| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.8616937691959715, | |
| "eval_steps": 1005, | |
| "global_step": 9048, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0038094331087355064, | |
| "grad_norm": 1.1105036735534668, | |
| "learning_rate": 1.2714024683199598e-06, | |
| "loss": 1.9169, | |
| "mean_token_accuracy": 0.5754982324317097, | |
| "num_tokens": 213515.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007618866217471013, | |
| "grad_norm": 0.8602012991905212, | |
| "learning_rate": 2.575404999930175e-06, | |
| "loss": 1.7612, | |
| "mean_token_accuracy": 0.5973538164049387, | |
| "num_tokens": 428291.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.01142829932620652, | |
| "grad_norm": 0.7212763428688049, | |
| "learning_rate": 3.87940753154039e-06, | |
| "loss": 1.7641, | |
| "mean_token_accuracy": 0.6031968526542186, | |
| "num_tokens": 649316.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.015237732434942025, | |
| "grad_norm": 0.9749614000320435, | |
| "learning_rate": 5.183410063150605e-06, | |
| "loss": 1.5732, | |
| "mean_token_accuracy": 0.6395209338515997, | |
| "num_tokens": 867038.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.01904716554367753, | |
| "grad_norm": 0.8746033310890198, | |
| "learning_rate": 6.48741259476082e-06, | |
| "loss": 1.5567, | |
| "mean_token_accuracy": 0.6250597681850195, | |
| "num_tokens": 1084477.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.02285659865241304, | |
| "grad_norm": 0.6283444762229919, | |
| "learning_rate": 7.791415126371035e-06, | |
| "loss": 1.4563, | |
| "mean_token_accuracy": 0.6498559027910232, | |
| "num_tokens": 1304254.0, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.026666031761148543, | |
| "grad_norm": 0.8473705053329468, | |
| "learning_rate": 9.09541765798125e-06, | |
| "loss": 1.5125, | |
| "mean_token_accuracy": 0.640368782542646, | |
| "num_tokens": 1518177.0, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.03047546486988405, | |
| "grad_norm": 0.8421404361724854, | |
| "learning_rate": 1.0399420189591466e-05, | |
| "loss": 1.43, | |
| "mean_token_accuracy": 0.6589812656864524, | |
| "num_tokens": 1745573.0, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.034284897978619555, | |
| "grad_norm": 0.7308921813964844, | |
| "learning_rate": 1.1703422721201682e-05, | |
| "loss": 1.3957, | |
| "mean_token_accuracy": 0.6596783269196749, | |
| "num_tokens": 1970323.0, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.03809433108735506, | |
| "grad_norm": 1.024109125137329, | |
| "learning_rate": 1.3007425252811896e-05, | |
| "loss": 1.2906, | |
| "mean_token_accuracy": 0.6734623985365034, | |
| "num_tokens": 2209851.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.04190376419609057, | |
| "grad_norm": 0.8211472034454346, | |
| "learning_rate": 1.4311427784422112e-05, | |
| "loss": 1.4547, | |
| "mean_token_accuracy": 0.65384187027812, | |
| "num_tokens": 2419422.0, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.04571319730482608, | |
| "grad_norm": 0.9193497896194458, | |
| "learning_rate": 1.5615430316032328e-05, | |
| "loss": 1.3763, | |
| "mean_token_accuracy": 0.6668608419597148, | |
| "num_tokens": 2650647.0, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.04952263041356158, | |
| "grad_norm": 0.9686090350151062, | |
| "learning_rate": 1.6919432847642544e-05, | |
| "loss": 1.3092, | |
| "mean_token_accuracy": 0.6819563843309879, | |
| "num_tokens": 2895742.0, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.053332063522297087, | |
| "grad_norm": 0.6123139262199402, | |
| "learning_rate": 1.8223435379252756e-05, | |
| "loss": 1.3106, | |
| "mean_token_accuracy": 0.6761070437729358, | |
| "num_tokens": 3131131.0, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.057141496631032594, | |
| "grad_norm": 0.8315911293029785, | |
| "learning_rate": 1.952743791086297e-05, | |
| "loss": 1.295, | |
| "mean_token_accuracy": 0.6829990902915597, | |
| "num_tokens": 3358554.0, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.0609509297397681, | |
| "grad_norm": 0.6099031567573547, | |
| "learning_rate": 2.0831440442473187e-05, | |
| "loss": 1.315, | |
| "mean_token_accuracy": 0.6704990575090051, | |
| "num_tokens": 3584968.0, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.0647603628485036, | |
| "grad_norm": 0.8671184778213501, | |
| "learning_rate": 2.2135442974083403e-05, | |
| "loss": 1.4007, | |
| "mean_token_accuracy": 0.6610645942389966, | |
| "num_tokens": 3789884.0, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.06856979595723911, | |
| "grad_norm": 0.8112688064575195, | |
| "learning_rate": 2.3439445505693616e-05, | |
| "loss": 1.3192, | |
| "mean_token_accuracy": 0.6786379875615239, | |
| "num_tokens": 4010228.0, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.07237922906597462, | |
| "grad_norm": 0.7991048097610474, | |
| "learning_rate": 2.474344803730383e-05, | |
| "loss": 1.357, | |
| "mean_token_accuracy": 0.6695337913930416, | |
| "num_tokens": 4240601.0, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.07618866217471013, | |
| "grad_norm": 0.6952106356620789, | |
| "learning_rate": 2.6047450568914047e-05, | |
| "loss": 1.3805, | |
| "mean_token_accuracy": 0.666619416512549, | |
| "num_tokens": 4457613.0, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.07999809528344563, | |
| "grad_norm": 0.5898691415786743, | |
| "learning_rate": 2.7351453100524263e-05, | |
| "loss": 1.3645, | |
| "mean_token_accuracy": 0.6681723784655332, | |
| "num_tokens": 4675575.0, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.08380752839218114, | |
| "grad_norm": 0.8592577576637268, | |
| "learning_rate": 2.865545563213448e-05, | |
| "loss": 1.3007, | |
| "mean_token_accuracy": 0.6759131707251071, | |
| "num_tokens": 4914793.0, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.08761696150091665, | |
| "grad_norm": 0.47871366143226624, | |
| "learning_rate": 2.9959458163744694e-05, | |
| "loss": 1.3316, | |
| "mean_token_accuracy": 0.6775730215013027, | |
| "num_tokens": 5145053.0, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.09142639460965216, | |
| "grad_norm": 0.6131187081336975, | |
| "learning_rate": 3.126346069535491e-05, | |
| "loss": 1.3631, | |
| "mean_token_accuracy": 0.6744197152554989, | |
| "num_tokens": 5353224.0, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.09523582771838766, | |
| "grad_norm": 0.6329927444458008, | |
| "learning_rate": 3.256746322696512e-05, | |
| "loss": 1.3321, | |
| "mean_token_accuracy": 0.677939809858799, | |
| "num_tokens": 5574886.0, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.0957120068569796, | |
| "eval_mean_token_accuracy": 0.6180267786704393, | |
| "eval_num_tokens": 5598115.0, | |
| "eval_test_loss": 1.8654624223709106, | |
| "eval_test_runtime": 94.5921, | |
| "eval_test_samples_per_second": 21.048, | |
| "eval_test_steps_per_second": 10.529, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 0.09904526082712316, | |
| "grad_norm": 0.5825843214988708, | |
| "learning_rate": 3.387146575857534e-05, | |
| "loss": 1.3293, | |
| "mean_token_accuracy": 0.6768566837534309, | |
| "num_tokens": 5800189.0, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.10285469393585867, | |
| "grad_norm": 0.47114425897598267, | |
| "learning_rate": 3.5175468290185554e-05, | |
| "loss": 1.273, | |
| "mean_token_accuracy": 0.6856468811631202, | |
| "num_tokens": 6035590.0, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.10666412704459417, | |
| "grad_norm": 0.6536944508552551, | |
| "learning_rate": 3.647947082179577e-05, | |
| "loss": 1.2521, | |
| "mean_token_accuracy": 0.6856056058779358, | |
| "num_tokens": 6271507.0, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.11047356015332968, | |
