814e-06, | |
| "loss": 0.0, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.8184818481848185, | |
| "grad_norm": 0.0001045699609676376, | |
| "learning_rate": 1.333670137599713e-06, | |
| "loss": 0.0, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.8228822882288229, | |
| "grad_norm": 0.00011044172424590215, | |
| "learning_rate": 1.1506584608200367e-06, | |
| "loss": 0.0, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.8272827282728272, | |
| "grad_norm": 0.003251630812883377, | |
| "learning_rate": 9.810017062595322e-07, | |
| "loss": 0.0, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.8316831683168316, | |
| "grad_norm": 0.00011532031930983067, | |
| "learning_rate": 8.247462563808817e-07, | |
| "loss": 0.0, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.8360836083608361, | |
| "grad_norm": 0.00012750219320878386, | |
| "learning_rate": 6.819348298638839e-07, | |
| "loss": 0.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.8404840484048405, | |
| "grad_norm": 0.00011365237151039764, | |
| "learning_rate": 5.526064699265753e-07, | |
| "loss": 0.0, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.8448844884488449, | |
| "grad_norm": 0.000160412528202869, | |
| "learning_rate": 4.367965336512403e-07, | |
| "loss": 0.0, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.8492849284928493, | |
| "grad_norm": 0.00024638298782519996, | |
| "learning_rate": 3.3453668231809286e-07, | |
| "loss": 0.0, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.8536853685368537, | |
| "grad_norm": 0.00020602620497811586, | |
| "learning_rate": 2.458548727494292e-07, | |
| "loss": 0.0, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.858085808580858, | |
| "grad_norm": 0.00011342952348059043, | |
| "learning_rate": 1.7077534966650766e-07, | |
| "loss": 0.0, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.8624862486248625, | |
| "grad_norm": 0.0010079805506393313, | |
| "learning_rate": 1.0931863906127327e-07, | |
| "loss": 0.0, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.8668866886688669, | |
| "grad_norm": 0.00019496685126796365, | |
| "learning_rate": 6.150154258476315e-08, | |
| "loss": 0.0, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.8712871287128713, | |
| "grad_norm": 0.00024074710381682962, | |
| "learning_rate": 2.7337132953697554e-08, | |
| "loss": 0.0, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.8756875687568757, | |
| "grad_norm": 0.0005757029284723103, | |
| "learning_rate": 6.834750376549792e-09, | |
| "loss": 0.0, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.8800880088008801, | |
| "grad_norm": 0.0019045682856813073, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.8800880088008801, | |
| "eval_loss": 0.00013592753384727985, | |
| "eval_runtime": 27.0476, | |
| "eval_samples_per_second": 14.16, | |
| "eval_steps_per_second": 3.549, | |
| "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": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.690927703443374e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |