| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 200, |
| "global_step": 1584, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 2.4575500309467317, |
| "epoch": 0.012630249447426587, |
| "grad_norm": 4.916348934173584, |
| "learning_rate": 1.8750000000000003e-06, |
| "loss": 3.6598, |
| "mean_token_accuracy": 0.4153611570596695, |
| "num_tokens": 59642.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 2.4072387635707857, |
| "epoch": 0.025260498894853173, |
| "grad_norm": 3.8026137351989746, |
| "learning_rate": 3.958333333333333e-06, |
| "loss": 3.3603, |
| "mean_token_accuracy": 0.4350100517272949, |
| "num_tokens": 119219.0, |
| "step": 20 |
| }, |
| { |
| "entropy": 2.3899864494800567, |
| "epoch": 0.03789074834227976, |
| "grad_norm": 3.7880399227142334, |
| "learning_rate": 6.041666666666667e-06, |
| "loss": 2.9434, |
| "mean_token_accuracy": 0.4788561977446079, |
| "num_tokens": 179590.0, |
| "step": 30 |
| }, |
| { |
| "entropy": 2.1122478008270265, |
| "epoch": 0.05052099778970635, |
| "grad_norm": 3.0592074394226074, |
| "learning_rate": 8.125000000000001e-06, |
| "loss": 2.3919, |
| "mean_token_accuracy": 0.574567300081253, |
| "num_tokens": 238845.0, |
| "step": 40 |
| }, |
| { |
| "entropy": 1.7037649989128112, |
| "epoch": 0.06315124723713293, |
| "grad_norm": 1.5836262702941895, |
| "learning_rate": 9.993489583333334e-06, |
| "loss": 1.912, |
| "mean_token_accuracy": 0.6467478528618813, |
| "num_tokens": 298317.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 1.5623225390911102, |
| "epoch": 0.07578149668455952, |
| "grad_norm": 1.217679738998413, |
| "learning_rate": 9.928385416666668e-06, |
| "loss": 1.6762, |
| "mean_token_accuracy": 0.679128734767437, |
| "num_tokens": 357858.0, |
| "step": 60 |
| }, |
| { |
| "entropy": 1.5071247130632401, |
| "epoch": 0.0884117461319861, |
| "grad_norm": 0.973615288734436, |
| "learning_rate": 9.863281250000001e-06, |
| "loss": 1.5372, |
| "mean_token_accuracy": 0.6943170607089997, |
| "num_tokens": 418834.0, |
| "step": 70 |
| }, |
| { |
| "entropy": 1.4568549275398255, |
| "epoch": 0.1010419955794127, |
| "grad_norm": 0.9853116869926453, |
| "learning_rate": 9.798177083333335e-06, |
| "loss": 1.4751, |
| "mean_token_accuracy": 0.7024633795022964, |
| "num_tokens": 478960.0, |
| "step": 80 |
| }, |
| { |
| "entropy": 1.4889154583215714, |
| "epoch": 0.11367224502683929, |
| "grad_norm": 0.9147132039070129, |
| "learning_rate": 9.733072916666667e-06, |
| "loss": 1.474, |
| "mean_token_accuracy": 0.6996816232800483, |
| "num_tokens": 541795.0, |
| "step": 90 |
| }, |
| { |
| "entropy": 1.4158774405717849, |
| "epoch": 0.12630249447426586, |
| "grad_norm": 0.9684887528419495, |
| "learning_rate": 9.66796875e-06, |
| "loss": 1.3805, |
| "mean_token_accuracy": 0.7165829420089722, |
| "num_tokens": 601174.0, |
| "step": 100 |
| }, |
| { |
| "entropy": 1.4276181221008302, |
| "epoch": 0.13893274392169244, |
| "grad_norm": 0.9440239667892456, |
| "learning_rate": 9.602864583333335e-06, |
| "loss": 1.3718, |
| "mean_token_accuracy": 0.7143253713846207, |
| "num_tokens": 661048.0, |
| "step": 110 |
| }, |
| { |
| "entropy": 1.4359370201826096, |
| "epoch": 0.15156299336911905, |
| "grad_norm": 0.8779081702232361, |
| "learning_rate": 9.537760416666667e-06, |
| "loss": 1.3661, |
| "mean_token_accuracy": 0.7162409156560898, |
| "num_tokens": 722298.0, |
| "step": 120 |
| }, |
| { |
| "entropy": 1.3943599790334702, |
| "epoch": 0.16419324281654563, |
| "grad_norm": 0.8999291062355042, |
| "learning_rate": 9.47265625e-06, |
| "loss": 1.3193, |
| "mean_token_accuracy": 0.7252198755741119, |
| "num_tokens": 782683.0, |
| "step": 130 |
| }, |
| { |
| "entropy": 1.3758090347051621, |
| "epoch": 0.1768234922639722, |
| "grad_norm": 0.8218080997467041, |
| "learning_rate": 9.407552083333334e-06, |
| "loss": 1.3054, |
| "mean_token_accuracy": 0.7277572214603424, |
| "num_tokens": 842988.0, |
| "step": 140 |
| }, |
| { |
| "entropy": 1.381770172715187, |
| "epoch": 0.1894537417113988, |
| "grad_norm": 0.8062577843666077, |
| "learning_rate": 9.342447916666668e-06, |
| "loss": 1.3291, |
| "mean_token_accuracy": 0.7222751513123512, |
| "num_tokens": 903912.0, |
| "step": 150 |
| }, |
| { |
| "entropy": 1.352141672372818, |
| "epoch": 0.2020839911588254, |
| "grad_norm": 0.8221862316131592, |
| "learning_rate": 9.277343750000001e-06, |
| "loss": 1.2974, |
| "mean_token_accuracy": 0.7260218441486359, |
| "num_tokens": 964887.0, |
| "step": 160 |
| }, |
| { |
| "entropy": 1.346352329850197, |
| "epoch": 0.21471424060625197, |
| "grad_norm": 0.7375346422195435, |
| "learning_rate": 9.212239583333335e-06, |
| "loss": 1.2969, |
| "mean_token_accuracy": 0.7252495244145394, |
| "num_tokens": 1026887.0, |
| "step": 170 |
| }, |
| { |
| "entropy": 1.3165962457656861, |
| "epoch": 0.22734449005367857, |
| "grad_norm": 0.7950690388679504, |
| "learning_rate": 9.147135416666667e-06, |
| "loss": 1.2824, |
| "mean_token_accuracy": 0.7250601649284363, |
| "num_tokens": 1086995.0, |
| "step": 180 |
| }, |
| { |
| "entropy": 1.3047442227602004, |
| "epoch": 0.23997473950110515, |
| "grad_norm": 0.7147737145423889, |
| "learning_rate": 9.082031250000001e-06, |
| "loss": 1.2628, |
| "mean_token_accuracy": 0.7318986386060715, |
| "num_tokens": 1147209.0, |
| "step": 190 |
| }, |
| { |
| "entropy": 1.2989415228366852, |
| "epoch": 0.25260498894853173, |
| "grad_norm": 0.756094753742218, |
| "learning_rate": 9.016927083333335e-06, |
| "loss": 1.2484, |
| "mean_token_accuracy": 0.7319697335362434, |
| "num_tokens": 1207602.0, |
| "step": 200 |
| }, |
| { |
| "entropy": 1.2904020875692368, |
| "epoch": 0.2652352383959583, |
| "grad_norm": 0.7715655565261841, |
| "learning_rate": 8.951822916666667e-06, |
| "loss": 1.2447, |
| "mean_token_accuracy": 0.7349080622196198, |
| "num_tokens": 1267500.0, |
| "step": 210 |
| }, |
| { |
| "entropy": 1.2543610483407974, |
| "epoch": 0.2778654878433849, |
| "grad_norm": 0.6824166774749756, |
| "learning_rate": 8.88671875e-06, |
| "loss": 1.2111, |
| "mean_token_accuracy": 0.7386362582445145, |
| "num_tokens": 1327666.0, |
| "step": 220 |
| }, |
| { |
| "entropy": 1.2946221768856048, |
| "epoch": 0.2904957372908115, |
| "grad_norm": 0.6559598445892334, |
| "learning_rate": 8.821614583333334e-06, |
| "loss": 1.2574, |
| "mean_token_accuracy": 0.7287471711635589, |
| "num_tokens": 1389712.0, |
| "step": 230 |
| }, |
| { |
| "entropy": 1.2489944666624069, |
| "epoch": 0.3031259867382381, |
| "grad_norm": 0.7000382542610168, |
| "learning_rate": 8.756510416666666e-06, |
| "loss": 1.2092, |
| "mean_token_accuracy": 0.7372458636760711, |
| "num_tokens": 1448670.0, |
| "step": 240 |
| }, |
| { |
| "entropy": 1.2534994542598725, |
| "epoch": 0.3157562361856647, |
| "grad_norm": 0.6579836010932922, |
| "learning_rate": 8.69140625e-06, |
| "loss": 1.2132, |
| "mean_token_accuracy": 0.7380462676286698, |
| "num_tokens": 1508428.0, |
| "step": 250 |
| }, |
| { |
| "entropy": 1.2474523901939392, |
| "epoch": 0.32838648563309125, |
| "grad_norm": 0.6546089053153992, |
| "learning_rate": 8.626302083333334e-06, |
| "loss": 1.2103, |
| "mean_token_accuracy": 0.7395781621336937, |
| "num_tokens": 1568018.0, |
| "step": 260 |
| }, |
| { |
| "entropy": 1.2445458561182021, |
| "epoch": 0.34101673508051783, |
| "grad_norm": 0.6377413868904114, |
| "learning_rate": 8.561197916666667e-06, |
| "loss": 1.2007, |
| "mean_token_accuracy": 0.7419240340590477, |
| "num_tokens": 1627904.0, |
| "step": 270 |
| }, |
| { |
| "entropy": 1.279063493013382, |
| "epoch": 0.3536469845279444, |
| "grad_norm": 0.6460844278335571, |
| "learning_rate": 8.496093750000001e-06, |
| "loss": 1.2497, |
| "mean_token_accuracy": 0.729638360440731, |
| "num_tokens": 1689637.0, |
| "step": 280 |
| }, |
| { |
| "entropy": 1.2362476408481597, |
| "epoch": 0.366277233975371, |
| "grad_norm": 0.6648440361022949, |
| "learning_rate": 8.430989583333335e-06, |
| "loss": 1.2091, |
| "mean_token_accuracy": 0.7385585099458695, |
| "num_tokens": 1749861.0, |
| "step": 290 |
| }, |
| { |
| "entropy": 1.2533661901950837, |
| "epoch": 0.3789074834227976, |
| "grad_norm": 0.6637682318687439, |
| "learning_rate": 8.365885416666667e-06, |
| "loss": 1.2163, |
| "mean_token_accuracy": 0.7371826618909836, |
| "num_tokens": 1810407.0, |
| "step": 300 |
| }, |
| { |
| "entropy": 1.2383619010448457, |
| "epoch": 0.3915377328702242, |
| "grad_norm": 0.660043478012085, |
| "learning_rate": 8.30078125e-06, |
| "loss": 1.2026, |
| "mean_token_accuracy": 0.7364327058196067, |
| "num_tokens": 1871544.0, |
| "step": 310 |
| }, |
| { |
| "entropy": 1.2316229462623596, |
| "epoch": 0.4041679823176508, |
| "grad_norm": 0.6285788416862488, |
| "learning_rate": 8.235677083333334e-06, |
| "loss": 1.2064, |
| "mean_token_accuracy": 0.7371214032173157, |
| "num_tokens": 1932125.0, |
| "step": 320 |
| }, |
| { |
| "entropy": 1.2459111303091048, |
| "epoch": 0.41679823176507735, |
| "grad_norm": 0.6204569339752197, |
| "learning_rate": 8.170572916666666e-06, |
| "loss": 1.1997, |
| "mean_token_accuracy": 0.7365512102842331, |
| "num_tokens": 1993924.0, |
| "step": 330 |
| }, |
| { |
| "entropy": 1.2156363114714623, |
| "epoch": 0.42942848121250393, |
| "grad_norm": 0.6501284241676331, |
| "learning_rate": 8.10546875e-06, |
| "loss": 1.1863, |
| "mean_token_accuracy": 0.741255110502243, |
| "num_tokens": 2054496.0, |
| "step": 340 |
| }, |
| { |
| "entropy": 1.2222040683031081, |
| "epoch": 0.4420587306599305, |
| "grad_norm": 0.602418065071106, |
| "learning_rate": 8.040364583333334e-06, |
| "loss": 1.1913, |
| "mean_token_accuracy": 0.739654652774334, |
| "num_tokens": 2114825.0, |
| "step": 350 |
| }, |
| { |
| "entropy": 1.2437947690486908, |
| "epoch": 0.45468898010735714, |
| "grad_norm": 0.6289706230163574, |
| "learning_rate": 7.975260416666668e-06, |
| "loss": 1.2142, |
| "mean_token_accuracy": 0.7374308854341507, |
| "num_tokens": 2176058.0, |
| "step": 360 |
| }, |
| { |
| "entropy": 1.2139764934778214, |
| "epoch": 0.4673192295547837, |
| "grad_norm": 0.6439516544342041, |
| "learning_rate": 7.910156250000001e-06, |
| "loss": 1.1769, |
| "mean_token_accuracy": 0.7426491379737854, |
| "num_tokens": 2236783.0, |
| "step": 370 |
| }, |
| { |
| "entropy": 1.19720456302166, |
| "epoch": 0.4799494790022103, |
| "grad_norm": 0.6499606966972351, |
| "learning_rate": 7.845052083333335e-06, |
| "loss": 1.1829, |
| "mean_token_accuracy": 0.7399616882205009, |
| "num_tokens": 2298432.0, |
| "step": 380 |
| }, |
| { |
| "entropy": 1.205560651421547, |
| "epoch": 0.4925797284496369, |
| "grad_norm": 0.6545577645301819, |
| "learning_rate": 7.779947916666667e-06, |
| "loss": 1.1577, |
| "mean_token_accuracy": 0.7463845536112785, |
| "num_tokens": 2357808.0, |
| "step": 390 |
| }, |
| { |
| "entropy": 1.19621299803257, |
| "epoch": 0.5052099778970635, |
| "grad_norm": 0.6930111050605774, |
| "learning_rate": 7.71484375e-06, |
| "loss": 1.1583, |
| "mean_token_accuracy": 0.7453805327415466, |
| "num_tokens": 2417574.0, |
| "step": 400 |
| }, |
| { |
| "entropy": 1.1963690370321274, |
| "epoch": 0.5178402273444901, |
| "grad_norm": 0.648593544960022, |
| "learning_rate": 7.649739583333334e-06, |
| "loss": 1.1723, |
| "mean_token_accuracy": 0.7415376961231231, |
| "num_tokens": 2478088.0, |
| "step": 410 |
| }, |
| { |
| "entropy": 1.216522666811943, |
| "epoch": 0.5304704767919166, |
| "grad_norm": 0.6348926424980164, |
| "learning_rate": 7.5846354166666665e-06, |
| "loss": 1.1701, |
| "mean_token_accuracy": 0.7432737082242966, |
| "num_tokens": 2538612.0, |
| "step": 420 |
| }, |
| { |
| "entropy": 1.1990931153297424, |
| "epoch": 0.5431007262393432, |
| "grad_norm": 0.627249002456665, |
| "learning_rate": 7.51953125e-06, |
| "loss": 1.1688, |
| "mean_token_accuracy": 0.7435364574193954, |
| "num_tokens": 2599023.0, |
| "step": 430 |
| }, |
| { |
| "entropy": 1.1872963696718215, |
| "epoch": 0.5557309756867698, |
| "grad_norm": 0.6614134311676025, |
| "learning_rate": 7.454427083333334e-06, |
| "loss": 1.1622, |
| "mean_token_accuracy": 0.7470521196722985, |
| "num_tokens": 2658338.0, |
| "step": 440 |
| }, |
| { |
| "entropy": 1.215770760178566, |
| "epoch": 0.5683612251341964, |
| "grad_norm": 0.6228342652320862, |
| "learning_rate": 7.389322916666667e-06, |
| "loss": 1.1898, |
| "mean_token_accuracy": 0.7409805700182914, |
| "num_tokens": 2719316.0, |
| "step": 450 |
| }, |
| { |
| "entropy": 1.1998004853725432, |
| "epoch": 0.580991474581623, |
| "grad_norm": 0.6525698304176331, |
| "learning_rate": 7.3242187500000006e-06, |
| "loss": 1.167, |
| "mean_token_accuracy": 0.7438512742519379, |
| "num_tokens": 2780272.0, |
| "step": 460 |
| }, |
| { |
| "entropy": 1.1898580551147462, |
| "epoch": 0.5936217240290496, |
| "grad_norm": 0.6669884324073792, |
| "learning_rate": 7.259114583333334e-06, |
| "loss": 1.1669, |
| "mean_token_accuracy": 0.7437147945165634, |
| "num_tokens": 2840261.0, |
| "step": 470 |
| }, |
| { |
| "entropy": 1.21882204413414, |
| "epoch": 0.6062519734764762, |
| "grad_norm": 0.6129422783851624, |
| "learning_rate": 7.194010416666667e-06, |
| "loss": 1.177, |
| "mean_token_accuracy": 0.7423913896083831, |
| "num_tokens": 2901347.0, |
| "step": 480 |
| }, |
| { |
| "entropy": 1.163309469819069, |
| "epoch": 0.6188822229239027, |
| "grad_norm": 0.6334741115570068, |
| "learning_rate": 7.128906250000001e-06, |
| "loss": 1.1393, |
| "mean_token_accuracy": 0.7511255607008934, |
| "num_tokens": 2960518.0, |
| "step": 490 |
| }, |
| { |
| "entropy": 1.1994746267795562, |
| "epoch": 0.6315124723713293, |
| "grad_norm": 0.6261829733848572, |
| "learning_rate": 7.063802083333335e-06, |
| "loss": 1.1605, |
| "mean_token_accuracy": 0.7433080047369003, |
| "num_tokens": 3021957.0, |
| "step": 500 |
| }, |
| { |
| "entropy": 1.167793545126915, |
| "epoch": 0.6441427218187559, |
| "grad_norm": 0.5909908413887024, |
| "learning_rate": 6.998697916666667e-06, |
| "loss": 1.1468, |
| "mean_token_accuracy": 0.7475745663046837, |
| "num_tokens": 3083301.0, |
| "step": 510 |
| }, |
| { |
| "entropy": 1.1670663714408875, |
| "epoch": 0.6567729712661825, |
| "grad_norm": 0.6018249988555908, |
| "learning_rate": 6.93359375e-06, |
| "loss": 1.1425, |
| "mean_token_accuracy": 0.7485125616192818, |
| "num_tokens": 3143187.0, |
| "step": 520 |
| }, |
| { |
| "entropy": 1.1626142784953117, |
| "epoch": 0.6694032207136091, |
| "grad_norm": 0.6088816523551941, |
| "learning_rate": 6.868489583333334e-06, |
| "loss": 1.1297, |
| "mean_token_accuracy": 0.7490727782249451, |
| "num_tokens": 3202489.0, |
| "step": 530 |
| }, |
| { |
| "entropy": 1.1758243769407273, |
| "epoch": 0.6820334701610357, |
| "grad_norm": 0.6021592020988464, |
| "learning_rate": 6.803385416666667e-06, |
| "loss": 1.1656, |
| "mean_token_accuracy": 0.7443674057722092, |
| "num_tokens": 3263476.0, |
| "step": 540 |
| }, |
| { |
| "entropy": 1.179671287536621, |
| "epoch": 0.6946637196084623, |
| "grad_norm": 0.5955655574798584, |
| "learning_rate": 6.738281250000001e-06, |
| "loss": 1.1385, |
| "mean_token_accuracy": 0.7481714516878128, |
| "num_tokens": 3324008.0, |
| "step": 550 |
| }, |
| { |
| "entropy": 1.1886188358068466, |
| "epoch": 0.7072939690558888, |
| "grad_norm": 0.6246835589408875, |
| "learning_rate": 6.6731770833333345e-06, |
| "loss": 1.1607, |
| "mean_token_accuracy": 0.7447509884834289, |
| "num_tokens": 3383861.0, |
| "step": 560 |
| }, |
| { |
| "entropy": 1.1690475821495057, |
| "epoch": 0.7199242185033154, |
| "grad_norm": 0.606743335723877, |
| "learning_rate": 6.6080729166666665e-06, |
| "loss": 1.1298, |
| "mean_token_accuracy": 0.7493681326508522, |
| "num_tokens": 3443946.0, |
| "step": 570 |
| }, |
| { |
| "entropy": 1.1725697651505471, |
| "epoch": 0.732554467950742, |
| "grad_norm": 0.6846170425415039, |
| "learning_rate": 6.54296875e-06, |
| "loss": 1.1452, |
| "mean_token_accuracy": 0.7482522815465927, |
| "num_tokens": 3503787.0, |
| "step": 580 |
| }, |
| { |
| "entropy": 1.1713406786322593, |
| "epoch": 0.7451847173981686, |
| "grad_norm": 0.6522074341773987, |
| "learning_rate": 6.477864583333334e-06, |
| "loss": 1.1338, |
| "mean_token_accuracy": 0.7498400524258614, |
| "num_tokens": 3563403.0, |
| "step": 590 |
| }, |
| { |
| "entropy": 1.1848436295986176, |
| "epoch": 0.7578149668455952, |
| "grad_norm": 0.6417824625968933, |
| "learning_rate": 6.412760416666667e-06, |
| "loss": 1.1499, |
| "mean_token_accuracy": 0.7452719643712044, |
| "num_tokens": 3625007.0, |
| "step": 600 |
| }, |
| { |
| "entropy": 1.1822121858596801, |
| "epoch": 0.7704452162930218, |
| "grad_norm": 0.6329619884490967, |
| "learning_rate": 6.3476562500000006e-06, |
| "loss": 1.159, |
| "mean_token_accuracy": 0.7452733591198921, |
| "num_tokens": 3686099.0, |
| "step": 610 |
| }, |
| { |
| "entropy": 1.190292978286743, |
| "epoch": 0.7830754657404484, |
| "grad_norm": 0.6627410054206848, |
| "learning_rate": 6.282552083333334e-06, |
| "loss": 1.1558, |
| "mean_token_accuracy": 0.7438480347394943, |
| "num_tokens": 3747233.0, |
| "step": 620 |
| }, |
| { |
| "entropy": 1.1619529083371163, |
| "epoch": 0.7957057151878749, |
| "grad_norm": 0.5941329002380371, |
| "learning_rate": 6.217447916666667e-06, |
| "loss": 1.1377, |
| "mean_token_accuracy": 0.7503219902515411, |
| "num_tokens": 3807833.0, |
| "step": 630 |
| }, |
| { |
| "entropy": 1.1658748656511306, |
| "epoch": 0.8083359646353016, |
| "grad_norm": 0.6438832879066467, |
| "learning_rate": 6.152343750000001e-06, |
| "loss": 1.1397, |
| "mean_token_accuracy": 0.7471553102135658, |
| "num_tokens": 3868549.0, |
| "step": 640 |
| }, |
| { |
| "entropy": 1.1782082825899125, |
| "epoch": 0.8209662140827282, |
| "grad_norm": 0.6389635801315308, |
| "learning_rate": 6.087239583333335e-06, |
| "loss": 1.1434, |
| "mean_token_accuracy": 0.7477709770202636, |
| "num_tokens": 3929057.0, |
| "step": 650 |
| }, |
| { |
| "entropy": 1.1625961899757384, |
| "epoch": 0.8335964635301547, |
| "grad_norm": 0.6134201288223267, |
| "learning_rate": 6.022135416666667e-06, |
| "loss": 1.1352, |
| "mean_token_accuracy": 0.748055274784565, |
| "num_tokens": 3990676.0, |
| "step": 660 |
| }, |
| { |
| "entropy": 1.1510928481817246, |
| "epoch": 0.8462267129775813, |
| "grad_norm": 0.6336613893508911, |
| "learning_rate": 5.95703125e-06, |
| "loss": 1.1182, |
| "mean_token_accuracy": 0.7524245917797089, |
| "num_tokens": 4051046.0, |
| "step": 670 |
| }, |
| { |
| "entropy": 1.1498646020889283, |
| "epoch": 0.8588569624250079, |
| "grad_norm": 0.6758144497871399, |
| "learning_rate": 5.891927083333334e-06, |
| "loss": 1.1186, |
| "mean_token_accuracy": 0.7507978692650795, |
| "num_tokens": 4111084.0, |
| "step": 680 |
| }, |
| { |
| "entropy": 1.167962297797203, |
| "epoch": 0.8714872118724345, |
| "grad_norm": 0.6285990476608276, |
| "learning_rate": 5.826822916666667e-06, |
| "loss": 1.1395, |
| "mean_token_accuracy": 0.7476246923208236, |
| "num_tokens": 4172628.0, |
| "step": 690 |
| }, |
| { |
| "entropy": 1.1178194358944893, |
| "epoch": 0.884117461319861, |
| "grad_norm": 0.64762282371521, |
| "learning_rate": 5.761718750000001e-06, |
| "loss": 1.0919, |
| "mean_token_accuracy": 0.7569874793291091, |
| "num_tokens": 4231821.0, |
| "step": 700 |
| }, |
| { |
| "entropy": 1.1606462925672532, |
| "epoch": 0.8967477107672877, |
| "grad_norm": 0.6292758584022522, |
| "learning_rate": 5.6966145833333344e-06, |
| "loss": 1.1354, |
| "mean_token_accuracy": 0.750880953669548, |
| "num_tokens": 4292646.0, |
| "step": 710 |
| }, |
| { |
| "entropy": 1.1580617666244506, |
| "epoch": 0.9093779602147143, |
| "grad_norm": 0.6393706798553467, |
| "learning_rate": 5.6315104166666665e-06, |
| "loss": 1.1205, |
| "mean_token_accuracy": 0.7499566927552224, |
| "num_tokens": 4353199.0, |
| "step": 720 |
| }, |
| { |
| "entropy": 1.1515695974230766, |
| "epoch": 0.9220082096621408, |
| "grad_norm": 0.687380313873291, |
| "learning_rate": 5.56640625e-06, |
| "loss": 1.1138, |
| "mean_token_accuracy": 0.7514134287834168, |
| "num_tokens": 4414122.0, |
| "step": 730 |
| }, |
| { |
| "entropy": 1.1574165880680085, |
| "epoch": 0.9346384591095674, |
| "grad_norm": 0.6102684736251831, |
| "learning_rate": 5.501302083333334e-06, |
| "loss": 1.1302, |
| "mean_token_accuracy": 0.7507740229368209, |
| "num_tokens": 4474548.0, |
| "step": 740 |
| }, |
| { |
| "entropy": 1.1491190433502196, |
| "epoch": 0.947268708556994, |
| "grad_norm": 0.623504638671875, |
| "learning_rate": 5.436197916666667e-06, |
| "loss": 1.129, |
| "mean_token_accuracy": 0.7512574091553688, |
| "num_tokens": 4534678.0, |
| "step": 750 |
| }, |
| { |
| "entropy": 1.1538215219974517, |
| "epoch": 0.9598989580044206, |
| "grad_norm": 0.6368807554244995, |
| "learning_rate": 5.3710937500000005e-06, |
| "loss": 1.1181, |
| "mean_token_accuracy": 0.7520082175731659, |
| "num_tokens": 4594878.0, |
| "step": 760 |
| }, |
| { |
| "entropy": 1.1623035803437234, |
| "epoch": 0.9725292074518471, |
| "grad_norm": 0.6332852840423584, |
| "learning_rate": 5.305989583333334e-06, |
| "loss": 1.1308, |
| "mean_token_accuracy": 0.7497873172163964, |
| "num_tokens": 4656513.0, |
| "step": 770 |
| }, |
| { |
| "entropy": 1.1483627527952194, |
| "epoch": 0.9851594568992738, |
| "grad_norm": 0.6341389417648315, |
| "learning_rate": 5.240885416666667e-06, |
| "loss": 1.1142, |
| "mean_token_accuracy": 0.7533516198396683, |
| "num_tokens": 4717111.0, |
| "step": 780 |
| }, |
| { |
| "entropy": 1.1455359414219857, |
| "epoch": 0.9977897063467004, |
| "grad_norm": 0.6641396880149841, |
| "learning_rate": 5.17578125e-06, |
| "loss": 1.1117, |
| "mean_token_accuracy": 0.7530950620770455, |
| "num_tokens": 4777713.0, |
| "step": 790 |
| }, |
| { |
| "entropy": 1.148778918461922, |
| "epoch": 1.0101041995579412, |
| "grad_norm": 0.6454346776008606, |
| "learning_rate": 5.110677083333334e-06, |
| "loss": 1.1146, |
| "mean_token_accuracy": 0.7511914097345792, |
| "num_tokens": 4837103.0, |
| "step": 800 |
| }, |
| { |
| "entropy": 1.1441998034715652, |
| "epoch": 1.0227344490053678, |
| "grad_norm": 0.6368332505226135, |
| "learning_rate": 5.045572916666667e-06, |
| "loss": 1.1003, |
| "mean_token_accuracy": 0.7535203993320465, |
| "num_tokens": 4898715.0, |
| "step": 810 |
| }, |
| { |
| "entropy": 1.1195117503404617, |
| "epoch": 1.0353646984527944, |
| "grad_norm": 0.6546683311462402, |
| "learning_rate": 4.98046875e-06, |
| "loss": 1.0924, |
| "mean_token_accuracy": 0.7574156150221825, |
| "num_tokens": 4959681.0, |
| "step": 820 |
| }, |
| { |
| "entropy": 1.1403603315353394, |
| "epoch": 1.047994947900221, |
| "grad_norm": 0.6645976305007935, |
| "learning_rate": 4.915364583333333e-06, |
| "loss": 1.1031, |
| "mean_token_accuracy": 0.7548869714140892, |
| "num_tokens": 5020382.0, |
| "step": 830 |
| }, |
| { |
| "entropy": 1.1299657106399537, |
| "epoch": 1.0606251973476477, |
| "grad_norm": 0.6225126385688782, |
| "learning_rate": 4.850260416666667e-06, |
| "loss": 1.0915, |
| "mean_token_accuracy": 0.7562400087714195, |
| "num_tokens": 5080360.0, |
| "step": 840 |
| }, |
| { |
| "entropy": 1.12370226085186, |
| "epoch": 1.0732554467950741, |
| "grad_norm": 0.6478942036628723, |
| "learning_rate": 4.785156250000001e-06, |
| "loss": 1.1064, |
| "mean_token_accuracy": 0.7542634457349777, |
| "num_tokens": 5140349.0, |
| "step": 850 |
| }, |
| { |
| "entropy": 1.1469928681850434, |
| "epoch": 1.0858856962425008, |
| "grad_norm": 0.615678608417511, |
| "learning_rate": 4.7200520833333336e-06, |
| "loss": 1.1043, |
| "mean_token_accuracy": 0.7529336720705032, |
| "num_tokens": 5201690.0, |
| "step": 860 |
| }, |
| { |
| "entropy": 1.137891921401024, |
| "epoch": 1.0985159456899274, |
| "grad_norm": 0.6458525061607361, |
| "learning_rate": 4.654947916666667e-06, |
| "loss": 1.1081, |
| "mean_token_accuracy": 0.7543051362037658, |
| "num_tokens": 5261698.0, |
| "step": 870 |
| }, |
| { |
| "entropy": 1.1202880129218102, |
| "epoch": 1.111146195137354, |
| "grad_norm": 0.6362131237983704, |
| "learning_rate": 4.58984375e-06, |
| "loss": 1.0951, |
| "mean_token_accuracy": 0.7552427321672439, |
| "num_tokens": 5321775.0, |
| "step": 880 |
| }, |
| { |
| "entropy": 1.1365787714719773, |
| "epoch": 1.1237764445847804, |
| "grad_norm": 0.6511764526367188, |
| "learning_rate": 4.524739583333334e-06, |
| "loss": 1.0961, |
| "mean_token_accuracy": 0.7562274217605591, |
| "num_tokens": 5383140.0, |
| "step": 890 |
| }, |
| { |
| "entropy": 1.1074503496289254, |
| "epoch": 1.136406694032207, |
| "grad_norm": 0.6207822561264038, |
| "learning_rate": 4.459635416666668e-06, |
| "loss": 1.0848, |
| "mean_token_accuracy": 0.7591574639081955, |
| "num_tokens": 5443006.0, |
| "step": 900 |
| }, |
| { |
| "entropy": 1.1545074522495269, |
| "epoch": 1.1490369434796337, |
| "grad_norm": 0.6404831409454346, |
| "learning_rate": 4.3945312500000005e-06, |
| "loss": 1.1121, |
| "mean_token_accuracy": 0.7507721096277237, |
| "num_tokens": 5503942.0, |
| "step": 910 |
| }, |
| { |
| "entropy": 1.1401477769017219, |
| "epoch": 1.1616671929270603, |
| "grad_norm": 0.6468749046325684, |
| "learning_rate": 4.329427083333333e-06, |
| "loss": 1.1011, |
| "mean_token_accuracy": 0.753543746471405, |
| "num_tokens": 5564518.0, |
| "step": 920 |
| }, |
| { |
| "entropy": 1.0945423126220704, |
| "epoch": 1.174297442374487, |
| "grad_norm": 0.6418051719665527, |
| "learning_rate": 4.264322916666667e-06, |
| "loss": 1.0614, |
| "mean_token_accuracy": 0.7643799662590027, |
| "num_tokens": 5624109.0, |
| "step": 930 |
| }, |
| { |
| "entropy": 1.1136713281273842, |
| "epoch": 1.1869276918219134, |
| "grad_norm": 0.6422064304351807, |
| "learning_rate": 4.19921875e-06, |
| "loss": 1.0974, |
| "mean_token_accuracy": 0.7561314895749092, |
| "num_tokens": 5684801.0, |
| "step": 940 |
| }, |
| { |
| "entropy": 1.1215770334005355, |
| "epoch": 1.19955794126934, |
| "grad_norm": 0.6453995108604431, |
| "learning_rate": 4.134114583333334e-06, |
| "loss": 1.0801, |
| "mean_token_accuracy": 0.7590720430016518, |
| "num_tokens": 5745499.0, |
| "step": 950 |
| }, |
| { |
| "entropy": 1.1010483756661416, |
| "epoch": 1.2121881907167666, |
| "grad_norm": 0.61696857213974, |
| "learning_rate": 4.0690104166666675e-06, |
| "loss": 1.049, |
| "mean_token_accuracy": 0.7627070844173431, |
| "num_tokens": 5806117.0, |
| "step": 960 |
| }, |
| { |
| "entropy": 1.1082940384745599, |
| "epoch": 1.2248184401641933, |
| "grad_norm": 0.6523500680923462, |
| "learning_rate": 4.00390625e-06, |
| "loss": 1.0807, |
| "mean_token_accuracy": 0.7579552844166756, |
| "num_tokens": 5865537.0, |
| "step": 970 |
| }, |
| { |
| "entropy": 1.102595229446888, |
| "epoch": 1.23744868961162, |
| "grad_norm": 0.6376118063926697, |
| "learning_rate": 3.938802083333333e-06, |
| "loss": 1.0679, |
| "mean_token_accuracy": 0.7592279806733131, |
| "num_tokens": 5925254.0, |
| "step": 980 |
| }, |
| { |
| "entropy": 1.1277900233864784, |
| "epoch": 1.2500789390590463, |
| "grad_norm": 0.6571747660636902, |
| "learning_rate": 3.873697916666667e-06, |
| "loss": 1.0888, |
| "mean_token_accuracy": 0.7549166217446327, |
| "num_tokens": 5986084.0, |
| "step": 990 |
| }, |
| { |
| "entropy": 1.113915103673935, |
| "epoch": 1.262709188506473, |
| "grad_norm": 0.6531611084938049, |
| "learning_rate": 3.8085937500000002e-06, |
| "loss": 1.0718, |
| "mean_token_accuracy": 0.7577856734395028, |
| "num_tokens": 6046857.0, |
| "step": 1000 |
| }, |
| { |
| "entropy": 1.0966202467679977, |
| "epoch": 1.2753394379538996, |
| "grad_norm": 0.636698842048645, |
| "learning_rate": 3.7434895833333336e-06, |
| "loss": 1.0699, |
| "mean_token_accuracy": 0.7601938605308532, |
| "num_tokens": 6106886.0, |
| "step": 1010 |
| }, |
| { |
| "entropy": 1.1121985822916032, |
| "epoch": 1.2879696874013262, |
| "grad_norm": 0.6492161750793457, |
| "learning_rate": 3.6783854166666673e-06, |
| "loss": 1.0851, |
| "mean_token_accuracy": 0.7588792949914932, |
| "num_tokens": 6167935.0, |
| "step": 1020 |
| }, |
| { |
| "entropy": 1.1355163961648942, |
| "epoch": 1.3005999368487529, |
| "grad_norm": 0.6697131395339966, |
| "learning_rate": 3.61328125e-06, |
| "loss": 1.094, |
| "mean_token_accuracy": 0.754327917098999, |
| "num_tokens": 6228870.0, |
| "step": 1030 |
| }, |
| { |
| "entropy": 1.11816665828228, |
| "epoch": 1.3132301862961793, |
| "grad_norm": 0.6773020625114441, |
| "learning_rate": 3.5481770833333335e-06, |
| "loss": 1.0893, |
| "mean_token_accuracy": 0.7571294933557511, |
| "num_tokens": 6288847.0, |
| "step": 1040 |
| }, |
| { |
| "entropy": 1.1343947052955627, |
| "epoch": 1.325860435743606, |
| "grad_norm": 0.6566488146781921, |
| "learning_rate": 3.483072916666667e-06, |
| "loss": 1.0875, |
| "mean_token_accuracy": 0.755756102502346, |
| "num_tokens": 6350161.0, |
| "step": 1050 |
| }, |
| { |
| "entropy": 1.1109364911913873, |
| "epoch": 1.3384906851910325, |
| "grad_norm": 0.6575057506561279, |
| "learning_rate": 3.41796875e-06, |
| "loss": 1.0782, |
| "mean_token_accuracy": 0.7591001376509666, |
| "num_tokens": 6410972.0, |
| "step": 1060 |
| }, |
| { |
| "entropy": 1.1165167808532714, |
| "epoch": 1.3511209346384592, |
| "grad_norm": 0.6655089259147644, |
| "learning_rate": 3.3528645833333334e-06, |
| "loss": 1.0901, |
| "mean_token_accuracy": 0.7573199763894081, |
| "num_tokens": 6471984.0, |
| "step": 1070 |
| }, |
| { |
| "entropy": 1.1066906094551086, |
| "epoch": 1.3637511840858858, |
| "grad_norm": 0.6363748908042908, |
| "learning_rate": 3.287760416666667e-06, |
| "loss": 1.0716, |
| "mean_token_accuracy": 0.7598252177238465, |
| "num_tokens": 6532514.0, |
| "step": 1080 |
| }, |
| { |
| "entropy": 1.1047193810343743, |
| "epoch": 1.3763814335333122, |
| "grad_norm": 0.6684281826019287, |
| "learning_rate": 3.2226562500000004e-06, |
| "loss": 1.0823, |
| "mean_token_accuracy": 0.7593759268522262, |
| "num_tokens": 6592949.0, |
| "step": 1090 |
| }, |
| { |
| "entropy": 1.1348285049200058, |
| "epoch": 1.3890116829807388, |
| "grad_norm": 0.6439023017883301, |
| "learning_rate": 3.1575520833333333e-06, |
| "loss": 1.1031, |
| "mean_token_accuracy": 0.7526842474937439, |
| "num_tokens": 6654231.0, |
| "step": 1100 |
| }, |
| { |
| "entropy": 1.1191302105784415, |
| "epoch": 1.4016419324281655, |
| "grad_norm": 0.6556984186172485, |
| "learning_rate": 3.092447916666667e-06, |
| "loss": 1.0799, |
| "mean_token_accuracy": 0.7590983435511589, |
| "num_tokens": 6714430.0, |
| "step": 1110 |
| }, |
| { |
| "entropy": 1.093433029949665, |
| "epoch": 1.4142721818755921, |
| "grad_norm": 0.6618829965591431, |
| "learning_rate": 3.0273437500000003e-06, |
| "loss": 1.0614, |
| "mean_token_accuracy": 0.7611085593700408, |
| "num_tokens": 6774176.0, |
| "step": 1120 |
| }, |
| { |
| "entropy": 1.135184645652771, |
| "epoch": 1.4269024313230187, |
| "grad_norm": 0.6382298469543457, |
| "learning_rate": 2.962239583333333e-06, |
| "loss": 1.0939, |
| "mean_token_accuracy": 0.7532851651310921, |
| "num_tokens": 6836522.0, |
| "step": 1130 |
| }, |
| { |
| "entropy": 1.1093149304389953, |
| "epoch": 1.4395326807704452, |
| "grad_norm": 0.6382166147232056, |
| "learning_rate": 2.897135416666667e-06, |
| "loss": 1.0709, |
| "mean_token_accuracy": 0.7608326107263566, |
| "num_tokens": 6896353.0, |
| "step": 1140 |
| }, |
| { |
| "entropy": 1.1047044202685357, |
| "epoch": 1.4521629302178718, |
| "grad_norm": 0.6356373429298401, |
| "learning_rate": 2.8320312500000002e-06, |
| "loss": 1.0738, |
| "mean_token_accuracy": 0.7615469440817833, |
| "num_tokens": 6956828.0, |
| "step": 1150 |
| }, |
| { |
| "entropy": 1.1073317646980285, |
| "epoch": 1.4647931796652984, |
| "grad_norm": 0.6593008041381836, |
| "learning_rate": 2.7669270833333335e-06, |
| "loss": 1.0589, |
| "mean_token_accuracy": 0.7599197804927826, |
| "num_tokens": 7017026.0, |
| "step": 1160 |
| }, |
| { |
| "entropy": 1.0851576775312424, |
| "epoch": 1.4774234291127248, |
| "grad_norm": 0.6466282606124878, |
| "learning_rate": 2.7018229166666673e-06, |
| "loss": 1.0584, |
| "mean_token_accuracy": 0.7626572713255882, |
| "num_tokens": 7076806.0, |
| "step": 1170 |
| }, |
| { |
| "entropy": 1.1103300124406814, |
| "epoch": 1.4900536785601517, |
| "grad_norm": 0.6285493969917297, |
| "learning_rate": 2.63671875e-06, |
| "loss": 1.0753, |
| "mean_token_accuracy": 0.7593718692660332, |
| "num_tokens": 7137946.0, |
| "step": 1180 |
| }, |
| { |
| "entropy": 1.1066975593566895, |
| "epoch": 1.502683928007578, |
| "grad_norm": 0.6664257645606995, |
| "learning_rate": 2.5716145833333334e-06, |
| "loss": 1.0642, |
| "mean_token_accuracy": 0.7612839996814728, |
| "num_tokens": 7200103.0, |
| "step": 1190 |
| }, |
| { |
| "entropy": 1.0994308680295943, |
| "epoch": 1.5153141774550047, |
| "grad_norm": 0.683022141456604, |
| "learning_rate": 2.506510416666667e-06, |
| "loss": 1.0726, |
| "mean_token_accuracy": 0.7611020535230637, |
| "num_tokens": 7259051.0, |
| "step": 1200 |
| }, |
| { |
| "entropy": 1.1130555748939515, |
| "epoch": 1.5279444269024314, |
| "grad_norm": 0.6556797623634338, |
| "learning_rate": 2.44140625e-06, |
| "loss": 1.0758, |
| "mean_token_accuracy": 0.7601210430264473, |
| "num_tokens": 7318904.0, |
| "step": 1210 |
| }, |
| { |
| "entropy": 1.112100276350975, |
| "epoch": 1.5405746763498578, |
| "grad_norm": 0.6336252689361572, |
| "learning_rate": 2.3763020833333338e-06, |
| "loss": 1.0691, |
| "mean_token_accuracy": 0.7613141894340515, |
| "num_tokens": 7378611.0, |
| "step": 1220 |
| }, |
| { |
| "entropy": 1.1018309980630874, |
| "epoch": 1.5532049257972846, |
| "grad_norm": 0.6907696723937988, |
| "learning_rate": 2.3111979166666667e-06, |
| "loss": 1.074, |
| "mean_token_accuracy": 0.7605119064450264, |
| "num_tokens": 7438960.0, |
| "step": 1230 |
| }, |
| { |
| "entropy": 1.071268692612648, |
| "epoch": 1.565835175244711, |
| "grad_norm": 0.6463876962661743, |
| "learning_rate": 2.2460937500000004e-06, |
| "loss": 1.0413, |
| "mean_token_accuracy": 0.7670892596244812, |
| "num_tokens": 7497275.0, |
| "step": 1240 |
| }, |
| { |
| "entropy": 1.134592017531395, |
| "epoch": 1.5784654246921377, |
| "grad_norm": 0.6366226077079773, |
| "learning_rate": 2.1809895833333337e-06, |
| "loss": 1.092, |
| "mean_token_accuracy": 0.7548690542578698, |
| "num_tokens": 7558285.0, |
| "step": 1250 |
| }, |
| { |
| "entropy": 1.1141762882471085, |
| "epoch": 1.5910956741395643, |
| "grad_norm": 0.6590870022773743, |
| "learning_rate": 2.1158854166666666e-06, |
| "loss": 1.0752, |
| "mean_token_accuracy": 0.7603784337639808, |
| "num_tokens": 7620287.0, |
| "step": 1260 |
| }, |
| { |
| "entropy": 1.09154414832592, |
| "epoch": 1.6037259235869907, |
| "grad_norm": 0.656830370426178, |
| "learning_rate": 2.0507812500000003e-06, |
| "loss": 1.0593, |
| "mean_token_accuracy": 0.76341772377491, |
| "num_tokens": 7681170.0, |
| "step": 1270 |
| }, |
| { |
| "entropy": 1.10728869587183, |
| "epoch": 1.6163561730344176, |
| "grad_norm": 0.6511245965957642, |
| "learning_rate": 1.9856770833333336e-06, |
| "loss": 1.0724, |
| "mean_token_accuracy": 0.7592613711953163, |
| "num_tokens": 7741125.0, |
| "step": 1280 |
| }, |
| { |
| "entropy": 1.1026839420199395, |
| "epoch": 1.628986422481844, |
| "grad_norm": 0.648682713508606, |
| "learning_rate": 1.920572916666667e-06, |
| "loss": 1.0678, |
| "mean_token_accuracy": 0.7615165829658508, |
| "num_tokens": 7801002.0, |
| "step": 1290 |
| }, |
| { |
| "entropy": 1.113681361079216, |
| "epoch": 1.6416166719292706, |
| "grad_norm": 0.6691455245018005, |
| "learning_rate": 1.8554687500000002e-06, |
| "loss": 1.0662, |
| "mean_token_accuracy": 0.76031324416399, |
| "num_tokens": 7861077.0, |
| "step": 1300 |
| }, |
| { |
| "entropy": 1.0854344859719276, |
| "epoch": 1.6542469213766973, |
| "grad_norm": 0.6221432685852051, |
| "learning_rate": 1.7903645833333335e-06, |
| "loss": 1.0564, |
| "mean_token_accuracy": 0.7638715595006943, |
| "num_tokens": 7920955.0, |
| "step": 1310 |
| }, |
| { |
| "entropy": 1.1128123462200166, |
| "epoch": 1.6668771708241237, |
| "grad_norm": 0.6376025080680847, |
| "learning_rate": 1.7252604166666668e-06, |
| "loss": 1.0803, |
| "mean_token_accuracy": 0.7579856783151626, |
| "num_tokens": 7981933.0, |
| "step": 1320 |
| }, |
| { |
| "entropy": 1.105194841325283, |
| "epoch": 1.6795074202715503, |
| "grad_norm": 0.712565541267395, |
| "learning_rate": 1.6601562500000001e-06, |
| "loss": 1.0758, |
| "mean_token_accuracy": 0.7577270165085792, |
| "num_tokens": 8042084.0, |
| "step": 1330 |
| }, |
| { |
| "entropy": 1.1065697744488716, |
| "epoch": 1.692137669718977, |
| "grad_norm": 0.6228471994400024, |
| "learning_rate": 1.5950520833333336e-06, |
| "loss": 1.0731, |
| "mean_token_accuracy": 0.7590463057160377, |
| "num_tokens": 8102976.0, |
| "step": 1340 |
| }, |
| { |
| "entropy": 1.1064435616135597, |
| "epoch": 1.7047679191664036, |
| "grad_norm": 0.6447433829307556, |
| "learning_rate": 1.5299479166666667e-06, |
| "loss": 1.0708, |
| "mean_token_accuracy": 0.7608707517385482, |
| "num_tokens": 8163206.0, |
| "step": 1350 |
| }, |
| { |
| "entropy": 1.1046179130673408, |
| "epoch": 1.7173981686138302, |
| "grad_norm": 0.6594550609588623, |
| "learning_rate": 1.46484375e-06, |
| "loss": 1.0606, |
| "mean_token_accuracy": 0.7627649754285812, |
| "num_tokens": 8224905.0, |
| "step": 1360 |
| }, |
| { |
| "entropy": 1.1129515051841736, |
| "epoch": 1.7300284180612566, |
| "grad_norm": 0.6550594568252563, |
| "learning_rate": 1.3997395833333335e-06, |
| "loss": 1.0741, |
| "mean_token_accuracy": 0.7577028945088387, |
| "num_tokens": 8286587.0, |
| "step": 1370 |
| }, |
| { |
| "entropy": 1.094475807249546, |
| "epoch": 1.7426586675086833, |
| "grad_norm": 0.6420894265174866, |
| "learning_rate": 1.3346354166666666e-06, |
| "loss": 1.0597, |
| "mean_token_accuracy": 0.7612502560019493, |
| "num_tokens": 8346283.0, |
| "step": 1380 |
| }, |
| { |
| "entropy": 1.1026990562677383, |
| "epoch": 1.75528891695611, |
| "grad_norm": 0.6647622585296631, |
| "learning_rate": 1.2695312500000002e-06, |
| "loss": 1.0705, |
| "mean_token_accuracy": 0.7592111378908157, |
| "num_tokens": 8406590.0, |
| "step": 1390 |
| }, |
| { |
| "entropy": 1.1024970307946205, |
| "epoch": 1.7679191664035365, |
| "grad_norm": 0.6625591516494751, |
| "learning_rate": 1.2044270833333335e-06, |
| "loss": 1.0783, |
| "mean_token_accuracy": 0.756389918923378, |
| "num_tokens": 8467230.0, |
| "step": 1400 |
| }, |
| { |
| "entropy": 1.1201951175928115, |
| "epoch": 1.7805494158509632, |
| "grad_norm": 0.6827495098114014, |
| "learning_rate": 1.1393229166666668e-06, |
| "loss": 1.0869, |
| "mean_token_accuracy": 0.756199948489666, |
| "num_tokens": 8527820.0, |
| "step": 1410 |
| }, |
| { |
| "entropy": 1.1082668006420135, |
| "epoch": 1.7931796652983896, |
| "grad_norm": 0.6496292948722839, |
| "learning_rate": 1.07421875e-06, |
| "loss": 1.0638, |
| "mean_token_accuracy": 0.7621515318751335, |
| "num_tokens": 8587544.0, |
| "step": 1420 |
| }, |
| { |
| "entropy": 1.0907854005694388, |
| "epoch": 1.8058099147458162, |
| "grad_norm": 0.6577737927436829, |
| "learning_rate": 1.0091145833333334e-06, |
| "loss": 1.0587, |
| "mean_token_accuracy": 0.7625794589519501, |
| "num_tokens": 8647424.0, |
| "step": 1430 |
| }, |
| { |
| "entropy": 1.0947823762893676, |
| "epoch": 1.8184401641932428, |
| "grad_norm": 0.6546240448951721, |
| "learning_rate": 9.440104166666668e-07, |
| "loss": 1.0648, |
| "mean_token_accuracy": 0.7618604898452759, |
| "num_tokens": 8706635.0, |
| "step": 1440 |
| }, |
| { |
| "entropy": 1.1016521960496903, |
| "epoch": 1.8310704136406692, |
| "grad_norm": 0.6349791884422302, |
| "learning_rate": 8.789062500000001e-07, |
| "loss": 1.0615, |
| "mean_token_accuracy": 0.7619734451174736, |
| "num_tokens": 8766624.0, |
| "step": 1450 |
| }, |
| { |
| "entropy": 1.110970026254654, |
| "epoch": 1.843700663088096, |
| "grad_norm": 0.6273230314254761, |
| "learning_rate": 8.138020833333334e-07, |
| "loss": 1.079, |
| "mean_token_accuracy": 0.7600797146558762, |
| "num_tokens": 8826556.0, |
| "step": 1460 |
| }, |
| { |
| "entropy": 1.1075817868113518, |
| "epoch": 1.8563309125355225, |
| "grad_norm": 0.6720101833343506, |
| "learning_rate": 7.486979166666668e-07, |
| "loss": 1.0695, |
| "mean_token_accuracy": 0.759764339029789, |
| "num_tokens": 8887460.0, |
| "step": 1470 |
| }, |
| { |
| "entropy": 1.0957570180296898, |
| "epoch": 1.8689611619829491, |
| "grad_norm": 0.6578065752983093, |
| "learning_rate": 6.835937500000001e-07, |
| "loss": 1.0658, |
| "mean_token_accuracy": 0.7630386680364609, |
| "num_tokens": 8947077.0, |
| "step": 1480 |
| }, |
| { |
| "entropy": 1.1054737836122512, |
| "epoch": 1.8815914114303758, |
| "grad_norm": 0.6177386045455933, |
| "learning_rate": 6.184895833333334e-07, |
| "loss": 1.062, |
| "mean_token_accuracy": 0.7603132933378219, |
| "num_tokens": 9008717.0, |
| "step": 1490 |
| }, |
| { |
| "entropy": 1.1026621460914612, |
| "epoch": 1.8942216608778022, |
| "grad_norm": 0.6226282119750977, |
| "learning_rate": 5.533854166666667e-07, |
| "loss": 1.0706, |
| "mean_token_accuracy": 0.7603669881820678, |
| "num_tokens": 9068623.0, |
| "step": 1500 |
| }, |
| { |
| "entropy": 1.1010279595851897, |
| "epoch": 1.906851910325229, |
| "grad_norm": 0.6504780650138855, |
| "learning_rate": 4.8828125e-07, |
| "loss": 1.0583, |
| "mean_token_accuracy": 0.7632956698536872, |
| "num_tokens": 9129086.0, |
| "step": 1510 |
| }, |
| { |
| "entropy": 1.1021641314029693, |
| "epoch": 1.9194821597726555, |
| "grad_norm": 0.667875349521637, |
| "learning_rate": 4.2317708333333337e-07, |
| "loss": 1.0698, |
| "mean_token_accuracy": 0.7609776973724365, |
| "num_tokens": 9189845.0, |
| "step": 1520 |
| }, |
| { |
| "entropy": 1.0909265503287315, |
| "epoch": 1.932112409220082, |
| "grad_norm": 0.650221586227417, |
| "learning_rate": 3.5807291666666667e-07, |
| "loss": 1.0541, |
| "mean_token_accuracy": 0.7616324663162232, |
| "num_tokens": 9250808.0, |
| "step": 1530 |
| }, |
| { |
| "entropy": 1.1204875528812408, |
| "epoch": 1.9447426586675087, |
| "grad_norm": 0.6560048460960388, |
| "learning_rate": 2.9296875000000003e-07, |
| "loss": 1.0821, |
| "mean_token_accuracy": 0.7588548183441162, |
| "num_tokens": 9312275.0, |
| "step": 1540 |
| }, |
| { |
| "entropy": 1.0873224779963493, |
| "epoch": 1.9573729081149351, |
| "grad_norm": 0.6481816172599792, |
| "learning_rate": 2.2786458333333333e-07, |
| "loss": 1.058, |
| "mean_token_accuracy": 0.762654073536396, |
| "num_tokens": 9372216.0, |
| "step": 1550 |
| }, |
| { |
| "entropy": 1.1072645708918571, |
| "epoch": 1.970003157562362, |
| "grad_norm": 0.6645349264144897, |
| "learning_rate": 1.627604166666667e-07, |
| "loss": 1.07, |
| "mean_token_accuracy": 0.7614389002323151, |
| "num_tokens": 9431986.0, |
| "step": 1560 |
| }, |
| { |
| "entropy": 1.1167670994997025, |
| "epoch": 1.9826334070097884, |
| "grad_norm": 0.6455146670341492, |
| "learning_rate": 9.765625e-08, |
| "loss": 1.0754, |
| "mean_token_accuracy": 0.7594234853982925, |
| "num_tokens": 9492961.0, |
| "step": 1570 |
| }, |
| { |
| "entropy": 1.104009985923767, |
| "epoch": 1.995263656457215, |
| "grad_norm": 0.6205505132675171, |
| "learning_rate": 3.2552083333333335e-08, |
| "loss": 1.0718, |
| "mean_token_accuracy": 0.7597839057445526, |
| "num_tokens": 9553806.0, |
| "step": 1580 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 1584, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 5.4237850982977536e+17, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