| "grad_norm": 0.49625030159950256, | |
| "learning_rate": 3.7783473353405986e-05, | |
| "loss": 1.3219, | |
| "mean_token_accuracy": 0.6740474671125412, | |
| "num_tokens": 6485242.0, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.11428299326206519, | |
| "grad_norm": 0.4760020971298218, | |
| "learning_rate": 3.90874758850162e-05, | |
| "loss": 1.3866, | |
| "mean_token_accuracy": 0.666905522160232, | |
| "num_tokens": 6694201.0, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.1180924263708007, | |
| "grad_norm": 0.6702063083648682, | |
| "learning_rate": 4.039147841662642e-05, | |
| "loss": 1.3396, | |
| "mean_token_accuracy": 0.673108272999525, | |
| "num_tokens": 6920931.0, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.1219018594795362, | |
| "grad_norm": 0.5828559398651123, | |
| "learning_rate": 4.169548094823663e-05, | |
| "loss": 1.2849, | |
| "mean_token_accuracy": 0.6773701002821326, | |
| "num_tokens": 7147355.0, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.1257112925882717, | |
| "grad_norm": 0.558748185634613, | |
| "learning_rate": 4.299948347984684e-05, | |
| "loss": 1.3391, | |
| "mean_token_accuracy": 0.6739463916048407, | |
| "num_tokens": 7365364.0, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.1295207256970072, | |
| "grad_norm": 0.5812460780143738, | |
| "learning_rate": 4.430348601145706e-05, | |
| "loss": 1.3572, | |
| "mean_token_accuracy": 0.6651050833985209, | |
| "num_tokens": 7575079.0, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.13333015880574273, | |
| "grad_norm": 0.7141745686531067, | |
| "learning_rate": 4.5607488543067274e-05, | |
| "loss": 1.2944, | |
| "mean_token_accuracy": 0.681589861959219, | |
| "num_tokens": 7804608.0, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.13713959191447822, | |
| "grad_norm": 0.5530197024345398, | |
| "learning_rate": 4.691149107467749e-05, | |
| "loss": 1.3375, | |
| "mean_token_accuracy": 0.6718398928642273, | |
| "num_tokens": 8017882.0, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.14094902502321374, | |
| "grad_norm": 0.48236706852912903, | |
| "learning_rate": 4.8215493606287705e-05, | |
| "loss": 1.335, | |
| "mean_token_accuracy": 0.6747591784223914, | |
| "num_tokens": 8238637.0, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.14475845813194924, | |
| "grad_norm": 0.5896688103675842, | |
| "learning_rate": 4.919348145872209e-05, | |
| "loss": 1.359, | |
| "mean_token_accuracy": 0.6685425175353885, | |
| "num_tokens": 8448265.0, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.14856789124068476, | |
| "grad_norm": 0.6068539619445801, | |
| "learning_rate": 4.9193144349007555e-05, | |
| "loss": 1.3475, | |
| "mean_token_accuracy": 0.6698486657813192, | |
| "num_tokens": 8663046.0, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.15237732434942025, | |
| "grad_norm": 0.4848249852657318, | |
| "learning_rate": 4.91923577659781e-05, | |
| "loss": 1.3355, | |
| "mean_token_accuracy": 0.6719444127753377, | |
| "num_tokens": 8882966.0, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.15618675745815574, | |
| "grad_norm": 0.5089111924171448, | |
| "learning_rate": 4.9191121724764224e-05, | |
| "loss": 1.3455, | |
| "mean_token_accuracy": 0.6727668078616261, | |
| "num_tokens": 9099039.0, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.15999619056689127, | |
| "grad_norm": 0.5716065168380737, | |
| "learning_rate": 4.9189436249142116e-05, | |
| "loss": 1.3555, | |
| "mean_token_accuracy": 0.6711426375433802, | |
| "num_tokens": 9320395.0, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.16380562367562676, | |
| "grad_norm": 0.7265896797180176, | |
| "learning_rate": 4.918730137153316e-05, | |
| "loss": 1.3418, | |
| "mean_token_accuracy": 0.6719378443434835, | |
| "num_tokens": 9535056.0, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.16761505678436228, | |
| "grad_norm": 0.6088116765022278, | |
| "learning_rate": 4.9184717133003326e-05, | |
| "loss": 1.306, | |
| "mean_token_accuracy": 0.6769841868430376, | |
| "num_tokens": 9753473.0, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.17142448989309778, | |
| "grad_norm": 0.3883936405181885, | |
| "learning_rate": 4.918168358326239e-05, | |
| "loss": 1.2348, | |
| "mean_token_accuracy": 0.6958686344325542, | |
| "num_tokens": 9977829.0, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.1752339230018333, | |
| "grad_norm": 0.5694851279258728, | |
| "learning_rate": 4.917820078066296e-05, | |
| "loss": 1.3571, | |
| "mean_token_accuracy": 0.6749148614704609, | |
| "num_tokens": 10202796.0, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.1790433561105688, | |
| "grad_norm": 0.4964405298233032, | |
| "learning_rate": 4.9174268792199355e-05, | |
| "loss": 1.292, | |
| "mean_token_accuracy": 0.682447912171483, | |
| "num_tokens": 10446726.0, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.1828527892193043, | |
| "grad_norm": 0.585851788520813, | |
| "learning_rate": 4.916988769350633e-05, | |
| "loss": 1.3271, | |
| "mean_token_accuracy": 0.6706608653068542, | |
| "num_tokens": 10675299.0, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.1866622223280398, | |
| "grad_norm": 0.4936956763267517, | |
| "learning_rate": 4.91650575688576e-05, | |
| "loss": 1.3212, | |
| "mean_token_accuracy": 0.6725098427385092, | |
| "num_tokens": 10908277.0, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.19047165543677533, | |
| "grad_norm": 0.4473949670791626, | |
| "learning_rate": 4.9159778511164254e-05, | |
| "loss": 1.2485, | |
| "mean_token_accuracy": 0.6835329543799162, | |
| "num_tokens": 11138801.0, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.1914240137139592, | |
| "eval_mean_token_accuracy": 0.6230506894878115, | |
| "eval_num_tokens": 11194791.0, | |
| "eval_test_loss": 1.832930564880371, | |
| "eval_test_runtime": 95.4667, | |
| "eval_test_samples_per_second": 20.855, | |
| "eval_test_steps_per_second": 10.433, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 0.19428108854551082, | |
| "grad_norm": 0.5689784288406372, | |
| "learning_rate": 4.915405062197292e-05, | |
| "loss": 1.2842, | |
| "mean_token_accuracy": 0.6809853713959455, | |
| "num_tokens": 11368252.0, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.19809052165424632, | |
| "grad_norm": 0.5339015126228333, | |
| "learning_rate": 4.914787401146385e-05, | |
| "loss": 1.3224, | |
| "mean_token_accuracy": 0.67562406193465, | |
| "num_tokens": 11590368.0, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.20189995476298184, | |
| "grad_norm": 0.6560924053192139, | |
| "learning_rate": 4.91412487984488e-05, | |
| "loss": 1.3732, | |
| "mean_token_accuracy": 0.6702003039419651, | |
| "num_tokens": 11798414.0, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.20570938787171733, | |
| "grad_norm": 0.5972558259963989, | |
| "learning_rate": 4.91341751103687e-05, | |
| "loss": 1.2983, | |
| "mean_token_accuracy": 0.6805376719683409, | |
| "num_tokens": 12013463.0, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.20951882098045285, | |
| "grad_norm": 0.4506518542766571, | |
| "learning_rate": 4.912665308329125e-05, | |
| "loss": 1.2653, | |
| "mean_token_accuracy": 0.6877350242808461, | |
| "num_tokens": 12236318.0, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.21332825408918835, | |
| "grad_norm": 0.5365843772888184, | |
| "learning_rate": 4.91186828619083e-05, | |
| "loss": 1.3285, | |
| "mean_token_accuracy": 0.6712553380057216, | |
| "num_tokens": 12458126.0, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.21713768719792387, | |
| "grad_norm": 0.4755626916885376, | |
| "learning_rate": 4.9110264599533055e-05, | |
| "loss": 1.3315, | |
| "mean_token_accuracy": 0.6608016982674598, | |
| "num_tokens": 12678890.0, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.22094712030665936, | |
| "grad_norm": 0.43261516094207764, | |
| "learning_rate": 4.9101398458097093e-05, | |
| "loss": 1.3166, | |
| "mean_token_accuracy": 0.6768794044852257, | |
| "num_tokens": 12900305.0, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.22475655341539488, | |
| "grad_norm": 0.5397626161575317, | |
| "learning_rate": 4.9092084608147315e-05, | |
| "loss": 1.3296, | |
| "mean_token_accuracy": 0.6792715717107057, | |
| "num_tokens": 13109419.0, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 0.22856598652413038, | |
| "grad_norm": 0.4163241386413574, | |
| "learning_rate": 4.908232322884261e-05, | |
| "loss": 1.2938, | |
| "mean_token_accuracy": 0.6871387459337711, | |
| "num_tokens": 13335797.0, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.23237541963286587, | |
| "grad_norm": 0.7546857595443726, | |
| "learning_rate": 4.907211450795045e-05, | |
| "loss": 1.2872, | |
| "mean_token_accuracy": 0.6850869571790099, | |
| "num_tokens": 13565988.0, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 0.2361848527416014, | |
| "grad_norm": 0.6345241069793701, | |
| "learning_rate": 4.906145864184325e-05, | |
| "loss": 1.3234, | |
| "mean_token_accuracy": 0.6739947069436312, | |
| "num_tokens": 13779004.0, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 0.23999428585033689, | |
| "grad_norm": 0.5710681080818176, | |
| "learning_rate": 4.905035583549459e-05, | |
| "loss": 1.3, | |
| "mean_token_accuracy": 0.6780852235853672, | |
| "num_tokens": 14005597.0, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 0.2438037189590724, | |
| "grad_norm": 0.5527021288871765, | |
| "learning_rate": 4.903880630247529e-05, | |
| "loss": 1.3019, | |
| "mean_token_accuracy": 0.6793860571458936, | |
| "num_tokens": 14235179.0, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 0.2476131520678079, | |
| "grad_norm": 0.4566735327243805, | |
| "learning_rate": 4.902681026494929e-05, | |
| "loss": 1.2927, | |
| "mean_token_accuracy": 0.6824004529044032, | |
| "num_tokens": 14464950.0, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.2514225851765434, | |
| "grad_norm": 0.5023188591003418, | |
| "learning_rate": 4.901436795366938e-05, | |
| "loss": 1.2996, | |
| "mean_token_accuracy": 0.6823519911617041, | |
| "num_tokens": 14686771.0, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 0.2552320182852789, | |
| "grad_norm": 0.6048426628112793, | |
| "learning_rate": 4.900147960797276e-05, | |
| "loss": 1.3523, | |
| "mean_token_accuracy": 0.6745322810485959, | |
| "num_tokens": 14896388.0, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 0.2590414513940144, | |
| "grad_norm": 0.5594220757484436, | |
| "learning_rate": 4.898814547577645e-05, | |
| "loss": 1.2733, | |
| "mean_token_accuracy": 0.685325993783772, | |
| "num_tokens": 15115431.0, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 0.26285088450274996, | |
| "grad_norm": 0.5266786813735962, | |
| "learning_rate": 4.89743658135725e-05, | |
| "loss": 1.378, | |
| "mean_token_accuracy": 0.661252242513001, | |
| "num_tokens": 15318046.0, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 0.26666031761148545, | |
| "grad_norm": 0.33945998549461365, | |
| "learning_rate": 4.896014088642304e-05, | |
| "loss": 1.2849, | |
| "mean_token_accuracy": 0.68093207962811, | |
| "num_tokens": 15546171.0, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.27046975072022095, | |
| "grad_norm": 0.38815465569496155, | |
| "learning_rate": 4.8945470967955234e-05, | |
| "loss": 1.3622, | |
| "mean_token_accuracy": 0.6677591029554606, | |
| "num_tokens": 15763709.0, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 0.27427918382895644, | |
| "grad_norm": 0.5876178741455078, | |
| "learning_rate": 4.8930356340355986e-05, | |
| "loss": 1.2209, | |
| "mean_token_accuracy": 0.7016260443255306, | |
| "num_tokens": 15994580.0, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 0.27808861693769193, | |
| "grad_norm": 0.6305630207061768, | |
| "learning_rate": 4.8914797294366514e-05, | |
| "loss": 1.3553, | |
| "mean_token_accuracy": 0.6636421175673604, | |
| "num_tokens": 16208325.0, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 0.2818980500464275, | |
| "grad_norm": 0.47434547543525696, | |
| "learning_rate": 4.889879412927675e-05, | |
| "loss": 1.3085, | |
| "mean_token_accuracy": 0.6797755250707269, | |
| "num_tokens": 16428418.0, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 0.285707483155163, | |
| "grad_norm": 0.5395858883857727, | |
| "learning_rate": 4.888234715291958e-05, | |
| "loss": 1.2705, | |
| "mean_token_accuracy": 0.6883305061608553, | |
| "num_tokens": 16658226.0, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.2871360205709388, | |
| "eval_mean_token_accuracy": 0.6258668910906496, | |
| "eval_num_tokens": 16745761.0, | |
| "eval_test_loss": 1.8088411092758179, | |
| "eval_test_runtime": 94.958, | |
| "eval_test_samples_per_second": 20.967, | |
| "eval_test_steps_per_second": 10.489, | |
| "step": 3015 | |
| }, | |
| { | |
| "epoch": 0.28951691626389847, | |
| "grad_norm": 0.5518168210983276, | |
| "learning_rate": 4.8865456681664965e-05, | |
| "loss": 1.2997, | |
| "mean_token_accuracy": 0.6776028882712126, | |
| "num_tokens": 16876039.0, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 0.29332634937263397, | |
| "grad_norm": 0.6039868593215942, | |
| "learning_rate": 4.88481230404138e-05, | |
| "loss": 1.2621, | |
| "mean_token_accuracy": 0.6928930662572383, | |
| "num_tokens": 17104229.0, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 0.2971357824813695, | |
| "grad_norm": 0.5715156197547913, | |
| "learning_rate": 4.883034656259167e-05, | |
| "loss": 1.3461, | |
| "mean_token_accuracy": 0.6714908115565776, | |
| "num_tokens": 17312134.0, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 0.300945215590105, | |
| "grad_norm": 0.5405182838439941, | |
| "learning_rate": 4.8812127590142505e-05, | |
| "loss": 1.2837, | |
| "mean_token_accuracy": 0.6896362887695432, | |
| "num_tokens": 17550198.0, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 0.3047546486988405, | |
| "grad_norm": 0.5504481792449951, | |
| "learning_rate": 4.8793466473521904e-05, | |
| "loss": 1.2181, | |
| "mean_token_accuracy": 0.6988515704870224, | |
| "num_tokens": 17778838.0, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.308564081807576, | |
| "grad_norm": 0.621837317943573, | |
| "learning_rate": 4.877436357169048e-05, | |
| "loss": 1.3323, | |
| "mean_token_accuracy": 0.6710341470316052, | |
| "num_tokens": 17985533.0, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 0.3123735149163115, | |
| "grad_norm": 0.6566672325134277, | |
| "learning_rate": 4.8754819252106876e-05, | |
| "loss": 1.2744, | |
| "mean_token_accuracy": 0.683073416352272, | |
| "num_tokens": 18208416.0, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 0.31618294802504704, | |
| "grad_norm": 0.5615633130073547, | |
| "learning_rate": 4.873483389072076e-05, | |
| "loss": 1.315, | |
| "mean_token_accuracy": 0.684354678913951, | |
| "num_tokens": 18426223.0, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 0.31999238113378253, | |
| "grad_norm": 0.4581094980239868, | |
| "learning_rate": 4.871440787196558e-05, | |
| "loss": 1.3269, | |
| "mean_token_accuracy": 0.6761635078117252, | |
| "num_tokens": 18635703.0, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 0.323801814242518, | |
| "grad_norm": 0.5478665232658386, | |
| "learning_rate": 4.8693541588751144e-05, | |
| "loss": 1.2554, | |
| "mean_token_accuracy": 0.688594707287848, | |
| "num_tokens": 18859074.0, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.3276112473512535, | |
| "grad_norm": 0.39972299337387085, | |
| "learning_rate": 4.867223544245607e-05, | |
| "loss": 1.2497, | |
| "mean_token_accuracy": 0.6876592069864274, | |
| "num_tokens": 19084486.0, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 0.33142068045998907, | |
| "grad_norm": 0.6696220636367798, | |
| "learning_rate": 4.865048984292009e-05, | |
| "loss": 1.2776, | |
| "mean_token_accuracy": 0.6786478063091635, | |
| "num_tokens": 19305228.0, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 0.33523011356872456, | |
| "grad_norm": 0.5517823100090027, | |
| "learning_rate": 4.8628305208436137e-05, | |
| "loss": 1.2922, | |
| "mean_token_accuracy": 0.6886478485539556, | |
| "num_tokens": 19538363.0, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 0.33903954667746006, | |
| "grad_norm": 0.44766560196876526, | |
| "learning_rate": 4.860568196574232e-05, | |
| "loss": 1.2851, | |
| "mean_token_accuracy": 0.6843299470841885, | |
| "num_tokens": 19774720.0, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 0.34284897978619555, | |
| "grad_norm": 0.38793668150901794, | |
| "learning_rate": 4.858262055001371e-05, | |
| "loss": 1.3057, | |
| "mean_token_accuracy": 0.6804726634174585, | |
| "num_tokens": 19998879.0, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.3466584128949311, | |
| "grad_norm": 0.45702189207077026, | |
| "learning_rate": 4.8559121404853944e-05, | |
| "loss": 1.1826, | |
| "mean_token_accuracy": 0.7049577981233597, | |
| "num_tokens": 20243495.0, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 0.3504678460036666, | |
| "grad_norm": 0.5189054608345032, | |
| "learning_rate": 4.853518498228674e-05, | |
| "loss": 1.2659, | |
| "mean_token_accuracy": 0.6826557310298085, | |
| "num_tokens": 20462476.0, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 0.3542772791124021, | |
| "grad_norm": 0.4221845269203186, | |
| "learning_rate": 4.851081174274715e-05, | |
| "loss": 1.3576, | |
| "mean_token_accuracy": 0.6631780494004488, | |
| "num_tokens": 20679798.0, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 0.3580867122211376, | |
| "grad_norm": 0.4048372209072113, | |
| "learning_rate": 4.8486002155072754e-05, | |
| "loss": 1.2332, | |
| "mean_token_accuracy": 0.7002108607441186, | |
| "num_tokens": 20913935.0, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 0.3618961453298731, | |
| "grad_norm": 0.5621294379234314, | |
| "learning_rate": 4.8460756696494594e-05, | |
| "loss": 1.2625, | |
| "mean_token_accuracy": 0.6872183892875909, | |
| "num_tokens": 21138524.0, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.3657055784386086, | |
| "grad_norm": 0.5211415886878967, | |
| "learning_rate": 4.843507585262804e-05, | |
| "loss": 1.2533, | |
| "mean_token_accuracy": 0.6849848669022321, | |
| "num_tokens": 21373326.0, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 0.3695150115473441, | |
| "grad_norm": 0.551052987575531, | |
| "learning_rate": 4.8408960117463386e-05, | |
| "loss": 1.304, | |
| "mean_token_accuracy": 0.6765170315280556, | |
| "num_tokens": 21590656.0, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 0.3733244446560796, | |
| "grad_norm": 0.5423365831375122, | |
| "learning_rate": 4.838240999335643e-05, | |
| "loss": 1.3441, | |
| "mean_token_accuracy": 0.6701787773519754, | |
| "num_tokens": 21795838.0, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 0.3771338777648151, | |
| "grad_norm": 0.46691930294036865, | |
| "learning_rate": 4.835542599101873e-05, | |
| "loss": 1.3163, | |
| "mean_token_accuracy": 0.6742871653288602, | |
| "num_tokens": 22007062.0, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 0.38094331087355066, | |
| "grad_norm": 0.6379289627075195, | |
| "learning_rate": 4.8328008629507863e-05, | |
| "loss": 1.3094, | |
| "mean_token_accuracy": 0.6776679191738367, | |
| "num_tokens": 22232306.0, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.3828480274279184, | |
| "eval_mean_token_accuracy": 0.6281169285496555, | |
| "eval_num_tokens": 22348477.0, | |
| "eval_test_loss": 1.793502926826477, | |
| "eval_test_runtime": 95.0461, | |
| "eval_test_samples_per_second": 20.948, | |
| "eval_test_steps_per_second": 10.479, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 0.38475274398228615, | |
| "grad_norm": 0.6131725311279297, | |
| "learning_rate": 4.830015843621735e-05, | |
| "loss": 1.2705, | |
| "mean_token_accuracy": 0.6874665239825845, | |
| "num_tokens": 22461894.0, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 0.38856217709102164, | |
| "grad_norm": 0.4669947326183319, | |
| "learning_rate": 4.8271875946866574e-05, | |
| "loss": 1.3255, | |
| "mean_token_accuracy": 0.6841361073777079, | |
| "num_tokens": 22684394.0, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 0.39237161019975714, | |
| "grad_norm": 0.42204299569129944, | |
| "learning_rate": 4.824316170549047e-05, | |
| "loss": 1.2425, | |
| "mean_token_accuracy": 0.6886863965541125, | |
| "num_tokens": 22918777.0, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 0.39618104330849263, | |
| "grad_norm": 0.5980663895606995, | |
| "learning_rate": 4.821401626442903e-05, | |
| "loss": 1.2868, | |
| "mean_token_accuracy": 0.6745259683579207, | |
| "num_tokens": 23139486.0, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 0.3999904764172282, | |
| "grad_norm": 0.46430954337120056, | |
| "learning_rate": 4.8184440184316695e-05, | |
| "loss": 1.228, | |
| "mean_token_accuracy": 0.6927272006869316, | |
| "num_tokens": 23372563.0, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.4037999095259637, | |
| "grad_norm": 0.5982958078384399, | |
| "learning_rate": 4.815443403407159e-05, | |
| "loss": 1.2377, | |
| "mean_token_accuracy": 0.687408297508955, | |
| "num_tokens": 23601002.0, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 0.40760934263469917, | |
| "grad_norm": 0.5242788195610046, | |
| "learning_rate": 4.812399839088453e-05, | |
| "loss": 1.2926, | |
| "mean_token_accuracy": 0.6808499401435256, | |
| "num_tokens": 23814142.0, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 0.41141877574343466, | |
| "grad_norm": 0.44663509726524353, | |
| "learning_rate": 4.809313384020799e-05, | |
| "loss": 1.2768, | |
| "mean_token_accuracy": 0.6787567920982838, | |
| "num_tokens": 24034008.0, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 0.4152282088521702, | |
| "grad_norm": 0.571322500705719, | |
| "learning_rate": 4.806184097574478e-05, | |
| "loss": 1.299, | |
| "mean_token_accuracy": 0.6753746373578906, | |
| "num_tokens": 24241179.0, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 0.4190376419609057, | |
| "grad_norm": 0.6444421410560608, | |
| "learning_rate": 4.8030120399436636e-05, | |
| "loss": 1.2922, | |
| "mean_token_accuracy": 0.6790545796975493, | |
| "num_tokens": 24463001.0, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.4228470750696412, | |
| "grad_norm": 0.5884628891944885, | |
| "learning_rate": 4.799797272145267e-05, | |
| "loss": 1.3354, | |
| "mean_token_accuracy": 0.6655034508556128, | |
| "num_tokens": 24672669.0, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 0.4266565081783767, | |
| "grad_norm": 0.6725838780403137, | |
| "learning_rate": 4.796539856017762e-05, | |
| "loss": 1.2866, | |
| "mean_token_accuracy": 0.6829743100330233, | |
| "num_tokens": 24895076.0, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 0.4304659412871122, | |
| "grad_norm": 0.5089847445487976, | |
| "learning_rate": 4.7932398542199935e-05, | |
| "loss": 1.3312, | |
| "mean_token_accuracy": 0.6777703372761608, | |
| "num_tokens": 25105078.0, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 0.43427537439584774, | |
| "grad_norm": 0.6170702576637268, | |
| "learning_rate": 4.7898973302299746e-05, | |
| "loss": 1.2308, | |
| "mean_token_accuracy": 0.6913123942911625, | |
| "num_tokens": 25330411.0, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 0.43808480750458323, | |
| "grad_norm": 0.47749921679496765, | |
| "learning_rate": 4.786512348343664e-05, | |
| "loss": 1.2394, | |
| "mean_token_accuracy": 0.6930743562057614, | |
| "num_tokens": 25558075.0, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.4418942406133187, | |
| "grad_norm": 0.5179374814033508, | |
| "learning_rate": 4.783084973673732e-05, | |
| "loss": 1.3121, | |
| "mean_token_accuracy": 0.6737616384401918, | |
| "num_tokens": 25787633.0, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 0.4457036737220542, | |
| "grad_norm": 0.4957481920719147, | |
| "learning_rate": 4.7796152721483024e-05, | |
| "loss": 1.2679, | |
| "mean_token_accuracy": 0.6782409870997071, | |
| "num_tokens": 26010384.0, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 0.44951310683078977, | |
| "grad_norm": 0.46905845403671265, | |
| "learning_rate": 4.776103310509691e-05, | |
| "loss": 1.3583, | |
| "mean_token_accuracy": 0.6669555108994245, | |
| "num_tokens": 26220009.0, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 0.45332253993952526, | |
| "grad_norm": 0.6176592707633972, | |
| "learning_rate": 4.7725491563131164e-05, | |
| "loss": 1.3376, | |
| "mean_token_accuracy": 0.6773041613399983, | |
| "num_tokens": 26437068.0, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 0.45713197304826075, | |
| "grad_norm": 0.641156017780304, | |
| "learning_rate": 4.7689528779254057e-05, | |
| "loss": 1.338, | |
| "mean_token_accuracy": 0.6686659481376409, | |
| "num_tokens": 26646369.0, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.46094140615699625, | |
| "grad_norm": 0.5560479760169983, | |
| "learning_rate": 4.7653145445236725e-05, | |
| "loss": 1.3156, | |
| "mean_token_accuracy": 0.6741218714043498, | |
| "num_tokens": 26872767.0, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 0.46475083926573174, | |
| "grad_norm": 0.6000213027000427, | |
| "learning_rate": 4.761634226093993e-05, | |
| "loss": 1.2637, | |
| "mean_token_accuracy": 0.6870461646467447, | |
| "num_tokens": 27092463.0, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 0.4685602723744673, | |
| "grad_norm": 0.3717496693134308, | |
| "learning_rate": 4.757911993430057e-05, | |
| "loss": 1.3356, | |
| "mean_token_accuracy": 0.6666051434352994, | |
| "num_tokens": 27314300.0, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 0.4723697054832028, | |
| "grad_norm": 0.839055061340332, | |
| "learning_rate": 4.754147918131804e-05, | |
| "loss": 1.2933, | |
| "mean_token_accuracy": 0.6818767448887229, | |
| "num_tokens": 27534317.0, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 0.4761791385919383, | |
| "grad_norm": 0.5968820452690125, | |
| "learning_rate": 4.7503420726040496e-05, | |
| "loss": 1.3218, | |
| "mean_token_accuracy": 0.6756005242466927, | |
| "num_tokens": 27744710.0, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.47856003428489796, | |
| "eval_mean_token_accuracy": 0.6309991637506638, | |
| "eval_num_tokens": 27879664.0, | |
| "eval_test_loss": 1.7806874513626099, | |
| "eval_test_runtime": 94.8719, | |
| "eval_test_samples_per_second": 20.986, | |
| "eval_test_steps_per_second": 10.498, | |
| "step": 5025 | |
| }, | |
| { | |
| "epoch": 0.47998857170067377, | |
| "grad_norm": 0.555782675743103, | |
| "learning_rate": 4.74649453005509e-05, | |
| "loss": 1.2746, | |
| "mean_token_accuracy": 0.684971004165709, | |
| "num_tokens": 27964540.0, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 0.4837980048094093, | |
| "grad_norm": 0.5832619071006775, | |
| "learning_rate": 4.742605364495298e-05, | |
| "loss": 1.2391, | |
| "mean_token_accuracy": 0.691305941529572, | |
| "num_tokens": 28195211.0, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 0.4876074379181448, | |
| "grad_norm": 0.4528619349002838, | |
| "learning_rate": 4.738674650735692e-05, | |
| "loss": 1.2295, | |
| "mean_token_accuracy": 0.683625971712172, | |
| "num_tokens": 28427726.0, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 0.4914168710268803, | |
| "grad_norm": 0.8959270119667053, | |
| "learning_rate": 4.734702464386503e-05, | |
| "loss": 1.3764, | |
| "mean_token_accuracy": 0.6636357877403498, | |
| "num_tokens": 28631998.0, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 0.4952263041356158, | |
| "grad_norm": 0.43296220898628235, | |
| "learning_rate": 4.73068888185572e-05, | |
| "loss": 1.2929, | |
| "mean_token_accuracy": 0.6792870191857219, | |
| "num_tokens": 28846791.0, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.49903573724435135, | |
| "grad_norm": 0.722977340221405, | |
| "learning_rate": 4.726633980347616e-05, | |
| "loss": 1.3176, | |
| "mean_token_accuracy": 0.6724835351109505, | |
| "num_tokens": 29054506.0, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 0.5028451703530868, | |
| "grad_norm": 0.41740506887435913, | |
| "learning_rate": 4.722537837861267e-05, | |
| "loss": 1.2455, | |
| "mean_token_accuracy": 0.688827583193779, | |
| "num_tokens": 29270620.0, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 0.5066546034618223, | |
| "grad_norm": 0.38050729036331177, | |
| "learning_rate": 4.718400533189051e-05, | |
| "loss": 1.2743, | |
| "mean_token_accuracy": 0.6829100279137492, | |
| "num_tokens": 29490565.0, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 0.5104640365705578, | |
| "grad_norm": 0.5724825263023376, | |
| "learning_rate": 4.7142221459151294e-05, | |
| "loss": 1.2773, | |
| "mean_token_accuracy": 0.6881643293425441, | |
| "num_tokens": 29704265.0, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 0.5142734696792933, | |
| "grad_norm": 0.6543896198272705, | |
| "learning_rate": 4.7100027564139196e-05, | |
| "loss": 1.3307, | |
| "mean_token_accuracy": 0.6777999725192785, | |
| "num_tokens": 29924515.0, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.5180829027880288, | |
| "grad_norm": 0.43163400888442993, | |
| "learning_rate": 4.705742445848548e-05, | |
| "loss": 1.2653, | |
| "mean_token_accuracy": 0.682813161984086, | |
| "num_tokens": 30148026.0, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 0.5218923358967643, | |
| "grad_norm": 0.47830525040626526, | |
| "learning_rate": 4.7014412961692864e-05, | |
| "loss": 1.1955, | |
| "mean_token_accuracy": 0.7004892747849226, | |
| "num_tokens": 30372129.0, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 0.5257017690054999, | |
| "grad_norm": 0.5903618931770325, | |
| "learning_rate": 4.697099390111981e-05, | |
| "loss": 1.2973, | |
| "mean_token_accuracy": 0.6818130781874061, | |
| "num_tokens": 30596623.0, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 0.5295112021142354, | |
| "grad_norm": 0.43726322054862976, | |
| "learning_rate": 4.6927168111964555e-05, | |
| "loss": 1.2095, | |
| "mean_token_accuracy": 0.696308933570981, | |
| "num_tokens": 30834116.0, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 0.5333206352229709, | |
| "grad_norm": 0.7869614958763123, | |
| "learning_rate": 4.6882936437249056e-05, | |
| "loss": 1.2275, | |
| "mean_token_accuracy": 0.6923372825607658, | |
| "num_tokens": 31066239.0, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.5371300683317064, | |
| "grad_norm": 0.4349427819252014, | |
| "learning_rate": 4.6838299727802786e-05, | |
| "loss": 1.2973, | |
| "mean_token_accuracy": 0.688424677029252, | |
| "num_tokens": 31302823.0, | |
| "step": 5640 | |
| }, | |
| { | |
| "epoch": 0.5409395014404419, | |
| "grad_norm": 0.5851991772651672, | |
| "learning_rate": 4.67932588422464e-05, | |
| "loss": 1.237, | |
| "mean_token_accuracy": 0.6886244036257267, | |
| "num_tokens": 31530684.0, | |
| "step": 5680 | |
| }, | |
| { | |
| "epoch": 0.5447489345491774, | |
| "grad_norm": 0.6614839434623718, | |
| "learning_rate": 4.6747814646975134e-05, | |
| "loss": 1.3017, | |
| "mean_token_accuracy": 0.6840987723320723, | |
| "num_tokens": 31741759.0, | |
| "step": 5720 | |
| }, | |
| { | |
| "epoch": 0.5485583676579129, | |
| "grad_norm": 0.4596734642982483, | |
| "learning_rate": 4.670196801614224e-05, | |
| "loss": 1.1938, | |
| "mean_token_accuracy": 0.7047518376260996, | |
| "num_tokens": 31987926.0, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 0.5523678007666484, | |
| "grad_norm": 0.5416800379753113, | |
| "learning_rate": 4.665571983164207e-05, | |
| "loss": 1.2874, | |
| "mean_token_accuracy": 0.6859219571575522, | |
| "num_tokens": 32213674.0, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.5561772338753839, | |
| "grad_norm": 0.4644794464111328, | |
| "learning_rate": 4.660907098309319e-05, | |
| "loss": 1.2893, | |
| "mean_token_accuracy": 0.6782131699845195, | |
| "num_tokens": 32429679.0, | |
| "step": 5840 | |
| }, | |
| { | |
| "epoch": 0.5599866669841195, | |
| "grad_norm": 0.5027694702148438, | |
| "learning_rate": 4.6562022367821244e-05, | |
| "loss": 1.2955, | |
| "mean_token_accuracy": 0.6798365904018283, | |
| "num_tokens": 32646061.0, | |
| "step": 5880 | |
| }, | |
| { | |
| "epoch": 0.563796100092855, | |
| "grad_norm": 0.5148358345031738, | |
| "learning_rate": 4.651457489084167e-05, | |
| "loss": 1.2533, | |
| "mean_token_accuracy": 0.684299885481596, | |
| "num_tokens": 32867990.0, | |
| "step": 5920 | |
| }, | |
| { | |
| "epoch": 0.5676055332015905, | |
| "grad_norm": 0.4006965756416321, | |
| "learning_rate": 4.646672946484232e-05, | |
| "loss": 1.2246, | |
| "mean_token_accuracy": 0.6978412168100476, | |
| "num_tokens": 33100846.0, | |
| "step": 5960 | |
| }, | |
| { | |
| "epoch": 0.571414966310326, | |
| "grad_norm": 0.5946612358093262, | |
| "learning_rate": 4.641848701016592e-05, | |
| "loss": 1.3112, | |
| "mean_token_accuracy": 0.682670296356082, | |
| "num_tokens": 33316830.0, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.5742720411418776, | |
| "eval_mean_token_accuracy": 0.6325134164597614, | |
| "eval_num_tokens": 33490786.0, | |
| "eval_test_loss": 1.7651844024658203, | |
| "eval_test_runtime": 95.3517, | |
| "eval_test_samples_per_second": 20.881, | |
| "eval_test_steps_per_second": 10.446, | |
| "step": 6030 | |
| }, | |
| { | |
| "epoch": 0.5752243994190614, | |
| "grad_norm": 0.5004485249519348, | |
| "learning_rate": 4.636984845479229e-05, | |
| "loss": 1.3189, | |
| "mean_token_accuracy": 0.6787041410803795, | |
| "num_tokens": 33547057.0, | |
| "step": 6040 | |
| }, | |
| { | |
| "epoch": 0.5790338325277969, | |
| "grad_norm": 0.6013615727424622, | |
| "learning_rate": 4.6320814734320574e-05, | |
| "loss": 1.2999, | |
| "mean_token_accuracy": 0.6829198809340596, | |
| "num_tokens": 33751128.0, | |
| "step": 6080 | |
| }, | |
| { | |
| "epoch": 0.5828432656365324, | |
| "grad_norm": 0.46301329135894775, | |
| "learning_rate": 4.627138679195122e-05, | |
| "loss": 1.2979, | |
| "mean_token_accuracy": 0.6834639564156533, | |
| "num_tokens": 33958374.0, | |
| "step": 6120 | |
| }, | |
| { | |
| "epoch": 0.5866526987452679, | |
| "grad_norm": 0.5537028908729553, | |
| "learning_rate": 4.622156557846782e-05, | |
| "loss": 1.2919, | |
| "mean_token_accuracy": 0.6853473074734211, | |
| "num_tokens": 34173776.0, | |
| "step": 6160 | |
| }, | |
| { | |
| "epoch": 0.5904621318540034, | |
| "grad_norm": 0.5172299146652222, | |
| "learning_rate": 4.617135205221882e-05, | |
| "loss": 1.2535, | |
| "mean_token_accuracy": 0.6891471687704325, | |
| "num_tokens": 34402012.0, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.594271564962739, | |
| "grad_norm": 0.45443201065063477, | |
| "learning_rate": 4.6120747179099115e-05, | |
| "loss": 1.3631, | |
| "mean_token_accuracy": 0.6746680632233619, | |
| "num_tokens": 34619563.0, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 0.5980809980714745, | |
| "grad_norm": 0.5318917632102966, | |
| "learning_rate": 4.606975193253145e-05, | |
| "loss": 1.2875, | |
| "mean_token_accuracy": 0.6842667568475008, | |
| "num_tokens": 34842995.0, | |
| "step": 6280 | |
| }, | |
| { | |
| "epoch": 0.60189043118021, | |
| "grad_norm": 0.41732507944107056, | |
| "learning_rate": 4.6018367293447696e-05, | |
| "loss": 1.2011, | |
| "mean_token_accuracy": 0.6991326250135899, | |
| "num_tokens": 35074476.0, | |
| "step": 6320 | |
| }, | |
| { | |
| "epoch": 0.6056998642889455, | |
| "grad_norm": 0.4196927845478058, | |
| "learning_rate": 4.5966594250269964e-05, | |
| "loss": 1.3135, | |
| "mean_token_accuracy": 0.6805538948625326, | |
| "num_tokens": 35296363.0, | |
| "step": 6360 | |
| }, | |
| { | |
| "epoch": 0.609509297397681, | |
| "grad_norm": 0.42691197991371155, | |
| "learning_rate": 4.5914433798891605e-05, | |
| "loss": 1.246, | |
| "mean_token_accuracy": 0.6876704445108771, | |
| "num_tokens": 35523754.0, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 0.6133187305064165, | |
| "grad_norm": 0.3611372113227844, | |
| "learning_rate": 4.5861886942658106e-05, | |
| "loss": 1.2269, | |
| "mean_token_accuracy": 0.6875138944014907, | |
| "num_tokens": 35758849.0, | |
| "step": 6440 | |
| }, | |
| { | |
| "epoch": 0.617128163615152, | |
| "grad_norm": 0.7133765816688538, | |
| "learning_rate": 4.580895469234769e-05, | |
| "loss": 1.2242, | |
| "mean_token_accuracy": 0.6886107694357634, | |
| "num_tokens": 35988842.0, | |
| "step": 6480 | |
| }, | |
| { | |
| "epoch": 0.6209375967238875, | |
| "grad_norm": 0.44684138894081116, | |
| "learning_rate": 4.575563806615196e-05, | |
| "loss": 1.2675, | |
| "mean_token_accuracy": 0.6812176534906029, | |
| "num_tokens": 36201602.0, | |
| "step": 6520 | |
| }, | |
| { | |
| "epoch": 0.624747029832623, | |
| "grad_norm": 0.5846595168113708, | |
| "learning_rate": 4.5701938089656256e-05, | |
| "loss": 1.2703, | |
| "mean_token_accuracy": 0.6853839591145515, | |
| "num_tokens": 36403261.0, | |
| "step": 6560 | |
| }, | |
| { | |
| "epoch": 0.6285564629413586, | |
| "grad_norm": 0.3759899437427521, | |
| "learning_rate": 4.5647855795819943e-05, | |
| "loss": 1.3111, | |
| "mean_token_accuracy": 0.6767927626147866, | |
| "num_tokens": 36619797.0, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 0.6323658960500941, | |
| "grad_norm": 0.6737694144248962, | |
| "learning_rate": 4.5593392224956576e-05, | |
| "loss": 1.3165, | |
| "mean_token_accuracy": 0.6752157468348742, | |
| "num_tokens": 36828768.0, | |
| "step": 6640 | |
| }, | |
| { | |
| "epoch": 0.6361753291588296, | |
| "grad_norm": 0.5695846676826477, | |
| "learning_rate": 4.5538548424713835e-05, | |
| "loss": 1.2397, | |
| "mean_token_accuracy": 0.6919887445867061, | |
| "num_tokens": 37053251.0, | |
| "step": 6680 | |
| }, | |
| { | |
| "epoch": 0.6399847622675651, | |
| "grad_norm": 0.5237749218940735, | |
| "learning_rate": 4.5483325450053406e-05, | |
| "loss": 1.2553, | |
| "mean_token_accuracy": 0.6820298057049513, | |
| "num_tokens": 37268972.0, | |
| "step": 6720 | |
| }, | |
| { | |
| "epoch": 0.6437941953763006, | |
| "grad_norm": 0.6554339528083801, | |
| "learning_rate": 4.5427724363230683e-05, | |
| "loss": 1.2682, | |
| "mean_token_accuracy": 0.6873216938227416, | |
| "num_tokens": 37492541.0, | |
| "step": 6760 | |
| }, | |
| { | |
| "epoch": 0.647603628485036, | |
| "grad_norm": 0.5178593397140503, | |
| "learning_rate": 4.537174623377432e-05, | |
| "loss": 1.2537, | |
| "mean_token_accuracy": 0.6826527412980795, | |
| "num_tokens": 37705009.0, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 0.6514130615937715, | |
| "grad_norm": 0.4857373833656311, | |
| "learning_rate": 4.53153921384657e-05, | |
| "loss": 1.3497, | |
| "mean_token_accuracy": 0.6726470049470663, | |
| "num_tokens": 37915354.0, | |
| "step": 6840 | |
| }, | |
| { | |
| "epoch": 0.655222494702507, | |
| "grad_norm": 0.48057419061660767, | |
| "learning_rate": 4.5258663161318136e-05, | |
| "loss": 1.2267, | |
| "mean_token_accuracy": 0.6866666225716471, | |
| "num_tokens": 38146196.0, | |
| "step": 6880 | |
| }, | |
| { | |
| "epoch": 0.6590319278112425, | |
| "grad_norm": 0.5138698220252991, | |
| "learning_rate": 4.5201560393556134e-05, | |
| "loss": 1.2439, | |
| "mean_token_accuracy": 0.6901180801913143, | |
| "num_tokens": 38373540.0, | |
| "step": 6920 | |
| }, | |
| { | |
| "epoch": 0.6628413609199781, | |
| "grad_norm": 0.47547754645347595, | |
| "learning_rate": 4.5144084933594303e-05, | |
| "loss": 1.2706, | |
| "mean_token_accuracy": 0.6800282135605812, | |
| "num_tokens": 38589036.0, | |
| "step": 6960 | |
| }, | |
| { | |
| "epoch": 0.6666507940287136, | |
| "grad_norm": 0.6765561103820801, | |
| "learning_rate": 4.508623788701628e-05, | |
| "loss": 1.2929, | |
| "mean_token_accuracy": 0.6894892951473593, | |
| "num_tokens": 38802771.0, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.6699840479988571, | |
| "eval_mean_token_accuracy": 0.6329328228970129, | |
| "eval_num_tokens": 38980983.0, | |
| "eval_test_loss": 1.7534339427947998, | |
| "eval_test_runtime": 95.0805, | |
| "eval_test_samples_per_second": 20.94, | |
| "eval_test_steps_per_second": 10.475, | |
| "step": 7035 | |
| }, | |
| { | |
| "epoch": 0.6704602271374491, | |
| "grad_norm": 0.40170061588287354, | |
| "learning_rate": 4.502802036655346e-05, | |
| "loss": 1.3205, | |
| "mean_token_accuracy": 0.675545847415924, | |
| "num_tokens": 39011417.0, | |
| "step": 7040 | |
| }, | |
| { | |
| "epoch": 0.6742696602461846, | |
| "grad_norm": 0.49673372507095337, | |
| "learning_rate": 4.4969433492063564e-05, | |
| "loss": 1.256, | |
| "mean_token_accuracy": 0.6876663960516453, | |
| "num_tokens": 39231629.0, | |
| "step": 7080 | |
| }, | |
| { | |
| "epoch": 0.6780790933549201, | |
| "grad_norm": 0.45921561121940613, | |
| "learning_rate": 4.491047839050912e-05, | |
| "loss": 1.2542, | |
| "mean_token_accuracy": 0.6906937116757035, | |
| "num_tokens": 39457882.0, | |
| "step": 7120 | |
| }, | |
| { | |
| "epoch": 0.6818885264636556, | |
| "grad_norm": 0.49605095386505127, | |
| "learning_rate": 4.4851156195935785e-05, | |
| "loss": 1.3266, | |
| "mean_token_accuracy": 0.673082504235208, | |
| "num_tokens": 39675712.0, | |
| "step": 7160 | |
| }, | |
| { | |
| "epoch": 0.6856979595723911, | |
| "grad_norm": 0.5613274574279785, | |
| "learning_rate": 4.479146804945053e-05, | |
| "loss": 1.3061, | |
| "mean_token_accuracy": 0.6837763454765081, | |
| "num_tokens": 39892449.0, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 0.6895073926811266, | |
| "grad_norm": 0.40411025285720825, | |
| "learning_rate": 4.473141509919966e-05, | |
| "loss": 1.2459, | |
| "mean_token_accuracy": 0.6935942692682147, | |
| "num_tokens": 40122187.0, | |
| "step": 7240 | |
| }, | |
| { | |
| "epoch": 0.6933168257898622, | |
| "grad_norm": 0.66608726978302, | |
| "learning_rate": 4.4670998500346795e-05, | |
| "loss": 1.263, | |
| "mean_token_accuracy": 0.6886698173359036, | |
| "num_tokens": 40339718.0, | |
| "step": 7280 | |
| }, | |
| { | |
| "epoch": 0.6971262588985977, | |
| "grad_norm": 0.5249150395393372, | |
| "learning_rate": 4.461021941505057e-05, | |
| "loss": 1.2077, | |
| "mean_token_accuracy": 0.6970062265172601, | |
| "num_tokens": 40568071.0, | |
| "step": 7320 | |
| }, | |
| { | |
| "epoch": 0.7009356920073332, | |
| "grad_norm": 0.5321863293647766, | |
| "learning_rate": 4.454907901244236e-05, | |
| "loss": 1.2908, | |
| "mean_token_accuracy": 0.6871679758653044, | |
| "num_tokens": 40781022.0, | |
| "step": 7360 | |
| }, | |
| { | |
| "epoch": 0.7047451251160687, | |
| "grad_norm": 0.5298981666564941, | |
| "learning_rate": 4.44875784686037e-05, | |
| "loss": 1.2256, | |
| "mean_token_accuracy": 0.6957620535045862, | |
| "num_tokens": 41015922.0, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 0.7085545582248042, | |
| "grad_norm": 0.6805555820465088, | |
| "learning_rate": 4.442571896654375e-05, | |
| "loss": 1.2059, | |
| "mean_token_accuracy": 0.6951308185234666, | |
| "num_tokens": 41247452.0, | |
| "step": 7440 | |
| }, | |
| { | |
| "epoch": 0.7123639913335397, | |
| "grad_norm": 0.3826749622821808, | |
| "learning_rate": 4.4363501696176494e-05, | |
| "loss": 1.2866, | |
| "mean_token_accuracy": 0.6792947178706527, | |
| "num_tokens": 41470415.0, | |
| "step": 7480 | |
| }, | |
| { | |
| "epoch": 0.7161734244422752, | |
| "grad_norm": 0.5363141298294067, | |
| "learning_rate": 4.4300927854297856e-05, | |
| "loss": 1.2691, | |
| "mean_token_accuracy": 0.682473830319941, | |
| "num_tokens": 41701000.0, | |
| "step": 7520 | |
| }, | |
| { | |
| "epoch": 0.7199828575510107, | |
| "grad_norm": 0.5626250505447388, | |
| "learning_rate": 4.423799864456266e-05, | |
| "loss": 1.3133, | |
| "mean_token_accuracy": 0.6788626465946436, | |
| "num_tokens": 41915333.0, | |
| "step": 7560 | |
| }, | |
| { | |
| "epoch": 0.7237922906597462, | |
| "grad_norm": 0.6899204850196838, | |
| "learning_rate": 4.417471527746152e-05, | |
| "loss": 1.365, | |
| "mean_token_accuracy": 0.6754604885354638, | |
| "num_tokens": 42139999.0, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 0.7276017237684818, | |
| "grad_norm": 0.5523748993873596, | |
| "learning_rate": 4.411107897029755e-05, | |
| "loss": 1.2776, | |
| "mean_token_accuracy": 0.6912444988265634, | |
| "num_tokens": 42367874.0, | |
| "step": 7640 | |
| }, | |
| { | |
| "epoch": 0.7314111568772173, | |
| "grad_norm": 0.5411382913589478, | |
| "learning_rate": 4.404709094716289e-05, | |
| "loss": 1.2326, | |
| "mean_token_accuracy": 0.6946828311309219, | |
| "num_tokens": 42594804.0, | |
| "step": 7680 | |
| }, | |
| { | |
| "epoch": 0.7352205899859527, | |
| "grad_norm": 0.6533775329589844, | |
| "learning_rate": 4.398275243891522e-05, | |
| "loss": 1.2828, | |
| "mean_token_accuracy": 0.6842706995084882, | |
| "num_tokens": 42814558.0, | |
| "step": 7720 | |
| }, | |
| { | |
| "epoch": 0.7390300230946882, | |
| "grad_norm": 0.3408315181732178, | |
| "learning_rate": 4.391806468315408e-05, | |
| "loss": 1.2614, | |
| "mean_token_accuracy": 0.690892388857901, | |
| "num_tokens": 43040642.0, | |
| "step": 7760 | |
| }, | |
| { | |
| "epoch": 0.7428394562034237, | |
| "grad_norm": 0.4586963355541229, | |
| "learning_rate": 4.385302892419702e-05, | |
| "loss": 1.2984, | |
| "mean_token_accuracy": 0.6800136685371398, | |
| "num_tokens": 43259728.0, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 0.7466488893121592, | |
| "grad_norm": 0.6477558016777039, | |
| "learning_rate": 4.37876464130557e-05, | |
| "loss": 1.3249, | |
| "mean_token_accuracy": 0.6777775203809142, | |
| "num_tokens": 43467264.0, | |
| "step": 7840 | |
| }, | |
| { | |
| "epoch": 0.7504583224208947, | |
| "grad_norm": 0.4374445080757141, | |
| "learning_rate": 4.3721918407411845e-05, | |
| "loss": 1.2729, | |
| "mean_token_accuracy": 0.689405850879848, | |
| "num_tokens": 43679068.0, | |
| "step": 7880 | |
| }, | |
| { | |
| "epoch": 0.7542677555296302, | |
| "grad_norm": 0.5325660109519958, | |
| "learning_rate": 4.3655846171592994e-05, | |
| "loss": 1.2863, | |
| "mean_token_accuracy": 0.6884377462789416, | |
| "num_tokens": 43899283.0, | |
| "step": 7920 | |
| }, | |
| { | |
| "epoch": 0.7580771886383657, | |
| "grad_norm": 0.7073720097541809, | |
| "learning_rate": 4.358943097654823e-05, | |
| "loss": 1.245, | |
| "mean_token_accuracy": 0.6904063617810607, | |
| "num_tokens": 44113559.0, | |
| "step": 7960 | |
| }, | |
| { | |
| "epoch": 0.7618866217471013, | |
| "grad_norm": 0.44697853922843933, | |
| "learning_rate": 4.3522674099823705e-05, | |
| "loss": 1.2699, | |
| "mean_token_accuracy": 0.6843698143959045, | |
| "num_tokens": 44334374.0, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.7656960548558368, | |
| "grad_norm": 0.4306088984012604, | |
| "learning_rate": 4.345557682553807e-05, | |
| "loss": 1.2319, | |
| "step": 8040 | |
| }, | |
| { | |
| "epoch": 0.7656960548558368, | |
| "eval_mean_token_accuracy": 0.6363147346070971, | |
| "eval_num_tokens": 44575460.0, | |
| "eval_test_loss": 1.7359126806259155, | |
| "eval_test_runtime": 95.9212, | |
| "eval_test_samples_per_second": 20.757, | |
| "eval_test_steps_per_second": 10.384, | |
| "step": 8040 | |
| }, | |
| { | |
| "epoch": 0.7695054879645723, | |
| "grad_norm": 0.6170753836631775, | |
| "learning_rate": 4.3388140444357795e-05, | |
| "loss": 1.2328, | |
| "mean_token_accuracy": 0.6931531462818384, | |
| "num_tokens": 44806038.0, | |
| "step": 8080 | |
| }, | |
| { | |
| "epoch": 0.7733149210733078, | |
| "grad_norm": 0.7038352489471436, | |
| "learning_rate": 4.332036625347232e-05, | |
| "loss": 1.2929, | |
| "mean_token_accuracy": 0.6844880169257521, | |
| "num_tokens": 45016584.0, | |
| "step": 8120 | |
| }, | |
| { | |
| "epoch": 0.7771243541820433, | |
| "grad_norm": 0.4224265515804291, | |
| "learning_rate": 4.325225555656911e-05, | |
| "loss": 1.2634, | |
| "mean_token_accuracy": 0.6930087611079216, | |
| "num_tokens": 45246046.0, | |
| "step": 8160 | |
| }, | |
| { | |
| "epoch": 0.7809337872907788, | |
| "grad_norm": 0.46587294340133667, | |
| "learning_rate": 4.3183809663808556e-05, | |
| "loss": 1.2605, | |
| "mean_token_accuracy": 0.687124558724463, | |
| "num_tokens": 45464284.0, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 0.7847432203995143, | |
| "grad_norm": 0.5252248644828796, | |
| "learning_rate": 4.311502989179882e-05, | |
| "loss": 1.2728, | |
| "mean_token_accuracy": 0.6883155029267073, | |
| "num_tokens": 45684249.0, | |
| "step": 8240 | |
| }, | |
| { | |
| "epoch": 0.7885526535082498, | |
| "grad_norm": 0.4695100486278534, | |
| "learning_rate": 4.304591756357046e-05, | |
| "loss": 1.27, | |
| "mean_token_accuracy": 0.6879516759887337, | |
| "num_tokens": 45919177.0, | |
| "step": 8280 | |
| }, | |
| { | |
| "epoch": 0.7923620866169853, | |
| "grad_norm": 0.46411824226379395, | |
| "learning_rate": 4.297647400855103e-05, | |
| "loss": 1.3028, | |
| "mean_token_accuracy": 0.683055117353797, | |
| "num_tokens": 46131789.0, | |
| "step": 8320 | |
| }, | |
| { | |
| "epoch": 0.7961715197257209, | |
| "grad_norm": 0.7392385601997375, | |
| "learning_rate": 4.290670056253944e-05, | |
| "loss": 1.173, | |
| "mean_token_accuracy": 0.6985200975090265, | |
| "num_tokens": 46348383.0, | |
| "step": 8360 | |
| }, | |
| { | |
| "epoch": 0.7999809528344564, | |
| "grad_norm": 0.5996558666229248, | |
| "learning_rate": 4.283659856768036e-05, | |
| "loss": 1.1934, | |
| "mean_token_accuracy": 0.6913962122052908, | |
| "num_tokens": 46572321.0, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 0.8037903859431919, | |
| "grad_norm": 0.6277273297309875, | |
| "learning_rate": 4.276616937243828e-05, | |
| "loss": 1.2401, | |
| "mean_token_accuracy": 0.6883677888661623, | |
| "num_tokens": 46798263.0, | |
| "step": 8440 | |
| }, | |
| { | |
| "epoch": 0.8075998190519273, | |
| "grad_norm": 0.7397225499153137, | |
| "learning_rate": 4.2695414331571673e-05, | |
| "loss": 1.3177, | |
| "mean_token_accuracy": 0.6755096849054099, | |
| "num_tokens": 47017444.0, | |
| "step": 8480 | |
| }, | |
| { | |
| "epoch": 0.8114092521606628, | |
| "grad_norm": 0.650918185710907, | |
| "learning_rate": 4.2624334806106894e-05, | |
| "loss": 1.3164, | |
| "mean_token_accuracy": 0.6786608980968595, | |
| "num_tokens": 47230158.0, | |
| "step": 8520 | |
| }, | |
| { | |
| "epoch": 0.8152186852693983, | |
| "grad_norm": 0.6894013285636902, | |
| "learning_rate": 4.255293216331197e-05, | |
| "loss": 1.2527, | |
| "mean_token_accuracy": 0.6907643361017108, | |
| "num_tokens": 47453276.0, | |
| "step": 8560 | |
| }, | |
| { | |
| "epoch": 0.8190281183781338, | |
| "grad_norm": 0.6085829138755798, | |
| "learning_rate": 4.2481207776670396e-05, | |
| "loss": 1.2798, | |
| "mean_token_accuracy": 0.6841305760666728, | |
| "num_tokens": 47662402.0, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 0.8228375514868693, | |
| "grad_norm": 0.47271421551704407, | |
| "learning_rate": 4.24091630258546e-05, | |
| "loss": 1.2038, | |
| "mean_token_accuracy": 0.6984878290444613, | |
| "num_tokens": 47889095.0, | |
| "step": 8640 | |
| }, | |
| { | |
| "epoch": 0.8266469845956048, | |
| "grad_norm": 0.6806793212890625, | |
| "learning_rate": 4.2336799296699454e-05, | |
| "loss": 1.1881, | |
| "mean_token_accuracy": 0.7019338620826602, | |
| "num_tokens": 48117494.0, | |
| "step": 8680 | |
| }, | |
| { | |
| "epoch": 0.8304564177043404, | |
| "grad_norm": 0.5494069457054138, | |
| "learning_rate": 4.2264117981175665e-05, | |
| "loss": 1.2331, | |
| "mean_token_accuracy": 0.6901240289211273, | |
| "num_tokens": 48340935.0, | |
| "step": 8720 | |
| }, | |
| { | |
| "epoch": 0.8342658508130759, | |
| "grad_norm": 0.6391497254371643, | |
| "learning_rate": 4.21911204773629e-05, | |
| "loss": 1.2149, | |
| "mean_token_accuracy": 0.6961538307368755, | |
| "num_tokens": 48573668.0, | |
| "step": 8760 | |
| }, | |
| { | |
| "epoch": 0.8380752839218114, | |
| "grad_norm": 0.3758852481842041, | |
| "learning_rate": 4.211780818942297e-05, | |
| "loss": 1.251, | |
| "mean_token_accuracy": 0.6919752093032002, | |
| "num_tokens": 48795852.0, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 0.8418847170305469, | |
| "grad_norm": 0.5446637868881226, | |
| "learning_rate": 4.2044182527572795e-05, | |
| "loss": 1.3, | |
| "mean_token_accuracy": 0.6852457968518137, | |
| "num_tokens": 49032650.0, | |
| "step": 8840 | |
| }, | |
| { | |
| "epoch": 0.8456941501392824, | |
| "grad_norm": 0.3522646427154541, | |
| "learning_rate": 4.197024490805727e-05, | |
| "loss": 1.2702, | |
| "mean_token_accuracy": 0.6935782097280025, | |
| "num_tokens": 49250248.0, | |
| "step": 8880 | |
| }, | |
| { | |
| "epoch": 0.8495035832480179, | |
| "grad_norm": 0.652208149433136, | |
| "learning_rate": 4.189599675312204e-05, | |
| "loss": 1.2844, | |
| "mean_token_accuracy": 0.6847639823332429, | |
| "num_tokens": 49476266.0, | |
| "step": 8920 | |
| }, | |
| { | |
| "epoch": 0.8533130163567534, | |
| "grad_norm": 0.41794517636299133, | |
| "learning_rate": 4.182143949098612e-05, | |
| "loss": 1.2659, | |
| "mean_token_accuracy": 0.6905384896323085, | |
| "num_tokens": 49700173.0, | |
| "step": 8960 | |
| }, | |
| { | |
| "epoch": 0.8571224494654889, | |
| "grad_norm": 0.532646656036377, | |
| "learning_rate": 4.1746574555814455e-05, | |
| "loss": 1.282, | |
| "mean_token_accuracy": 0.6890167951583862, | |
| "num_tokens": 49930863.0, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.8609318825742244, | |
| "grad_norm": 0.5750353932380676, | |
| "learning_rate": 4.1671403387690284e-05, | |
| "loss": 1.1884, | |
| "mean_token_accuracy": 0.7017395876348018, | |
| "num_tokens": 50166067.0, | |
| "step": 9040 | |
| }, | |
| { | |
| "epoch": 0.8614080617128164, | |
| "eval_mean_token_accuracy": 0.6381066715621565, | |
| "eval_num_tokens": 50195310.0, | |
| "eval_test_loss": 1.723710060119629, | |
| "eval_test_runtime": 96.0763, | |
| "eval_test_samples_per_second": 20.723, | |
| "eval_test_steps_per_second": 10.367, | |
| "step": 9045 | |
| } | |
| ], | |
| "logging_steps": 40, | |
| "max_steps": 30161, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 3016, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.1928985580997181e+18, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |