| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 804, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 1.1252599358558655, |
| "epoch": 0.0037313432835820895, |
| "grad_norm": 1.5272046327590942, |
| "learning_rate": 0.0002, |
| "loss": 2.4594485759735107, |
| "mean_token_accuracy": 0.5409960895776749, |
| "num_tokens": 16356.0, |
| "step": 1 |
| }, |
| { |
| "entropy": 1.2122794389724731, |
| "epoch": 0.007462686567164179, |
| "grad_norm": 1.4455077648162842, |
| "learning_rate": 0.0002, |
| "loss": 2.145378828048706, |
| "mean_token_accuracy": 0.5760411769151688, |
| "num_tokens": 32558.0, |
| "step": 2 |
| }, |
| { |
| "entropy": 1.3942747116088867, |
| "epoch": 0.011194029850746268, |
| "grad_norm": 1.157368779182434, |
| "learning_rate": 0.0002, |
| "loss": 1.7391576766967773, |
| "mean_token_accuracy": 0.5944286286830902, |
| "num_tokens": 48726.0, |
| "step": 3 |
| }, |
| { |
| "entropy": 1.3707774877548218, |
| "epoch": 0.014925373134328358, |
| "grad_norm": 0.9394316673278809, |
| "learning_rate": 0.0002, |
| "loss": 1.4157556295394897, |
| "mean_token_accuracy": 0.6357247680425644, |
| "num_tokens": 65120.0, |
| "step": 4 |
| }, |
| { |
| "entropy": 1.3594374060630798, |
| "epoch": 0.018656716417910446, |
| "grad_norm": 1.1642231941223145, |
| "learning_rate": 0.0002, |
| "loss": 1.2978066205978394, |
| "mean_token_accuracy": 0.6369745284318924, |
| "num_tokens": 81608.0, |
| "step": 5 |
| }, |
| { |
| "entropy": 1.2569016814231873, |
| "epoch": 0.022388059701492536, |
| "grad_norm": 0.66248619556427, |
| "learning_rate": 0.0002, |
| "loss": 1.1587367057800293, |
| "mean_token_accuracy": 0.6628502756357193, |
| "num_tokens": 97998.0, |
| "step": 6 |
| }, |
| { |
| "entropy": 1.1753060221672058, |
| "epoch": 0.026119402985074626, |
| "grad_norm": 0.4127490520477295, |
| "learning_rate": 0.0002, |
| "loss": 1.0793308019638062, |
| "mean_token_accuracy": 0.6721777319908142, |
| "num_tokens": 114263.0, |
| "step": 7 |
| }, |
| { |
| "entropy": 1.0782537758350372, |
| "epoch": 0.029850746268656716, |
| "grad_norm": 0.4080350995063782, |
| "learning_rate": 0.0002, |
| "loss": 1.0125200748443604, |
| "mean_token_accuracy": 0.6795568466186523, |
| "num_tokens": 130561.0, |
| "step": 8 |
| }, |
| { |
| "entropy": 0.9824364632368088, |
| "epoch": 0.033582089552238806, |
| "grad_norm": 0.6127004027366638, |
| "learning_rate": 0.0002, |
| "loss": 0.9604068398475647, |
| "mean_token_accuracy": 0.6915741860866547, |
| "num_tokens": 146920.0, |
| "step": 9 |
| }, |
| { |
| "entropy": 0.9657841473817825, |
| "epoch": 0.03731343283582089, |
| "grad_norm": 0.4609244763851166, |
| "learning_rate": 0.0002, |
| "loss": 0.8914750218391418, |
| "mean_token_accuracy": 0.7017619609832764, |
| "num_tokens": 163146.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 0.966868206858635, |
| "epoch": 0.041044776119402986, |
| "grad_norm": 0.5290998816490173, |
| "learning_rate": 0.0002, |
| "loss": 0.8461531400680542, |
| "mean_token_accuracy": 0.7099837809801102, |
| "num_tokens": 179554.0, |
| "step": 11 |
| }, |
| { |
| "entropy": 0.884843111038208, |
| "epoch": 0.04477611940298507, |
| "grad_norm": 0.720565915107727, |
| "learning_rate": 0.0002, |
| "loss": 0.7980917692184448, |
| "mean_token_accuracy": 0.7177292704582214, |
| "num_tokens": 195815.0, |
| "step": 12 |
| }, |
| { |
| "entropy": 0.7850211411714554, |
| "epoch": 0.048507462686567165, |
| "grad_norm": 0.44593071937561035, |
| "learning_rate": 0.0002, |
| "loss": 0.7502663731575012, |
| "mean_token_accuracy": 0.7325886785984039, |
| "num_tokens": 211880.0, |
| "step": 13 |
| }, |
| { |
| "entropy": 0.7349942475557327, |
| "epoch": 0.05223880597014925, |
| "grad_norm": 0.36987370252609253, |
| "learning_rate": 0.0002, |
| "loss": 0.72371906042099, |
| "mean_token_accuracy": 0.7311157435178757, |
| "num_tokens": 228155.0, |
| "step": 14 |
| }, |
| { |
| "entropy": 0.7018705755472183, |
| "epoch": 0.055970149253731345, |
| "grad_norm": 0.36635148525238037, |
| "learning_rate": 0.0002, |
| "loss": 0.7155212759971619, |
| "mean_token_accuracy": 0.7326428145170212, |
| "num_tokens": 244542.0, |
| "step": 15 |
| }, |
| { |
| "entropy": 0.672577753663063, |
| "epoch": 0.05970149253731343, |
| "grad_norm": 0.35952258110046387, |
| "learning_rate": 0.0002, |
| "loss": 0.6820313930511475, |
| "mean_token_accuracy": 0.7404341697692871, |
| "num_tokens": 261048.0, |
| "step": 16 |
| }, |
| { |
| "entropy": 0.6772939264774323, |
| "epoch": 0.06343283582089553, |
| "grad_norm": 0.33045217394828796, |
| "learning_rate": 0.0002, |
| "loss": 0.6607145667076111, |
| "mean_token_accuracy": 0.7477577179670334, |
| "num_tokens": 277687.0, |
| "step": 17 |
| }, |
| { |
| "entropy": 0.6678493618965149, |
| "epoch": 0.06716417910447761, |
| "grad_norm": 0.33739686012268066, |
| "learning_rate": 0.0002, |
| "loss": 0.6409961581230164, |
| "mean_token_accuracy": 0.7541278004646301, |
| "num_tokens": 293981.0, |
| "step": 18 |
| }, |
| { |
| "entropy": 0.6659611165523529, |
| "epoch": 0.0708955223880597, |
| "grad_norm": 0.3104625642299652, |
| "learning_rate": 0.0002, |
| "loss": 0.6443870663642883, |
| "mean_token_accuracy": 0.7474546879529953, |
| "num_tokens": 310476.0, |
| "step": 19 |
| }, |
| { |
| "entropy": 0.6284213960170746, |
| "epoch": 0.07462686567164178, |
| "grad_norm": 0.30897003412246704, |
| "learning_rate": 0.0002, |
| "loss": 0.6230261921882629, |
| "mean_token_accuracy": 0.756799504160881, |
| "num_tokens": 326572.0, |
| "step": 20 |
| }, |
| { |
| "entropy": 0.6472804546356201, |
| "epoch": 0.07835820895522388, |
| "grad_norm": 0.30225658416748047, |
| "learning_rate": 0.0002, |
| "loss": 0.6453258991241455, |
| "mean_token_accuracy": 0.7508129775524139, |
| "num_tokens": 342839.0, |
| "step": 21 |
| }, |
| { |
| "entropy": 0.6091666221618652, |
| "epoch": 0.08208955223880597, |
| "grad_norm": 0.29752060770988464, |
| "learning_rate": 0.0002, |
| "loss": 0.6133284568786621, |
| "mean_token_accuracy": 0.7591582834720612, |
| "num_tokens": 359190.0, |
| "step": 22 |
| }, |
| { |
| "entropy": 0.5776377767324448, |
| "epoch": 0.08582089552238806, |
| "grad_norm": 0.2850731313228607, |
| "learning_rate": 0.0002, |
| "loss": 0.5787464380264282, |
| "mean_token_accuracy": 0.7750633060932159, |
| "num_tokens": 375488.0, |
| "step": 23 |
| }, |
| { |
| "entropy": 0.595000296831131, |
| "epoch": 0.08955223880597014, |
| "grad_norm": 0.2667350172996521, |
| "learning_rate": 0.0002, |
| "loss": 0.5960222482681274, |
| "mean_token_accuracy": 0.766336128115654, |
| "num_tokens": 391795.0, |
| "step": 24 |
| }, |
| { |
| "entropy": 0.6175636053085327, |
| "epoch": 0.09328358208955224, |
| "grad_norm": 0.2455701231956482, |
| "learning_rate": 0.0002, |
| "loss": 0.6085698008537292, |
| "mean_token_accuracy": 0.7611224502325058, |
| "num_tokens": 408117.0, |
| "step": 25 |
| }, |
| { |
| "entropy": 0.6171998977661133, |
| "epoch": 0.09701492537313433, |
| "grad_norm": 0.2530118525028229, |
| "learning_rate": 0.0002, |
| "loss": 0.6029692888259888, |
| "mean_token_accuracy": 0.7604100853204727, |
| "num_tokens": 424406.0, |
| "step": 26 |
| }, |
| { |
| "entropy": 0.5962555855512619, |
| "epoch": 0.10074626865671642, |
| "grad_norm": 0.24561311304569244, |
| "learning_rate": 0.0002, |
| "loss": 0.5802175402641296, |
| "mean_token_accuracy": 0.7689433097839355, |
| "num_tokens": 440903.0, |
| "step": 27 |
| }, |
| { |
| "entropy": 0.5888170152902603, |
| "epoch": 0.1044776119402985, |
| "grad_norm": 0.25386282801628113, |
| "learning_rate": 0.0002, |
| "loss": 0.5859516859054565, |
| "mean_token_accuracy": 0.7674518972635269, |
| "num_tokens": 457200.0, |
| "step": 28 |
| }, |
| { |
| "entropy": 0.5723881423473358, |
| "epoch": 0.10820895522388059, |
| "grad_norm": 0.27193617820739746, |
| "learning_rate": 0.0002, |
| "loss": 0.5771776437759399, |
| "mean_token_accuracy": 0.7725424915552139, |
| "num_tokens": 473544.0, |
| "step": 29 |
| }, |
| { |
| "entropy": 0.5730441808700562, |
| "epoch": 0.11194029850746269, |
| "grad_norm": 0.2024512141942978, |
| "learning_rate": 0.0002, |
| "loss": 0.578813374042511, |
| "mean_token_accuracy": 0.7728265821933746, |
| "num_tokens": 489999.0, |
| "step": 30 |
| }, |
| { |
| "entropy": 0.5549605935811996, |
| "epoch": 0.11567164179104478, |
| "grad_norm": 0.22189044952392578, |
| "learning_rate": 0.0002, |
| "loss": 0.5619395971298218, |
| "mean_token_accuracy": 0.7789465039968491, |
| "num_tokens": 506495.0, |
| "step": 31 |
| }, |
| { |
| "entropy": 0.5610107928514481, |
| "epoch": 0.11940298507462686, |
| "grad_norm": 0.2719445824623108, |
| "learning_rate": 0.0002, |
| "loss": 0.5629929900169373, |
| "mean_token_accuracy": 0.7746118456125259, |
| "num_tokens": 522631.0, |
| "step": 32 |
| }, |
| { |
| "entropy": 0.5653866827487946, |
| "epoch": 0.12313432835820895, |
| "grad_norm": 0.23799815773963928, |
| "learning_rate": 0.0002, |
| "loss": 0.5669984221458435, |
| "mean_token_accuracy": 0.7757989466190338, |
| "num_tokens": 538947.0, |
| "step": 33 |
| }, |
| { |
| "entropy": 0.5670903027057648, |
| "epoch": 0.12686567164179105, |
| "grad_norm": 0.20069265365600586, |
| "learning_rate": 0.0002, |
| "loss": 0.563256025314331, |
| "mean_token_accuracy": 0.7756769955158234, |
| "num_tokens": 555387.0, |
| "step": 34 |
| }, |
| { |
| "entropy": 0.5583736747503281, |
| "epoch": 0.13059701492537312, |
| "grad_norm": 0.22184117138385773, |
| "learning_rate": 0.0002, |
| "loss": 0.5706378221511841, |
| "mean_token_accuracy": 0.7733749896287918, |
| "num_tokens": 571634.0, |
| "step": 35 |
| }, |
| { |
| "entropy": 0.5658847540616989, |
| "epoch": 0.13432835820895522, |
| "grad_norm": 0.224237859249115, |
| "learning_rate": 0.0002, |
| "loss": 0.5681460499763489, |
| "mean_token_accuracy": 0.7719594538211823, |
| "num_tokens": 587820.0, |
| "step": 36 |
| }, |
| { |
| "entropy": 0.5816620290279388, |
| "epoch": 0.13805970149253732, |
| "grad_norm": 0.1926281452178955, |
| "learning_rate": 0.0002, |
| "loss": 0.5734426975250244, |
| "mean_token_accuracy": 0.7705242782831192, |
| "num_tokens": 604217.0, |
| "step": 37 |
| }, |
| { |
| "entropy": 0.5649492144584656, |
| "epoch": 0.1417910447761194, |
| "grad_norm": 0.183609277009964, |
| "learning_rate": 0.0002, |
| "loss": 0.5558274388313293, |
| "mean_token_accuracy": 0.7762331962585449, |
| "num_tokens": 620577.0, |
| "step": 38 |
| }, |
| { |
| "entropy": 0.5601995438337326, |
| "epoch": 0.1455223880597015, |
| "grad_norm": 0.202256977558136, |
| "learning_rate": 0.0002, |
| "loss": 0.5571293234825134, |
| "mean_token_accuracy": 0.7767272889614105, |
| "num_tokens": 637054.0, |
| "step": 39 |
| }, |
| { |
| "entropy": 0.5497418493032455, |
| "epoch": 0.14925373134328357, |
| "grad_norm": 0.1708270013332367, |
| "learning_rate": 0.0002, |
| "loss": 0.5532903671264648, |
| "mean_token_accuracy": 0.7797733545303345, |
| "num_tokens": 653436.0, |
| "step": 40 |
| }, |
| { |
| "entropy": 0.5556538105010986, |
| "epoch": 0.15298507462686567, |
| "grad_norm": 0.20446668565273285, |
| "learning_rate": 0.0002, |
| "loss": 0.5670064687728882, |
| "mean_token_accuracy": 0.775859147310257, |
| "num_tokens": 669638.0, |
| "step": 41 |
| }, |
| { |
| "entropy": 0.56488898396492, |
| "epoch": 0.15671641791044777, |
| "grad_norm": 0.24446451663970947, |
| "learning_rate": 0.0002, |
| "loss": 0.5717874765396118, |
| "mean_token_accuracy": 0.7694851458072662, |
| "num_tokens": 685904.0, |
| "step": 42 |
| }, |
| { |
| "entropy": 0.5678331106901169, |
| "epoch": 0.16044776119402984, |
| "grad_norm": 0.16702726483345032, |
| "learning_rate": 0.0002, |
| "loss": 0.5660833120346069, |
| "mean_token_accuracy": 0.772446408867836, |
| "num_tokens": 702392.0, |
| "step": 43 |
| }, |
| { |
| "entropy": 0.5622523128986359, |
| "epoch": 0.16417910447761194, |
| "grad_norm": 0.22485850751399994, |
| "learning_rate": 0.0002, |
| "loss": 0.5579752922058105, |
| "mean_token_accuracy": 0.7759791761636734, |
| "num_tokens": 718676.0, |
| "step": 44 |
| }, |
| { |
| "entropy": 0.5567733347415924, |
| "epoch": 0.16791044776119404, |
| "grad_norm": 0.20440097153186798, |
| "learning_rate": 0.0002, |
| "loss": 0.5456885099411011, |
| "mean_token_accuracy": 0.7794095277786255, |
| "num_tokens": 734725.0, |
| "step": 45 |
| }, |
| { |
| "entropy": 0.5643369555473328, |
| "epoch": 0.17164179104477612, |
| "grad_norm": 0.19125841557979584, |
| "learning_rate": 0.0002, |
| "loss": 0.5527964234352112, |
| "mean_token_accuracy": 0.7792517989873886, |
| "num_tokens": 751201.0, |
| "step": 46 |
| }, |
| { |
| "entropy": 0.5354443341493607, |
| "epoch": 0.17537313432835822, |
| "grad_norm": 0.20153310894966125, |
| "learning_rate": 0.0002, |
| "loss": 0.5336775779724121, |
| "mean_token_accuracy": 0.7870942652225494, |
| "num_tokens": 767416.0, |
| "step": 47 |
| }, |
| { |
| "entropy": 0.55471371114254, |
| "epoch": 0.1791044776119403, |
| "grad_norm": 0.14250335097312927, |
| "learning_rate": 0.0002, |
| "loss": 0.5625114440917969, |
| "mean_token_accuracy": 0.7742648422718048, |
| "num_tokens": 783611.0, |
| "step": 48 |
| }, |
| { |
| "entropy": 0.5457955002784729, |
| "epoch": 0.1828358208955224, |
| "grad_norm": 0.19951990246772766, |
| "learning_rate": 0.0002, |
| "loss": 0.5628947615623474, |
| "mean_token_accuracy": 0.7743187099695206, |
| "num_tokens": 799889.0, |
| "step": 49 |
| }, |
| { |
| "entropy": 0.5597822219133377, |
| "epoch": 0.1865671641791045, |
| "grad_norm": 0.20659729838371277, |
| "learning_rate": 0.0002, |
| "loss": 0.568906307220459, |
| "mean_token_accuracy": 0.7727647572755814, |
| "num_tokens": 816273.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 0.5573585480451584, |
| "epoch": 0.19029850746268656, |
| "grad_norm": 0.1831238865852356, |
| "learning_rate": 0.0002, |
| "loss": 0.5604618787765503, |
| "mean_token_accuracy": 0.7756351828575134, |
| "num_tokens": 832733.0, |
| "step": 51 |
| }, |
| { |
| "entropy": 0.5423409044742584, |
| "epoch": 0.19402985074626866, |
| "grad_norm": 0.14581772685050964, |
| "learning_rate": 0.0002, |
| "loss": 0.5418893098831177, |
| "mean_token_accuracy": 0.7838970720767975, |
| "num_tokens": 848916.0, |
| "step": 52 |
| }, |
| { |
| "entropy": 0.5627928078174591, |
| "epoch": 0.19776119402985073, |
| "grad_norm": 0.16460320353507996, |
| "learning_rate": 0.0002, |
| "loss": 0.5579115748405457, |
| "mean_token_accuracy": 0.7746649384498596, |
| "num_tokens": 865489.0, |
| "step": 53 |
| }, |
| { |
| "entropy": 0.5563036799430847, |
| "epoch": 0.20149253731343283, |
| "grad_norm": 0.19165952503681183, |
| "learning_rate": 0.0002, |
| "loss": 0.5476850271224976, |
| "mean_token_accuracy": 0.7774810045957565, |
| "num_tokens": 881736.0, |
| "step": 54 |
| }, |
| { |
| "entropy": 0.5470448881387711, |
| "epoch": 0.20522388059701493, |
| "grad_norm": 0.1646890491247177, |
| "learning_rate": 0.0002, |
| "loss": 0.5458868145942688, |
| "mean_token_accuracy": 0.7782557755708694, |
| "num_tokens": 898517.0, |
| "step": 55 |
| }, |
| { |
| "entropy": 0.5484187304973602, |
| "epoch": 0.208955223880597, |
| "grad_norm": 0.1645505279302597, |
| "learning_rate": 0.0002, |
| "loss": 0.5549262166023254, |
| "mean_token_accuracy": 0.7769160270690918, |
| "num_tokens": 914935.0, |
| "step": 56 |
| }, |
| { |
| "entropy": 0.5458521693944931, |
| "epoch": 0.2126865671641791, |
| "grad_norm": 0.1692931056022644, |
| "learning_rate": 0.0002, |
| "loss": 0.5458835959434509, |
| "mean_token_accuracy": 0.7802194207906723, |
| "num_tokens": 931146.0, |
| "step": 57 |
| }, |
| { |
| "entropy": 0.5500072538852692, |
| "epoch": 0.21641791044776118, |
| "grad_norm": 0.16163933277130127, |
| "learning_rate": 0.0002, |
| "loss": 0.5568903088569641, |
| "mean_token_accuracy": 0.7765295654535294, |
| "num_tokens": 947337.0, |
| "step": 58 |
| }, |
| { |
| "entropy": 0.5492704510688782, |
| "epoch": 0.22014925373134328, |
| "grad_norm": 0.17235516011714935, |
| "learning_rate": 0.0002, |
| "loss": 0.5551934242248535, |
| "mean_token_accuracy": 0.776619091629982, |
| "num_tokens": 963641.0, |
| "step": 59 |
| }, |
| { |
| "entropy": 0.5444371253252029, |
| "epoch": 0.22388059701492538, |
| "grad_norm": 0.14536716043949127, |
| "learning_rate": 0.0002, |
| "loss": 0.5435407161712646, |
| "mean_token_accuracy": 0.7797929793596268, |
| "num_tokens": 979911.0, |
| "step": 60 |
| }, |
| { |
| "entropy": 0.5620079189538956, |
| "epoch": 0.22761194029850745, |
| "grad_norm": 0.13450083136558533, |
| "learning_rate": 0.0002, |
| "loss": 0.5577633380889893, |
| "mean_token_accuracy": 0.7778456509113312, |
| "num_tokens": 995908.0, |
| "step": 61 |
| }, |
| { |
| "entropy": 0.5657089501619339, |
| "epoch": 0.23134328358208955, |
| "grad_norm": 0.15202735364437103, |
| "learning_rate": 0.0002, |
| "loss": 0.5610611438751221, |
| "mean_token_accuracy": 0.7757387459278107, |
| "num_tokens": 1012180.0, |
| "step": 62 |
| }, |
| { |
| "entropy": 0.5450915098190308, |
| "epoch": 0.23507462686567165, |
| "grad_norm": 0.15015734732151031, |
| "learning_rate": 0.0002, |
| "loss": 0.5425537824630737, |
| "mean_token_accuracy": 0.7805133759975433, |
| "num_tokens": 1028512.0, |
| "step": 63 |
| }, |
| { |
| "entropy": 0.5538493543863297, |
| "epoch": 0.23880597014925373, |
| "grad_norm": 0.1517547070980072, |
| "learning_rate": 0.0002, |
| "loss": 0.556670606136322, |
| "mean_token_accuracy": 0.7770132273435593, |
| "num_tokens": 1044687.0, |
| "step": 64 |
| }, |
| { |
| "entropy": 0.5587822049856186, |
| "epoch": 0.24253731343283583, |
| "grad_norm": 0.19014914333820343, |
| "learning_rate": 0.0002, |
| "loss": 0.5700101852416992, |
| "mean_token_accuracy": 0.772544339299202, |
| "num_tokens": 1061062.0, |
| "step": 65 |
| }, |
| { |
| "entropy": 0.5355288237333298, |
| "epoch": 0.2462686567164179, |
| "grad_norm": 0.1184922531247139, |
| "learning_rate": 0.0002, |
| "loss": 0.5346988439559937, |
| "mean_token_accuracy": 0.7839833199977875, |
| "num_tokens": 1077509.0, |
| "step": 66 |
| }, |
| { |
| "entropy": 0.5530640184879303, |
| "epoch": 0.25, |
| "grad_norm": 0.13407526910305023, |
| "learning_rate": 0.0002, |
| "loss": 0.5536749958992004, |
| "mean_token_accuracy": 0.7773692905902863, |
| "num_tokens": 1093638.0, |
| "step": 67 |
| }, |
| { |
| "entropy": 0.5652015656232834, |
| "epoch": 0.2537313432835821, |
| "grad_norm": 0.153024822473526, |
| "learning_rate": 0.0002, |
| "loss": 0.5643336176872253, |
| "mean_token_accuracy": 0.7709111124277115, |
| "num_tokens": 1109853.0, |
| "step": 68 |
| }, |
| { |
| "entropy": 0.5639313161373138, |
| "epoch": 0.2574626865671642, |
| "grad_norm": 0.12071388214826584, |
| "learning_rate": 0.0002, |
| "loss": 0.5607717633247375, |
| "mean_token_accuracy": 0.7756941467523575, |
| "num_tokens": 1126313.0, |
| "step": 69 |
| }, |
| { |
| "entropy": 0.5238342434167862, |
| "epoch": 0.26119402985074625, |
| "grad_norm": 0.1702871322631836, |
| "learning_rate": 0.0002, |
| "loss": 0.5316657423973083, |
| "mean_token_accuracy": 0.7838077694177628, |
| "num_tokens": 1142735.0, |
| "step": 70 |
| }, |
| { |
| "entropy": 0.5565781593322754, |
| "epoch": 0.26492537313432835, |
| "grad_norm": 0.149235799908638, |
| "learning_rate": 0.0002, |
| "loss": 0.5614414215087891, |
| "mean_token_accuracy": 0.773883730173111, |
| "num_tokens": 1158984.0, |
| "step": 71 |
| }, |
| { |
| "entropy": 0.5476623624563217, |
| "epoch": 0.26865671641791045, |
| "grad_norm": 0.1385108083486557, |
| "learning_rate": 0.0002, |
| "loss": 0.5471611618995667, |
| "mean_token_accuracy": 0.7764377444982529, |
| "num_tokens": 1175464.0, |
| "step": 72 |
| }, |
| { |
| "entropy": 0.5478420704603195, |
| "epoch": 0.27238805970149255, |
| "grad_norm": 0.15060606598854065, |
| "learning_rate": 0.0002, |
| "loss": 0.5479435324668884, |
| "mean_token_accuracy": 0.780957043170929, |
| "num_tokens": 1191692.0, |
| "step": 73 |
| }, |
| { |
| "entropy": 0.5595236271619797, |
| "epoch": 0.27611940298507465, |
| "grad_norm": 0.14150963723659515, |
| "learning_rate": 0.0002, |
| "loss": 0.5619409084320068, |
| "mean_token_accuracy": 0.7719392776489258, |
| "num_tokens": 1208094.0, |
| "step": 74 |
| }, |
| { |
| "entropy": 0.5449002534151077, |
| "epoch": 0.2798507462686567, |
| "grad_norm": 0.14890889823436737, |
| "learning_rate": 0.0002, |
| "loss": 0.5443488359451294, |
| "mean_token_accuracy": 0.7798673063516617, |
| "num_tokens": 1224365.0, |
| "step": 75 |
| }, |
| { |
| "entropy": 0.5484029799699783, |
| "epoch": 0.2835820895522388, |
| "grad_norm": 0.15145590901374817, |
| "learning_rate": 0.0002, |
| "loss": 0.5470284223556519, |
| "mean_token_accuracy": 0.7791313678026199, |
| "num_tokens": 1240643.0, |
| "step": 76 |
| }, |
| { |
| "entropy": 0.5593999028205872, |
| "epoch": 0.2873134328358209, |
| "grad_norm": 0.14717823266983032, |
| "learning_rate": 0.0002, |
| "loss": 0.5637351870536804, |
| "mean_token_accuracy": 0.7750686705112457, |
| "num_tokens": 1257021.0, |
| "step": 77 |
| }, |
| { |
| "entropy": 0.5433298945426941, |
| "epoch": 0.291044776119403, |
| "grad_norm": 0.1443137675523758, |
| "learning_rate": 0.0002, |
| "loss": 0.5431897640228271, |
| "mean_token_accuracy": 0.7794067114591599, |
| "num_tokens": 1273443.0, |
| "step": 78 |
| }, |
| { |
| "entropy": 0.5216437131166458, |
| "epoch": 0.2947761194029851, |
| "grad_norm": 0.13810165226459503, |
| "learning_rate": 0.0002, |
| "loss": 0.5294400453567505, |
| "mean_token_accuracy": 0.7879589647054672, |
| "num_tokens": 1289892.0, |
| "step": 79 |
| }, |
| { |
| "entropy": 0.5532664507627487, |
| "epoch": 0.29850746268656714, |
| "grad_norm": 0.13138633966445923, |
| "learning_rate": 0.0002, |
| "loss": 0.5561643838882446, |
| "mean_token_accuracy": 0.7741746455430984, |
| "num_tokens": 1306464.0, |
| "step": 80 |
| }, |
| { |
| "entropy": 0.5681420713663101, |
| "epoch": 0.30223880597014924, |
| "grad_norm": 0.14669597148895264, |
| "learning_rate": 0.0002, |
| "loss": 0.5661838054656982, |
| "mean_token_accuracy": 0.7706888020038605, |
| "num_tokens": 1322824.0, |
| "step": 81 |
| }, |
| { |
| "entropy": 0.559690997004509, |
| "epoch": 0.30597014925373134, |
| "grad_norm": 0.1413508951663971, |
| "learning_rate": 0.0002, |
| "loss": 0.5601946711540222, |
| "mean_token_accuracy": 0.7730322033166885, |
| "num_tokens": 1338856.0, |
| "step": 82 |
| }, |
| { |
| "entropy": 0.5706894546747208, |
| "epoch": 0.30970149253731344, |
| "grad_norm": 0.13088394701480865, |
| "learning_rate": 0.0002, |
| "loss": 0.5635526180267334, |
| "mean_token_accuracy": 0.7743044942617416, |
| "num_tokens": 1355304.0, |
| "step": 83 |
| }, |
| { |
| "entropy": 0.5481306463479996, |
| "epoch": 0.31343283582089554, |
| "grad_norm": 0.14168421924114227, |
| "learning_rate": 0.0002, |
| "loss": 0.545617938041687, |
| "mean_token_accuracy": 0.7795596569776535, |
| "num_tokens": 1371531.0, |
| "step": 84 |
| }, |
| { |
| "entropy": 0.5452685356140137, |
| "epoch": 0.31716417910447764, |
| "grad_norm": 0.15333154797554016, |
| "learning_rate": 0.0002, |
| "loss": 0.5560483932495117, |
| "mean_token_accuracy": 0.776432678103447, |
| "num_tokens": 1387418.0, |
| "step": 85 |
| }, |
| { |
| "entropy": 0.5682359039783478, |
| "epoch": 0.3208955223880597, |
| "grad_norm": 0.14833585917949677, |
| "learning_rate": 0.0002, |
| "loss": 0.5745234489440918, |
| "mean_token_accuracy": 0.7686294168233871, |
| "num_tokens": 1404189.0, |
| "step": 86 |
| }, |
| { |
| "entropy": 0.5457154810428619, |
| "epoch": 0.3246268656716418, |
| "grad_norm": 0.1413474828004837, |
| "learning_rate": 0.0002, |
| "loss": 0.5498673915863037, |
| "mean_token_accuracy": 0.7782109826803207, |
| "num_tokens": 1420503.0, |
| "step": 87 |
| }, |
| { |
| "entropy": 0.5686518847942352, |
| "epoch": 0.3283582089552239, |
| "grad_norm": 0.1304078996181488, |
| "learning_rate": 0.0002, |
| "loss": 0.557553768157959, |
| "mean_token_accuracy": 0.7750136256217957, |
| "num_tokens": 1436924.0, |
| "step": 88 |
| }, |
| { |
| "entropy": 0.5596078038215637, |
| "epoch": 0.332089552238806, |
| "grad_norm": 0.15332210063934326, |
| "learning_rate": 0.0002, |
| "loss": 0.5475339293479919, |
| "mean_token_accuracy": 0.7792017161846161, |
| "num_tokens": 1453240.0, |
| "step": 89 |
| }, |
| { |
| "entropy": 0.551189586520195, |
| "epoch": 0.3358208955223881, |
| "grad_norm": 0.15169446170330048, |
| "learning_rate": 0.0002, |
| "loss": 0.5489795207977295, |
| "mean_token_accuracy": 0.779973953962326, |
| "num_tokens": 1469600.0, |
| "step": 90 |
| }, |
| { |
| "entropy": 0.5438839942216873, |
| "epoch": 0.33955223880597013, |
| "grad_norm": 0.13516585528850555, |
| "learning_rate": 0.0002, |
| "loss": 0.5512352585792542, |
| "mean_token_accuracy": 0.7747772932052612, |
| "num_tokens": 1485909.0, |
| "step": 91 |
| }, |
| { |
| "entropy": 0.5321949571371078, |
| "epoch": 0.34328358208955223, |
| "grad_norm": 0.1753428429365158, |
| "learning_rate": 0.0002, |
| "loss": 0.5507063269615173, |
| "mean_token_accuracy": 0.7773251980543137, |
| "num_tokens": 1502058.0, |
| "step": 92 |
| }, |
| { |
| "entropy": 0.5305195599794388, |
| "epoch": 0.34701492537313433, |
| "grad_norm": 0.1354769617319107, |
| "learning_rate": 0.0002, |
| "loss": 0.5354310870170593, |
| "mean_token_accuracy": 0.7847408354282379, |
| "num_tokens": 1518339.0, |
| "step": 93 |
| }, |
| { |
| "entropy": 0.5443465560674667, |
| "epoch": 0.35074626865671643, |
| "grad_norm": 0.14657573401927948, |
| "learning_rate": 0.0002, |
| "loss": 0.5417787432670593, |
| "mean_token_accuracy": 0.7811830341815948, |
| "num_tokens": 1534491.0, |
| "step": 94 |
| }, |
| { |
| "entropy": 0.5754250586032867, |
| "epoch": 0.35447761194029853, |
| "grad_norm": 0.15212133526802063, |
| "learning_rate": 0.0002, |
| "loss": 0.5706509351730347, |
| "mean_token_accuracy": 0.7703712284564972, |
| "num_tokens": 1550876.0, |
| "step": 95 |
| }, |
| { |
| "entropy": 0.557824432849884, |
| "epoch": 0.3582089552238806, |
| "grad_norm": 0.1554679125547409, |
| "learning_rate": 0.0002, |
| "loss": 0.5593215227127075, |
| "mean_token_accuracy": 0.7741101384162903, |
| "num_tokens": 1567415.0, |
| "step": 96 |
| }, |
| { |
| "entropy": 0.5387020260095596, |
| "epoch": 0.3619402985074627, |
| "grad_norm": 0.13061970472335815, |
| "learning_rate": 0.0002, |
| "loss": 0.5440589785575867, |
| "mean_token_accuracy": 0.7789928615093231, |
| "num_tokens": 1583414.0, |
| "step": 97 |
| }, |
| { |
| "entropy": 0.5756299942731857, |
| "epoch": 0.3656716417910448, |
| "grad_norm": 0.13083241879940033, |
| "learning_rate": 0.0002, |
| "loss": 0.5734657645225525, |
| "mean_token_accuracy": 0.7728305459022522, |
| "num_tokens": 1599863.0, |
| "step": 98 |
| }, |
| { |
| "entropy": 0.5417134463787079, |
| "epoch": 0.3694029850746269, |
| "grad_norm": 0.12928514182567596, |
| "learning_rate": 0.0002, |
| "loss": 0.5430588722229004, |
| "mean_token_accuracy": 0.7812702059745789, |
| "num_tokens": 1616458.0, |
| "step": 99 |
| }, |
| { |
| "entropy": 0.5377703309059143, |
| "epoch": 0.373134328358209, |
| "grad_norm": 0.15239068865776062, |
| "learning_rate": 0.0002, |
| "loss": 0.5473966598510742, |
| "mean_token_accuracy": 0.7786829918622971, |
| "num_tokens": 1632949.0, |
| "step": 100 |
| }, |
| { |
| "entropy": 0.5387261509895325, |
| "epoch": 0.376865671641791, |
| "grad_norm": 0.12599654495716095, |
| "learning_rate": 0.0002, |
| "loss": 0.5419601202011108, |
| "mean_token_accuracy": 0.7828179448843002, |
| "num_tokens": 1649221.0, |
| "step": 101 |
| }, |
| { |
| "entropy": 0.525150403380394, |
| "epoch": 0.3805970149253731, |
| "grad_norm": 0.14492617547512054, |
| "learning_rate": 0.0002, |
| "loss": 0.5233801603317261, |
| "mean_token_accuracy": 0.7907245010137558, |
| "num_tokens": 1665333.0, |
| "step": 102 |
| }, |
| { |
| "entropy": 0.5416120439767838, |
| "epoch": 0.3843283582089552, |
| "grad_norm": 0.1340053528547287, |
| "learning_rate": 0.0002, |
| "loss": 0.5428943634033203, |
| "mean_token_accuracy": 0.7812149673700333, |
| "num_tokens": 1681708.0, |
| "step": 103 |
| }, |
| { |
| "entropy": 0.554007038474083, |
| "epoch": 0.3880597014925373, |
| "grad_norm": 0.13095539808273315, |
| "learning_rate": 0.0002, |
| "loss": 0.5535528659820557, |
| "mean_token_accuracy": 0.7748290300369263, |
| "num_tokens": 1697996.0, |
| "step": 104 |
| }, |
| { |
| "entropy": 0.5498805791139603, |
| "epoch": 0.3917910447761194, |
| "grad_norm": 0.13662110269069672, |
| "learning_rate": 0.0002, |
| "loss": 0.5495188236236572, |
| "mean_token_accuracy": 0.7773355841636658, |
| "num_tokens": 1714189.0, |
| "step": 105 |
| }, |
| { |
| "entropy": 0.5359694361686707, |
| "epoch": 0.39552238805970147, |
| "grad_norm": 0.14686588943004608, |
| "learning_rate": 0.0002, |
| "loss": 0.5403894186019897, |
| "mean_token_accuracy": 0.7827219069004059, |
| "num_tokens": 1730526.0, |
| "step": 106 |
| }, |
| { |
| "entropy": 0.5346398502588272, |
| "epoch": 0.39925373134328357, |
| "grad_norm": 0.15840110182762146, |
| "learning_rate": 0.0002, |
| "loss": 0.5430917143821716, |
| "mean_token_accuracy": 0.7820771336555481, |
| "num_tokens": 1746695.0, |
| "step": 107 |
| }, |
| { |
| "entropy": 0.5540575981140137, |
| "epoch": 0.40298507462686567, |
| "grad_norm": 0.1280706822872162, |
| "learning_rate": 0.0002, |
| "loss": 0.554350733757019, |
| "mean_token_accuracy": 0.7738704979419708, |
| "num_tokens": 1763146.0, |
| "step": 108 |
| }, |
| { |
| "entropy": 0.5532242506742477, |
| "epoch": 0.40671641791044777, |
| "grad_norm": 0.14326687157154083, |
| "learning_rate": 0.0002, |
| "loss": 0.549531102180481, |
| "mean_token_accuracy": 0.7799077033996582, |
| "num_tokens": 1779588.0, |
| "step": 109 |
| }, |
| { |
| "entropy": 0.5488840639591217, |
| "epoch": 0.41044776119402987, |
| "grad_norm": 0.1641664206981659, |
| "learning_rate": 0.0002, |
| "loss": 0.5526561141014099, |
| "mean_token_accuracy": 0.7772204279899597, |
| "num_tokens": 1795725.0, |
| "step": 110 |
| }, |
| { |
| "entropy": 0.5405448526144028, |
| "epoch": 0.4141791044776119, |
| "grad_norm": 0.12611819803714752, |
| "learning_rate": 0.0002, |
| "loss": 0.5453507304191589, |
| "mean_token_accuracy": 0.7808022946119308, |
| "num_tokens": 1812086.0, |
| "step": 111 |
| }, |
| { |
| "entropy": 0.5460507422685623, |
| "epoch": 0.417910447761194, |
| "grad_norm": 0.13933971524238586, |
| "learning_rate": 0.0002, |
| "loss": 0.5422803163528442, |
| "mean_token_accuracy": 0.7813504338264465, |
| "num_tokens": 1828659.0, |
| "step": 112 |
| }, |
| { |
| "entropy": 0.538304015994072, |
| "epoch": 0.4216417910447761, |
| "grad_norm": 0.141179159283638, |
| "learning_rate": 0.0002, |
| "loss": 0.532465398311615, |
| "mean_token_accuracy": 0.7852248400449753, |
| "num_tokens": 1844812.0, |
| "step": 113 |
| }, |
| { |
| "entropy": 0.5350681394338608, |
| "epoch": 0.4253731343283582, |
| "grad_norm": 0.13486936688423157, |
| "learning_rate": 0.0002, |
| "loss": 0.5440570116043091, |
| "mean_token_accuracy": 0.777926430106163, |
| "num_tokens": 1861264.0, |
| "step": 114 |
| }, |
| { |
| "entropy": 0.5501060783863068, |
| "epoch": 0.4291044776119403, |
| "grad_norm": 0.13664987683296204, |
| "learning_rate": 0.0002, |
| "loss": 0.5591107606887817, |
| "mean_token_accuracy": 0.775740459561348, |
| "num_tokens": 1877580.0, |
| "step": 115 |
| }, |
| { |
| "entropy": 0.5360018759965897, |
| "epoch": 0.43283582089552236, |
| "grad_norm": 0.13318665325641632, |
| "learning_rate": 0.0002, |
| "loss": 0.5407794117927551, |
| "mean_token_accuracy": 0.7835452556610107, |
| "num_tokens": 1894091.0, |
| "step": 116 |
| }, |
| { |
| "entropy": 0.5619556903839111, |
| "epoch": 0.43656716417910446, |
| "grad_norm": 0.14123328030109406, |
| "learning_rate": 0.0002, |
| "loss": 0.565187931060791, |
| "mean_token_accuracy": 0.7725419700145721, |
| "num_tokens": 1910754.0, |
| "step": 117 |
| }, |
| { |
| "entropy": 0.5347717702388763, |
| "epoch": 0.44029850746268656, |
| "grad_norm": 0.12933014333248138, |
| "learning_rate": 0.0002, |
| "loss": 0.5354520678520203, |
| "mean_token_accuracy": 0.7833744138479233, |
| "num_tokens": 1927012.0, |
| "step": 118 |
| }, |
| { |
| "entropy": 0.5738185495138168, |
| "epoch": 0.44402985074626866, |
| "grad_norm": 0.133438378572464, |
| "learning_rate": 0.0002, |
| "loss": 0.5667454600334167, |
| "mean_token_accuracy": 0.7717069238424301, |
| "num_tokens": 1943548.0, |
| "step": 119 |
| }, |
| { |
| "entropy": 0.554510086774826, |
| "epoch": 0.44776119402985076, |
| "grad_norm": 0.12262225896120071, |
| "learning_rate": 0.0002, |
| "loss": 0.5506184101104736, |
| "mean_token_accuracy": 0.775943785905838, |
| "num_tokens": 1959867.0, |
| "step": 120 |
| }, |
| { |
| "entropy": 0.5555571466684341, |
| "epoch": 0.45149253731343286, |
| "grad_norm": 0.11127299070358276, |
| "learning_rate": 0.0002, |
| "loss": 0.5589133501052856, |
| "mean_token_accuracy": 0.7727361172437668, |
| "num_tokens": 1976136.0, |
| "step": 121 |
| }, |
| { |
| "entropy": 0.5591738820075989, |
| "epoch": 0.4552238805970149, |
| "grad_norm": 0.1432109773159027, |
| "learning_rate": 0.0002, |
| "loss": 0.5588327646255493, |
| "mean_token_accuracy": 0.7737594991922379, |
| "num_tokens": 1992550.0, |
| "step": 122 |
| }, |
| { |
| "entropy": 0.5391146838665009, |
| "epoch": 0.458955223880597, |
| "grad_norm": 0.13062386214733124, |
| "learning_rate": 0.0002, |
| "loss": 0.5422841906547546, |
| "mean_token_accuracy": 0.7834550440311432, |
| "num_tokens": 2009014.0, |
| "step": 123 |
| }, |
| { |
| "entropy": 0.5341935455799103, |
| "epoch": 0.4626865671641791, |
| "grad_norm": 0.14751774072647095, |
| "learning_rate": 0.0002, |
| "loss": 0.5423805117607117, |
| "mean_token_accuracy": 0.7806256413459778, |
| "num_tokens": 2025108.0, |
| "step": 124 |
| }, |
| { |
| "entropy": 0.5553800165653229, |
| "epoch": 0.4664179104477612, |
| "grad_norm": 0.11514256149530411, |
| "learning_rate": 0.0002, |
| "loss": 0.5563713908195496, |
| "mean_token_accuracy": 0.7750208824872971, |
| "num_tokens": 2041632.0, |
| "step": 125 |
| }, |
| { |
| "entropy": 0.5523609668016434, |
| "epoch": 0.4701492537313433, |
| "grad_norm": 0.11926240473985672, |
| "learning_rate": 0.0002, |
| "loss": 0.5513243675231934, |
| "mean_token_accuracy": 0.7778878957033157, |
| "num_tokens": 2057845.0, |
| "step": 126 |
| }, |
| { |
| "entropy": 0.5531231909990311, |
| "epoch": 0.47388059701492535, |
| "grad_norm": 0.12325365096330643, |
| "learning_rate": 0.0002, |
| "loss": 0.5501022338867188, |
| "mean_token_accuracy": 0.7794498950242996, |
| "num_tokens": 2074061.0, |
| "step": 127 |
| }, |
| { |
| "entropy": 0.5707463771104813, |
| "epoch": 0.47761194029850745, |
| "grad_norm": 0.12264610081911087, |
| "learning_rate": 0.0002, |
| "loss": 0.5643318891525269, |
| "mean_token_accuracy": 0.7725578248500824, |
| "num_tokens": 2090392.0, |
| "step": 128 |
| }, |
| { |
| "entropy": 0.5620923340320587, |
| "epoch": 0.48134328358208955, |
| "grad_norm": 0.12227845191955566, |
| "learning_rate": 0.0002, |
| "loss": 0.5618777275085449, |
| "mean_token_accuracy": 0.7738128900527954, |
| "num_tokens": 2106808.0, |
| "step": 129 |
| }, |
| { |
| "entropy": 0.5335849225521088, |
| "epoch": 0.48507462686567165, |
| "grad_norm": 0.13943326473236084, |
| "learning_rate": 0.0002, |
| "loss": 0.5424497127532959, |
| "mean_token_accuracy": 0.7806478142738342, |
| "num_tokens": 2123165.0, |
| "step": 130 |
| }, |
| { |
| "entropy": 0.5359144806861877, |
| "epoch": 0.48880597014925375, |
| "grad_norm": 0.12483876943588257, |
| "learning_rate": 0.0002, |
| "loss": 0.5395646095275879, |
| "mean_token_accuracy": 0.7870306819677353, |
| "num_tokens": 2139477.0, |
| "step": 131 |
| }, |
| { |
| "entropy": 0.535539984703064, |
| "epoch": 0.4925373134328358, |
| "grad_norm": 0.11990942060947418, |
| "learning_rate": 0.0002, |
| "loss": 0.5427770018577576, |
| "mean_token_accuracy": 0.7822177410125732, |
| "num_tokens": 2155944.0, |
| "step": 132 |
| }, |
| { |
| "entropy": 0.5514626950025558, |
| "epoch": 0.4962686567164179, |
| "grad_norm": 0.12458693981170654, |
| "learning_rate": 0.0002, |
| "loss": 0.5494319796562195, |
| "mean_token_accuracy": 0.7803364396095276, |
| "num_tokens": 2172469.0, |
| "step": 133 |
| }, |
| { |
| "entropy": 0.5426991879940033, |
| "epoch": 0.5, |
| "grad_norm": 0.11668461561203003, |
| "learning_rate": 0.0002, |
| "loss": 0.5489028692245483, |
| "mean_token_accuracy": 0.7810677289962769, |
| "num_tokens": 2188553.0, |
| "step": 134 |
| }, |
| { |
| "entropy": 0.5441031008958817, |
| "epoch": 0.503731343283582, |
| "grad_norm": 0.13241265714168549, |
| "learning_rate": 0.0002, |
| "loss": 0.5465919375419617, |
| "mean_token_accuracy": 0.7807785272598267, |
| "num_tokens": 2204852.0, |
| "step": 135 |
| }, |
| { |
| "entropy": 0.5434937253594398, |
| "epoch": 0.5074626865671642, |
| "grad_norm": 0.11302844434976578, |
| "learning_rate": 0.0002, |
| "loss": 0.5382369756698608, |
| "mean_token_accuracy": 0.7834479212760925, |
| "num_tokens": 2221638.0, |
| "step": 136 |
| }, |
| { |
| "entropy": 0.5558972805738449, |
| "epoch": 0.5111940298507462, |
| "grad_norm": 0.11993750184774399, |
| "learning_rate": 0.0002, |
| "loss": 0.5551699995994568, |
| "mean_token_accuracy": 0.7742699831724167, |
| "num_tokens": 2238083.0, |
| "step": 137 |
| }, |
| { |
| "entropy": 0.5582057237625122, |
| "epoch": 0.5149253731343284, |
| "grad_norm": 0.13113079965114594, |
| "learning_rate": 0.0002, |
| "loss": 0.5590707659721375, |
| "mean_token_accuracy": 0.7712962329387665, |
| "num_tokens": 2254320.0, |
| "step": 138 |
| }, |
| { |
| "entropy": 0.5411713272333145, |
| "epoch": 0.5186567164179104, |
| "grad_norm": 0.11980149149894714, |
| "learning_rate": 0.0002, |
| "loss": 0.5429773926734924, |
| "mean_token_accuracy": 0.7832571119070053, |
| "num_tokens": 2270681.0, |
| "step": 139 |
| }, |
| { |
| "entropy": 0.566581204533577, |
| "epoch": 0.5223880597014925, |
| "grad_norm": 0.14235219359397888, |
| "learning_rate": 0.0002, |
| "loss": 0.5644463300704956, |
| "mean_token_accuracy": 0.7723579555749893, |
| "num_tokens": 2286945.0, |
| "step": 140 |
| }, |
| { |
| "entropy": 0.5441527515649796, |
| "epoch": 0.5261194029850746, |
| "grad_norm": 0.12448754906654358, |
| "learning_rate": 0.0002, |
| "loss": 0.5482107400894165, |
| "mean_token_accuracy": 0.7760092467069626, |
| "num_tokens": 2303281.0, |
| "step": 141 |
| }, |
| { |
| "entropy": 0.5435121208429337, |
| "epoch": 0.5298507462686567, |
| "grad_norm": 0.13480845093727112, |
| "learning_rate": 0.0002, |
| "loss": 0.5531845092773438, |
| "mean_token_accuracy": 0.775780513882637, |
| "num_tokens": 2319724.0, |
| "step": 142 |
| }, |
| { |
| "entropy": 0.5717597007751465, |
| "epoch": 0.5335820895522388, |
| "grad_norm": 0.11915597319602966, |
| "learning_rate": 0.0002, |
| "loss": 0.569578230381012, |
| "mean_token_accuracy": 0.769955039024353, |
| "num_tokens": 2336259.0, |
| "step": 143 |
| }, |
| { |
| "entropy": 0.5528465509414673, |
| "epoch": 0.5373134328358209, |
| "grad_norm": 0.11445717513561249, |
| "learning_rate": 0.0002, |
| "loss": 0.5499665141105652, |
| "mean_token_accuracy": 0.7776763439178467, |
| "num_tokens": 2352674.0, |
| "step": 144 |
| }, |
| { |
| "entropy": 0.5425368100404739, |
| "epoch": 0.5410447761194029, |
| "grad_norm": 0.11935009807348251, |
| "learning_rate": 0.0002, |
| "loss": 0.5474374294281006, |
| "mean_token_accuracy": 0.7792418152093887, |
| "num_tokens": 2369032.0, |
| "step": 145 |
| }, |
| { |
| "entropy": 0.5291661024093628, |
| "epoch": 0.5447761194029851, |
| "grad_norm": 0.12481313943862915, |
| "learning_rate": 0.0002, |
| "loss": 0.5336353778839111, |
| "mean_token_accuracy": 0.7851836085319519, |
| "num_tokens": 2385099.0, |
| "step": 146 |
| }, |
| { |
| "entropy": 0.547185942530632, |
| "epoch": 0.5485074626865671, |
| "grad_norm": 0.12664265930652618, |
| "learning_rate": 0.0002, |
| "loss": 0.5480313301086426, |
| "mean_token_accuracy": 0.7745092064142227, |
| "num_tokens": 2401455.0, |
| "step": 147 |
| }, |
| { |
| "entropy": 0.5601523667573929, |
| "epoch": 0.5522388059701493, |
| "grad_norm": 0.12579131126403809, |
| "learning_rate": 0.0002, |
| "loss": 0.5535739660263062, |
| "mean_token_accuracy": 0.7742781490087509, |
| "num_tokens": 2417958.0, |
| "step": 148 |
| }, |
| { |
| "entropy": 0.5490868240594864, |
| "epoch": 0.5559701492537313, |
| "grad_norm": 0.13660171627998352, |
| "learning_rate": 0.0002, |
| "loss": 0.5434013605117798, |
| "mean_token_accuracy": 0.778279185295105, |
| "num_tokens": 2434495.0, |
| "step": 149 |
| }, |
| { |
| "entropy": 0.5388410687446594, |
| "epoch": 0.5597014925373134, |
| "grad_norm": 0.11539566516876221, |
| "learning_rate": 0.0002, |
| "loss": 0.5389751195907593, |
| "mean_token_accuracy": 0.7835458070039749, |
| "num_tokens": 2450891.0, |
| "step": 150 |
| }, |
| { |
| "entropy": 0.5269395709037781, |
| "epoch": 0.5634328358208955, |
| "grad_norm": 0.13228651881217957, |
| "learning_rate": 0.0002, |
| "loss": 0.537408709526062, |
| "mean_token_accuracy": 0.7821726351976395, |
| "num_tokens": 2467236.0, |
| "step": 151 |
| }, |
| { |
| "entropy": 0.5306248813867569, |
| "epoch": 0.5671641791044776, |
| "grad_norm": 0.13402500748634338, |
| "learning_rate": 0.0002, |
| "loss": 0.5424383878707886, |
| "mean_token_accuracy": 0.7803402543067932, |
| "num_tokens": 2483482.0, |
| "step": 152 |
| }, |
| { |
| "entropy": 0.5398715287446976, |
| "epoch": 0.5708955223880597, |
| "grad_norm": 0.12408295273780823, |
| "learning_rate": 0.0002, |
| "loss": 0.5466125011444092, |
| "mean_token_accuracy": 0.7775432020425797, |
| "num_tokens": 2499977.0, |
| "step": 153 |
| }, |
| { |
| "entropy": 0.5459054559469223, |
| "epoch": 0.5746268656716418, |
| "grad_norm": 0.12587407231330872, |
| "learning_rate": 0.0002, |
| "loss": 0.5417993664741516, |
| "mean_token_accuracy": 0.7816223502159119, |
| "num_tokens": 2516528.0, |
| "step": 154 |
| }, |
| { |
| "entropy": 0.5609378665685654, |
| "epoch": 0.5783582089552238, |
| "grad_norm": 0.12681882083415985, |
| "learning_rate": 0.0002, |
| "loss": 0.5533650517463684, |
| "mean_token_accuracy": 0.777653306722641, |
| "num_tokens": 2532845.0, |
| "step": 155 |
| }, |
| { |
| "entropy": 0.5719186663627625, |
| "epoch": 0.582089552238806, |
| "grad_norm": 0.1375240981578827, |
| "learning_rate": 0.0002, |
| "loss": 0.5615803003311157, |
| "mean_token_accuracy": 0.7738198488950729, |
| "num_tokens": 2549262.0, |
| "step": 156 |
| }, |
| { |
| "entropy": 0.5423252731561661, |
| "epoch": 0.585820895522388, |
| "grad_norm": 0.136957049369812, |
| "learning_rate": 0.0002, |
| "loss": 0.5401554107666016, |
| "mean_token_accuracy": 0.7814236879348755, |
| "num_tokens": 2565963.0, |
| "step": 157 |
| }, |
| { |
| "entropy": 0.5454217344522476, |
| "epoch": 0.5895522388059702, |
| "grad_norm": 0.15682168304920197, |
| "learning_rate": 0.0002, |
| "loss": 0.557049572467804, |
| "mean_token_accuracy": 0.7741558998823166, |
| "num_tokens": 2582344.0, |
| "step": 158 |
| }, |
| { |
| "entropy": 0.5459867268800735, |
| "epoch": 0.5932835820895522, |
| "grad_norm": 0.14311513304710388, |
| "learning_rate": 0.0002, |
| "loss": 0.556149423122406, |
| "mean_token_accuracy": 0.7749217599630356, |
| "num_tokens": 2598805.0, |
| "step": 159 |
| }, |
| { |
| "entropy": 0.5436315834522247, |
| "epoch": 0.5970149253731343, |
| "grad_norm": 0.11805713176727295, |
| "learning_rate": 0.0002, |
| "loss": 0.5419399738311768, |
| "mean_token_accuracy": 0.7781417071819305, |
| "num_tokens": 2615297.0, |
| "step": 160 |
| }, |
| { |
| "entropy": 0.5604213327169418, |
| "epoch": 0.6007462686567164, |
| "grad_norm": 0.11683984845876694, |
| "learning_rate": 0.0002, |
| "loss": 0.556625247001648, |
| "mean_token_accuracy": 0.7760651558637619, |
| "num_tokens": 2631406.0, |
| "step": 161 |
| }, |
| { |
| "entropy": 0.5391066372394562, |
| "epoch": 0.6044776119402985, |
| "grad_norm": 0.13629689812660217, |
| "learning_rate": 0.0002, |
| "loss": 0.537336528301239, |
| "mean_token_accuracy": 0.7833027243614197, |
| "num_tokens": 2647860.0, |
| "step": 162 |
| }, |
| { |
| "entropy": 0.5620129704475403, |
| "epoch": 0.6082089552238806, |
| "grad_norm": 0.11577955633401871, |
| "learning_rate": 0.0002, |
| "loss": 0.5653657913208008, |
| "mean_token_accuracy": 0.7747004181146622, |
| "num_tokens": 2664397.0, |
| "step": 163 |
| }, |
| { |
| "entropy": 0.5598644763231277, |
| "epoch": 0.6119402985074627, |
| "grad_norm": 0.1359051913022995, |
| "learning_rate": 0.0002, |
| "loss": 0.5655931830406189, |
| "mean_token_accuracy": 0.7714291960000992, |
| "num_tokens": 2681011.0, |
| "step": 164 |
| }, |
| { |
| "entropy": 0.5512835085391998, |
| "epoch": 0.6156716417910447, |
| "grad_norm": 0.1351737082004547, |
| "learning_rate": 0.0002, |
| "loss": 0.5605036616325378, |
| "mean_token_accuracy": 0.7735864818096161, |
| "num_tokens": 2697468.0, |
| "step": 165 |
| }, |
| { |
| "entropy": 0.5435576289892197, |
| "epoch": 0.6194029850746269, |
| "grad_norm": 0.13584591448307037, |
| "learning_rate": 0.0002, |
| "loss": 0.5412253141403198, |
| "mean_token_accuracy": 0.7839856892824173, |
| "num_tokens": 2713936.0, |
| "step": 166 |
| }, |
| { |
| "entropy": 0.5420274585485458, |
| "epoch": 0.6231343283582089, |
| "grad_norm": 0.12248866260051727, |
| "learning_rate": 0.0002, |
| "loss": 0.542800784111023, |
| "mean_token_accuracy": 0.782304584980011, |
| "num_tokens": 2730132.0, |
| "step": 167 |
| }, |
| { |
| "entropy": 0.5529382824897766, |
| "epoch": 0.6268656716417911, |
| "grad_norm": 0.12444604933261871, |
| "learning_rate": 0.0002, |
| "loss": 0.5469269156455994, |
| "mean_token_accuracy": 0.7799636423587799, |
| "num_tokens": 2746646.0, |
| "step": 168 |
| }, |
| { |
| "entropy": 0.5443761944770813, |
| "epoch": 0.6305970149253731, |
| "grad_norm": 0.12793844938278198, |
| "learning_rate": 0.0002, |
| "loss": 0.5471650958061218, |
| "mean_token_accuracy": 0.7768973857164383, |
| "num_tokens": 2763158.0, |
| "step": 169 |
| }, |
| { |
| "entropy": 0.5275103449821472, |
| "epoch": 0.6343283582089553, |
| "grad_norm": 0.13484962284564972, |
| "learning_rate": 0.0002, |
| "loss": 0.5369510054588318, |
| "mean_token_accuracy": 0.7838299572467804, |
| "num_tokens": 2779532.0, |
| "step": 170 |
| }, |
| { |
| "entropy": 0.5403365641832352, |
| "epoch": 0.6380597014925373, |
| "grad_norm": 0.16462746262550354, |
| "learning_rate": 0.0002, |
| "loss": 0.5484907627105713, |
| "mean_token_accuracy": 0.7792782485485077, |
| "num_tokens": 2795830.0, |
| "step": 171 |
| }, |
| { |
| "entropy": 0.5489327162504196, |
| "epoch": 0.6417910447761194, |
| "grad_norm": 0.1286742389202118, |
| "learning_rate": 0.0002, |
| "loss": 0.5405184030532837, |
| "mean_token_accuracy": 0.7797237783670425, |
| "num_tokens": 2812320.0, |
| "step": 172 |
| }, |
| { |
| "entropy": 0.5569936782121658, |
| "epoch": 0.6455223880597015, |
| "grad_norm": 0.12988999485969543, |
| "learning_rate": 0.0002, |
| "loss": 0.5561147928237915, |
| "mean_token_accuracy": 0.7730411440134048, |
| "num_tokens": 2828770.0, |
| "step": 173 |
| }, |
| { |
| "entropy": 0.5592756867408752, |
| "epoch": 0.6492537313432836, |
| "grad_norm": 0.12970879673957825, |
| "learning_rate": 0.0002, |
| "loss": 0.5530601739883423, |
| "mean_token_accuracy": 0.7757252007722855, |
| "num_tokens": 2845351.0, |
| "step": 174 |
| }, |
| { |
| "entropy": 0.5501866191625595, |
| "epoch": 0.6529850746268657, |
| "grad_norm": 0.12796641886234283, |
| "learning_rate": 0.0002, |
| "loss": 0.5499067306518555, |
| "mean_token_accuracy": 0.7755600959062576, |
| "num_tokens": 2861823.0, |
| "step": 175 |
| }, |
| { |
| "entropy": 0.5400368571281433, |
| "epoch": 0.6567164179104478, |
| "grad_norm": 0.15053920447826385, |
| "learning_rate": 0.0002, |
| "loss": 0.5535704493522644, |
| "mean_token_accuracy": 0.7780491262674332, |
| "num_tokens": 2878252.0, |
| "step": 176 |
| }, |
| { |
| "entropy": 0.5162946879863739, |
| "epoch": 0.6604477611940298, |
| "grad_norm": 0.13528653979301453, |
| "learning_rate": 0.0002, |
| "loss": 0.5270611047744751, |
| "mean_token_accuracy": 0.7838902622461319, |
| "num_tokens": 2894467.0, |
| "step": 177 |
| }, |
| { |
| "entropy": 0.5470219254493713, |
| "epoch": 0.664179104477612, |
| "grad_norm": 0.11602969467639923, |
| "learning_rate": 0.0002, |
| "loss": 0.5448654890060425, |
| "mean_token_accuracy": 0.7792890965938568, |
| "num_tokens": 2910687.0, |
| "step": 178 |
| }, |
| { |
| "entropy": 0.5483407229185104, |
| "epoch": 0.667910447761194, |
| "grad_norm": 0.11689810454845428, |
| "learning_rate": 0.0002, |
| "loss": 0.5397474765777588, |
| "mean_token_accuracy": 0.782607913017273, |
| "num_tokens": 2927204.0, |
| "step": 179 |
| }, |
| { |
| "entropy": 0.5604808628559113, |
| "epoch": 0.6716417910447762, |
| "grad_norm": 0.11573274433612823, |
| "learning_rate": 0.0002, |
| "loss": 0.5622426867485046, |
| "mean_token_accuracy": 0.7709476500749588, |
| "num_tokens": 2943647.0, |
| "step": 180 |
| }, |
| { |
| "entropy": 0.5465309917926788, |
| "epoch": 0.6753731343283582, |
| "grad_norm": 0.12910929322242737, |
| "learning_rate": 0.0002, |
| "loss": 0.5447050929069519, |
| "mean_token_accuracy": 0.7817826271057129, |
| "num_tokens": 2960118.0, |
| "step": 181 |
| }, |
| { |
| "entropy": 0.5373580604791641, |
| "epoch": 0.6791044776119403, |
| "grad_norm": 0.11300910264253616, |
| "learning_rate": 0.0002, |
| "loss": 0.5408024191856384, |
| "mean_token_accuracy": 0.7808624356985092, |
| "num_tokens": 2976400.0, |
| "step": 182 |
| }, |
| { |
| "entropy": 0.5293615311384201, |
| "epoch": 0.6828358208955224, |
| "grad_norm": 0.11850351095199585, |
| "learning_rate": 0.0002, |
| "loss": 0.5275492668151855, |
| "mean_token_accuracy": 0.7858620285987854, |
| "num_tokens": 2992805.0, |
| "step": 183 |
| }, |
| { |
| "entropy": 0.5392166376113892, |
| "epoch": 0.6865671641791045, |
| "grad_norm": 0.13984566926956177, |
| "learning_rate": 0.0002, |
| "loss": 0.5452960133552551, |
| "mean_token_accuracy": 0.7782400995492935, |
| "num_tokens": 3008922.0, |
| "step": 184 |
| }, |
| { |
| "entropy": 0.5336991101503372, |
| "epoch": 0.6902985074626866, |
| "grad_norm": 0.13704419136047363, |
| "learning_rate": 0.0002, |
| "loss": 0.535088837146759, |
| "mean_token_accuracy": 0.7827304899692535, |
| "num_tokens": 3025145.0, |
| "step": 185 |
| }, |
| { |
| "entropy": 0.5472408533096313, |
| "epoch": 0.6940298507462687, |
| "grad_norm": 0.13761988282203674, |
| "learning_rate": 0.0002, |
| "loss": 0.5527719855308533, |
| "mean_token_accuracy": 0.7758041769266129, |
| "num_tokens": 3041557.0, |
| "step": 186 |
| }, |
| { |
| "entropy": 0.5575349479913712, |
| "epoch": 0.6977611940298507, |
| "grad_norm": 0.13612273335456848, |
| "learning_rate": 0.0002, |
| "loss": 0.5594455003738403, |
| "mean_token_accuracy": 0.7736956477165222, |
| "num_tokens": 3058147.0, |
| "step": 187 |
| }, |
| { |
| "entropy": 0.534651517868042, |
| "epoch": 0.7014925373134329, |
| "grad_norm": 0.13108359277248383, |
| "learning_rate": 0.0002, |
| "loss": 0.5342751741409302, |
| "mean_token_accuracy": 0.7839203029870987, |
| "num_tokens": 3074561.0, |
| "step": 188 |
| }, |
| { |
| "entropy": 0.5401168167591095, |
| "epoch": 0.7052238805970149, |
| "grad_norm": 0.13905395567417145, |
| "learning_rate": 0.0002, |
| "loss": 0.5421609282493591, |
| "mean_token_accuracy": 0.7798676788806915, |
| "num_tokens": 3090912.0, |
| "step": 189 |
| }, |
| { |
| "entropy": 0.557087853550911, |
| "epoch": 0.7089552238805971, |
| "grad_norm": 0.1418144255876541, |
| "learning_rate": 0.0002, |
| "loss": 0.5533076524734497, |
| "mean_token_accuracy": 0.7786961942911148, |
| "num_tokens": 3107399.0, |
| "step": 190 |
| }, |
| { |
| "entropy": 0.5592824518680573, |
| "epoch": 0.7126865671641791, |
| "grad_norm": 0.12663999199867249, |
| "learning_rate": 0.0002, |
| "loss": 0.5629890561103821, |
| "mean_token_accuracy": 0.7717658579349518, |
| "num_tokens": 3123700.0, |
| "step": 191 |
| }, |
| { |
| "entropy": 0.5323676615953445, |
| "epoch": 0.7164179104477612, |
| "grad_norm": 0.12304801493883133, |
| "learning_rate": 0.0002, |
| "loss": 0.5336155891418457, |
| "mean_token_accuracy": 0.7829046249389648, |
| "num_tokens": 3140139.0, |
| "step": 192 |
| }, |
| { |
| "entropy": 0.5500892251729965, |
| "epoch": 0.7201492537313433, |
| "grad_norm": 0.1362822949886322, |
| "learning_rate": 0.0002, |
| "loss": 0.5507694482803345, |
| "mean_token_accuracy": 0.7789083570241928, |
| "num_tokens": 3156416.0, |
| "step": 193 |
| }, |
| { |
| "entropy": 0.5433221906423569, |
| "epoch": 0.7238805970149254, |
| "grad_norm": 0.12761962413787842, |
| "learning_rate": 0.0002, |
| "loss": 0.5437319278717041, |
| "mean_token_accuracy": 0.781817153096199, |
| "num_tokens": 3172921.0, |
| "step": 194 |
| }, |
| { |
| "entropy": 0.5233415514230728, |
| "epoch": 0.7276119402985075, |
| "grad_norm": 0.13844530284404755, |
| "learning_rate": 0.0002, |
| "loss": 0.527815580368042, |
| "mean_token_accuracy": 0.7870106399059296, |
| "num_tokens": 3189338.0, |
| "step": 195 |
| }, |
| { |
| "entropy": 0.5365970134735107, |
| "epoch": 0.7313432835820896, |
| "grad_norm": 0.1401812732219696, |
| "learning_rate": 0.0002, |
| "loss": 0.5423948764801025, |
| "mean_token_accuracy": 0.7830164879560471, |
| "num_tokens": 3205498.0, |
| "step": 196 |
| }, |
| { |
| "entropy": 0.5402543991804123, |
| "epoch": 0.7350746268656716, |
| "grad_norm": 0.13760241866111755, |
| "learning_rate": 0.0002, |
| "loss": 0.5467079281806946, |
| "mean_token_accuracy": 0.7759327441453934, |
| "num_tokens": 3221694.0, |
| "step": 197 |
| }, |
| { |
| "entropy": 0.518856555223465, |
| "epoch": 0.7388059701492538, |
| "grad_norm": 0.13099920749664307, |
| "learning_rate": 0.0002, |
| "loss": 0.5236851572990417, |
| "mean_token_accuracy": 0.7862046808004379, |
| "num_tokens": 3237616.0, |
| "step": 198 |
| }, |
| { |
| "entropy": 0.5530437529087067, |
| "epoch": 0.7425373134328358, |
| "grad_norm": 0.14511296153068542, |
| "learning_rate": 0.0002, |
| "loss": 0.5545330047607422, |
| "mean_token_accuracy": 0.7748849540948868, |
| "num_tokens": 3253631.0, |
| "step": 199 |
| }, |
| { |
| "entropy": 0.5781400501728058, |
| "epoch": 0.746268656716418, |
| "grad_norm": 0.12067750841379166, |
| "learning_rate": 0.0002, |
| "loss": 0.5656425952911377, |
| "mean_token_accuracy": 0.7702538073062897, |
| "num_tokens": 3269970.0, |
| "step": 200 |
| }, |
| { |
| "entropy": 0.5544750243425369, |
| "epoch": 0.75, |
| "grad_norm": 0.1294824481010437, |
| "learning_rate": 0.0002, |
| "loss": 0.5445467829704285, |
| "mean_token_accuracy": 0.782656341791153, |
| "num_tokens": 3286159.0, |
| "step": 201 |
| }, |
| { |
| "entropy": 0.5497170388698578, |
| "epoch": 0.753731343283582, |
| "grad_norm": 0.1282891482114792, |
| "learning_rate": 0.0002, |
| "loss": 0.5531092882156372, |
| "mean_token_accuracy": 0.7757890969514847, |
| "num_tokens": 3302360.0, |
| "step": 202 |
| }, |
| { |
| "entropy": 0.5317273736000061, |
| "epoch": 0.7574626865671642, |
| "grad_norm": 0.13666750490665436, |
| "learning_rate": 0.0002, |
| "loss": 0.540383517742157, |
| "mean_token_accuracy": 0.781007394194603, |
| "num_tokens": 3318907.0, |
| "step": 203 |
| }, |
| { |
| "entropy": 0.530354455113411, |
| "epoch": 0.7611940298507462, |
| "grad_norm": 0.12450651079416275, |
| "learning_rate": 0.0002, |
| "loss": 0.541254460811615, |
| "mean_token_accuracy": 0.7815611213445663, |
| "num_tokens": 3335442.0, |
| "step": 204 |
| }, |
| { |
| "entropy": 0.5449293404817581, |
| "epoch": 0.7649253731343284, |
| "grad_norm": 0.10265552997589111, |
| "learning_rate": 0.0002, |
| "loss": 0.5422887206077576, |
| "mean_token_accuracy": 0.7810045182704926, |
| "num_tokens": 3352094.0, |
| "step": 205 |
| }, |
| { |
| "entropy": 0.5616812407970428, |
| "epoch": 0.7686567164179104, |
| "grad_norm": 0.1246832013130188, |
| "learning_rate": 0.0002, |
| "loss": 0.5582008361816406, |
| "mean_token_accuracy": 0.7723671197891235, |
| "num_tokens": 3368585.0, |
| "step": 206 |
| }, |
| { |
| "entropy": 0.5451930612325668, |
| "epoch": 0.7723880597014925, |
| "grad_norm": 0.11660035699605942, |
| "learning_rate": 0.0002, |
| "loss": 0.5484489798545837, |
| "mean_token_accuracy": 0.7763334810733795, |
| "num_tokens": 3385036.0, |
| "step": 207 |
| }, |
| { |
| "entropy": 0.5639515221118927, |
| "epoch": 0.7761194029850746, |
| "grad_norm": 0.12933674454689026, |
| "learning_rate": 0.0002, |
| "loss": 0.5658361911773682, |
| "mean_token_accuracy": 0.7725699245929718, |
| "num_tokens": 3401320.0, |
| "step": 208 |
| }, |
| { |
| "entropy": 0.5312725454568863, |
| "epoch": 0.7798507462686567, |
| "grad_norm": 0.1233212873339653, |
| "learning_rate": 0.0002, |
| "loss": 0.5363055467605591, |
| "mean_token_accuracy": 0.784421756863594, |
| "num_tokens": 3417649.0, |
| "step": 209 |
| }, |
| { |
| "entropy": 0.5425254255533218, |
| "epoch": 0.7835820895522388, |
| "grad_norm": 0.13222278654575348, |
| "learning_rate": 0.0002, |
| "loss": 0.5436025261878967, |
| "mean_token_accuracy": 0.7787772417068481, |
| "num_tokens": 3433790.0, |
| "step": 210 |
| }, |
| { |
| "entropy": 0.543636292219162, |
| "epoch": 0.7873134328358209, |
| "grad_norm": 0.13862311840057373, |
| "learning_rate": 0.0002, |
| "loss": 0.5420448780059814, |
| "mean_token_accuracy": 0.7795868813991547, |
| "num_tokens": 3450117.0, |
| "step": 211 |
| }, |
| { |
| "entropy": 0.5281382650136948, |
| "epoch": 0.7910447761194029, |
| "grad_norm": 0.1595291793346405, |
| "learning_rate": 0.0002, |
| "loss": 0.5370541214942932, |
| "mean_token_accuracy": 0.7808540761470795, |
| "num_tokens": 3466277.0, |
| "step": 212 |
| }, |
| { |
| "entropy": 0.5353750139474869, |
| "epoch": 0.7947761194029851, |
| "grad_norm": 0.12935572862625122, |
| "learning_rate": 0.0002, |
| "loss": 0.5377589464187622, |
| "mean_token_accuracy": 0.7809354364871979, |
| "num_tokens": 3482704.0, |
| "step": 213 |
| }, |
| { |
| "entropy": 0.5566835999488831, |
| "epoch": 0.7985074626865671, |
| "grad_norm": 0.14469140768051147, |
| "learning_rate": 0.0002, |
| "loss": 0.5535346269607544, |
| "mean_token_accuracy": 0.7752833813428879, |
| "num_tokens": 3499188.0, |
| "step": 214 |
| }, |
| { |
| "entropy": 0.5423330366611481, |
| "epoch": 0.8022388059701493, |
| "grad_norm": 0.1273944228887558, |
| "learning_rate": 0.0002, |
| "loss": 0.5377318859100342, |
| "mean_token_accuracy": 0.7822183817625046, |
| "num_tokens": 3515601.0, |
| "step": 215 |
| }, |
| { |
| "entropy": 0.5524076521396637, |
| "epoch": 0.8059701492537313, |
| "grad_norm": 0.11869970709085464, |
| "learning_rate": 0.0002, |
| "loss": 0.5472428202629089, |
| "mean_token_accuracy": 0.7758542001247406, |
| "num_tokens": 3531754.0, |
| "step": 216 |
| }, |
| { |
| "entropy": 0.542460486292839, |
| "epoch": 0.8097014925373134, |
| "grad_norm": 0.13727042078971863, |
| "learning_rate": 0.0002, |
| "loss": 0.5429178476333618, |
| "mean_token_accuracy": 0.7770164906978607, |
| "num_tokens": 3548154.0, |
| "step": 217 |
| }, |
| { |
| "entropy": 0.5552876144647598, |
| "epoch": 0.8134328358208955, |
| "grad_norm": 0.12215881049633026, |
| "learning_rate": 0.0002, |
| "loss": 0.5609681606292725, |
| "mean_token_accuracy": 0.772984117269516, |
| "num_tokens": 3564502.0, |
| "step": 218 |
| }, |
| { |
| "entropy": 0.5337259769439697, |
| "epoch": 0.8171641791044776, |
| "grad_norm": 0.11268289387226105, |
| "learning_rate": 0.0002, |
| "loss": 0.5395273566246033, |
| "mean_token_accuracy": 0.7825619727373123, |
| "num_tokens": 3580885.0, |
| "step": 219 |
| }, |
| { |
| "entropy": 0.5418431162834167, |
| "epoch": 0.8208955223880597, |
| "grad_norm": 0.11015959084033966, |
| "learning_rate": 0.0002, |
| "loss": 0.5433358550071716, |
| "mean_token_accuracy": 0.7813500016927719, |
| "num_tokens": 3597111.0, |
| "step": 220 |
| }, |
| { |
| "entropy": 0.5243253856897354, |
| "epoch": 0.8246268656716418, |
| "grad_norm": 0.11686558276414871, |
| "learning_rate": 0.0002, |
| "loss": 0.5268687605857849, |
| "mean_token_accuracy": 0.7868369519710541, |
| "num_tokens": 3613408.0, |
| "step": 221 |
| }, |
| { |
| "entropy": 0.5422593802213669, |
| "epoch": 0.8283582089552238, |
| "grad_norm": 0.11102818697690964, |
| "learning_rate": 0.0002, |
| "loss": 0.544140100479126, |
| "mean_token_accuracy": 0.7773995846509933, |
| "num_tokens": 3629913.0, |
| "step": 222 |
| }, |
| { |
| "entropy": 0.5217659026384354, |
| "epoch": 0.832089552238806, |
| "grad_norm": 0.1485036462545395, |
| "learning_rate": 0.0002, |
| "loss": 0.5262643098831177, |
| "mean_token_accuracy": 0.78458371758461, |
| "num_tokens": 3645963.0, |
| "step": 223 |
| }, |
| { |
| "entropy": 0.5594004988670349, |
| "epoch": 0.835820895522388, |
| "grad_norm": 0.12285251170396805, |
| "learning_rate": 0.0002, |
| "loss": 0.5570402145385742, |
| "mean_token_accuracy": 0.777274951338768, |
| "num_tokens": 3662490.0, |
| "step": 224 |
| }, |
| { |
| "entropy": 0.5407282412052155, |
| "epoch": 0.8395522388059702, |
| "grad_norm": 0.15121062099933624, |
| "learning_rate": 0.0002, |
| "loss": 0.5382089614868164, |
| "mean_token_accuracy": 0.7809132933616638, |
| "num_tokens": 3678702.0, |
| "step": 225 |
| }, |
| { |
| "entropy": 0.5616153031587601, |
| "epoch": 0.8432835820895522, |
| "grad_norm": 0.12743256986141205, |
| "learning_rate": 0.0002, |
| "loss": 0.564304530620575, |
| "mean_token_accuracy": 0.7692510485649109, |
| "num_tokens": 3695166.0, |
| "step": 226 |
| }, |
| { |
| "entropy": 0.5475097596645355, |
| "epoch": 0.8470149253731343, |
| "grad_norm": 0.1539081186056137, |
| "learning_rate": 0.0002, |
| "loss": 0.5548152923583984, |
| "mean_token_accuracy": 0.7743651568889618, |
| "num_tokens": 3711616.0, |
| "step": 227 |
| }, |
| { |
| "entropy": 0.5481910109519958, |
| "epoch": 0.8507462686567164, |
| "grad_norm": 0.1484076827764511, |
| "learning_rate": 0.0002, |
| "loss": 0.5484428405761719, |
| "mean_token_accuracy": 0.7790233790874481, |
| "num_tokens": 3727989.0, |
| "step": 228 |
| }, |
| { |
| "entropy": 0.5537362694740295, |
| "epoch": 0.8544776119402985, |
| "grad_norm": 0.1087861955165863, |
| "learning_rate": 0.0002, |
| "loss": 0.5553393363952637, |
| "mean_token_accuracy": 0.7768412679433823, |
| "num_tokens": 3744366.0, |
| "step": 229 |
| }, |
| { |
| "entropy": 0.5454827398061752, |
| "epoch": 0.8582089552238806, |
| "grad_norm": 0.1402716040611267, |
| "learning_rate": 0.0002, |
| "loss": 0.5433673858642578, |
| "mean_token_accuracy": 0.7785142213106155, |
| "num_tokens": 3760739.0, |
| "step": 230 |
| }, |
| { |
| "entropy": 0.5385030508041382, |
| "epoch": 0.8619402985074627, |
| "grad_norm": 0.11684905737638474, |
| "learning_rate": 0.0002, |
| "loss": 0.5348043441772461, |
| "mean_token_accuracy": 0.7803275287151337, |
| "num_tokens": 3776908.0, |
| "step": 231 |
| }, |
| { |
| "entropy": 0.5422927439212799, |
| "epoch": 0.8656716417910447, |
| "grad_norm": 0.12288942188024521, |
| "learning_rate": 0.0002, |
| "loss": 0.5377333164215088, |
| "mean_token_accuracy": 0.7818553447723389, |
| "num_tokens": 3793205.0, |
| "step": 232 |
| }, |
| { |
| "entropy": 0.5357609391212463, |
| "epoch": 0.8694029850746269, |
| "grad_norm": 0.1362125277519226, |
| "learning_rate": 0.0002, |
| "loss": 0.5425816774368286, |
| "mean_token_accuracy": 0.7811540961265564, |
| "num_tokens": 3809862.0, |
| "step": 233 |
| }, |
| { |
| "entropy": 0.5333165973424911, |
| "epoch": 0.8731343283582089, |
| "grad_norm": 0.13793174922466278, |
| "learning_rate": 0.0002, |
| "loss": 0.5445235371589661, |
| "mean_token_accuracy": 0.7829307168722153, |
| "num_tokens": 3826344.0, |
| "step": 234 |
| }, |
| { |
| "entropy": 0.5329077392816544, |
| "epoch": 0.8768656716417911, |
| "grad_norm": 0.1477857381105423, |
| "learning_rate": 0.0002, |
| "loss": 0.5414869785308838, |
| "mean_token_accuracy": 0.7830378264188766, |
| "num_tokens": 3842531.0, |
| "step": 235 |
| }, |
| { |
| "entropy": 0.5350211411714554, |
| "epoch": 0.8805970149253731, |
| "grad_norm": 0.12600158154964447, |
| "learning_rate": 0.0002, |
| "loss": 0.5402480959892273, |
| "mean_token_accuracy": 0.7799132764339447, |
| "num_tokens": 3858515.0, |
| "step": 236 |
| }, |
| { |
| "entropy": 0.5374290496110916, |
| "epoch": 0.8843283582089553, |
| "grad_norm": 0.11570360511541367, |
| "learning_rate": 0.0002, |
| "loss": 0.5416617393493652, |
| "mean_token_accuracy": 0.7798490077257156, |
| "num_tokens": 3874532.0, |
| "step": 237 |
| }, |
| { |
| "entropy": 0.5542231947183609, |
| "epoch": 0.8880597014925373, |
| "grad_norm": 0.1174546405673027, |
| "learning_rate": 0.0002, |
| "loss": 0.5402619242668152, |
| "mean_token_accuracy": 0.783805713057518, |
| "num_tokens": 3890754.0, |
| "step": 238 |
| }, |
| { |
| "entropy": 0.5457619428634644, |
| "epoch": 0.8917910447761194, |
| "grad_norm": 0.1097981184720993, |
| "learning_rate": 0.0002, |
| "loss": 0.5387850999832153, |
| "mean_token_accuracy": 0.7809126079082489, |
| "num_tokens": 3907083.0, |
| "step": 239 |
| }, |
| { |
| "entropy": 0.5505993664264679, |
| "epoch": 0.8955223880597015, |
| "grad_norm": 0.1605318784713745, |
| "learning_rate": 0.0002, |
| "loss": 0.5579661130905151, |
| "mean_token_accuracy": 0.7762876152992249, |
| "num_tokens": 3923407.0, |
| "step": 240 |
| }, |
| { |
| "entropy": 0.530156746506691, |
| "epoch": 0.8992537313432836, |
| "grad_norm": 0.1350473314523697, |
| "learning_rate": 0.0002, |
| "loss": 0.5382238626480103, |
| "mean_token_accuracy": 0.7808812856674194, |
| "num_tokens": 3939911.0, |
| "step": 241 |
| }, |
| { |
| "entropy": 0.5484286248683929, |
| "epoch": 0.9029850746268657, |
| "grad_norm": 0.12200196087360382, |
| "learning_rate": 0.0002, |
| "loss": 0.5492263436317444, |
| "mean_token_accuracy": 0.7769957631826401, |
| "num_tokens": 3956364.0, |
| "step": 242 |
| }, |
| { |
| "entropy": 0.564001739025116, |
| "epoch": 0.9067164179104478, |
| "grad_norm": 0.12944912910461426, |
| "learning_rate": 0.0002, |
| "loss": 0.5527751445770264, |
| "mean_token_accuracy": 0.7752685695886612, |
| "num_tokens": 3972416.0, |
| "step": 243 |
| }, |
| { |
| "entropy": 0.5483242124319077, |
| "epoch": 0.9104477611940298, |
| "grad_norm": 0.11748934537172318, |
| "learning_rate": 0.0002, |
| "loss": 0.539544403553009, |
| "mean_token_accuracy": 0.7804093211889267, |
| "num_tokens": 3988684.0, |
| "step": 244 |
| }, |
| { |
| "entropy": 0.5459276288747787, |
| "epoch": 0.914179104477612, |
| "grad_norm": 0.11960487812757492, |
| "learning_rate": 0.0002, |
| "loss": 0.5457820892333984, |
| "mean_token_accuracy": 0.7765375673770905, |
| "num_tokens": 4005007.0, |
| "step": 245 |
| }, |
| { |
| "entropy": 0.5338165760040283, |
| "epoch": 0.917910447761194, |
| "grad_norm": 0.15193022787570953, |
| "learning_rate": 0.0002, |
| "loss": 0.5428902506828308, |
| "mean_token_accuracy": 0.7773576080799103, |
| "num_tokens": 4021203.0, |
| "step": 246 |
| }, |
| { |
| "entropy": 0.5363887250423431, |
| "epoch": 0.9216417910447762, |
| "grad_norm": 0.12848109006881714, |
| "learning_rate": 0.0002, |
| "loss": 0.5404307842254639, |
| "mean_token_accuracy": 0.7816079705953598, |
| "num_tokens": 4037629.0, |
| "step": 247 |
| }, |
| { |
| "entropy": 0.5554599910974503, |
| "epoch": 0.9253731343283582, |
| "grad_norm": 0.12674938142299652, |
| "learning_rate": 0.0002, |
| "loss": 0.5589783787727356, |
| "mean_token_accuracy": 0.7735093683004379, |
| "num_tokens": 4053712.0, |
| "step": 248 |
| }, |
| { |
| "entropy": 0.5205483213067055, |
| "epoch": 0.9291044776119403, |
| "grad_norm": 0.11436060070991516, |
| "learning_rate": 0.0002, |
| "loss": 0.5130552649497986, |
| "mean_token_accuracy": 0.791333943605423, |
| "num_tokens": 4070059.0, |
| "step": 249 |
| }, |
| { |
| "entropy": 0.5335096418857574, |
| "epoch": 0.9328358208955224, |
| "grad_norm": 0.1217891201376915, |
| "learning_rate": 0.0002, |
| "loss": 0.5378496050834656, |
| "mean_token_accuracy": 0.7827204316854477, |
| "num_tokens": 4086206.0, |
| "step": 250 |
| }, |
| { |
| "entropy": 0.5518199652433395, |
| "epoch": 0.9365671641791045, |
| "grad_norm": 0.12599335610866547, |
| "learning_rate": 0.0002, |
| "loss": 0.5531160831451416, |
| "mean_token_accuracy": 0.7761316746473312, |
| "num_tokens": 4102559.0, |
| "step": 251 |
| }, |
| { |
| "entropy": 0.5334750711917877, |
| "epoch": 0.9402985074626866, |
| "grad_norm": 0.14029689133167267, |
| "learning_rate": 0.0002, |
| "loss": 0.5439124703407288, |
| "mean_token_accuracy": 0.778576448559761, |
| "num_tokens": 4119087.0, |
| "step": 252 |
| }, |
| { |
| "entropy": 0.5320268049836159, |
| "epoch": 0.9440298507462687, |
| "grad_norm": 0.16887114942073822, |
| "learning_rate": 0.0002, |
| "loss": 0.5468459129333496, |
| "mean_token_accuracy": 0.7793016135692596, |
| "num_tokens": 4135364.0, |
| "step": 253 |
| }, |
| { |
| "entropy": 0.5465639531612396, |
| "epoch": 0.9477611940298507, |
| "grad_norm": 0.10890156030654907, |
| "learning_rate": 0.0002, |
| "loss": 0.5426977276802063, |
| "mean_token_accuracy": 0.7816688269376755, |
| "num_tokens": 4151566.0, |
| "step": 254 |
| }, |
| { |
| "entropy": 0.5731644630432129, |
| "epoch": 0.9514925373134329, |
| "grad_norm": 0.12351793795824051, |
| "learning_rate": 0.0002, |
| "loss": 0.5633487701416016, |
| "mean_token_accuracy": 0.7741439342498779, |
| "num_tokens": 4168221.0, |
| "step": 255 |
| }, |
| { |
| "entropy": 0.5632396638393402, |
| "epoch": 0.9552238805970149, |
| "grad_norm": 0.12178079783916473, |
| "learning_rate": 0.0002, |
| "loss": 0.553379237651825, |
| "mean_token_accuracy": 0.7742060422897339, |
| "num_tokens": 4184355.0, |
| "step": 256 |
| }, |
| { |
| "entropy": 0.5469898581504822, |
| "epoch": 0.9589552238805971, |
| "grad_norm": 0.11878334730863571, |
| "learning_rate": 0.0002, |
| "loss": 0.5426266193389893, |
| "mean_token_accuracy": 0.781843975186348, |
| "num_tokens": 4200684.0, |
| "step": 257 |
| }, |
| { |
| "entropy": 0.5285292565822601, |
| "epoch": 0.9626865671641791, |
| "grad_norm": 0.13341104984283447, |
| "learning_rate": 0.0002, |
| "loss": 0.5364401340484619, |
| "mean_token_accuracy": 0.7835129797458649, |
| "num_tokens": 4216892.0, |
| "step": 258 |
| }, |
| { |
| "entropy": 0.5344170331954956, |
| "epoch": 0.9664179104477612, |
| "grad_norm": 0.15148194134235382, |
| "learning_rate": 0.0002, |
| "loss": 0.5506371259689331, |
| "mean_token_accuracy": 0.7755082547664642, |
| "num_tokens": 4232968.0, |
| "step": 259 |
| }, |
| { |
| "entropy": 0.5352845042943954, |
| "epoch": 0.9701492537313433, |
| "grad_norm": 0.1262950450181961, |
| "learning_rate": 0.0002, |
| "loss": 0.5373809933662415, |
| "mean_token_accuracy": 0.78326316177845, |
| "num_tokens": 4249320.0, |
| "step": 260 |
| }, |
| { |
| "entropy": 0.5614136457443237, |
| "epoch": 0.9738805970149254, |
| "grad_norm": 0.1043989509344101, |
| "learning_rate": 0.0002, |
| "loss": 0.5557535886764526, |
| "mean_token_accuracy": 0.7743047475814819, |
| "num_tokens": 4265861.0, |
| "step": 261 |
| }, |
| { |
| "entropy": 0.5495678186416626, |
| "epoch": 0.9776119402985075, |
| "grad_norm": 0.11363489180803299, |
| "learning_rate": 0.0002, |
| "loss": 0.5477911829948425, |
| "mean_token_accuracy": 0.7793729305267334, |
| "num_tokens": 4282124.0, |
| "step": 262 |
| }, |
| { |
| "entropy": 0.5560399442911148, |
| "epoch": 0.9813432835820896, |
| "grad_norm": 0.13492529094219208, |
| "learning_rate": 0.0002, |
| "loss": 0.5476356744766235, |
| "mean_token_accuracy": 0.7775848060846329, |
| "num_tokens": 4298418.0, |
| "step": 263 |
| }, |
| { |
| "entropy": 0.5467169433832169, |
| "epoch": 0.9850746268656716, |
| "grad_norm": 0.11416758596897125, |
| "learning_rate": 0.0002, |
| "loss": 0.5518941879272461, |
| "mean_token_accuracy": 0.7747822403907776, |
| "num_tokens": 4314661.0, |
| "step": 264 |
| }, |
| { |
| "entropy": 0.5399381667375565, |
| "epoch": 0.9888059701492538, |
| "grad_norm": 0.12329445779323578, |
| "learning_rate": 0.0002, |
| "loss": 0.5468961000442505, |
| "mean_token_accuracy": 0.7787373811006546, |
| "num_tokens": 4330935.0, |
| "step": 265 |
| }, |
| { |
| "entropy": 0.5411980152130127, |
| "epoch": 0.9925373134328358, |
| "grad_norm": 0.11828603595495224, |
| "learning_rate": 0.0002, |
| "loss": 0.5393509268760681, |
| "mean_token_accuracy": 0.779281958937645, |
| "num_tokens": 4347264.0, |
| "step": 266 |
| }, |
| { |
| "entropy": 0.5383543074131012, |
| "epoch": 0.996268656716418, |
| "grad_norm": 0.11229536682367325, |
| "learning_rate": 0.0002, |
| "loss": 0.5365405678749084, |
| "mean_token_accuracy": 0.7820824384689331, |
| "num_tokens": 4363841.0, |
| "step": 267 |
| }, |
| { |
| "entropy": 0.5358562171459198, |
| "epoch": 1.0, |
| "grad_norm": 0.13165827095508575, |
| "learning_rate": 0.0002, |
| "loss": 0.5385161638259888, |
| "mean_token_accuracy": 0.7834518551826477, |
| "num_tokens": 4380166.0, |
| "step": 268 |
| }, |
| { |
| "entropy": 0.5379189997911453, |
| "epoch": 1.0037313432835822, |
| "grad_norm": 0.12124547362327576, |
| "learning_rate": 0.0002, |
| "loss": 0.5334954261779785, |
| "mean_token_accuracy": 0.7833122462034225, |
| "num_tokens": 4396136.0, |
| "step": 269 |
| }, |
| { |
| "entropy": 0.5334272235631943, |
| "epoch": 1.007462686567164, |
| "grad_norm": 0.11506830900907516, |
| "learning_rate": 0.0002, |
| "loss": 0.5307578444480896, |
| "mean_token_accuracy": 0.7872792929410934, |
| "num_tokens": 4412387.0, |
| "step": 270 |
| }, |
| { |
| "entropy": 0.5356503129005432, |
| "epoch": 1.0111940298507462, |
| "grad_norm": 0.1304478794336319, |
| "learning_rate": 0.0002, |
| "loss": 0.5306524038314819, |
| "mean_token_accuracy": 0.7832244485616684, |
| "num_tokens": 4428667.0, |
| "step": 271 |
| }, |
| { |
| "entropy": 0.5497903525829315, |
| "epoch": 1.0149253731343284, |
| "grad_norm": 0.15135708451271057, |
| "learning_rate": 0.0002, |
| "loss": 0.560257077217102, |
| "mean_token_accuracy": 0.7752327620983124, |
| "num_tokens": 4445170.0, |
| "step": 272 |
| }, |
| { |
| "entropy": 0.5109370350837708, |
| "epoch": 1.0186567164179103, |
| "grad_norm": 0.13103792071342468, |
| "learning_rate": 0.0002, |
| "loss": 0.5192195773124695, |
| "mean_token_accuracy": 0.7912150472402573, |
| "num_tokens": 4461277.0, |
| "step": 273 |
| }, |
| { |
| "entropy": 0.5275025740265846, |
| "epoch": 1.0223880597014925, |
| "grad_norm": 0.13188353180885315, |
| "learning_rate": 0.0002, |
| "loss": 0.5317577123641968, |
| "mean_token_accuracy": 0.7839648872613907, |
| "num_tokens": 4477626.0, |
| "step": 274 |
| }, |
| { |
| "entropy": 0.527364656329155, |
| "epoch": 1.0261194029850746, |
| "grad_norm": 0.12292712926864624, |
| "learning_rate": 0.0002, |
| "loss": 0.5318381190299988, |
| "mean_token_accuracy": 0.7836149483919144, |
| "num_tokens": 4493733.0, |
| "step": 275 |
| }, |
| { |
| "entropy": 0.5450979322195053, |
| "epoch": 1.0298507462686568, |
| "grad_norm": 0.1152101531624794, |
| "learning_rate": 0.0002, |
| "loss": 0.5406237840652466, |
| "mean_token_accuracy": 0.7790733575820923, |
| "num_tokens": 4510024.0, |
| "step": 276 |
| }, |
| { |
| "entropy": 0.5455430746078491, |
| "epoch": 1.0335820895522387, |
| "grad_norm": 0.13864102959632874, |
| "learning_rate": 0.0002, |
| "loss": 0.5378905534744263, |
| "mean_token_accuracy": 0.7805504500865936, |
| "num_tokens": 4526387.0, |
| "step": 277 |
| }, |
| { |
| "entropy": 0.5328749716281891, |
| "epoch": 1.037313432835821, |
| "grad_norm": 0.11296509951353073, |
| "learning_rate": 0.0002, |
| "loss": 0.5293452739715576, |
| "mean_token_accuracy": 0.7843665927648544, |
| "num_tokens": 4542547.0, |
| "step": 278 |
| }, |
| { |
| "entropy": 0.5041251480579376, |
| "epoch": 1.041044776119403, |
| "grad_norm": 0.13656830787658691, |
| "learning_rate": 0.0002, |
| "loss": 0.5081103444099426, |
| "mean_token_accuracy": 0.7913767695426941, |
| "num_tokens": 4558579.0, |
| "step": 279 |
| }, |
| { |
| "entropy": 0.521636962890625, |
| "epoch": 1.044776119402985, |
| "grad_norm": 0.14005547761917114, |
| "learning_rate": 0.0002, |
| "loss": 0.5281530618667603, |
| "mean_token_accuracy": 0.7840014696121216, |
| "num_tokens": 4574899.0, |
| "step": 280 |
| }, |
| { |
| "entropy": 0.5319028049707413, |
| "epoch": 1.0485074626865671, |
| "grad_norm": 0.13617247343063354, |
| "learning_rate": 0.0002, |
| "loss": 0.5312793254852295, |
| "mean_token_accuracy": 0.7853630483150482, |
| "num_tokens": 4591253.0, |
| "step": 281 |
| }, |
| { |
| "entropy": 0.5084699764847755, |
| "epoch": 1.0522388059701493, |
| "grad_norm": 0.16692741215229034, |
| "learning_rate": 0.0002, |
| "loss": 0.5056694149971008, |
| "mean_token_accuracy": 0.7926139831542969, |
| "num_tokens": 4607402.0, |
| "step": 282 |
| }, |
| { |
| "entropy": 0.5244627818465233, |
| "epoch": 1.0559701492537314, |
| "grad_norm": 0.15793491899967194, |
| "learning_rate": 0.0002, |
| "loss": 0.5185582637786865, |
| "mean_token_accuracy": 0.7895916700363159, |
| "num_tokens": 4623784.0, |
| "step": 283 |
| }, |
| { |
| "entropy": 0.534734770655632, |
| "epoch": 1.0597014925373134, |
| "grad_norm": 0.1454075276851654, |
| "learning_rate": 0.0002, |
| "loss": 0.5379710793495178, |
| "mean_token_accuracy": 0.7811556309461594, |
| "num_tokens": 4640136.0, |
| "step": 284 |
| }, |
| { |
| "entropy": 0.5411804914474487, |
| "epoch": 1.0634328358208955, |
| "grad_norm": 0.1313299983739853, |
| "learning_rate": 0.0002, |
| "loss": 0.541705846786499, |
| "mean_token_accuracy": 0.7807521224021912, |
| "num_tokens": 4656611.0, |
| "step": 285 |
| }, |
| { |
| "entropy": 0.5163163989782333, |
| "epoch": 1.0671641791044777, |
| "grad_norm": 0.17188362777233124, |
| "learning_rate": 0.0002, |
| "loss": 0.5217083692550659, |
| "mean_token_accuracy": 0.789138063788414, |
| "num_tokens": 4673147.0, |
| "step": 286 |
| }, |
| { |
| "entropy": 0.5266972482204437, |
| "epoch": 1.0708955223880596, |
| "grad_norm": 0.11896864324808121, |
| "learning_rate": 0.0002, |
| "loss": 0.5250995755195618, |
| "mean_token_accuracy": 0.7870500683784485, |
| "num_tokens": 4689405.0, |
| "step": 287 |
| }, |
| { |
| "entropy": 0.5317090004682541, |
| "epoch": 1.0746268656716418, |
| "grad_norm": 0.13104526698589325, |
| "learning_rate": 0.0002, |
| "loss": 0.5348522067070007, |
| "mean_token_accuracy": 0.7840689569711685, |
| "num_tokens": 4705558.0, |
| "step": 288 |
| }, |
| { |
| "entropy": 0.5158203095197678, |
| "epoch": 1.078358208955224, |
| "grad_norm": 0.1275770515203476, |
| "learning_rate": 0.0002, |
| "loss": 0.5190145969390869, |
| "mean_token_accuracy": 0.7877327054738998, |
| "num_tokens": 4721890.0, |
| "step": 289 |
| }, |
| { |
| "entropy": 0.5378855019807816, |
| "epoch": 1.0820895522388059, |
| "grad_norm": 0.1394091099500656, |
| "learning_rate": 0.0002, |
| "loss": 0.5460761785507202, |
| "mean_token_accuracy": 0.7771806716918945, |
| "num_tokens": 4738329.0, |
| "step": 290 |
| }, |
| { |
| "entropy": 0.5318425595760345, |
| "epoch": 1.085820895522388, |
| "grad_norm": 0.1306176483631134, |
| "learning_rate": 0.0002, |
| "loss": 0.5319812297821045, |
| "mean_token_accuracy": 0.7831690907478333, |
| "num_tokens": 4754645.0, |
| "step": 291 |
| }, |
| { |
| "entropy": 0.5362639278173447, |
| "epoch": 1.0895522388059702, |
| "grad_norm": 0.11495408415794373, |
| "learning_rate": 0.0002, |
| "loss": 0.5298461318016052, |
| "mean_token_accuracy": 0.7854064851999283, |
| "num_tokens": 4770684.0, |
| "step": 292 |
| }, |
| { |
| "entropy": 0.5535065084695816, |
| "epoch": 1.0932835820895523, |
| "grad_norm": 0.1391877681016922, |
| "learning_rate": 0.0002, |
| "loss": 0.5405028462409973, |
| "mean_token_accuracy": 0.7819728404283524, |
| "num_tokens": 4787120.0, |
| "step": 293 |
| }, |
| { |
| "entropy": 0.5380821079015732, |
| "epoch": 1.0970149253731343, |
| "grad_norm": 0.12256049364805222, |
| "learning_rate": 0.0002, |
| "loss": 0.5349643230438232, |
| "mean_token_accuracy": 0.7820280939340591, |
| "num_tokens": 4803563.0, |
| "step": 294 |
| }, |
| { |
| "entropy": 0.5238383859395981, |
| "epoch": 1.1007462686567164, |
| "grad_norm": 0.15560781955718994, |
| "learning_rate": 0.0002, |
| "loss": 0.5352126359939575, |
| "mean_token_accuracy": 0.780738353729248, |
| "num_tokens": 4819844.0, |
| "step": 295 |
| }, |
| { |
| "entropy": 0.5378861427307129, |
| "epoch": 1.1044776119402986, |
| "grad_norm": 0.13858315348625183, |
| "learning_rate": 0.0002, |
| "loss": 0.5486723780632019, |
| "mean_token_accuracy": 0.7793371677398682, |
| "num_tokens": 4836369.0, |
| "step": 296 |
| }, |
| { |
| "entropy": 0.5251282304525375, |
| "epoch": 1.1082089552238805, |
| "grad_norm": 0.12815874814987183, |
| "learning_rate": 0.0002, |
| "loss": 0.5300880670547485, |
| "mean_token_accuracy": 0.7837522327899933, |
| "num_tokens": 4852748.0, |
| "step": 297 |
| }, |
| { |
| "entropy": 0.5302699953317642, |
| "epoch": 1.1119402985074627, |
| "grad_norm": 0.13173414766788483, |
| "learning_rate": 0.0002, |
| "loss": 0.5258138179779053, |
| "mean_token_accuracy": 0.7880112379789352, |
| "num_tokens": 4869067.0, |
| "step": 298 |
| }, |
| { |
| "entropy": 0.5506465286016464, |
| "epoch": 1.1156716417910448, |
| "grad_norm": 0.13485312461853027, |
| "learning_rate": 0.0002, |
| "loss": 0.5452370047569275, |
| "mean_token_accuracy": 0.7781666219234467, |
| "num_tokens": 4885458.0, |
| "step": 299 |
| }, |
| { |
| "entropy": 0.5438030511140823, |
| "epoch": 1.1194029850746268, |
| "grad_norm": 0.11468689143657684, |
| "learning_rate": 0.0002, |
| "loss": 0.5406007766723633, |
| "mean_token_accuracy": 0.7828387320041656, |
| "num_tokens": 4902011.0, |
| "step": 300 |
| }, |
| { |
| "entropy": 0.5346951633691788, |
| "epoch": 1.123134328358209, |
| "grad_norm": 0.18234607577323914, |
| "learning_rate": 0.0002, |
| "loss": 0.547614574432373, |
| "mean_token_accuracy": 0.7783486694097519, |
| "num_tokens": 4918391.0, |
| "step": 301 |
| }, |
| { |
| "entropy": 0.525826022028923, |
| "epoch": 1.126865671641791, |
| "grad_norm": 0.1330524981021881, |
| "learning_rate": 0.0002, |
| "loss": 0.5309886932373047, |
| "mean_token_accuracy": 0.7852450311183929, |
| "num_tokens": 4934473.0, |
| "step": 302 |
| }, |
| { |
| "entropy": 0.5369850844144821, |
| "epoch": 1.1305970149253732, |
| "grad_norm": 0.19903826713562012, |
| "learning_rate": 0.0002, |
| "loss": 0.5340496301651001, |
| "mean_token_accuracy": 0.7836938202381134, |
| "num_tokens": 4950866.0, |
| "step": 303 |
| }, |
| { |
| "entropy": 0.5211250185966492, |
| "epoch": 1.1343283582089552, |
| "grad_norm": 0.11684370040893555, |
| "learning_rate": 0.0002, |
| "loss": 0.5170819759368896, |
| "mean_token_accuracy": 0.7884699255228043, |
| "num_tokens": 4966997.0, |
| "step": 304 |
| }, |
| { |
| "entropy": 0.5429866313934326, |
| "epoch": 1.1380597014925373, |
| "grad_norm": 0.18943680822849274, |
| "learning_rate": 0.0002, |
| "loss": 0.5370672941207886, |
| "mean_token_accuracy": 0.7861049920320511, |
| "num_tokens": 4983682.0, |
| "step": 305 |
| }, |
| { |
| "entropy": 0.5364594161510468, |
| "epoch": 1.1417910447761195, |
| "grad_norm": 0.12661154568195343, |
| "learning_rate": 0.0002, |
| "loss": 0.5316832065582275, |
| "mean_token_accuracy": 0.7845533788204193, |
| "num_tokens": 5000291.0, |
| "step": 306 |
| }, |
| { |
| "entropy": 0.5343837141990662, |
| "epoch": 1.1455223880597014, |
| "grad_norm": 0.14650367200374603, |
| "learning_rate": 0.0002, |
| "loss": 0.5416120886802673, |
| "mean_token_accuracy": 0.7780052423477173, |
| "num_tokens": 5016325.0, |
| "step": 307 |
| }, |
| { |
| "entropy": 0.5302508473396301, |
| "epoch": 1.1492537313432836, |
| "grad_norm": 0.20089952647686005, |
| "learning_rate": 0.0002, |
| "loss": 0.5454406142234802, |
| "mean_token_accuracy": 0.7800105661153793, |
| "num_tokens": 5032656.0, |
| "step": 308 |
| }, |
| { |
| "entropy": 0.5269667655229568, |
| "epoch": 1.1529850746268657, |
| "grad_norm": 0.13522252440452576, |
| "learning_rate": 0.0002, |
| "loss": 0.5410094261169434, |
| "mean_token_accuracy": 0.7831864953041077, |
| "num_tokens": 5049009.0, |
| "step": 309 |
| }, |
| { |
| "entropy": 0.5341744273900986, |
| "epoch": 1.1567164179104479, |
| "grad_norm": 0.1476895660161972, |
| "learning_rate": 0.0002, |
| "loss": 0.5322161912918091, |
| "mean_token_accuracy": 0.7857746630907059, |
| "num_tokens": 5065552.0, |
| "step": 310 |
| }, |
| { |
| "entropy": 0.5290868133306503, |
| "epoch": 1.1604477611940298, |
| "grad_norm": 0.1331428736448288, |
| "learning_rate": 0.0002, |
| "loss": 0.522707462310791, |
| "mean_token_accuracy": 0.7874923199415207, |
| "num_tokens": 5081914.0, |
| "step": 311 |
| }, |
| { |
| "entropy": 0.5462541282176971, |
| "epoch": 1.164179104477612, |
| "grad_norm": 0.12951326370239258, |
| "learning_rate": 0.0002, |
| "loss": 0.5369530320167542, |
| "mean_token_accuracy": 0.7838002741336823, |
| "num_tokens": 5098199.0, |
| "step": 312 |
| }, |
| { |
| "entropy": 0.551513135433197, |
| "epoch": 1.1679104477611941, |
| "grad_norm": 0.14431481063365936, |
| "learning_rate": 0.0002, |
| "loss": 0.5480935573577881, |
| "mean_token_accuracy": 0.776902437210083, |
| "num_tokens": 5114428.0, |
| "step": 313 |
| }, |
| { |
| "entropy": 0.529523603618145, |
| "epoch": 1.171641791044776, |
| "grad_norm": 0.13575024902820587, |
| "learning_rate": 0.0002, |
| "loss": 0.5334714651107788, |
| "mean_token_accuracy": 0.7833124548196793, |
| "num_tokens": 5130815.0, |
| "step": 314 |
| }, |
| { |
| "entropy": 0.5216026604175568, |
| "epoch": 1.1753731343283582, |
| "grad_norm": 0.15921851992607117, |
| "learning_rate": 0.0002, |
| "loss": 0.5353596806526184, |
| "mean_token_accuracy": 0.7833358347415924, |
| "num_tokens": 5146990.0, |
| "step": 315 |
| }, |
| { |
| "entropy": 0.5145125165581703, |
| "epoch": 1.1791044776119404, |
| "grad_norm": 0.15616123378276825, |
| "learning_rate": 0.0002, |
| "loss": 0.5262758135795593, |
| "mean_token_accuracy": 0.7852197736501694, |
| "num_tokens": 5163296.0, |
| "step": 316 |
| }, |
| { |
| "entropy": 0.535229504108429, |
| "epoch": 1.1828358208955223, |
| "grad_norm": 0.12585321068763733, |
| "learning_rate": 0.0002, |
| "loss": 0.5314123034477234, |
| "mean_token_accuracy": 0.7854515314102173, |
| "num_tokens": 5179530.0, |
| "step": 317 |
| }, |
| { |
| "entropy": 0.5560932010412216, |
| "epoch": 1.1865671641791045, |
| "grad_norm": 0.14919495582580566, |
| "learning_rate": 0.0002, |
| "loss": 0.5446042418479919, |
| "mean_token_accuracy": 0.7800046056509018, |
| "num_tokens": 5195710.0, |
| "step": 318 |
| }, |
| { |
| "entropy": 0.5391595363616943, |
| "epoch": 1.1902985074626866, |
| "grad_norm": 0.1282576620578766, |
| "learning_rate": 0.0002, |
| "loss": 0.5283731818199158, |
| "mean_token_accuracy": 0.7876599133014679, |
| "num_tokens": 5211945.0, |
| "step": 319 |
| }, |
| { |
| "entropy": 0.5341296344995499, |
| "epoch": 1.1940298507462686, |
| "grad_norm": 0.1332569122314453, |
| "learning_rate": 0.0002, |
| "loss": 0.5286970138549805, |
| "mean_token_accuracy": 0.7866556644439697, |
| "num_tokens": 5228316.0, |
| "step": 320 |
| }, |
| { |
| "entropy": 0.5466953366994858, |
| "epoch": 1.1977611940298507, |
| "grad_norm": 0.1697065532207489, |
| "learning_rate": 0.0002, |
| "loss": 0.5528241395950317, |
| "mean_token_accuracy": 0.7779474407434464, |
| "num_tokens": 5244879.0, |
| "step": 321 |
| }, |
| { |
| "entropy": 0.525031566619873, |
| "epoch": 1.2014925373134329, |
| "grad_norm": 0.14148105680942535, |
| "learning_rate": 0.0002, |
| "loss": 0.5351812839508057, |
| "mean_token_accuracy": 0.7808531671762466, |
| "num_tokens": 5261038.0, |
| "step": 322 |
| }, |
| { |
| "entropy": 0.5082430616021156, |
| "epoch": 1.205223880597015, |
| "grad_norm": 0.17106738686561584, |
| "learning_rate": 0.0002, |
| "loss": 0.5224143862724304, |
| "mean_token_accuracy": 0.7910729199647903, |
| "num_tokens": 5277354.0, |
| "step": 323 |
| }, |
| { |
| "entropy": 0.5237574726343155, |
| "epoch": 1.208955223880597, |
| "grad_norm": 0.1340343952178955, |
| "learning_rate": 0.0002, |
| "loss": 0.5248754024505615, |
| "mean_token_accuracy": 0.7857117801904678, |
| "num_tokens": 5293487.0, |
| "step": 324 |
| }, |
| { |
| "entropy": 0.5556118786334991, |
| "epoch": 1.212686567164179, |
| "grad_norm": 0.13427753746509552, |
| "learning_rate": 0.0002, |
| "loss": 0.5479714870452881, |
| "mean_token_accuracy": 0.7781947702169418, |
| "num_tokens": 5309935.0, |
| "step": 325 |
| }, |
| { |
| "entropy": 0.5380184501409531, |
| "epoch": 1.2164179104477613, |
| "grad_norm": 0.10940642654895782, |
| "learning_rate": 0.0002, |
| "loss": 0.539406418800354, |
| "mean_token_accuracy": 0.7808454930782318, |
| "num_tokens": 5326360.0, |
| "step": 326 |
| }, |
| { |
| "entropy": 0.5419078320264816, |
| "epoch": 1.2201492537313432, |
| "grad_norm": 0.12656880915164948, |
| "learning_rate": 0.0002, |
| "loss": 0.5394376516342163, |
| "mean_token_accuracy": 0.7804330289363861, |
| "num_tokens": 5342851.0, |
| "step": 327 |
| }, |
| { |
| "entropy": 0.529717817902565, |
| "epoch": 1.2238805970149254, |
| "grad_norm": 0.12337954342365265, |
| "learning_rate": 0.0002, |
| "loss": 0.5289559960365295, |
| "mean_token_accuracy": 0.7851734757423401, |
| "num_tokens": 5359329.0, |
| "step": 328 |
| }, |
| { |
| "entropy": 0.5380574017763138, |
| "epoch": 1.2276119402985075, |
| "grad_norm": 0.12867099046707153, |
| "learning_rate": 0.0002, |
| "loss": 0.5476554036140442, |
| "mean_token_accuracy": 0.7801157683134079, |
| "num_tokens": 5375805.0, |
| "step": 329 |
| }, |
| { |
| "entropy": 0.5268337428569794, |
| "epoch": 1.2313432835820897, |
| "grad_norm": 0.1258673518896103, |
| "learning_rate": 0.0002, |
| "loss": 0.5261831283569336, |
| "mean_token_accuracy": 0.7846096456050873, |
| "num_tokens": 5392238.0, |
| "step": 330 |
| }, |
| { |
| "entropy": 0.5357686281204224, |
| "epoch": 1.2350746268656716, |
| "grad_norm": 0.12291644513607025, |
| "learning_rate": 0.0002, |
| "loss": 0.5372765064239502, |
| "mean_token_accuracy": 0.7802401781082153, |
| "num_tokens": 5408651.0, |
| "step": 331 |
| }, |
| { |
| "entropy": 0.527915745973587, |
| "epoch": 1.2388059701492538, |
| "grad_norm": 0.13585242629051208, |
| "learning_rate": 0.0002, |
| "loss": 0.5243189334869385, |
| "mean_token_accuracy": 0.7886078208684921, |
| "num_tokens": 5424924.0, |
| "step": 332 |
| }, |
| { |
| "entropy": 0.5427118986845016, |
| "epoch": 1.242537313432836, |
| "grad_norm": 0.12335648387670517, |
| "learning_rate": 0.0002, |
| "loss": 0.5404365658760071, |
| "mean_token_accuracy": 0.7831614464521408, |
| "num_tokens": 5441203.0, |
| "step": 333 |
| }, |
| { |
| "entropy": 0.5376623272895813, |
| "epoch": 1.2462686567164178, |
| "grad_norm": 0.13139311969280243, |
| "learning_rate": 0.0002, |
| "loss": 0.5389487147331238, |
| "mean_token_accuracy": 0.7810561805963516, |
| "num_tokens": 5457484.0, |
| "step": 334 |
| }, |
| { |
| "entropy": 0.5217746645212173, |
| "epoch": 1.25, |
| "grad_norm": 0.1306585967540741, |
| "learning_rate": 0.0002, |
| "loss": 0.5279544591903687, |
| "mean_token_accuracy": 0.7842136025428772, |
| "num_tokens": 5473729.0, |
| "step": 335 |
| }, |
| { |
| "entropy": 0.5274703353643417, |
| "epoch": 1.2537313432835822, |
| "grad_norm": 0.14970748126506805, |
| "learning_rate": 0.0002, |
| "loss": 0.5365568399429321, |
| "mean_token_accuracy": 0.7839529067277908, |
| "num_tokens": 5489912.0, |
| "step": 336 |
| }, |
| { |
| "entropy": 0.5338452607393265, |
| "epoch": 1.2574626865671643, |
| "grad_norm": 0.14781597256660461, |
| "learning_rate": 0.0002, |
| "loss": 0.5315080881118774, |
| "mean_token_accuracy": 0.7842566519975662, |
| "num_tokens": 5506142.0, |
| "step": 337 |
| }, |
| { |
| "entropy": 0.5166743621230125, |
| "epoch": 1.2611940298507462, |
| "grad_norm": 0.13472828269004822, |
| "learning_rate": 0.0002, |
| "loss": 0.5181722640991211, |
| "mean_token_accuracy": 0.7923096716403961, |
| "num_tokens": 5522391.0, |
| "step": 338 |
| }, |
| { |
| "entropy": 0.5320258289575577, |
| "epoch": 1.2649253731343284, |
| "grad_norm": 0.1183825433254242, |
| "learning_rate": 0.0002, |
| "loss": 0.5311023592948914, |
| "mean_token_accuracy": 0.7839165031909943, |
| "num_tokens": 5538704.0, |
| "step": 339 |
| }, |
| { |
| "entropy": 0.5334226191043854, |
| "epoch": 1.2686567164179103, |
| "grad_norm": 0.14933781325817108, |
| "learning_rate": 0.0002, |
| "loss": 0.5333026647567749, |
| "mean_token_accuracy": 0.7848058938980103, |
| "num_tokens": 5555055.0, |
| "step": 340 |
| }, |
| { |
| "entropy": 0.537438154220581, |
| "epoch": 1.2723880597014925, |
| "grad_norm": 0.12592282891273499, |
| "learning_rate": 0.0002, |
| "loss": 0.5388475060462952, |
| "mean_token_accuracy": 0.7794025540351868, |
| "num_tokens": 5571313.0, |
| "step": 341 |
| }, |
| { |
| "entropy": 0.5343907475471497, |
| "epoch": 1.2761194029850746, |
| "grad_norm": 0.12412987649440765, |
| "learning_rate": 0.0002, |
| "loss": 0.5304772853851318, |
| "mean_token_accuracy": 0.7845743894577026, |
| "num_tokens": 5587580.0, |
| "step": 342 |
| }, |
| { |
| "entropy": 0.5301965326070786, |
| "epoch": 1.2798507462686568, |
| "grad_norm": 0.16127265989780426, |
| "learning_rate": 0.0002, |
| "loss": 0.5408694744110107, |
| "mean_token_accuracy": 0.7812603116035461, |
| "num_tokens": 5603839.0, |
| "step": 343 |
| }, |
| { |
| "entropy": 0.5359622687101364, |
| "epoch": 1.2835820895522387, |
| "grad_norm": 0.13306041061878204, |
| "learning_rate": 0.0002, |
| "loss": 0.530299186706543, |
| "mean_token_accuracy": 0.7862377017736435, |
| "num_tokens": 5620424.0, |
| "step": 344 |
| }, |
| { |
| "entropy": 0.5345901101827621, |
| "epoch": 1.287313432835821, |
| "grad_norm": 0.1319621503353119, |
| "learning_rate": 0.0002, |
| "loss": 0.5262933969497681, |
| "mean_token_accuracy": 0.7865736335515976, |
| "num_tokens": 5636665.0, |
| "step": 345 |
| }, |
| { |
| "entropy": 0.5548627972602844, |
| "epoch": 1.291044776119403, |
| "grad_norm": 0.14354409277439117, |
| "learning_rate": 0.0002, |
| "loss": 0.5601977109909058, |
| "mean_token_accuracy": 0.7732233703136444, |
| "num_tokens": 5652965.0, |
| "step": 346 |
| }, |
| { |
| "entropy": 0.5372962802648544, |
| "epoch": 1.294776119402985, |
| "grad_norm": 0.14606493711471558, |
| "learning_rate": 0.0002, |
| "loss": 0.5434338450431824, |
| "mean_token_accuracy": 0.778582826256752, |
| "num_tokens": 5669095.0, |
| "step": 347 |
| }, |
| { |
| "entropy": 0.5190770104527473, |
| "epoch": 1.2985074626865671, |
| "grad_norm": 0.1386556774377823, |
| "learning_rate": 0.0002, |
| "loss": 0.5281475782394409, |
| "mean_token_accuracy": 0.7864956706762314, |
| "num_tokens": 5685417.0, |
| "step": 348 |
| }, |
| { |
| "entropy": 0.5303623229265213, |
| "epoch": 1.3022388059701493, |
| "grad_norm": 0.1381293386220932, |
| "learning_rate": 0.0002, |
| "loss": 0.5297045707702637, |
| "mean_token_accuracy": 0.787194088101387, |
| "num_tokens": 5701479.0, |
| "step": 349 |
| }, |
| { |
| "entropy": 0.5480183511972427, |
| "epoch": 1.3059701492537314, |
| "grad_norm": 0.14476633071899414, |
| "learning_rate": 0.0002, |
| "loss": 0.5485386848449707, |
| "mean_token_accuracy": 0.7778423577547073, |
| "num_tokens": 5717835.0, |
| "step": 350 |
| }, |
| { |
| "entropy": 0.5416014343500137, |
| "epoch": 1.3097014925373134, |
| "grad_norm": 0.1554112285375595, |
| "learning_rate": 0.0002, |
| "loss": 0.5435051321983337, |
| "mean_token_accuracy": 0.7781781554222107, |
| "num_tokens": 5734186.0, |
| "step": 351 |
| }, |
| { |
| "entropy": 0.5319079011678696, |
| "epoch": 1.3134328358208955, |
| "grad_norm": 0.12464872002601624, |
| "learning_rate": 0.0002, |
| "loss": 0.5298937559127808, |
| "mean_token_accuracy": 0.7838649600744247, |
| "num_tokens": 5750536.0, |
| "step": 352 |
| }, |
| { |
| "entropy": 0.5341033190488815, |
| "epoch": 1.3171641791044777, |
| "grad_norm": 0.14333154261112213, |
| "learning_rate": 0.0002, |
| "loss": 0.5349255204200745, |
| "mean_token_accuracy": 0.7815588861703873, |
| "num_tokens": 5767125.0, |
| "step": 353 |
| }, |
| { |
| "entropy": 0.5315425246953964, |
| "epoch": 1.3208955223880596, |
| "grad_norm": 0.17208492755889893, |
| "learning_rate": 0.0002, |
| "loss": 0.5414083003997803, |
| "mean_token_accuracy": 0.7796328663825989, |
| "num_tokens": 5783479.0, |
| "step": 354 |
| }, |
| { |
| "entropy": 0.5361844450235367, |
| "epoch": 1.3246268656716418, |
| "grad_norm": 0.1708763688802719, |
| "learning_rate": 0.0002, |
| "loss": 0.5366734266281128, |
| "mean_token_accuracy": 0.7876496613025665, |
| "num_tokens": 5799910.0, |
| "step": 355 |
| }, |
| { |
| "entropy": 0.5498687773942947, |
| "epoch": 1.328358208955224, |
| "grad_norm": 0.17310158908367157, |
| "learning_rate": 0.0002, |
| "loss": 0.5564769506454468, |
| "mean_token_accuracy": 0.7720024138689041, |
| "num_tokens": 5816362.0, |
| "step": 356 |
| }, |
| { |
| "entropy": 0.5196370631456375, |
| "epoch": 1.332089552238806, |
| "grad_norm": 0.1835440844297409, |
| "learning_rate": 0.0002, |
| "loss": 0.5195181369781494, |
| "mean_token_accuracy": 0.7891091108322144, |
| "num_tokens": 5832701.0, |
| "step": 357 |
| }, |
| { |
| "entropy": 0.5453412234783173, |
| "epoch": 1.335820895522388, |
| "grad_norm": 0.14006684720516205, |
| "learning_rate": 0.0002, |
| "loss": 0.5332884788513184, |
| "mean_token_accuracy": 0.7857294678688049, |
| "num_tokens": 5849223.0, |
| "step": 358 |
| }, |
| { |
| "entropy": 0.5444671809673309, |
| "epoch": 1.3395522388059702, |
| "grad_norm": 0.1194646805524826, |
| "learning_rate": 0.0002, |
| "loss": 0.5364049673080444, |
| "mean_token_accuracy": 0.7796007543802261, |
| "num_tokens": 5865804.0, |
| "step": 359 |
| }, |
| { |
| "entropy": 0.544802263379097, |
| "epoch": 1.3432835820895521, |
| "grad_norm": 0.14779537916183472, |
| "learning_rate": 0.0002, |
| "loss": 0.5425033569335938, |
| "mean_token_accuracy": 0.7787866294384003, |
| "num_tokens": 5882072.0, |
| "step": 360 |
| }, |
| { |
| "entropy": 0.5151367485523224, |
| "epoch": 1.3470149253731343, |
| "grad_norm": 0.1605149209499359, |
| "learning_rate": 0.0002, |
| "loss": 0.5231281518936157, |
| "mean_token_accuracy": 0.7887785583734512, |
| "num_tokens": 5898462.0, |
| "step": 361 |
| }, |
| { |
| "entropy": 0.5230250060558319, |
| "epoch": 1.3507462686567164, |
| "grad_norm": 0.15028275549411774, |
| "learning_rate": 0.0002, |
| "loss": 0.5356472730636597, |
| "mean_token_accuracy": 0.7828852087259293, |
| "num_tokens": 5914774.0, |
| "step": 362 |
| }, |
| { |
| "entropy": 0.5213946998119354, |
| "epoch": 1.3544776119402986, |
| "grad_norm": 0.1838817298412323, |
| "learning_rate": 0.0002, |
| "loss": 0.5313252806663513, |
| "mean_token_accuracy": 0.7832992523908615, |
| "num_tokens": 5931259.0, |
| "step": 363 |
| }, |
| { |
| "entropy": 0.5186553969979286, |
| "epoch": 1.3582089552238805, |
| "grad_norm": 0.2248377501964569, |
| "learning_rate": 0.0002, |
| "loss": 0.5184941291809082, |
| "mean_token_accuracy": 0.7860872000455856, |
| "num_tokens": 5947748.0, |
| "step": 364 |
| }, |
| { |
| "entropy": 0.544600322842598, |
| "epoch": 1.3619402985074627, |
| "grad_norm": 0.14680452644824982, |
| "learning_rate": 0.0002, |
| "loss": 0.5427520275115967, |
| "mean_token_accuracy": 0.7797152549028397, |
| "num_tokens": 5964194.0, |
| "step": 365 |
| }, |
| { |
| "entropy": 0.5615398287773132, |
| "epoch": 1.3656716417910448, |
| "grad_norm": 0.1536853313446045, |
| "learning_rate": 0.0002, |
| "loss": 0.5516420006752014, |
| "mean_token_accuracy": 0.7758041322231293, |
| "num_tokens": 5980772.0, |
| "step": 366 |
| }, |
| { |
| "entropy": 0.5228852480649948, |
| "epoch": 1.3694029850746268, |
| "grad_norm": 0.13101591169834137, |
| "learning_rate": 0.0002, |
| "loss": 0.5237991213798523, |
| "mean_token_accuracy": 0.7876576334238052, |
| "num_tokens": 5997044.0, |
| "step": 367 |
| }, |
| { |
| "entropy": 0.5480576753616333, |
| "epoch": 1.373134328358209, |
| "grad_norm": 0.16748443245887756, |
| "learning_rate": 0.0002, |
| "loss": 0.5517894625663757, |
| "mean_token_accuracy": 0.7773436009883881, |
| "num_tokens": 6013386.0, |
| "step": 368 |
| }, |
| { |
| "entropy": 0.5288672149181366, |
| "epoch": 1.376865671641791, |
| "grad_norm": 0.19619230926036835, |
| "learning_rate": 0.0002, |
| "loss": 0.5373691916465759, |
| "mean_token_accuracy": 0.780240923166275, |
| "num_tokens": 6029720.0, |
| "step": 369 |
| }, |
| { |
| "entropy": 0.5135577768087387, |
| "epoch": 1.3805970149253732, |
| "grad_norm": 0.2507493793964386, |
| "learning_rate": 0.0002, |
| "loss": 0.5186033844947815, |
| "mean_token_accuracy": 0.7899419814348221, |
| "num_tokens": 6045961.0, |
| "step": 370 |
| }, |
| { |
| "entropy": 0.5094781517982483, |
| "epoch": 1.3843283582089552, |
| "grad_norm": 0.13880524039268494, |
| "learning_rate": 0.0002, |
| "loss": 0.511122465133667, |
| "mean_token_accuracy": 0.7924890667200089, |
| "num_tokens": 6062070.0, |
| "step": 371 |
| }, |
| { |
| "entropy": 0.5384761989116669, |
| "epoch": 1.3880597014925373, |
| "grad_norm": 0.15249879658222198, |
| "learning_rate": 0.0002, |
| "loss": 0.5380364656448364, |
| "mean_token_accuracy": 0.7848134189844131, |
| "num_tokens": 6078391.0, |
| "step": 372 |
| }, |
| { |
| "entropy": 0.5328753143548965, |
| "epoch": 1.3917910447761195, |
| "grad_norm": 0.2661060094833374, |
| "learning_rate": 0.0002, |
| "loss": 0.537780225276947, |
| "mean_token_accuracy": 0.7847133278846741, |
| "num_tokens": 6094477.0, |
| "step": 373 |
| }, |
| { |
| "entropy": 0.5370789244771004, |
| "epoch": 1.3955223880597014, |
| "grad_norm": 0.2634597420692444, |
| "learning_rate": 0.0002, |
| "loss": 0.5364189147949219, |
| "mean_token_accuracy": 0.7840721160173416, |
| "num_tokens": 6110772.0, |
| "step": 374 |
| }, |
| { |
| "entropy": 0.5268249362707138, |
| "epoch": 1.3992537313432836, |
| "grad_norm": 0.22895245254039764, |
| "learning_rate": 0.0002, |
| "loss": 0.5262951254844666, |
| "mean_token_accuracy": 0.789451465010643, |
| "num_tokens": 6127325.0, |
| "step": 375 |
| }, |
| { |
| "entropy": 0.5351117700338364, |
| "epoch": 1.4029850746268657, |
| "grad_norm": 0.19925457239151, |
| "learning_rate": 0.0002, |
| "loss": 0.5433847904205322, |
| "mean_token_accuracy": 0.7802492529153824, |
| "num_tokens": 6143882.0, |
| "step": 376 |
| }, |
| { |
| "entropy": 0.5502782762050629, |
| "epoch": 1.4067164179104479, |
| "grad_norm": 0.17558914422988892, |
| "learning_rate": 0.0002, |
| "loss": 0.5481917858123779, |
| "mean_token_accuracy": 0.7766920328140259, |
| "num_tokens": 6160190.0, |
| "step": 377 |
| }, |
| { |
| "entropy": 0.5352517813444138, |
| "epoch": 1.4104477611940298, |
| "grad_norm": 0.146221324801445, |
| "learning_rate": 0.0002, |
| "loss": 0.5301755666732788, |
| "mean_token_accuracy": 0.7837377339601517, |
| "num_tokens": 6176349.0, |
| "step": 378 |
| }, |
| { |
| "entropy": 0.5405967086553574, |
| "epoch": 1.414179104477612, |
| "grad_norm": 0.12776251137256622, |
| "learning_rate": 0.0002, |
| "loss": 0.5331057906150818, |
| "mean_token_accuracy": 0.780713751912117, |
| "num_tokens": 6192841.0, |
| "step": 379 |
| }, |
| { |
| "entropy": 0.5342811495065689, |
| "epoch": 1.417910447761194, |
| "grad_norm": 0.1610269546508789, |
| "learning_rate": 0.0002, |
| "loss": 0.5360278487205505, |
| "mean_token_accuracy": 0.7841250151395798, |
| "num_tokens": 6209309.0, |
| "step": 380 |
| }, |
| { |
| "entropy": 0.5595536530017853, |
| "epoch": 1.421641791044776, |
| "grad_norm": 0.14842213690280914, |
| "learning_rate": 0.0002, |
| "loss": 0.5625566244125366, |
| "mean_token_accuracy": 0.7719989120960236, |
| "num_tokens": 6225546.0, |
| "step": 381 |
| }, |
| { |
| "entropy": 0.5405392497777939, |
| "epoch": 1.4253731343283582, |
| "grad_norm": 0.14307768642902374, |
| "learning_rate": 0.0002, |
| "loss": 0.542119026184082, |
| "mean_token_accuracy": 0.7774962782859802, |
| "num_tokens": 6241926.0, |
| "step": 382 |
| }, |
| { |
| "entropy": 0.5474280267953873, |
| "epoch": 1.4291044776119404, |
| "grad_norm": 0.1544881910085678, |
| "learning_rate": 0.0002, |
| "loss": 0.5368967056274414, |
| "mean_token_accuracy": 0.7811332195997238, |
| "num_tokens": 6258308.0, |
| "step": 383 |
| }, |
| { |
| "entropy": 0.5335361063480377, |
| "epoch": 1.4328358208955223, |
| "grad_norm": 0.1556805670261383, |
| "learning_rate": 0.0002, |
| "loss": 0.5310883522033691, |
| "mean_token_accuracy": 0.7856934368610382, |
| "num_tokens": 6274507.0, |
| "step": 384 |
| }, |
| { |
| "entropy": 0.5351490825414658, |
| "epoch": 1.4365671641791045, |
| "grad_norm": 0.14044375717639923, |
| "learning_rate": 0.0002, |
| "loss": 0.5397570133209229, |
| "mean_token_accuracy": 0.783098429441452, |
| "num_tokens": 6290975.0, |
| "step": 385 |
| }, |
| { |
| "entropy": 0.4921220541000366, |
| "epoch": 1.4402985074626866, |
| "grad_norm": 0.12986476719379425, |
| "learning_rate": 0.0002, |
| "loss": 0.5014299154281616, |
| "mean_token_accuracy": 0.7965962290763855, |
| "num_tokens": 6307425.0, |
| "step": 386 |
| }, |
| { |
| "entropy": 0.5247820392251015, |
| "epoch": 1.4440298507462686, |
| "grad_norm": 0.1698978841304779, |
| "learning_rate": 0.0002, |
| "loss": 0.5379964113235474, |
| "mean_token_accuracy": 0.7814551293849945, |
| "num_tokens": 6323780.0, |
| "step": 387 |
| }, |
| { |
| "entropy": 0.5345189422369003, |
| "epoch": 1.4477611940298507, |
| "grad_norm": 0.1367090493440628, |
| "learning_rate": 0.0002, |
| "loss": 0.537565290927887, |
| "mean_token_accuracy": 0.784070760011673, |
| "num_tokens": 6340186.0, |
| "step": 388 |
| }, |
| { |
| "entropy": 0.5414960086345673, |
| "epoch": 1.4514925373134329, |
| "grad_norm": 0.1301267296075821, |
| "learning_rate": 0.0002, |
| "loss": 0.5394765138626099, |
| "mean_token_accuracy": 0.782965213060379, |
| "num_tokens": 6356569.0, |
| "step": 389 |
| }, |
| { |
| "entropy": 0.5540374219417572, |
| "epoch": 1.455223880597015, |
| "grad_norm": 0.13357287645339966, |
| "learning_rate": 0.0002, |
| "loss": 0.5477027893066406, |
| "mean_token_accuracy": 0.7795010060071945, |
| "num_tokens": 6373045.0, |
| "step": 390 |
| }, |
| { |
| "entropy": 0.5205369591712952, |
| "epoch": 1.458955223880597, |
| "grad_norm": 0.12282112240791321, |
| "learning_rate": 0.0002, |
| "loss": 0.5204013586044312, |
| "mean_token_accuracy": 0.7873378843069077, |
| "num_tokens": 6389314.0, |
| "step": 391 |
| }, |
| { |
| "entropy": 0.5305770337581635, |
| "epoch": 1.462686567164179, |
| "grad_norm": 0.13189756870269775, |
| "learning_rate": 0.0002, |
| "loss": 0.5303516983985901, |
| "mean_token_accuracy": 0.7838032990694046, |
| "num_tokens": 6405894.0, |
| "step": 392 |
| }, |
| { |
| "entropy": 0.5181146785616875, |
| "epoch": 1.4664179104477613, |
| "grad_norm": 0.1386764943599701, |
| "learning_rate": 0.0002, |
| "loss": 0.5264506340026855, |
| "mean_token_accuracy": 0.7876634448766708, |
| "num_tokens": 6422416.0, |
| "step": 393 |
| }, |
| { |
| "entropy": 0.5263199657201767, |
| "epoch": 1.4701492537313432, |
| "grad_norm": 0.1376650333404541, |
| "learning_rate": 0.0002, |
| "loss": 0.5290877819061279, |
| "mean_token_accuracy": 0.7844877988100052, |
| "num_tokens": 6438912.0, |
| "step": 394 |
| }, |
| { |
| "entropy": 0.5413987934589386, |
| "epoch": 1.4738805970149254, |
| "grad_norm": 0.13445527851581573, |
| "learning_rate": 0.0002, |
| "loss": 0.5450388789176941, |
| "mean_token_accuracy": 0.7817119061946869, |
| "num_tokens": 6455269.0, |
| "step": 395 |
| }, |
| { |
| "entropy": 0.5384629666805267, |
| "epoch": 1.4776119402985075, |
| "grad_norm": 0.13142827153205872, |
| "learning_rate": 0.0002, |
| "loss": 0.5374310612678528, |
| "mean_token_accuracy": 0.7820507287979126, |
| "num_tokens": 6471637.0, |
| "step": 396 |
| }, |
| { |
| "entropy": 0.5372477173805237, |
| "epoch": 1.4813432835820897, |
| "grad_norm": 0.14841656386852264, |
| "learning_rate": 0.0002, |
| "loss": 0.5355952978134155, |
| "mean_token_accuracy": 0.7830248177051544, |
| "num_tokens": 6488013.0, |
| "step": 397 |
| }, |
| { |
| "entropy": 0.5425705909729004, |
| "epoch": 1.4850746268656716, |
| "grad_norm": 0.15021778643131256, |
| "learning_rate": 0.0002, |
| "loss": 0.5400471687316895, |
| "mean_token_accuracy": 0.781876802444458, |
| "num_tokens": 6504279.0, |
| "step": 398 |
| }, |
| { |
| "entropy": 0.5224127918481827, |
| "epoch": 1.4888059701492538, |
| "grad_norm": 0.12955059111118317, |
| "learning_rate": 0.0002, |
| "loss": 0.5219926238059998, |
| "mean_token_accuracy": 0.7877543270587921, |
| "num_tokens": 6520733.0, |
| "step": 399 |
| }, |
| { |
| "entropy": 0.5333951413631439, |
| "epoch": 1.4925373134328357, |
| "grad_norm": 0.17889584600925446, |
| "learning_rate": 0.0002, |
| "loss": 0.5392360091209412, |
| "mean_token_accuracy": 0.7824366092681885, |
| "num_tokens": 6537132.0, |
| "step": 400 |
| }, |
| { |
| "entropy": 0.5253015607595444, |
| "epoch": 1.4962686567164178, |
| "grad_norm": 0.13992291688919067, |
| "learning_rate": 0.0002, |
| "loss": 0.5284996032714844, |
| "mean_token_accuracy": 0.7846586257219315, |
| "num_tokens": 6553376.0, |
| "step": 401 |
| }, |
| { |
| "entropy": 0.5389015972614288, |
| "epoch": 1.5, |
| "grad_norm": 0.1771402657032013, |
| "learning_rate": 0.0002, |
| "loss": 0.5397541522979736, |
| "mean_token_accuracy": 0.7802968770265579, |
| "num_tokens": 6569726.0, |
| "step": 402 |
| }, |
| { |
| "entropy": 0.5217711627483368, |
| "epoch": 1.5037313432835822, |
| "grad_norm": 0.14012446999549866, |
| "learning_rate": 0.0002, |
| "loss": 0.5213160514831543, |
| "mean_token_accuracy": 0.7892279177904129, |
| "num_tokens": 6585668.0, |
| "step": 403 |
| }, |
| { |
| "entropy": 0.5436341613531113, |
| "epoch": 1.5074626865671643, |
| "grad_norm": 0.14205221831798553, |
| "learning_rate": 0.0002, |
| "loss": 0.5369667410850525, |
| "mean_token_accuracy": 0.7853035032749176, |
| "num_tokens": 6601971.0, |
| "step": 404 |
| }, |
| { |
| "entropy": 0.5419598519802094, |
| "epoch": 1.5111940298507462, |
| "grad_norm": 0.12913939356803894, |
| "learning_rate": 0.0002, |
| "loss": 0.5461199879646301, |
| "mean_token_accuracy": 0.7778468281030655, |
| "num_tokens": 6618227.0, |
| "step": 405 |
| }, |
| { |
| "entropy": 0.5244314223527908, |
| "epoch": 1.5149253731343284, |
| "grad_norm": 0.12582488358020782, |
| "learning_rate": 0.0002, |
| "loss": 0.5249899625778198, |
| "mean_token_accuracy": 0.7869550138711929, |
| "num_tokens": 6634263.0, |
| "step": 406 |
| }, |
| { |
| "entropy": 0.5192151591181755, |
| "epoch": 1.5186567164179103, |
| "grad_norm": 0.12192798405885696, |
| "learning_rate": 0.0002, |
| "loss": 0.5195121169090271, |
| "mean_token_accuracy": 0.7890169769525528, |
| "num_tokens": 6650710.0, |
| "step": 407 |
| }, |
| { |
| "entropy": 0.5417191088199615, |
| "epoch": 1.5223880597014925, |
| "grad_norm": 0.12495096772909164, |
| "learning_rate": 0.0002, |
| "loss": 0.5419042110443115, |
| "mean_token_accuracy": 0.7829593569040298, |
| "num_tokens": 6667126.0, |
| "step": 408 |
| }, |
| { |
| "entropy": 0.5327671319246292, |
| "epoch": 1.5261194029850746, |
| "grad_norm": 0.13744905591011047, |
| "learning_rate": 0.0002, |
| "loss": 0.5395404696464539, |
| "mean_token_accuracy": 0.7790274918079376, |
| "num_tokens": 6683496.0, |
| "step": 409 |
| }, |
| { |
| "entropy": 0.5271615833044052, |
| "epoch": 1.5298507462686568, |
| "grad_norm": 0.1438809484243393, |
| "learning_rate": 0.0002, |
| "loss": 0.5334298014640808, |
| "mean_token_accuracy": 0.7829102724790573, |
| "num_tokens": 6699740.0, |
| "step": 410 |
| }, |
| { |
| "entropy": 0.531884953379631, |
| "epoch": 1.533582089552239, |
| "grad_norm": 0.13385534286499023, |
| "learning_rate": 0.0002, |
| "loss": 0.536655843257904, |
| "mean_token_accuracy": 0.7825047969818115, |
| "num_tokens": 6716189.0, |
| "step": 411 |
| }, |
| { |
| "entropy": 0.5317309200763702, |
| "epoch": 1.537313432835821, |
| "grad_norm": 0.1314501166343689, |
| "learning_rate": 0.0002, |
| "loss": 0.5290773510932922, |
| "mean_token_accuracy": 0.7854558974504471, |
| "num_tokens": 6732551.0, |
| "step": 412 |
| }, |
| { |
| "entropy": 0.5539980232715607, |
| "epoch": 1.5410447761194028, |
| "grad_norm": 0.1458398699760437, |
| "learning_rate": 0.0002, |
| "loss": 0.5473334789276123, |
| "mean_token_accuracy": 0.7760033905506134, |
| "num_tokens": 6748864.0, |
| "step": 413 |
| }, |
| { |
| "entropy": 0.5428999215364456, |
| "epoch": 1.544776119402985, |
| "grad_norm": 0.13901032507419586, |
| "learning_rate": 0.0002, |
| "loss": 0.539047122001648, |
| "mean_token_accuracy": 0.7827116996049881, |
| "num_tokens": 6765395.0, |
| "step": 414 |
| }, |
| { |
| "entropy": 0.5432773679494858, |
| "epoch": 1.5485074626865671, |
| "grad_norm": 0.14465473592281342, |
| "learning_rate": 0.0002, |
| "loss": 0.5457994937896729, |
| "mean_token_accuracy": 0.7813904881477356, |
| "num_tokens": 6781707.0, |
| "step": 415 |
| }, |
| { |
| "entropy": 0.5466908067464828, |
| "epoch": 1.5522388059701493, |
| "grad_norm": 0.15542781352996826, |
| "learning_rate": 0.0002, |
| "loss": 0.5543336272239685, |
| "mean_token_accuracy": 0.7712786942720413, |
| "num_tokens": 6798148.0, |
| "step": 416 |
| }, |
| { |
| "entropy": 0.5359790623188019, |
| "epoch": 1.5559701492537314, |
| "grad_norm": 0.14516834914684296, |
| "learning_rate": 0.0002, |
| "loss": 0.5413256883621216, |
| "mean_token_accuracy": 0.7785655856132507, |
| "num_tokens": 6814466.0, |
| "step": 417 |
| }, |
| { |
| "entropy": 0.5583276748657227, |
| "epoch": 1.5597014925373134, |
| "grad_norm": 0.13656160235404968, |
| "learning_rate": 0.0002, |
| "loss": 0.5516223311424255, |
| "mean_token_accuracy": 0.7762998938560486, |
| "num_tokens": 6830735.0, |
| "step": 418 |
| }, |
| { |
| "entropy": 0.5358896553516388, |
| "epoch": 1.5634328358208955, |
| "grad_norm": 0.14226435124874115, |
| "learning_rate": 0.0002, |
| "loss": 0.5317986607551575, |
| "mean_token_accuracy": 0.7799608558416367, |
| "num_tokens": 6846813.0, |
| "step": 419 |
| }, |
| { |
| "entropy": 0.5227169692516327, |
| "epoch": 1.5671641791044775, |
| "grad_norm": 0.12050090730190277, |
| "learning_rate": 0.0002, |
| "loss": 0.5181660652160645, |
| "mean_token_accuracy": 0.7909824550151825, |
| "num_tokens": 6863164.0, |
| "step": 420 |
| }, |
| { |
| "entropy": 0.5254937335848808, |
| "epoch": 1.5708955223880596, |
| "grad_norm": 0.16780491173267365, |
| "learning_rate": 0.0002, |
| "loss": 0.5342957973480225, |
| "mean_token_accuracy": 0.7820688188076019, |
| "num_tokens": 6879490.0, |
| "step": 421 |
| }, |
| { |
| "entropy": 0.5317967236042023, |
| "epoch": 1.5746268656716418, |
| "grad_norm": 0.1419839859008789, |
| "learning_rate": 0.0002, |
| "loss": 0.5389913320541382, |
| "mean_token_accuracy": 0.7807403206825256, |
| "num_tokens": 6895575.0, |
| "step": 422 |
| }, |
| { |
| "entropy": 0.5322583019733429, |
| "epoch": 1.578358208955224, |
| "grad_norm": 0.12827512621879578, |
| "learning_rate": 0.0002, |
| "loss": 0.5381664037704468, |
| "mean_token_accuracy": 0.7817981690168381, |
| "num_tokens": 6911878.0, |
| "step": 423 |
| }, |
| { |
| "entropy": 0.5387236326932907, |
| "epoch": 1.582089552238806, |
| "grad_norm": 0.12765879929065704, |
| "learning_rate": 0.0002, |
| "loss": 0.529690146446228, |
| "mean_token_accuracy": 0.78398197889328, |
| "num_tokens": 6927968.0, |
| "step": 424 |
| }, |
| { |
| "entropy": 0.5259698033332825, |
| "epoch": 1.585820895522388, |
| "grad_norm": 0.12896887958049774, |
| "learning_rate": 0.0002, |
| "loss": 0.5257452726364136, |
| "mean_token_accuracy": 0.784736692905426, |
| "num_tokens": 6944160.0, |
| "step": 425 |
| }, |
| { |
| "entropy": 0.5407612174749374, |
| "epoch": 1.5895522388059702, |
| "grad_norm": 0.15370482206344604, |
| "learning_rate": 0.0002, |
| "loss": 0.5432077050209045, |
| "mean_token_accuracy": 0.7800670862197876, |
| "num_tokens": 6960660.0, |
| "step": 426 |
| }, |
| { |
| "entropy": 0.5060318633913994, |
| "epoch": 1.5932835820895521, |
| "grad_norm": 0.12490323185920715, |
| "learning_rate": 0.0002, |
| "loss": 0.5139111876487732, |
| "mean_token_accuracy": 0.795085221529007, |
| "num_tokens": 6976860.0, |
| "step": 427 |
| }, |
| { |
| "entropy": 0.5371197015047073, |
| "epoch": 1.5970149253731343, |
| "grad_norm": 0.16227304935455322, |
| "learning_rate": 0.0002, |
| "loss": 0.5454593896865845, |
| "mean_token_accuracy": 0.7793577611446381, |
| "num_tokens": 6993201.0, |
| "step": 428 |
| }, |
| { |
| "entropy": 0.5539979338645935, |
| "epoch": 1.6007462686567164, |
| "grad_norm": 0.13361889123916626, |
| "learning_rate": 0.0002, |
| "loss": 0.5502566695213318, |
| "mean_token_accuracy": 0.7786790579557419, |
| "num_tokens": 7009703.0, |
| "step": 429 |
| }, |
| { |
| "entropy": 0.5556806176900864, |
| "epoch": 1.6044776119402986, |
| "grad_norm": 0.1667691469192505, |
| "learning_rate": 0.0002, |
| "loss": 0.5449712872505188, |
| "mean_token_accuracy": 0.780407726764679, |
| "num_tokens": 7026094.0, |
| "step": 430 |
| }, |
| { |
| "entropy": 0.5384839177131653, |
| "epoch": 1.6082089552238807, |
| "grad_norm": 0.12696734070777893, |
| "learning_rate": 0.0002, |
| "loss": 0.5345733165740967, |
| "mean_token_accuracy": 0.7819247841835022, |
| "num_tokens": 7042593.0, |
| "step": 431 |
| }, |
| { |
| "entropy": 0.5386346727609634, |
| "epoch": 1.6119402985074627, |
| "grad_norm": 0.147373229265213, |
| "learning_rate": 0.0002, |
| "loss": 0.5412130355834961, |
| "mean_token_accuracy": 0.7804325222969055, |
| "num_tokens": 7058806.0, |
| "step": 432 |
| }, |
| { |
| "entropy": 0.5403921753168106, |
| "epoch": 1.6156716417910446, |
| "grad_norm": 0.16267037391662598, |
| "learning_rate": 0.0002, |
| "loss": 0.5482686758041382, |
| "mean_token_accuracy": 0.7770579606294632, |
| "num_tokens": 7075197.0, |
| "step": 433 |
| }, |
| { |
| "entropy": 0.5261446088552475, |
| "epoch": 1.6194029850746268, |
| "grad_norm": 0.1406918317079544, |
| "learning_rate": 0.0002, |
| "loss": 0.5294413566589355, |
| "mean_token_accuracy": 0.7843372225761414, |
| "num_tokens": 7091337.0, |
| "step": 434 |
| }, |
| { |
| "entropy": 0.549157440662384, |
| "epoch": 1.623134328358209, |
| "grad_norm": 0.14974337816238403, |
| "learning_rate": 0.0002, |
| "loss": 0.5489839911460876, |
| "mean_token_accuracy": 0.7769932746887207, |
| "num_tokens": 7107831.0, |
| "step": 435 |
| }, |
| { |
| "entropy": 0.5432016402482986, |
| "epoch": 1.626865671641791, |
| "grad_norm": 0.12874630093574524, |
| "learning_rate": 0.0002, |
| "loss": 0.5399404764175415, |
| "mean_token_accuracy": 0.7796168625354767, |
| "num_tokens": 7124099.0, |
| "step": 436 |
| }, |
| { |
| "entropy": 0.5315826684236526, |
| "epoch": 1.6305970149253732, |
| "grad_norm": 0.14230771362781525, |
| "learning_rate": 0.0002, |
| "loss": 0.5255374312400818, |
| "mean_token_accuracy": 0.7866114228963852, |
| "num_tokens": 7140289.0, |
| "step": 437 |
| }, |
| { |
| "entropy": 0.5232831239700317, |
| "epoch": 1.6343283582089554, |
| "grad_norm": 0.14123974740505219, |
| "learning_rate": 0.0002, |
| "loss": 0.5273715257644653, |
| "mean_token_accuracy": 0.7859690189361572, |
| "num_tokens": 7156440.0, |
| "step": 438 |
| }, |
| { |
| "entropy": 0.5186443999409676, |
| "epoch": 1.6380597014925373, |
| "grad_norm": 0.13414812088012695, |
| "learning_rate": 0.0002, |
| "loss": 0.5205132961273193, |
| "mean_token_accuracy": 0.7903359532356262, |
| "num_tokens": 7172893.0, |
| "step": 439 |
| }, |
| { |
| "entropy": 0.5275304913520813, |
| "epoch": 1.6417910447761193, |
| "grad_norm": 0.14953523874282837, |
| "learning_rate": 0.0002, |
| "loss": 0.5419523119926453, |
| "mean_token_accuracy": 0.7794922292232513, |
| "num_tokens": 7189127.0, |
| "step": 440 |
| }, |
| { |
| "entropy": 0.5328174978494644, |
| "epoch": 1.6455223880597014, |
| "grad_norm": 0.1327817291021347, |
| "learning_rate": 0.0002, |
| "loss": 0.5345782041549683, |
| "mean_token_accuracy": 0.7820658534765244, |
| "num_tokens": 7205954.0, |
| "step": 441 |
| }, |
| { |
| "entropy": 0.5310873091220856, |
| "epoch": 1.6492537313432836, |
| "grad_norm": 0.12221065163612366, |
| "learning_rate": 0.0002, |
| "loss": 0.5308910608291626, |
| "mean_token_accuracy": 0.7833030670881271, |
| "num_tokens": 7222313.0, |
| "step": 442 |
| }, |
| { |
| "entropy": 0.554708406329155, |
| "epoch": 1.6529850746268657, |
| "grad_norm": 0.12560638785362244, |
| "learning_rate": 0.0002, |
| "loss": 0.545296847820282, |
| "mean_token_accuracy": 0.7799463421106339, |
| "num_tokens": 7238905.0, |
| "step": 443 |
| }, |
| { |
| "entropy": 0.563832476735115, |
| "epoch": 1.6567164179104479, |
| "grad_norm": 0.13055559992790222, |
| "learning_rate": 0.0002, |
| "loss": 0.5532341003417969, |
| "mean_token_accuracy": 0.7776053845882416, |
| "num_tokens": 7255300.0, |
| "step": 444 |
| }, |
| { |
| "entropy": 0.5307375490665436, |
| "epoch": 1.6604477611940298, |
| "grad_norm": 0.15053775906562805, |
| "learning_rate": 0.0002, |
| "loss": 0.5317035913467407, |
| "mean_token_accuracy": 0.785681426525116, |
| "num_tokens": 7271783.0, |
| "step": 445 |
| }, |
| { |
| "entropy": 0.5366283506155014, |
| "epoch": 1.664179104477612, |
| "grad_norm": 0.15906590223312378, |
| "learning_rate": 0.0002, |
| "loss": 0.5418851375579834, |
| "mean_token_accuracy": 0.7813013046979904, |
| "num_tokens": 7287905.0, |
| "step": 446 |
| }, |
| { |
| "entropy": 0.5389909148216248, |
| "epoch": 1.667910447761194, |
| "grad_norm": 0.14213815331459045, |
| "learning_rate": 0.0002, |
| "loss": 0.5390112996101379, |
| "mean_token_accuracy": 0.7836989611387253, |
| "num_tokens": 7304276.0, |
| "step": 447 |
| }, |
| { |
| "entropy": 0.5144886821508408, |
| "epoch": 1.671641791044776, |
| "grad_norm": 0.13463731110095978, |
| "learning_rate": 0.0002, |
| "loss": 0.5202685594558716, |
| "mean_token_accuracy": 0.7872409075498581, |
| "num_tokens": 7320667.0, |
| "step": 448 |
| }, |
| { |
| "entropy": 0.5335572957992554, |
| "epoch": 1.6753731343283582, |
| "grad_norm": 0.14656713604927063, |
| "learning_rate": 0.0002, |
| "loss": 0.5400261282920837, |
| "mean_token_accuracy": 0.7817242443561554, |
| "num_tokens": 7337144.0, |
| "step": 449 |
| }, |
| { |
| "entropy": 0.5281338393688202, |
| "epoch": 1.6791044776119404, |
| "grad_norm": 0.1680002212524414, |
| "learning_rate": 0.0002, |
| "loss": 0.5353543162345886, |
| "mean_token_accuracy": 0.7814422249794006, |
| "num_tokens": 7353364.0, |
| "step": 450 |
| }, |
| { |
| "entropy": 0.5364942997694016, |
| "epoch": 1.6828358208955225, |
| "grad_norm": 0.1267850548028946, |
| "learning_rate": 0.0002, |
| "loss": 0.5377545356750488, |
| "mean_token_accuracy": 0.7809863239526749, |
| "num_tokens": 7369750.0, |
| "step": 451 |
| }, |
| { |
| "entropy": 0.5447039008140564, |
| "epoch": 1.6865671641791045, |
| "grad_norm": 0.15159733593463898, |
| "learning_rate": 0.0002, |
| "loss": 0.5360575914382935, |
| "mean_token_accuracy": 0.78272545337677, |
| "num_tokens": 7386193.0, |
| "step": 452 |
| }, |
| { |
| "entropy": 0.545790895819664, |
| "epoch": 1.6902985074626866, |
| "grad_norm": 0.1268368512392044, |
| "learning_rate": 0.0002, |
| "loss": 0.5380033254623413, |
| "mean_token_accuracy": 0.7833728045225143, |
| "num_tokens": 7402761.0, |
| "step": 453 |
| }, |
| { |
| "entropy": 0.5338544324040413, |
| "epoch": 1.6940298507462686, |
| "grad_norm": 0.15270428359508514, |
| "learning_rate": 0.0002, |
| "loss": 0.5454051494598389, |
| "mean_token_accuracy": 0.7767380028963089, |
| "num_tokens": 7419069.0, |
| "step": 454 |
| }, |
| { |
| "entropy": 0.5388719588518143, |
| "epoch": 1.6977611940298507, |
| "grad_norm": 0.13864320516586304, |
| "learning_rate": 0.0002, |
| "loss": 0.5421789288520813, |
| "mean_token_accuracy": 0.7788304835557938, |
| "num_tokens": 7435482.0, |
| "step": 455 |
| }, |
| { |
| "entropy": 0.5148054957389832, |
| "epoch": 1.7014925373134329, |
| "grad_norm": 0.14946040511131287, |
| "learning_rate": 0.0002, |
| "loss": 0.5127865076065063, |
| "mean_token_accuracy": 0.7906823009252548, |
| "num_tokens": 7451952.0, |
| "step": 456 |
| }, |
| { |
| "entropy": 0.534477524459362, |
| "epoch": 1.705223880597015, |
| "grad_norm": 0.1717679649591446, |
| "learning_rate": 0.0002, |
| "loss": 0.5412492156028748, |
| "mean_token_accuracy": 0.7818314135074615, |
| "num_tokens": 7468126.0, |
| "step": 457 |
| }, |
| { |
| "entropy": 0.5328005701303482, |
| "epoch": 1.7089552238805972, |
| "grad_norm": 0.15371167659759521, |
| "learning_rate": 0.0002, |
| "loss": 0.5356004238128662, |
| "mean_token_accuracy": 0.7810291647911072, |
| "num_tokens": 7484502.0, |
| "step": 458 |
| }, |
| { |
| "entropy": 0.5207308679819107, |
| "epoch": 1.712686567164179, |
| "grad_norm": 0.1436253786087036, |
| "learning_rate": 0.0002, |
| "loss": 0.5236414670944214, |
| "mean_token_accuracy": 0.7883539646863937, |
| "num_tokens": 7500934.0, |
| "step": 459 |
| }, |
| { |
| "entropy": 0.544979989528656, |
| "epoch": 1.716417910447761, |
| "grad_norm": 0.14674878120422363, |
| "learning_rate": 0.0002, |
| "loss": 0.5436829328536987, |
| "mean_token_accuracy": 0.7812975496053696, |
| "num_tokens": 7517358.0, |
| "step": 460 |
| }, |
| { |
| "entropy": 0.5219089984893799, |
| "epoch": 1.7201492537313432, |
| "grad_norm": 0.12910769879817963, |
| "learning_rate": 0.0002, |
| "loss": 0.5183199048042297, |
| "mean_token_accuracy": 0.7882828712463379, |
| "num_tokens": 7533579.0, |
| "step": 461 |
| }, |
| { |
| "entropy": 0.5276739448308945, |
| "epoch": 1.7238805970149254, |
| "grad_norm": 0.1639186143875122, |
| "learning_rate": 0.0002, |
| "loss": 0.5332796573638916, |
| "mean_token_accuracy": 0.7821054309606552, |
| "num_tokens": 7549888.0, |
| "step": 462 |
| }, |
| { |
| "entropy": 0.5602854788303375, |
| "epoch": 1.7276119402985075, |
| "grad_norm": 0.1194547489285469, |
| "learning_rate": 0.0002, |
| "loss": 0.5576431751251221, |
| "mean_token_accuracy": 0.7757057994604111, |
| "num_tokens": 7566184.0, |
| "step": 463 |
| }, |
| { |
| "entropy": 0.5395274758338928, |
| "epoch": 1.7313432835820897, |
| "grad_norm": 0.15242868661880493, |
| "learning_rate": 0.0002, |
| "loss": 0.5404262542724609, |
| "mean_token_accuracy": 0.7818314135074615, |
| "num_tokens": 7582568.0, |
| "step": 464 |
| }, |
| { |
| "entropy": 0.5593254417181015, |
| "epoch": 1.7350746268656716, |
| "grad_norm": 0.14382942020893097, |
| "learning_rate": 0.0002, |
| "loss": 0.5552665591239929, |
| "mean_token_accuracy": 0.7748626619577408, |
| "num_tokens": 7598871.0, |
| "step": 465 |
| }, |
| { |
| "entropy": 0.5491506904363632, |
| "epoch": 1.7388059701492538, |
| "grad_norm": 0.1650640070438385, |
| "learning_rate": 0.0002, |
| "loss": 0.5474691390991211, |
| "mean_token_accuracy": 0.7765067666769028, |
| "num_tokens": 7615230.0, |
| "step": 466 |
| }, |
| { |
| "entropy": 0.5213493853807449, |
| "epoch": 1.7425373134328357, |
| "grad_norm": 0.13563208281993866, |
| "learning_rate": 0.0002, |
| "loss": 0.5261605381965637, |
| "mean_token_accuracy": 0.7881209254264832, |
| "num_tokens": 7631522.0, |
| "step": 467 |
| }, |
| { |
| "entropy": 0.5157024711370468, |
| "epoch": 1.7462686567164178, |
| "grad_norm": 0.1542738676071167, |
| "learning_rate": 0.0002, |
| "loss": 0.5211755633354187, |
| "mean_token_accuracy": 0.7880145311355591, |
| "num_tokens": 7647788.0, |
| "step": 468 |
| }, |
| { |
| "entropy": 0.522106796503067, |
| "epoch": 1.75, |
| "grad_norm": 0.15090176463127136, |
| "learning_rate": 0.0002, |
| "loss": 0.5321544408798218, |
| "mean_token_accuracy": 0.7835402488708496, |
| "num_tokens": 7663946.0, |
| "step": 469 |
| }, |
| { |
| "entropy": 0.5192100554704666, |
| "epoch": 1.7537313432835822, |
| "grad_norm": 0.13470226526260376, |
| "learning_rate": 0.0002, |
| "loss": 0.5192607641220093, |
| "mean_token_accuracy": 0.78950996696949, |
| "num_tokens": 7680385.0, |
| "step": 470 |
| }, |
| { |
| "entropy": 0.5306961834430695, |
| "epoch": 1.7574626865671643, |
| "grad_norm": 0.1407928615808487, |
| "learning_rate": 0.0002, |
| "loss": 0.5337006449699402, |
| "mean_token_accuracy": 0.7824085056781769, |
| "num_tokens": 7696843.0, |
| "step": 471 |
| }, |
| { |
| "entropy": 0.5406042486429214, |
| "epoch": 1.7611940298507462, |
| "grad_norm": 0.13469810783863068, |
| "learning_rate": 0.0002, |
| "loss": 0.538582444190979, |
| "mean_token_accuracy": 0.7809197902679443, |
| "num_tokens": 7712975.0, |
| "step": 472 |
| }, |
| { |
| "entropy": 0.5491573810577393, |
| "epoch": 1.7649253731343284, |
| "grad_norm": 0.1444787234067917, |
| "learning_rate": 0.0002, |
| "loss": 0.5437332987785339, |
| "mean_token_accuracy": 0.7785926908254623, |
| "num_tokens": 7729110.0, |
| "step": 473 |
| }, |
| { |
| "entropy": 0.5284659117460251, |
| "epoch": 1.7686567164179103, |
| "grad_norm": 0.13380731642246246, |
| "learning_rate": 0.0002, |
| "loss": 0.5290377140045166, |
| "mean_token_accuracy": 0.7867089062929153, |
| "num_tokens": 7745260.0, |
| "step": 474 |
| }, |
| { |
| "entropy": 0.5411970764398575, |
| "epoch": 1.7723880597014925, |
| "grad_norm": 0.14951449632644653, |
| "learning_rate": 0.0002, |
| "loss": 0.5399128198623657, |
| "mean_token_accuracy": 0.7825370728969574, |
| "num_tokens": 7761697.0, |
| "step": 475 |
| }, |
| { |
| "entropy": 0.5321852564811707, |
| "epoch": 1.7761194029850746, |
| "grad_norm": 0.14506123960018158, |
| "learning_rate": 0.0002, |
| "loss": 0.5308146476745605, |
| "mean_token_accuracy": 0.7839493304491043, |
| "num_tokens": 7777948.0, |
| "step": 476 |
| }, |
| { |
| "entropy": 0.5451095849275589, |
| "epoch": 1.7798507462686568, |
| "grad_norm": 0.1395159214735031, |
| "learning_rate": 0.0002, |
| "loss": 0.5458859801292419, |
| "mean_token_accuracy": 0.7780490517616272, |
| "num_tokens": 7794600.0, |
| "step": 477 |
| }, |
| { |
| "entropy": 0.540743038058281, |
| "epoch": 1.783582089552239, |
| "grad_norm": 0.16432784497737885, |
| "learning_rate": 0.0002, |
| "loss": 0.5531184673309326, |
| "mean_token_accuracy": 0.7764357030391693, |
| "num_tokens": 7810879.0, |
| "step": 478 |
| }, |
| { |
| "entropy": 0.5496429800987244, |
| "epoch": 1.787313432835821, |
| "grad_norm": 0.16351141035556793, |
| "learning_rate": 0.0002, |
| "loss": 0.5479351878166199, |
| "mean_token_accuracy": 0.7774319350719452, |
| "num_tokens": 7826918.0, |
| "step": 479 |
| }, |
| { |
| "entropy": 0.544413760304451, |
| "epoch": 1.7910447761194028, |
| "grad_norm": 0.15414181351661682, |
| "learning_rate": 0.0002, |
| "loss": 0.5385620594024658, |
| "mean_token_accuracy": 0.7812491655349731, |
| "num_tokens": 7843129.0, |
| "step": 480 |
| }, |
| { |
| "entropy": 0.5379054397344589, |
| "epoch": 1.794776119402985, |
| "grad_norm": 0.11959221214056015, |
| "learning_rate": 0.0002, |
| "loss": 0.5366896986961365, |
| "mean_token_accuracy": 0.7819821834564209, |
| "num_tokens": 7859313.0, |
| "step": 481 |
| }, |
| { |
| "entropy": 0.5396502763032913, |
| "epoch": 1.7985074626865671, |
| "grad_norm": 0.16873717308044434, |
| "learning_rate": 0.0002, |
| "loss": 0.543642520904541, |
| "mean_token_accuracy": 0.778361052274704, |
| "num_tokens": 7875717.0, |
| "step": 482 |
| }, |
| { |
| "entropy": 0.5259319245815277, |
| "epoch": 1.8022388059701493, |
| "grad_norm": 0.14154605567455292, |
| "learning_rate": 0.0002, |
| "loss": 0.5334436297416687, |
| "mean_token_accuracy": 0.782321959733963, |
| "num_tokens": 7891916.0, |
| "step": 483 |
| }, |
| { |
| "entropy": 0.537188783288002, |
| "epoch": 1.8059701492537314, |
| "grad_norm": 0.1662653684616089, |
| "learning_rate": 0.0002, |
| "loss": 0.5412865877151489, |
| "mean_token_accuracy": 0.7793920636177063, |
| "num_tokens": 7908452.0, |
| "step": 484 |
| }, |
| { |
| "entropy": 0.5351036489009857, |
| "epoch": 1.8097014925373134, |
| "grad_norm": 0.1512536108493805, |
| "learning_rate": 0.0002, |
| "loss": 0.5372329354286194, |
| "mean_token_accuracy": 0.7832370102405548, |
| "num_tokens": 7924868.0, |
| "step": 485 |
| }, |
| { |
| "entropy": 0.5288292467594147, |
| "epoch": 1.8134328358208955, |
| "grad_norm": 0.12068290263414383, |
| "learning_rate": 0.0002, |
| "loss": 0.5237841010093689, |
| "mean_token_accuracy": 0.7875753492116928, |
| "num_tokens": 7941504.0, |
| "step": 486 |
| }, |
| { |
| "entropy": 0.54118712246418, |
| "epoch": 1.8171641791044775, |
| "grad_norm": 0.1403750479221344, |
| "learning_rate": 0.0002, |
| "loss": 0.5366389751434326, |
| "mean_token_accuracy": 0.7817981988191605, |
| "num_tokens": 7957740.0, |
| "step": 487 |
| }, |
| { |
| "entropy": 0.5360180139541626, |
| "epoch": 1.8208955223880596, |
| "grad_norm": 0.13557849824428558, |
| "learning_rate": 0.0002, |
| "loss": 0.5330834984779358, |
| "mean_token_accuracy": 0.785433441400528, |
| "num_tokens": 7973923.0, |
| "step": 488 |
| }, |
| { |
| "entropy": 0.5322665572166443, |
| "epoch": 1.8246268656716418, |
| "grad_norm": 0.15730200707912445, |
| "learning_rate": 0.0002, |
| "loss": 0.5395612120628357, |
| "mean_token_accuracy": 0.7816035896539688, |
| "num_tokens": 7990204.0, |
| "step": 489 |
| }, |
| { |
| "entropy": 0.5226064473390579, |
| "epoch": 1.828358208955224, |
| "grad_norm": 0.15754419565200806, |
| "learning_rate": 0.0002, |
| "loss": 0.5315011739730835, |
| "mean_token_accuracy": 0.7830054759979248, |
| "num_tokens": 8006570.0, |
| "step": 490 |
| }, |
| { |
| "entropy": 0.5503351092338562, |
| "epoch": 1.832089552238806, |
| "grad_norm": 0.15290714800357819, |
| "learning_rate": 0.0002, |
| "loss": 0.5466629862785339, |
| "mean_token_accuracy": 0.7775450199842453, |
| "num_tokens": 8023066.0, |
| "step": 491 |
| }, |
| { |
| "entropy": 0.527627021074295, |
| "epoch": 1.835820895522388, |
| "grad_norm": 0.15022015571594238, |
| "learning_rate": 0.0002, |
| "loss": 0.5163387656211853, |
| "mean_token_accuracy": 0.7932963818311691, |
| "num_tokens": 8039479.0, |
| "step": 492 |
| }, |
| { |
| "entropy": 0.5327048450708389, |
| "epoch": 1.8395522388059702, |
| "grad_norm": 0.17557500302791595, |
| "learning_rate": 0.0002, |
| "loss": 0.5422053337097168, |
| "mean_token_accuracy": 0.7802214026451111, |
| "num_tokens": 8055584.0, |
| "step": 493 |
| }, |
| { |
| "entropy": 0.5464971214532852, |
| "epoch": 1.8432835820895521, |
| "grad_norm": 0.15567541122436523, |
| "learning_rate": 0.0002, |
| "loss": 0.5497090816497803, |
| "mean_token_accuracy": 0.7779724895954132, |
| "num_tokens": 8072044.0, |
| "step": 494 |
| }, |
| { |
| "entropy": 0.5542419105768204, |
| "epoch": 1.8470149253731343, |
| "grad_norm": 0.14640675485134125, |
| "learning_rate": 0.0002, |
| "loss": 0.5521622896194458, |
| "mean_token_accuracy": 0.7741546481847763, |
| "num_tokens": 8088280.0, |
| "step": 495 |
| }, |
| { |
| "entropy": 0.5443165600299835, |
| "epoch": 1.8507462686567164, |
| "grad_norm": 0.12965157628059387, |
| "learning_rate": 0.0002, |
| "loss": 0.5416553020477295, |
| "mean_token_accuracy": 0.7801788151264191, |
| "num_tokens": 8104908.0, |
| "step": 496 |
| }, |
| { |
| "entropy": 0.5297946631908417, |
| "epoch": 1.8544776119402986, |
| "grad_norm": 0.142304927110672, |
| "learning_rate": 0.0002, |
| "loss": 0.5312761664390564, |
| "mean_token_accuracy": 0.7836353629827499, |
| "num_tokens": 8121371.0, |
| "step": 497 |
| }, |
| { |
| "entropy": 0.5366119146347046, |
| "epoch": 1.8582089552238807, |
| "grad_norm": 0.1411743462085724, |
| "learning_rate": 0.0002, |
| "loss": 0.5410764217376709, |
| "mean_token_accuracy": 0.781540110707283, |
| "num_tokens": 8138061.0, |
| "step": 498 |
| }, |
| { |
| "entropy": 0.5247031301259995, |
| "epoch": 1.8619402985074627, |
| "grad_norm": 0.14166688919067383, |
| "learning_rate": 0.0002, |
| "loss": 0.5256608724594116, |
| "mean_token_accuracy": 0.7848968654870987, |
| "num_tokens": 8154161.0, |
| "step": 499 |
| }, |
| { |
| "entropy": 0.5351924449205399, |
| "epoch": 1.8656716417910446, |
| "grad_norm": 0.17830049991607666, |
| "learning_rate": 0.0002, |
| "loss": 0.5383147597312927, |
| "mean_token_accuracy": 0.7815695554018021, |
| "num_tokens": 8170608.0, |
| "step": 500 |
| }, |
| { |
| "entropy": 0.5542074143886566, |
| "epoch": 1.8694029850746268, |
| "grad_norm": 0.12173671275377274, |
| "learning_rate": 0.0002, |
| "loss": 0.5499637722969055, |
| "mean_token_accuracy": 0.7789600938558578, |
| "num_tokens": 8187103.0, |
| "step": 501 |
| }, |
| { |
| "entropy": 0.5351245850324631, |
| "epoch": 1.873134328358209, |
| "grad_norm": 0.14185409247875214, |
| "learning_rate": 0.0002, |
| "loss": 0.536176323890686, |
| "mean_token_accuracy": 0.7841825634241104, |
| "num_tokens": 8203592.0, |
| "step": 502 |
| }, |
| { |
| "entropy": 0.5373983830213547, |
| "epoch": 1.876865671641791, |
| "grad_norm": 0.17772969603538513, |
| "learning_rate": 0.0002, |
| "loss": 0.5430812835693359, |
| "mean_token_accuracy": 0.7797273248434067, |
| "num_tokens": 8220339.0, |
| "step": 503 |
| }, |
| { |
| "entropy": 0.5503710508346558, |
| "epoch": 1.8805970149253732, |
| "grad_norm": 0.11666758358478546, |
| "learning_rate": 0.0002, |
| "loss": 0.5451328754425049, |
| "mean_token_accuracy": 0.7796283811330795, |
| "num_tokens": 8236676.0, |
| "step": 504 |
| }, |
| { |
| "entropy": 0.5530927777290344, |
| "epoch": 1.8843283582089554, |
| "grad_norm": 0.15003131330013275, |
| "learning_rate": 0.0002, |
| "loss": 0.5507726073265076, |
| "mean_token_accuracy": 0.7755273729562759, |
| "num_tokens": 8252936.0, |
| "step": 505 |
| }, |
| { |
| "entropy": 0.5568642169237137, |
| "epoch": 1.8880597014925373, |
| "grad_norm": 0.11633913964033127, |
| "learning_rate": 0.0002, |
| "loss": 0.5578622221946716, |
| "mean_token_accuracy": 0.7727280408143997, |
| "num_tokens": 8269300.0, |
| "step": 506 |
| }, |
| { |
| "entropy": 0.5416045486927032, |
| "epoch": 1.8917910447761193, |
| "grad_norm": 0.13926060497760773, |
| "learning_rate": 0.0002, |
| "loss": 0.539110004901886, |
| "mean_token_accuracy": 0.7808459550142288, |
| "num_tokens": 8285821.0, |
| "step": 507 |
| }, |
| { |
| "entropy": 0.5235913172364235, |
| "epoch": 1.8955223880597014, |
| "grad_norm": 0.15037575364112854, |
| "learning_rate": 0.0002, |
| "loss": 0.5311864018440247, |
| "mean_token_accuracy": 0.7844250351190567, |
| "num_tokens": 8302090.0, |
| "step": 508 |
| }, |
| { |
| "entropy": 0.5290363878011703, |
| "epoch": 1.8992537313432836, |
| "grad_norm": 0.1490047127008438, |
| "learning_rate": 0.0002, |
| "loss": 0.5299670696258545, |
| "mean_token_accuracy": 0.7859402745962143, |
| "num_tokens": 8318466.0, |
| "step": 509 |
| }, |
| { |
| "entropy": 0.5315206944942474, |
| "epoch": 1.9029850746268657, |
| "grad_norm": 0.13377943634986877, |
| "learning_rate": 0.0002, |
| "loss": 0.5337252616882324, |
| "mean_token_accuracy": 0.7828749120235443, |
| "num_tokens": 8334745.0, |
| "step": 510 |
| }, |
| { |
| "entropy": 0.5423215478658676, |
| "epoch": 1.9067164179104479, |
| "grad_norm": 0.15232154726982117, |
| "learning_rate": 0.0002, |
| "loss": 0.5416263937950134, |
| "mean_token_accuracy": 0.7799512296915054, |
| "num_tokens": 8351242.0, |
| "step": 511 |
| }, |
| { |
| "entropy": 0.5543504655361176, |
| "epoch": 1.9104477611940298, |
| "grad_norm": 0.13427108526229858, |
| "learning_rate": 0.0002, |
| "loss": 0.5506000518798828, |
| "mean_token_accuracy": 0.7755409181118011, |
| "num_tokens": 8367420.0, |
| "step": 512 |
| }, |
| { |
| "entropy": 0.550254225730896, |
| "epoch": 1.914179104477612, |
| "grad_norm": 0.11858320236206055, |
| "learning_rate": 0.0002, |
| "loss": 0.5511072874069214, |
| "mean_token_accuracy": 0.7755705565214157, |
| "num_tokens": 8384061.0, |
| "step": 513 |
| }, |
| { |
| "entropy": 0.5377238839864731, |
| "epoch": 1.917910447761194, |
| "grad_norm": 0.12511996924877167, |
| "learning_rate": 0.0002, |
| "loss": 0.5389660596847534, |
| "mean_token_accuracy": 0.7831044644117355, |
| "num_tokens": 8400633.0, |
| "step": 514 |
| }, |
| { |
| "entropy": 0.5361113250255585, |
| "epoch": 1.921641791044776, |
| "grad_norm": 0.12344465404748917, |
| "learning_rate": 0.0002, |
| "loss": 0.5370752811431885, |
| "mean_token_accuracy": 0.7807898819446564, |
| "num_tokens": 8416861.0, |
| "step": 515 |
| }, |
| { |
| "entropy": 0.5242543518543243, |
| "epoch": 1.9253731343283582, |
| "grad_norm": 0.1386454999446869, |
| "learning_rate": 0.0002, |
| "loss": 0.5270183086395264, |
| "mean_token_accuracy": 0.7850740849971771, |
| "num_tokens": 8433185.0, |
| "step": 516 |
| }, |
| { |
| "entropy": 0.5437794327735901, |
| "epoch": 1.9291044776119404, |
| "grad_norm": 0.14425401389598846, |
| "learning_rate": 0.0002, |
| "loss": 0.5506728887557983, |
| "mean_token_accuracy": 0.7757706642150879, |
| "num_tokens": 8449733.0, |
| "step": 517 |
| }, |
| { |
| "entropy": 0.5406046584248543, |
| "epoch": 1.9328358208955225, |
| "grad_norm": 0.14911134541034698, |
| "learning_rate": 0.0002, |
| "loss": 0.548379123210907, |
| "mean_token_accuracy": 0.7779932767152786, |
| "num_tokens": 8466361.0, |
| "step": 518 |
| }, |
| { |
| "entropy": 0.5405861437320709, |
| "epoch": 1.9365671641791045, |
| "grad_norm": 0.14282535016536713, |
| "learning_rate": 0.0002, |
| "loss": 0.548710286617279, |
| "mean_token_accuracy": 0.7777822762727737, |
| "num_tokens": 8482665.0, |
| "step": 519 |
| }, |
| { |
| "entropy": 0.5399511456489563, |
| "epoch": 1.9402985074626866, |
| "grad_norm": 0.12479828298091888, |
| "learning_rate": 0.0002, |
| "loss": 0.5291218161582947, |
| "mean_token_accuracy": 0.7843096703290939, |
| "num_tokens": 8499055.0, |
| "step": 520 |
| }, |
| { |
| "entropy": 0.5444321632385254, |
| "epoch": 1.9440298507462686, |
| "grad_norm": 0.12792018055915833, |
| "learning_rate": 0.0002, |
| "loss": 0.5360825657844543, |
| "mean_token_accuracy": 0.7802168279886246, |
| "num_tokens": 8515278.0, |
| "step": 521 |
| }, |
| { |
| "entropy": 0.5425550192594528, |
| "epoch": 1.9477611940298507, |
| "grad_norm": 0.1359100043773651, |
| "learning_rate": 0.0002, |
| "loss": 0.5348109602928162, |
| "mean_token_accuracy": 0.7856102138757706, |
| "num_tokens": 8531537.0, |
| "step": 522 |
| }, |
| { |
| "entropy": 0.5213616788387299, |
| "epoch": 1.9514925373134329, |
| "grad_norm": 0.13139159977436066, |
| "learning_rate": 0.0002, |
| "loss": 0.5230988264083862, |
| "mean_token_accuracy": 0.7867463678121567, |
| "num_tokens": 8548083.0, |
| "step": 523 |
| }, |
| { |
| "entropy": 0.5190410166978836, |
| "epoch": 1.955223880597015, |
| "grad_norm": 0.15547826886177063, |
| "learning_rate": 0.0002, |
| "loss": 0.5325782299041748, |
| "mean_token_accuracy": 0.7832194417715073, |
| "num_tokens": 8564230.0, |
| "step": 524 |
| }, |
| { |
| "entropy": 0.52348792552948, |
| "epoch": 1.9589552238805972, |
| "grad_norm": 0.1523766815662384, |
| "learning_rate": 0.0002, |
| "loss": 0.5354534983634949, |
| "mean_token_accuracy": 0.7842649668455124, |
| "num_tokens": 8580635.0, |
| "step": 525 |
| }, |
| { |
| "entropy": 0.5572555512189865, |
| "epoch": 1.962686567164179, |
| "grad_norm": 0.14281845092773438, |
| "learning_rate": 0.0002, |
| "loss": 0.5519654750823975, |
| "mean_token_accuracy": 0.7774257510900497, |
| "num_tokens": 8596922.0, |
| "step": 526 |
| }, |
| { |
| "entropy": 0.5348088294267654, |
| "epoch": 1.966417910447761, |
| "grad_norm": 0.13406869769096375, |
| "learning_rate": 0.0002, |
| "loss": 0.5264569520950317, |
| "mean_token_accuracy": 0.7871492505073547, |
| "num_tokens": 8613021.0, |
| "step": 527 |
| }, |
| { |
| "entropy": 0.5417614132165909, |
| "epoch": 1.9701492537313432, |
| "grad_norm": 0.1383802443742752, |
| "learning_rate": 0.0002, |
| "loss": 0.5400649309158325, |
| "mean_token_accuracy": 0.7791371643543243, |
| "num_tokens": 8629306.0, |
| "step": 528 |
| }, |
| { |
| "entropy": 0.5383206903934479, |
| "epoch": 1.9738805970149254, |
| "grad_norm": 0.1241500973701477, |
| "learning_rate": 0.0002, |
| "loss": 0.5367660522460938, |
| "mean_token_accuracy": 0.7832890450954437, |
| "num_tokens": 8645689.0, |
| "step": 529 |
| }, |
| { |
| "entropy": 0.5394852757453918, |
| "epoch": 1.9776119402985075, |
| "grad_norm": 0.15868568420410156, |
| "learning_rate": 0.0002, |
| "loss": 0.5445812940597534, |
| "mean_token_accuracy": 0.779988020658493, |
| "num_tokens": 8662313.0, |
| "step": 530 |
| }, |
| { |
| "entropy": 0.5260857045650482, |
| "epoch": 1.9813432835820897, |
| "grad_norm": 0.18396267294883728, |
| "learning_rate": 0.0002, |
| "loss": 0.5409348607063293, |
| "mean_token_accuracy": 0.7792966812849045, |
| "num_tokens": 8678538.0, |
| "step": 531 |
| }, |
| { |
| "entropy": 0.5298324376344681, |
| "epoch": 1.9850746268656716, |
| "grad_norm": 0.14512184262275696, |
| "learning_rate": 0.0002, |
| "loss": 0.5299750566482544, |
| "mean_token_accuracy": 0.7861876487731934, |
| "num_tokens": 8694908.0, |
| "step": 532 |
| }, |
| { |
| "entropy": 0.5502649545669556, |
| "epoch": 1.9888059701492538, |
| "grad_norm": 0.14106029272079468, |
| "learning_rate": 0.0002, |
| "loss": 0.5504357814788818, |
| "mean_token_accuracy": 0.7764988094568253, |
| "num_tokens": 8711073.0, |
| "step": 533 |
| }, |
| { |
| "entropy": 0.5545000582933426, |
| "epoch": 1.9925373134328357, |
| "grad_norm": 0.13844344019889832, |
| "learning_rate": 0.0002, |
| "loss": 0.542668342590332, |
| "mean_token_accuracy": 0.7807209938764572, |
| "num_tokens": 8727523.0, |
| "step": 534 |
| }, |
| { |
| "entropy": 0.5462679266929626, |
| "epoch": 1.9962686567164178, |
| "grad_norm": 0.12744911015033722, |
| "learning_rate": 0.0002, |
| "loss": 0.5405843257904053, |
| "mean_token_accuracy": 0.7816927134990692, |
| "num_tokens": 8743979.0, |
| "step": 535 |
| }, |
| { |
| "entropy": 0.5320557206869125, |
| "epoch": 2.0, |
| "grad_norm": 0.16281932592391968, |
| "learning_rate": 0.0002, |
| "loss": 0.5311223268508911, |
| "mean_token_accuracy": 0.786607027053833, |
| "num_tokens": 8760258.0, |
| "step": 536 |
| }, |
| { |
| "entropy": 0.514387771487236, |
| "epoch": 2.003731343283582, |
| "grad_norm": 0.12895433604717255, |
| "learning_rate": 0.0002, |
| "loss": 0.5092605948448181, |
| "mean_token_accuracy": 0.7921301871538162, |
| "num_tokens": 8776490.0, |
| "step": 537 |
| }, |
| { |
| "entropy": 0.505175344645977, |
| "epoch": 2.0074626865671643, |
| "grad_norm": 0.14586053788661957, |
| "learning_rate": 0.0002, |
| "loss": 0.5081736445426941, |
| "mean_token_accuracy": 0.792929545044899, |
| "num_tokens": 8792697.0, |
| "step": 538 |
| }, |
| { |
| "entropy": 0.5013257712125778, |
| "epoch": 2.0111940298507465, |
| "grad_norm": 0.16472575068473816, |
| "learning_rate": 0.0002, |
| "loss": 0.5096633434295654, |
| "mean_token_accuracy": 0.7939840257167816, |
| "num_tokens": 8809073.0, |
| "step": 539 |
| }, |
| { |
| "entropy": 0.5075839981436729, |
| "epoch": 2.014925373134328, |
| "grad_norm": 0.14700031280517578, |
| "learning_rate": 0.0002, |
| "loss": 0.5165898203849792, |
| "mean_token_accuracy": 0.7912854254245758, |
| "num_tokens": 8825729.0, |
| "step": 540 |
| }, |
| { |
| "entropy": 0.5040686130523682, |
| "epoch": 2.0186567164179103, |
| "grad_norm": 0.14292173087596893, |
| "learning_rate": 0.0002, |
| "loss": 0.5061570405960083, |
| "mean_token_accuracy": 0.795031800866127, |
| "num_tokens": 8841947.0, |
| "step": 541 |
| }, |
| { |
| "entropy": 0.5193552151322365, |
| "epoch": 2.0223880597014925, |
| "grad_norm": 0.14543044567108154, |
| "learning_rate": 0.0002, |
| "loss": 0.5203323364257812, |
| "mean_token_accuracy": 0.7902332097291946, |
| "num_tokens": 8858149.0, |
| "step": 542 |
| }, |
| { |
| "entropy": 0.5397831946611404, |
| "epoch": 2.0261194029850746, |
| "grad_norm": 0.158218652009964, |
| "learning_rate": 0.0002, |
| "loss": 0.5323266983032227, |
| "mean_token_accuracy": 0.7858591377735138, |
| "num_tokens": 8875098.0, |
| "step": 543 |
| }, |
| { |
| "entropy": 0.5114955455064774, |
| "epoch": 2.029850746268657, |
| "grad_norm": 0.15131299197673798, |
| "learning_rate": 0.0002, |
| "loss": 0.5060538053512573, |
| "mean_token_accuracy": 0.7936214655637741, |
| "num_tokens": 8891394.0, |
| "step": 544 |
| }, |
| { |
| "entropy": 0.5161869823932648, |
| "epoch": 2.033582089552239, |
| "grad_norm": 0.1509423553943634, |
| "learning_rate": 0.0002, |
| "loss": 0.5164708495140076, |
| "mean_token_accuracy": 0.7936760634183884, |
| "num_tokens": 8907732.0, |
| "step": 545 |
| }, |
| { |
| "entropy": 0.5270879864692688, |
| "epoch": 2.0373134328358207, |
| "grad_norm": 0.1780722588300705, |
| "learning_rate": 0.0002, |
| "loss": 0.5269711017608643, |
| "mean_token_accuracy": 0.7908553630113602, |
| "num_tokens": 8924021.0, |
| "step": 546 |
| }, |
| { |
| "entropy": 0.5072071552276611, |
| "epoch": 2.041044776119403, |
| "grad_norm": 0.183442622423172, |
| "learning_rate": 0.0002, |
| "loss": 0.5065768361091614, |
| "mean_token_accuracy": 0.7947991639375687, |
| "num_tokens": 8940093.0, |
| "step": 547 |
| }, |
| { |
| "entropy": 0.5042447373270988, |
| "epoch": 2.044776119402985, |
| "grad_norm": 0.17836566269397736, |
| "learning_rate": 0.0002, |
| "loss": 0.5076130032539368, |
| "mean_token_accuracy": 0.7956184297800064, |
| "num_tokens": 8956488.0, |
| "step": 548 |
| }, |
| { |
| "entropy": 0.5160414427518845, |
| "epoch": 2.048507462686567, |
| "grad_norm": 0.1813444197177887, |
| "learning_rate": 0.0002, |
| "loss": 0.5185638070106506, |
| "mean_token_accuracy": 0.7914257943630219, |
| "num_tokens": 8972821.0, |
| "step": 549 |
| }, |
| { |
| "entropy": 0.5095068141818047, |
| "epoch": 2.0522388059701493, |
| "grad_norm": 0.1596636325120926, |
| "learning_rate": 0.0002, |
| "loss": 0.5114534497261047, |
| "mean_token_accuracy": 0.7929072827100754, |
| "num_tokens": 8989113.0, |
| "step": 550 |
| }, |
| { |
| "entropy": 0.5208977907896042, |
| "epoch": 2.0559701492537314, |
| "grad_norm": 0.1905519962310791, |
| "learning_rate": 0.0002, |
| "loss": 0.520250678062439, |
| "mean_token_accuracy": 0.7889162003993988, |
| "num_tokens": 9005625.0, |
| "step": 551 |
| }, |
| { |
| "entropy": 0.5316548496484756, |
| "epoch": 2.0597014925373136, |
| "grad_norm": 0.17044304311275482, |
| "learning_rate": 0.0002, |
| "loss": 0.5357919931411743, |
| "mean_token_accuracy": 0.7843163162469864, |
| "num_tokens": 9022111.0, |
| "step": 552 |
| }, |
| { |
| "entropy": 0.5097266733646393, |
| "epoch": 2.0634328358208953, |
| "grad_norm": 0.16406644880771637, |
| "learning_rate": 0.0002, |
| "loss": 0.5119821429252625, |
| "mean_token_accuracy": 0.7929173111915588, |
| "num_tokens": 9038538.0, |
| "step": 553 |
| }, |
| { |
| "entropy": 0.5017875283956528, |
| "epoch": 2.0671641791044775, |
| "grad_norm": 0.17073358595371246, |
| "learning_rate": 0.0002, |
| "loss": 0.49950656294822693, |
| "mean_token_accuracy": 0.7964527904987335, |
| "num_tokens": 9054505.0, |
| "step": 554 |
| }, |
| { |
| "entropy": 0.5142332687973976, |
| "epoch": 2.0708955223880596, |
| "grad_norm": 0.15373753011226654, |
| "learning_rate": 0.0002, |
| "loss": 0.5101239681243896, |
| "mean_token_accuracy": 0.7907733470201492, |
| "num_tokens": 9070674.0, |
| "step": 555 |
| }, |
| { |
| "entropy": 0.5031990930438042, |
| "epoch": 2.074626865671642, |
| "grad_norm": 0.1746947318315506, |
| "learning_rate": 0.0002, |
| "loss": 0.5004132390022278, |
| "mean_token_accuracy": 0.7996517866849899, |
| "num_tokens": 9086918.0, |
| "step": 556 |
| }, |
| { |
| "entropy": 0.5246330350637436, |
| "epoch": 2.078358208955224, |
| "grad_norm": 0.15763328969478607, |
| "learning_rate": 0.0002, |
| "loss": 0.524131715297699, |
| "mean_token_accuracy": 0.787426695227623, |
| "num_tokens": 9103177.0, |
| "step": 557 |
| }, |
| { |
| "entropy": 0.5197997018694878, |
| "epoch": 2.082089552238806, |
| "grad_norm": 0.22649353742599487, |
| "learning_rate": 0.0002, |
| "loss": 0.5266055464744568, |
| "mean_token_accuracy": 0.7880847156047821, |
| "num_tokens": 9119670.0, |
| "step": 558 |
| }, |
| { |
| "entropy": 0.49009376764297485, |
| "epoch": 2.0858208955223883, |
| "grad_norm": 0.15409116446971893, |
| "learning_rate": 0.0002, |
| "loss": 0.4931286573410034, |
| "mean_token_accuracy": 0.8020200729370117, |
| "num_tokens": 9135989.0, |
| "step": 559 |
| }, |
| { |
| "entropy": 0.5187191814184189, |
| "epoch": 2.08955223880597, |
| "grad_norm": 0.1616578996181488, |
| "learning_rate": 0.0002, |
| "loss": 0.5154696702957153, |
| "mean_token_accuracy": 0.7906142175197601, |
| "num_tokens": 9152260.0, |
| "step": 560 |
| }, |
| { |
| "entropy": 0.5114191174507141, |
| "epoch": 2.093283582089552, |
| "grad_norm": 0.16386725008487701, |
| "learning_rate": 0.0002, |
| "loss": 0.512050211429596, |
| "mean_token_accuracy": 0.7936253696680069, |
| "num_tokens": 9168527.0, |
| "step": 561 |
| }, |
| { |
| "entropy": 0.5055832713842392, |
| "epoch": 2.0970149253731343, |
| "grad_norm": 0.1755300611257553, |
| "learning_rate": 0.0002, |
| "loss": 0.5091363191604614, |
| "mean_token_accuracy": 0.792420282959938, |
| "num_tokens": 9184796.0, |
| "step": 562 |
| }, |
| { |
| "entropy": 0.5080666542053223, |
| "epoch": 2.1007462686567164, |
| "grad_norm": 0.15171435475349426, |
| "learning_rate": 0.0002, |
| "loss": 0.5046528577804565, |
| "mean_token_accuracy": 0.7957985401153564, |
| "num_tokens": 9201110.0, |
| "step": 563 |
| }, |
| { |
| "entropy": 0.515281043946743, |
| "epoch": 2.1044776119402986, |
| "grad_norm": 0.15376724302768707, |
| "learning_rate": 0.0002, |
| "loss": 0.5201134085655212, |
| "mean_token_accuracy": 0.7918084561824799, |
| "num_tokens": 9217424.0, |
| "step": 564 |
| }, |
| { |
| "entropy": 0.4946657717227936, |
| "epoch": 2.1082089552238807, |
| "grad_norm": 0.19233454763889313, |
| "learning_rate": 0.0002, |
| "loss": 0.5023438930511475, |
| "mean_token_accuracy": 0.7974200546741486, |
| "num_tokens": 9233277.0, |
| "step": 565 |
| }, |
| { |
| "entropy": 0.5108638033270836, |
| "epoch": 2.111940298507463, |
| "grad_norm": 0.17138978838920593, |
| "learning_rate": 0.0002, |
| "loss": 0.5143155455589294, |
| "mean_token_accuracy": 0.7916038930416107, |
| "num_tokens": 9249654.0, |
| "step": 566 |
| }, |
| { |
| "entropy": 0.5251251608133316, |
| "epoch": 2.1156716417910446, |
| "grad_norm": 0.17068861424922943, |
| "learning_rate": 0.0002, |
| "loss": 0.5207733511924744, |
| "mean_token_accuracy": 0.7910687476396561, |
| "num_tokens": 9266056.0, |
| "step": 567 |
| }, |
| { |
| "entropy": 0.5243038684129715, |
| "epoch": 2.1194029850746268, |
| "grad_norm": 0.14862465858459473, |
| "learning_rate": 0.0002, |
| "loss": 0.5170590877532959, |
| "mean_token_accuracy": 0.7908887565135956, |
| "num_tokens": 9282442.0, |
| "step": 568 |
| }, |
| { |
| "entropy": 0.5186082571744919, |
| "epoch": 2.123134328358209, |
| "grad_norm": 0.16986294090747833, |
| "learning_rate": 0.0002, |
| "loss": 0.5129036903381348, |
| "mean_token_accuracy": 0.7898953557014465, |
| "num_tokens": 9298793.0, |
| "step": 569 |
| }, |
| { |
| "entropy": 0.5368679314851761, |
| "epoch": 2.126865671641791, |
| "grad_norm": 0.16030335426330566, |
| "learning_rate": 0.0002, |
| "loss": 0.5358678698539734, |
| "mean_token_accuracy": 0.7853581607341766, |
| "num_tokens": 9315309.0, |
| "step": 570 |
| }, |
| { |
| "entropy": 0.5219630897045135, |
| "epoch": 2.1305970149253732, |
| "grad_norm": 0.17326173186302185, |
| "learning_rate": 0.0002, |
| "loss": 0.5228327512741089, |
| "mean_token_accuracy": 0.7907015681266785, |
| "num_tokens": 9331882.0, |
| "step": 571 |
| }, |
| { |
| "entropy": 0.5124536007642746, |
| "epoch": 2.1343283582089554, |
| "grad_norm": 0.15773673355579376, |
| "learning_rate": 0.0002, |
| "loss": 0.5175159573554993, |
| "mean_token_accuracy": 0.7902040630578995, |
| "num_tokens": 9347989.0, |
| "step": 572 |
| }, |
| { |
| "entropy": 0.5093891024589539, |
| "epoch": 2.138059701492537, |
| "grad_norm": 0.20576871931552887, |
| "learning_rate": 0.0002, |
| "loss": 0.5115762948989868, |
| "mean_token_accuracy": 0.7953972965478897, |
| "num_tokens": 9364225.0, |
| "step": 573 |
| }, |
| { |
| "entropy": 0.5184158161282539, |
| "epoch": 2.1417910447761193, |
| "grad_norm": 0.17257744073867798, |
| "learning_rate": 0.0002, |
| "loss": 0.520084023475647, |
| "mean_token_accuracy": 0.7893062382936478, |
| "num_tokens": 9380636.0, |
| "step": 574 |
| }, |
| { |
| "entropy": 0.5080177336931229, |
| "epoch": 2.1455223880597014, |
| "grad_norm": 0.17332564294338226, |
| "learning_rate": 0.0002, |
| "loss": 0.5134720802307129, |
| "mean_token_accuracy": 0.7942183613777161, |
| "num_tokens": 9396929.0, |
| "step": 575 |
| }, |
| { |
| "entropy": 0.5290546417236328, |
| "epoch": 2.1492537313432836, |
| "grad_norm": 0.1932397186756134, |
| "learning_rate": 0.0002, |
| "loss": 0.5360841751098633, |
| "mean_token_accuracy": 0.7828881293535233, |
| "num_tokens": 9413366.0, |
| "step": 576 |
| }, |
| { |
| "entropy": 0.5072494596242905, |
| "epoch": 2.1529850746268657, |
| "grad_norm": 0.16703151166439056, |
| "learning_rate": 0.0002, |
| "loss": 0.5068556070327759, |
| "mean_token_accuracy": 0.7964113056659698, |
| "num_tokens": 9429598.0, |
| "step": 577 |
| }, |
| { |
| "entropy": 0.537635087966919, |
| "epoch": 2.156716417910448, |
| "grad_norm": 0.1960078775882721, |
| "learning_rate": 0.0002, |
| "loss": 0.5281818509101868, |
| "mean_token_accuracy": 0.788207396864891, |
| "num_tokens": 9445840.0, |
| "step": 578 |
| }, |
| { |
| "entropy": 0.5197459384799004, |
| "epoch": 2.16044776119403, |
| "grad_norm": 0.15743547677993774, |
| "learning_rate": 0.0002, |
| "loss": 0.5147677659988403, |
| "mean_token_accuracy": 0.7911603003740311, |
| "num_tokens": 9462052.0, |
| "step": 579 |
| }, |
| { |
| "entropy": 0.5118173435330391, |
| "epoch": 2.1641791044776117, |
| "grad_norm": 0.19164370000362396, |
| "learning_rate": 0.0002, |
| "loss": 0.52142733335495, |
| "mean_token_accuracy": 0.7907678633928299, |
| "num_tokens": 9478438.0, |
| "step": 580 |
| }, |
| { |
| "entropy": 0.4885973185300827, |
| "epoch": 2.167910447761194, |
| "grad_norm": 0.19939400255680084, |
| "learning_rate": 0.0002, |
| "loss": 0.5009985566139221, |
| "mean_token_accuracy": 0.8004379421472549, |
| "num_tokens": 9494746.0, |
| "step": 581 |
| }, |
| { |
| "entropy": 0.510225921869278, |
| "epoch": 2.171641791044776, |
| "grad_norm": 0.14978954195976257, |
| "learning_rate": 0.0002, |
| "loss": 0.5146667957305908, |
| "mean_token_accuracy": 0.7889236658811569, |
| "num_tokens": 9511170.0, |
| "step": 582 |
| }, |
| { |
| "entropy": 0.5335607677698135, |
| "epoch": 2.175373134328358, |
| "grad_norm": 0.1833840310573578, |
| "learning_rate": 0.0002, |
| "loss": 0.5320448875427246, |
| "mean_token_accuracy": 0.7853577733039856, |
| "num_tokens": 9527657.0, |
| "step": 583 |
| }, |
| { |
| "entropy": 0.514546662569046, |
| "epoch": 2.1791044776119404, |
| "grad_norm": 0.1715938001871109, |
| "learning_rate": 0.0002, |
| "loss": 0.5071934461593628, |
| "mean_token_accuracy": 0.7936844527721405, |
| "num_tokens": 9543856.0, |
| "step": 584 |
| }, |
| { |
| "entropy": 0.547237440943718, |
| "epoch": 2.1828358208955225, |
| "grad_norm": 0.18783694505691528, |
| "learning_rate": 0.0002, |
| "loss": 0.5413283109664917, |
| "mean_token_accuracy": 0.7836454808712006, |
| "num_tokens": 9560231.0, |
| "step": 585 |
| }, |
| { |
| "entropy": 0.5140117108821869, |
| "epoch": 2.1865671641791047, |
| "grad_norm": 0.15842805802822113, |
| "learning_rate": 0.0002, |
| "loss": 0.5159974098205566, |
| "mean_token_accuracy": 0.7902732044458389, |
| "num_tokens": 9576515.0, |
| "step": 586 |
| }, |
| { |
| "entropy": 0.5116063803434372, |
| "epoch": 2.1902985074626864, |
| "grad_norm": 0.20097385346889496, |
| "learning_rate": 0.0002, |
| "loss": 0.5277289152145386, |
| "mean_token_accuracy": 0.7865602523088455, |
| "num_tokens": 9592878.0, |
| "step": 587 |
| }, |
| { |
| "entropy": 0.4998101592063904, |
| "epoch": 2.1940298507462686, |
| "grad_norm": 0.16410379111766815, |
| "learning_rate": 0.0002, |
| "loss": 0.4998311996459961, |
| "mean_token_accuracy": 0.7967907339334488, |
| "num_tokens": 9609017.0, |
| "step": 588 |
| }, |
| { |
| "entropy": 0.5323350727558136, |
| "epoch": 2.1977611940298507, |
| "grad_norm": 0.16125793755054474, |
| "learning_rate": 0.0002, |
| "loss": 0.5221167802810669, |
| "mean_token_accuracy": 0.7891288846731186, |
| "num_tokens": 9625394.0, |
| "step": 589 |
| }, |
| { |
| "entropy": 0.5273734927177429, |
| "epoch": 2.201492537313433, |
| "grad_norm": 0.14303171634674072, |
| "learning_rate": 0.0002, |
| "loss": 0.5178185701370239, |
| "mean_token_accuracy": 0.7917496263980865, |
| "num_tokens": 9641742.0, |
| "step": 590 |
| }, |
| { |
| "entropy": 0.5158755928277969, |
| "epoch": 2.205223880597015, |
| "grad_norm": 0.246815025806427, |
| "learning_rate": 0.0002, |
| "loss": 0.5244193077087402, |
| "mean_token_accuracy": 0.7877120673656464, |
| "num_tokens": 9657778.0, |
| "step": 591 |
| }, |
| { |
| "entropy": 0.5100853517651558, |
| "epoch": 2.208955223880597, |
| "grad_norm": 0.19973590970039368, |
| "learning_rate": 0.0002, |
| "loss": 0.5179952383041382, |
| "mean_token_accuracy": 0.7902611941099167, |
| "num_tokens": 9674100.0, |
| "step": 592 |
| }, |
| { |
| "entropy": 0.5189848691225052, |
| "epoch": 2.2126865671641793, |
| "grad_norm": 0.16376113891601562, |
| "learning_rate": 0.0002, |
| "loss": 0.5188950896263123, |
| "mean_token_accuracy": 0.7889793217182159, |
| "num_tokens": 9690472.0, |
| "step": 593 |
| }, |
| { |
| "entropy": 0.5194961428642273, |
| "epoch": 2.216417910447761, |
| "grad_norm": 0.17298442125320435, |
| "learning_rate": 0.0002, |
| "loss": 0.5182253122329712, |
| "mean_token_accuracy": 0.7859162986278534, |
| "num_tokens": 9706960.0, |
| "step": 594 |
| }, |
| { |
| "entropy": 0.5170838832855225, |
| "epoch": 2.220149253731343, |
| "grad_norm": 0.16964717209339142, |
| "learning_rate": 0.0002, |
| "loss": 0.5017987489700317, |
| "mean_token_accuracy": 0.7995617836713791, |
| "num_tokens": 9723463.0, |
| "step": 595 |
| }, |
| { |
| "entropy": 0.5201168805360794, |
| "epoch": 2.2238805970149254, |
| "grad_norm": 0.15137676894664764, |
| "learning_rate": 0.0002, |
| "loss": 0.5144810080528259, |
| "mean_token_accuracy": 0.7936932742595673, |
| "num_tokens": 9739747.0, |
| "step": 596 |
| }, |
| { |
| "entropy": 0.5158815681934357, |
| "epoch": 2.2276119402985075, |
| "grad_norm": 0.18565919995307922, |
| "learning_rate": 0.0002, |
| "loss": 0.5173157453536987, |
| "mean_token_accuracy": 0.7909886389970779, |
| "num_tokens": 9756070.0, |
| "step": 597 |
| }, |
| { |
| "entropy": 0.5193395465612411, |
| "epoch": 2.2313432835820897, |
| "grad_norm": 0.17240218818187714, |
| "learning_rate": 0.0002, |
| "loss": 0.5264596343040466, |
| "mean_token_accuracy": 0.7854616194963455, |
| "num_tokens": 9772382.0, |
| "step": 598 |
| }, |
| { |
| "entropy": 0.5041865631937981, |
| "epoch": 2.235074626865672, |
| "grad_norm": 0.20082825422286987, |
| "learning_rate": 0.0002, |
| "loss": 0.5166579484939575, |
| "mean_token_accuracy": 0.7908422499895096, |
| "num_tokens": 9788569.0, |
| "step": 599 |
| }, |
| { |
| "entropy": 0.5216381996870041, |
| "epoch": 2.2388059701492535, |
| "grad_norm": 0.16799849271774292, |
| "learning_rate": 0.0002, |
| "loss": 0.5247564911842346, |
| "mean_token_accuracy": 0.7881680577993393, |
| "num_tokens": 9804703.0, |
| "step": 600 |
| }, |
| { |
| "entropy": 0.5119138211011887, |
| "epoch": 2.2425373134328357, |
| "grad_norm": 0.18399521708488464, |
| "learning_rate": 0.0002, |
| "loss": 0.51201331615448, |
| "mean_token_accuracy": 0.7929508537054062, |
| "num_tokens": 9820905.0, |
| "step": 601 |
| }, |
| { |
| "entropy": 0.509235605597496, |
| "epoch": 2.246268656716418, |
| "grad_norm": 0.17125427722930908, |
| "learning_rate": 0.0002, |
| "loss": 0.511957585811615, |
| "mean_token_accuracy": 0.7914097458124161, |
| "num_tokens": 9837139.0, |
| "step": 602 |
| }, |
| { |
| "entropy": 0.5030566602945328, |
| "epoch": 2.25, |
| "grad_norm": 0.20380555093288422, |
| "learning_rate": 0.0002, |
| "loss": 0.5067389011383057, |
| "mean_token_accuracy": 0.792277991771698, |
| "num_tokens": 9853277.0, |
| "step": 603 |
| }, |
| { |
| "entropy": 0.5081905350089073, |
| "epoch": 2.253731343283582, |
| "grad_norm": 0.2351624220609665, |
| "learning_rate": 0.0002, |
| "loss": 0.5083048343658447, |
| "mean_token_accuracy": 0.7942824959754944, |
| "num_tokens": 9869499.0, |
| "step": 604 |
| }, |
| { |
| "entropy": 0.5159982368350029, |
| "epoch": 2.2574626865671643, |
| "grad_norm": 0.1657196432352066, |
| "learning_rate": 0.0002, |
| "loss": 0.5164907574653625, |
| "mean_token_accuracy": 0.7928267419338226, |
| "num_tokens": 9885895.0, |
| "step": 605 |
| }, |
| { |
| "entropy": 0.5120485201478004, |
| "epoch": 2.2611940298507465, |
| "grad_norm": 0.19525906443595886, |
| "learning_rate": 0.0002, |
| "loss": 0.5122599601745605, |
| "mean_token_accuracy": 0.7941529303789139, |
| "num_tokens": 9902217.0, |
| "step": 606 |
| }, |
| { |
| "entropy": 0.5153840184211731, |
| "epoch": 2.264925373134328, |
| "grad_norm": 0.16772477328777313, |
| "learning_rate": 0.0002, |
| "loss": 0.518422544002533, |
| "mean_token_accuracy": 0.7902101129293442, |
| "num_tokens": 9918280.0, |
| "step": 607 |
| }, |
| { |
| "entropy": 0.5186069160699844, |
| "epoch": 2.2686567164179103, |
| "grad_norm": 0.21358108520507812, |
| "learning_rate": 0.0002, |
| "loss": 0.5168492794036865, |
| "mean_token_accuracy": 0.7902675271034241, |
| "num_tokens": 9934568.0, |
| "step": 608 |
| }, |
| { |
| "entropy": 0.5108095407485962, |
| "epoch": 2.2723880597014925, |
| "grad_norm": 0.1788581758737564, |
| "learning_rate": 0.0002, |
| "loss": 0.5080869197845459, |
| "mean_token_accuracy": 0.7928066253662109, |
| "num_tokens": 9950663.0, |
| "step": 609 |
| }, |
| { |
| "entropy": 0.5284161567687988, |
| "epoch": 2.2761194029850746, |
| "grad_norm": 0.16903458535671234, |
| "learning_rate": 0.0002, |
| "loss": 0.5222840309143066, |
| "mean_token_accuracy": 0.7903593182563782, |
| "num_tokens": 9966970.0, |
| "step": 610 |
| }, |
| { |
| "entropy": 0.5287255197763443, |
| "epoch": 2.279850746268657, |
| "grad_norm": 0.19697894155979156, |
| "learning_rate": 0.0002, |
| "loss": 0.5318788290023804, |
| "mean_token_accuracy": 0.7886946499347687, |
| "num_tokens": 9983124.0, |
| "step": 611 |
| }, |
| { |
| "entropy": 0.520504355430603, |
| "epoch": 2.283582089552239, |
| "grad_norm": 0.19185076653957367, |
| "learning_rate": 0.0002, |
| "loss": 0.5249224901199341, |
| "mean_token_accuracy": 0.7904132008552551, |
| "num_tokens": 9999615.0, |
| "step": 612 |
| }, |
| { |
| "entropy": 0.523640438914299, |
| "epoch": 2.2873134328358207, |
| "grad_norm": 0.16966436803340912, |
| "learning_rate": 0.0002, |
| "loss": 0.5245820879936218, |
| "mean_token_accuracy": 0.7893378287553787, |
| "num_tokens": 10015832.0, |
| "step": 613 |
| }, |
| { |
| "entropy": 0.5163002237677574, |
| "epoch": 2.291044776119403, |
| "grad_norm": 0.17059721052646637, |
| "learning_rate": 0.0002, |
| "loss": 0.5116417407989502, |
| "mean_token_accuracy": 0.7942870259284973, |
| "num_tokens": 10032423.0, |
| "step": 614 |
| }, |
| { |
| "entropy": 0.5114529654383659, |
| "epoch": 2.294776119402985, |
| "grad_norm": 0.15924490988254547, |
| "learning_rate": 0.0002, |
| "loss": 0.5043569207191467, |
| "mean_token_accuracy": 0.796301007270813, |
| "num_tokens": 10048865.0, |
| "step": 615 |
| }, |
| { |
| "entropy": 0.5217558741569519, |
| "epoch": 2.298507462686567, |
| "grad_norm": 0.19407594203948975, |
| "learning_rate": 0.0002, |
| "loss": 0.5268961787223816, |
| "mean_token_accuracy": 0.7873952984809875, |
| "num_tokens": 10065139.0, |
| "step": 616 |
| }, |
| { |
| "entropy": 0.5149405896663666, |
| "epoch": 2.3022388059701493, |
| "grad_norm": 0.2706405818462372, |
| "learning_rate": 0.0002, |
| "loss": 0.5237134695053101, |
| "mean_token_accuracy": 0.7873686105012894, |
| "num_tokens": 10081600.0, |
| "step": 617 |
| }, |
| { |
| "entropy": 0.5043307095766068, |
| "epoch": 2.3059701492537314, |
| "grad_norm": 0.17558449506759644, |
| "learning_rate": 0.0002, |
| "loss": 0.5110175609588623, |
| "mean_token_accuracy": 0.7918807119131088, |
| "num_tokens": 10098070.0, |
| "step": 618 |
| }, |
| { |
| "entropy": 0.5341879576444626, |
| "epoch": 2.3097014925373136, |
| "grad_norm": 0.2522954046726227, |
| "learning_rate": 0.0002, |
| "loss": 0.5399251580238342, |
| "mean_token_accuracy": 0.7831520438194275, |
| "num_tokens": 10114246.0, |
| "step": 619 |
| }, |
| { |
| "entropy": 0.5141963139176369, |
| "epoch": 2.3134328358208958, |
| "grad_norm": 0.15956595540046692, |
| "learning_rate": 0.0002, |
| "loss": 0.5093508958816528, |
| "mean_token_accuracy": 0.795027032494545, |
| "num_tokens": 10130661.0, |
| "step": 620 |
| }, |
| { |
| "entropy": 0.5376107692718506, |
| "epoch": 2.3171641791044775, |
| "grad_norm": 0.19181214272975922, |
| "learning_rate": 0.0002, |
| "loss": 0.5305299758911133, |
| "mean_token_accuracy": 0.7849787622690201, |
| "num_tokens": 10147207.0, |
| "step": 621 |
| }, |
| { |
| "entropy": 0.5455309748649597, |
| "epoch": 2.3208955223880596, |
| "grad_norm": 0.1975255161523819, |
| "learning_rate": 0.0002, |
| "loss": 0.545431911945343, |
| "mean_token_accuracy": 0.7809810787439346, |
| "num_tokens": 10163656.0, |
| "step": 622 |
| }, |
| { |
| "entropy": 0.5049594789743423, |
| "epoch": 2.324626865671642, |
| "grad_norm": 0.18025490641593933, |
| "learning_rate": 0.0002, |
| "loss": 0.5164157748222351, |
| "mean_token_accuracy": 0.7886074334383011, |
| "num_tokens": 10179824.0, |
| "step": 623 |
| }, |
| { |
| "entropy": 0.5351590216159821, |
| "epoch": 2.328358208955224, |
| "grad_norm": 0.1925417184829712, |
| "learning_rate": 0.0002, |
| "loss": 0.5373331308364868, |
| "mean_token_accuracy": 0.7835313230752945, |
| "num_tokens": 10196172.0, |
| "step": 624 |
| }, |
| { |
| "entropy": 0.5278169363737106, |
| "epoch": 2.332089552238806, |
| "grad_norm": 0.1565990149974823, |
| "learning_rate": 0.0002, |
| "loss": 0.522457480430603, |
| "mean_token_accuracy": 0.7869259119033813, |
| "num_tokens": 10212470.0, |
| "step": 625 |
| }, |
| { |
| "entropy": 0.5306902080774307, |
| "epoch": 2.3358208955223883, |
| "grad_norm": 0.2147248536348343, |
| "learning_rate": 0.0002, |
| "loss": 0.5292284488677979, |
| "mean_token_accuracy": 0.7863074541091919, |
| "num_tokens": 10228715.0, |
| "step": 626 |
| }, |
| { |
| "entropy": 0.5062485262751579, |
| "epoch": 2.33955223880597, |
| "grad_norm": 0.1553015112876892, |
| "learning_rate": 0.0002, |
| "loss": 0.5081652998924255, |
| "mean_token_accuracy": 0.7945156097412109, |
| "num_tokens": 10244969.0, |
| "step": 627 |
| }, |
| { |
| "entropy": 0.5141769051551819, |
| "epoch": 2.343283582089552, |
| "grad_norm": 0.19284914433956146, |
| "learning_rate": 0.0002, |
| "loss": 0.5236477255821228, |
| "mean_token_accuracy": 0.7886645644903183, |
| "num_tokens": 10261007.0, |
| "step": 628 |
| }, |
| { |
| "entropy": 0.4981055110692978, |
| "epoch": 2.3470149253731343, |
| "grad_norm": 0.16024231910705566, |
| "learning_rate": 0.0002, |
| "loss": 0.4995430111885071, |
| "mean_token_accuracy": 0.7983840107917786, |
| "num_tokens": 10277375.0, |
| "step": 629 |
| }, |
| { |
| "entropy": 0.5120137110352516, |
| "epoch": 2.3507462686567164, |
| "grad_norm": 0.1672038435935974, |
| "learning_rate": 0.0002, |
| "loss": 0.5123609900474548, |
| "mean_token_accuracy": 0.7897045016288757, |
| "num_tokens": 10293551.0, |
| "step": 630 |
| }, |
| { |
| "entropy": 0.5364943742752075, |
| "epoch": 2.3544776119402986, |
| "grad_norm": 0.16704966127872467, |
| "learning_rate": 0.0002, |
| "loss": 0.5279155969619751, |
| "mean_token_accuracy": 0.7879881709814072, |
| "num_tokens": 10309769.0, |
| "step": 631 |
| }, |
| { |
| "entropy": 0.5146841406822205, |
| "epoch": 2.3582089552238807, |
| "grad_norm": 0.15153193473815918, |
| "learning_rate": 0.0002, |
| "loss": 0.509688138961792, |
| "mean_token_accuracy": 0.7947437018156052, |
| "num_tokens": 10326061.0, |
| "step": 632 |
| }, |
| { |
| "entropy": 0.5298689603805542, |
| "epoch": 2.361940298507463, |
| "grad_norm": 0.17587172985076904, |
| "learning_rate": 0.0002, |
| "loss": 0.5311003923416138, |
| "mean_token_accuracy": 0.7837311923503876, |
| "num_tokens": 10342521.0, |
| "step": 633 |
| }, |
| { |
| "entropy": 0.5115828365087509, |
| "epoch": 2.3656716417910446, |
| "grad_norm": 0.1934461146593094, |
| "learning_rate": 0.0002, |
| "loss": 0.5190796852111816, |
| "mean_token_accuracy": 0.7925439327955246, |
| "num_tokens": 10358909.0, |
| "step": 634 |
| }, |
| { |
| "entropy": 0.5075828209519386, |
| "epoch": 2.3694029850746268, |
| "grad_norm": 0.21415792405605316, |
| "learning_rate": 0.0002, |
| "loss": 0.5214318633079529, |
| "mean_token_accuracy": 0.7880290448665619, |
| "num_tokens": 10375163.0, |
| "step": 635 |
| }, |
| { |
| "entropy": 0.5180066004395485, |
| "epoch": 2.373134328358209, |
| "grad_norm": 0.18038702011108398, |
| "learning_rate": 0.0002, |
| "loss": 0.5189198851585388, |
| "mean_token_accuracy": 0.7890142649412155, |
| "num_tokens": 10391439.0, |
| "step": 636 |
| }, |
| { |
| "entropy": 0.5283991098403931, |
| "epoch": 2.376865671641791, |
| "grad_norm": 0.16108715534210205, |
| "learning_rate": 0.0002, |
| "loss": 0.5257266759872437, |
| "mean_token_accuracy": 0.7871113568544388, |
| "num_tokens": 10407630.0, |
| "step": 637 |
| }, |
| { |
| "entropy": 0.5280372202396393, |
| "epoch": 2.3805970149253732, |
| "grad_norm": 0.16095519065856934, |
| "learning_rate": 0.0002, |
| "loss": 0.5244664549827576, |
| "mean_token_accuracy": 0.7871528714895248, |
| "num_tokens": 10423743.0, |
| "step": 638 |
| }, |
| { |
| "entropy": 0.5138130635023117, |
| "epoch": 2.3843283582089554, |
| "grad_norm": 0.1816115826368332, |
| "learning_rate": 0.0002, |
| "loss": 0.5087350606918335, |
| "mean_token_accuracy": 0.7927713841199875, |
| "num_tokens": 10439965.0, |
| "step": 639 |
| }, |
| { |
| "entropy": 0.5233205705881119, |
| "epoch": 2.388059701492537, |
| "grad_norm": 0.14982642233371735, |
| "learning_rate": 0.0002, |
| "loss": 0.5211974382400513, |
| "mean_token_accuracy": 0.7872030586004257, |
| "num_tokens": 10456452.0, |
| "step": 640 |
| }, |
| { |
| "entropy": 0.5170662999153137, |
| "epoch": 2.3917910447761193, |
| "grad_norm": 0.1906667947769165, |
| "learning_rate": 0.0002, |
| "loss": 0.5255247354507446, |
| "mean_token_accuracy": 0.7896150350570679, |
| "num_tokens": 10472813.0, |
| "step": 641 |
| }, |
| { |
| "entropy": 0.5200142711400986, |
| "epoch": 2.3955223880597014, |
| "grad_norm": 0.1779758781194687, |
| "learning_rate": 0.0002, |
| "loss": 0.5246179699897766, |
| "mean_token_accuracy": 0.7881338894367218, |
| "num_tokens": 10489056.0, |
| "step": 642 |
| }, |
| { |
| "entropy": 0.512392520904541, |
| "epoch": 2.3992537313432836, |
| "grad_norm": 0.17630194127559662, |
| "learning_rate": 0.0002, |
| "loss": 0.5218361616134644, |
| "mean_token_accuracy": 0.7907772660255432, |
| "num_tokens": 10505420.0, |
| "step": 643 |
| }, |
| { |
| "entropy": 0.5451202541589737, |
| "epoch": 2.4029850746268657, |
| "grad_norm": 0.19215244054794312, |
| "learning_rate": 0.0002, |
| "loss": 0.5432225465774536, |
| "mean_token_accuracy": 0.7790527492761612, |
| "num_tokens": 10521867.0, |
| "step": 644 |
| }, |
| { |
| "entropy": 0.5459208488464355, |
| "epoch": 2.406716417910448, |
| "grad_norm": 0.16801214218139648, |
| "learning_rate": 0.0002, |
| "loss": 0.5392849445343018, |
| "mean_token_accuracy": 0.7836306095123291, |
| "num_tokens": 10538310.0, |
| "step": 645 |
| }, |
| { |
| "entropy": 0.5442663133144379, |
| "epoch": 2.41044776119403, |
| "grad_norm": 0.15560470521450043, |
| "learning_rate": 0.0002, |
| "loss": 0.5366043448448181, |
| "mean_token_accuracy": 0.7847527861595154, |
| "num_tokens": 10554547.0, |
| "step": 646 |
| }, |
| { |
| "entropy": 0.5072978064417839, |
| "epoch": 2.4141791044776117, |
| "grad_norm": 0.18043409287929535, |
| "learning_rate": 0.0002, |
| "loss": 0.5118624567985535, |
| "mean_token_accuracy": 0.7946688085794449, |
| "num_tokens": 10570788.0, |
| "step": 647 |
| }, |
| { |
| "entropy": 0.5075184851884842, |
| "epoch": 2.417910447761194, |
| "grad_norm": 0.17947684228420258, |
| "learning_rate": 0.0002, |
| "loss": 0.5117331743240356, |
| "mean_token_accuracy": 0.7947508692741394, |
| "num_tokens": 10587121.0, |
| "step": 648 |
| }, |
| { |
| "entropy": 0.517532154917717, |
| "epoch": 2.421641791044776, |
| "grad_norm": 0.16557396948337555, |
| "learning_rate": 0.0002, |
| "loss": 0.5233572125434875, |
| "mean_token_accuracy": 0.7889866530895233, |
| "num_tokens": 10603693.0, |
| "step": 649 |
| }, |
| { |
| "entropy": 0.5167470872402191, |
| "epoch": 2.425373134328358, |
| "grad_norm": 0.20198127627372742, |
| "learning_rate": 0.0002, |
| "loss": 0.52220219373703, |
| "mean_token_accuracy": 0.7884171158075333, |
| "num_tokens": 10619935.0, |
| "step": 650 |
| }, |
| { |
| "entropy": 0.5239948183298111, |
| "epoch": 2.4291044776119404, |
| "grad_norm": 0.16395677626132965, |
| "learning_rate": 0.0002, |
| "loss": 0.515950083732605, |
| "mean_token_accuracy": 0.7930485159158707, |
| "num_tokens": 10636364.0, |
| "step": 651 |
| }, |
| { |
| "entropy": 0.5453772097826004, |
| "epoch": 2.4328358208955225, |
| "grad_norm": 0.1742180585861206, |
| "learning_rate": 0.0002, |
| "loss": 0.5400189161300659, |
| "mean_token_accuracy": 0.7808364629745483, |
| "num_tokens": 10652822.0, |
| "step": 652 |
| }, |
| { |
| "entropy": 0.5059739500284195, |
| "epoch": 2.4365671641791042, |
| "grad_norm": 0.15183326601982117, |
| "learning_rate": 0.0002, |
| "loss": 0.5052129626274109, |
| "mean_token_accuracy": 0.79251728951931, |
| "num_tokens": 10669132.0, |
| "step": 653 |
| }, |
| { |
| "entropy": 0.5017483532428741, |
| "epoch": 2.4402985074626864, |
| "grad_norm": 0.19091397523880005, |
| "learning_rate": 0.0002, |
| "loss": 0.511145293712616, |
| "mean_token_accuracy": 0.7911116033792496, |
| "num_tokens": 10685463.0, |
| "step": 654 |
| }, |
| { |
| "entropy": 0.5011494755744934, |
| "epoch": 2.4440298507462686, |
| "grad_norm": 0.17223528027534485, |
| "learning_rate": 0.0002, |
| "loss": 0.5099227428436279, |
| "mean_token_accuracy": 0.7950053960084915, |
| "num_tokens": 10701789.0, |
| "step": 655 |
| }, |
| { |
| "entropy": 0.5244463533163071, |
| "epoch": 2.4477611940298507, |
| "grad_norm": 0.18068721890449524, |
| "learning_rate": 0.0002, |
| "loss": 0.5334460139274597, |
| "mean_token_accuracy": 0.7825381457805634, |
| "num_tokens": 10718316.0, |
| "step": 656 |
| }, |
| { |
| "entropy": 0.5284494459629059, |
| "epoch": 2.451492537313433, |
| "grad_norm": 0.1803717166185379, |
| "learning_rate": 0.0002, |
| "loss": 0.5221861600875854, |
| "mean_token_accuracy": 0.7873756438493729, |
| "num_tokens": 10734783.0, |
| "step": 657 |
| }, |
| { |
| "entropy": 0.5439791679382324, |
| "epoch": 2.455223880597015, |
| "grad_norm": 0.19709013402462006, |
| "learning_rate": 0.0002, |
| "loss": 0.5368636846542358, |
| "mean_token_accuracy": 0.7826108187437057, |
| "num_tokens": 10751204.0, |
| "step": 658 |
| }, |
| { |
| "entropy": 0.533074140548706, |
| "epoch": 2.458955223880597, |
| "grad_norm": 0.19073714315891266, |
| "learning_rate": 0.0002, |
| "loss": 0.5240392684936523, |
| "mean_token_accuracy": 0.7884863913059235, |
| "num_tokens": 10767375.0, |
| "step": 659 |
| }, |
| { |
| "entropy": 0.5342555195093155, |
| "epoch": 2.4626865671641793, |
| "grad_norm": 0.20184998214244843, |
| "learning_rate": 0.0002, |
| "loss": 0.5400923490524292, |
| "mean_token_accuracy": 0.7812093794345856, |
| "num_tokens": 10783882.0, |
| "step": 660 |
| }, |
| { |
| "entropy": 0.511204443871975, |
| "epoch": 2.466417910447761, |
| "grad_norm": 0.16802184283733368, |
| "learning_rate": 0.0002, |
| "loss": 0.5158311128616333, |
| "mean_token_accuracy": 0.7900519818067551, |
| "num_tokens": 10800017.0, |
| "step": 661 |
| }, |
| { |
| "entropy": 0.5205785110592842, |
| "epoch": 2.470149253731343, |
| "grad_norm": 0.1793476641178131, |
| "learning_rate": 0.0002, |
| "loss": 0.5293420553207397, |
| "mean_token_accuracy": 0.7884000837802887, |
| "num_tokens": 10816075.0, |
| "step": 662 |
| }, |
| { |
| "entropy": 0.5157626122236252, |
| "epoch": 2.4738805970149254, |
| "grad_norm": 0.16907013952732086, |
| "learning_rate": 0.0002, |
| "loss": 0.516871452331543, |
| "mean_token_accuracy": 0.7913013398647308, |
| "num_tokens": 10832423.0, |
| "step": 663 |
| }, |
| { |
| "entropy": 0.519728496670723, |
| "epoch": 2.4776119402985075, |
| "grad_norm": 0.1553056240081787, |
| "learning_rate": 0.0002, |
| "loss": 0.513472318649292, |
| "mean_token_accuracy": 0.7909292727708817, |
| "num_tokens": 10848523.0, |
| "step": 664 |
| }, |
| { |
| "entropy": 0.5463406443595886, |
| "epoch": 2.4813432835820897, |
| "grad_norm": 0.17515431344509125, |
| "learning_rate": 0.0002, |
| "loss": 0.54231858253479, |
| "mean_token_accuracy": 0.7850616276264191, |
| "num_tokens": 10865213.0, |
| "step": 665 |
| }, |
| { |
| "entropy": 0.5244969800114632, |
| "epoch": 2.485074626865672, |
| "grad_norm": 0.1701967716217041, |
| "learning_rate": 0.0002, |
| "loss": 0.5245336890220642, |
| "mean_token_accuracy": 0.7891378104686737, |
| "num_tokens": 10881303.0, |
| "step": 666 |
| }, |
| { |
| "entropy": 0.5184817910194397, |
| "epoch": 2.4888059701492535, |
| "grad_norm": 0.19157923758029938, |
| "learning_rate": 0.0002, |
| "loss": 0.5247556567192078, |
| "mean_token_accuracy": 0.785953015089035, |
| "num_tokens": 10897482.0, |
| "step": 667 |
| }, |
| { |
| "entropy": 0.5223782360553741, |
| "epoch": 2.4925373134328357, |
| "grad_norm": 0.17246930301189423, |
| "learning_rate": 0.0002, |
| "loss": 0.5262410044670105, |
| "mean_token_accuracy": 0.7882735878229141, |
| "num_tokens": 10913655.0, |
| "step": 668 |
| }, |
| { |
| "entropy": 0.5228146463632584, |
| "epoch": 2.496268656716418, |
| "grad_norm": 0.16310639679431915, |
| "learning_rate": 0.0002, |
| "loss": 0.5172871351242065, |
| "mean_token_accuracy": 0.7915017306804657, |
| "num_tokens": 10930154.0, |
| "step": 669 |
| }, |
| { |
| "entropy": 0.5221740305423737, |
| "epoch": 2.5, |
| "grad_norm": 0.18735598027706146, |
| "learning_rate": 0.0002, |
| "loss": 0.5257362723350525, |
| "mean_token_accuracy": 0.7887838333845139, |
| "num_tokens": 10946340.0, |
| "step": 670 |
| }, |
| { |
| "entropy": 0.5169780999422073, |
| "epoch": 2.503731343283582, |
| "grad_norm": 0.14733028411865234, |
| "learning_rate": 0.0002, |
| "loss": 0.5194424390792847, |
| "mean_token_accuracy": 0.7905304580926895, |
| "num_tokens": 10962759.0, |
| "step": 671 |
| }, |
| { |
| "entropy": 0.5055693164467812, |
| "epoch": 2.5074626865671643, |
| "grad_norm": 0.19379651546478271, |
| "learning_rate": 0.0002, |
| "loss": 0.5177527666091919, |
| "mean_token_accuracy": 0.7898499518632889, |
| "num_tokens": 10979008.0, |
| "step": 672 |
| }, |
| { |
| "entropy": 0.5121094956994057, |
| "epoch": 2.5111940298507465, |
| "grad_norm": 0.15117555856704712, |
| "learning_rate": 0.0002, |
| "loss": 0.5123557448387146, |
| "mean_token_accuracy": 0.7921885997056961, |
| "num_tokens": 10995341.0, |
| "step": 673 |
| }, |
| { |
| "entropy": 0.510958768427372, |
| "epoch": 2.5149253731343286, |
| "grad_norm": 0.16086755692958832, |
| "learning_rate": 0.0002, |
| "loss": 0.512763500213623, |
| "mean_token_accuracy": 0.7908799052238464, |
| "num_tokens": 11011614.0, |
| "step": 674 |
| }, |
| { |
| "entropy": 0.5388418585062027, |
| "epoch": 2.5186567164179103, |
| "grad_norm": 0.15542912483215332, |
| "learning_rate": 0.0002, |
| "loss": 0.5308148860931396, |
| "mean_token_accuracy": 0.7864223122596741, |
| "num_tokens": 11028101.0, |
| "step": 675 |
| }, |
| { |
| "entropy": 0.5350766628980637, |
| "epoch": 2.5223880597014925, |
| "grad_norm": 0.16258253157138824, |
| "learning_rate": 0.0002, |
| "loss": 0.5348981618881226, |
| "mean_token_accuracy": 0.7819909602403641, |
| "num_tokens": 11044797.0, |
| "step": 676 |
| }, |
| { |
| "entropy": 0.5268663913011551, |
| "epoch": 2.5261194029850746, |
| "grad_norm": 0.16777002811431885, |
| "learning_rate": 0.0002, |
| "loss": 0.5311545133590698, |
| "mean_token_accuracy": 0.7837276756763458, |
| "num_tokens": 11061244.0, |
| "step": 677 |
| }, |
| { |
| "entropy": 0.5325150638818741, |
| "epoch": 2.529850746268657, |
| "grad_norm": 0.18713748455047607, |
| "learning_rate": 0.0002, |
| "loss": 0.538362443447113, |
| "mean_token_accuracy": 0.7810118645429611, |
| "num_tokens": 11077665.0, |
| "step": 678 |
| }, |
| { |
| "entropy": 0.5273797065019608, |
| "epoch": 2.533582089552239, |
| "grad_norm": 0.20784977078437805, |
| "learning_rate": 0.0002, |
| "loss": 0.5332233905792236, |
| "mean_token_accuracy": 0.7837549448013306, |
| "num_tokens": 11094026.0, |
| "step": 679 |
| }, |
| { |
| "entropy": 0.5151130110025406, |
| "epoch": 2.5373134328358207, |
| "grad_norm": 0.14911554753780365, |
| "learning_rate": 0.0002, |
| "loss": 0.5166280269622803, |
| "mean_token_accuracy": 0.7905122190713882, |
| "num_tokens": 11110472.0, |
| "step": 680 |
| }, |
| { |
| "entropy": 0.5299919918179512, |
| "epoch": 2.541044776119403, |
| "grad_norm": 0.16033315658569336, |
| "learning_rate": 0.0002, |
| "loss": 0.5272996425628662, |
| "mean_token_accuracy": 0.7861689925193787, |
| "num_tokens": 11127092.0, |
| "step": 681 |
| }, |
| { |
| "entropy": 0.5214884579181671, |
| "epoch": 2.544776119402985, |
| "grad_norm": 0.16872185468673706, |
| "learning_rate": 0.0002, |
| "loss": 0.5199981927871704, |
| "mean_token_accuracy": 0.7895201146602631, |
| "num_tokens": 11143559.0, |
| "step": 682 |
| }, |
| { |
| "entropy": 0.5108799561858177, |
| "epoch": 2.548507462686567, |
| "grad_norm": 0.18172214925289154, |
| "learning_rate": 0.0002, |
| "loss": 0.5163415670394897, |
| "mean_token_accuracy": 0.7903354316949844, |
| "num_tokens": 11159784.0, |
| "step": 683 |
| }, |
| { |
| "entropy": 0.5106753259897232, |
| "epoch": 2.5522388059701493, |
| "grad_norm": 0.17978516221046448, |
| "learning_rate": 0.0002, |
| "loss": 0.5151717662811279, |
| "mean_token_accuracy": 0.7921337932348251, |
| "num_tokens": 11175894.0, |
| "step": 684 |
| }, |
| { |
| "entropy": 0.5103955268859863, |
| "epoch": 2.5559701492537314, |
| "grad_norm": 0.1955893486738205, |
| "learning_rate": 0.0002, |
| "loss": 0.5164350271224976, |
| "mean_token_accuracy": 0.7899248152971268, |
| "num_tokens": 11192027.0, |
| "step": 685 |
| }, |
| { |
| "entropy": 0.5159337744116783, |
| "epoch": 2.5597014925373136, |
| "grad_norm": 0.16053813695907593, |
| "learning_rate": 0.0002, |
| "loss": 0.5092947483062744, |
| "mean_token_accuracy": 0.7930262684822083, |
| "num_tokens": 11208393.0, |
| "step": 686 |
| }, |
| { |
| "entropy": 0.5295651033520699, |
| "epoch": 2.5634328358208958, |
| "grad_norm": 0.18861955404281616, |
| "learning_rate": 0.0002, |
| "loss": 0.5229110717773438, |
| "mean_token_accuracy": 0.7858004420995712, |
| "num_tokens": 11224619.0, |
| "step": 687 |
| }, |
| { |
| "entropy": 0.5221749693155289, |
| "epoch": 2.5671641791044775, |
| "grad_norm": 0.19261310994625092, |
| "learning_rate": 0.0002, |
| "loss": 0.522315263748169, |
| "mean_token_accuracy": 0.7886650264263153, |
| "num_tokens": 11241328.0, |
| "step": 688 |
| }, |
| { |
| "entropy": 0.52728471159935, |
| "epoch": 2.5708955223880596, |
| "grad_norm": 0.18678954243659973, |
| "learning_rate": 0.0002, |
| "loss": 0.5328472852706909, |
| "mean_token_accuracy": 0.7843927890062332, |
| "num_tokens": 11257570.0, |
| "step": 689 |
| }, |
| { |
| "entropy": 0.5190518647432327, |
| "epoch": 2.574626865671642, |
| "grad_norm": 0.203090101480484, |
| "learning_rate": 0.0002, |
| "loss": 0.5219579935073853, |
| "mean_token_accuracy": 0.7903515100479126, |
| "num_tokens": 11273928.0, |
| "step": 690 |
| }, |
| { |
| "entropy": 0.532374307513237, |
| "epoch": 2.578358208955224, |
| "grad_norm": 0.17883291840553284, |
| "learning_rate": 0.0002, |
| "loss": 0.5301664471626282, |
| "mean_token_accuracy": 0.786909282207489, |
| "num_tokens": 11290512.0, |
| "step": 691 |
| }, |
| { |
| "entropy": 0.5225525200366974, |
| "epoch": 2.582089552238806, |
| "grad_norm": 0.18782855570316315, |
| "learning_rate": 0.0002, |
| "loss": 0.5248557925224304, |
| "mean_token_accuracy": 0.7887990474700928, |
| "num_tokens": 11307004.0, |
| "step": 692 |
| }, |
| { |
| "entropy": 0.5286060273647308, |
| "epoch": 2.585820895522388, |
| "grad_norm": 0.1517600119113922, |
| "learning_rate": 0.0002, |
| "loss": 0.5230860710144043, |
| "mean_token_accuracy": 0.7889273017644882, |
| "num_tokens": 11323351.0, |
| "step": 693 |
| }, |
| { |
| "entropy": 0.5293424725532532, |
| "epoch": 2.58955223880597, |
| "grad_norm": 0.16056305170059204, |
| "learning_rate": 0.0002, |
| "loss": 0.5270227789878845, |
| "mean_token_accuracy": 0.7839792966842651, |
| "num_tokens": 11339674.0, |
| "step": 694 |
| }, |
| { |
| "entropy": 0.5310518890619278, |
| "epoch": 2.593283582089552, |
| "grad_norm": 0.2366829663515091, |
| "learning_rate": 0.0002, |
| "loss": 0.5457290410995483, |
| "mean_token_accuracy": 0.7800269424915314, |
| "num_tokens": 11356362.0, |
| "step": 695 |
| }, |
| { |
| "entropy": 0.4979932904243469, |
| "epoch": 2.5970149253731343, |
| "grad_norm": 0.17415735125541687, |
| "learning_rate": 0.0002, |
| "loss": 0.501044511795044, |
| "mean_token_accuracy": 0.7960302978754044, |
| "num_tokens": 11372742.0, |
| "step": 696 |
| }, |
| { |
| "entropy": 0.5189961865544319, |
| "epoch": 2.6007462686567164, |
| "grad_norm": 0.2072351723909378, |
| "learning_rate": 0.0002, |
| "loss": 0.5230023264884949, |
| "mean_token_accuracy": 0.7875116765499115, |
| "num_tokens": 11389116.0, |
| "step": 697 |
| }, |
| { |
| "entropy": 0.53299380838871, |
| "epoch": 2.6044776119402986, |
| "grad_norm": 0.17261625826358795, |
| "learning_rate": 0.0002, |
| "loss": 0.5309001803398132, |
| "mean_token_accuracy": 0.7872489094734192, |
| "num_tokens": 11405618.0, |
| "step": 698 |
| }, |
| { |
| "entropy": 0.5474159270524979, |
| "epoch": 2.6082089552238807, |
| "grad_norm": 0.19560639560222626, |
| "learning_rate": 0.0002, |
| "loss": 0.5431969165802002, |
| "mean_token_accuracy": 0.778765469789505, |
| "num_tokens": 11421941.0, |
| "step": 699 |
| }, |
| { |
| "entropy": 0.5396469086408615, |
| "epoch": 2.611940298507463, |
| "grad_norm": 0.16076397895812988, |
| "learning_rate": 0.0002, |
| "loss": 0.5324077010154724, |
| "mean_token_accuracy": 0.7857459485530853, |
| "num_tokens": 11438291.0, |
| "step": 700 |
| }, |
| { |
| "entropy": 0.5099673420190811, |
| "epoch": 2.6156716417910446, |
| "grad_norm": 0.19986586272716522, |
| "learning_rate": 0.0002, |
| "loss": 0.5106230974197388, |
| "mean_token_accuracy": 0.7931589931249619, |
| "num_tokens": 11454650.0, |
| "step": 701 |
| }, |
| { |
| "entropy": 0.5407261997461319, |
| "epoch": 2.6194029850746268, |
| "grad_norm": 0.16104711592197418, |
| "learning_rate": 0.0002, |
| "loss": 0.539045512676239, |
| "mean_token_accuracy": 0.7831651568412781, |
| "num_tokens": 11471221.0, |
| "step": 702 |
| }, |
| { |
| "entropy": 0.5171382799744606, |
| "epoch": 2.623134328358209, |
| "grad_norm": 0.15661297738552094, |
| "learning_rate": 0.0002, |
| "loss": 0.5130681395530701, |
| "mean_token_accuracy": 0.790818989276886, |
| "num_tokens": 11487542.0, |
| "step": 703 |
| }, |
| { |
| "entropy": 0.5257025063037872, |
| "epoch": 2.626865671641791, |
| "grad_norm": 0.18307827413082123, |
| "learning_rate": 0.0002, |
| "loss": 0.5302746295928955, |
| "mean_token_accuracy": 0.7874888926744461, |
| "num_tokens": 11503935.0, |
| "step": 704 |
| }, |
| { |
| "entropy": 0.5218972563743591, |
| "epoch": 2.6305970149253732, |
| "grad_norm": 0.18001461029052734, |
| "learning_rate": 0.0002, |
| "loss": 0.5302802920341492, |
| "mean_token_accuracy": 0.7863849401473999, |
| "num_tokens": 11520468.0, |
| "step": 705 |
| }, |
| { |
| "entropy": 0.5167787075042725, |
| "epoch": 2.6343283582089554, |
| "grad_norm": 0.18107154965400696, |
| "learning_rate": 0.0002, |
| "loss": 0.5208386778831482, |
| "mean_token_accuracy": 0.7903514206409454, |
| "num_tokens": 11536840.0, |
| "step": 706 |
| }, |
| { |
| "entropy": 0.5043365880846977, |
| "epoch": 2.638059701492537, |
| "grad_norm": 0.17698994278907776, |
| "learning_rate": 0.0002, |
| "loss": 0.5047900676727295, |
| "mean_token_accuracy": 0.7941503077745438, |
| "num_tokens": 11553192.0, |
| "step": 707 |
| }, |
| { |
| "entropy": 0.5243512690067291, |
| "epoch": 2.6417910447761193, |
| "grad_norm": 0.21682633459568024, |
| "learning_rate": 0.0002, |
| "loss": 0.5239225029945374, |
| "mean_token_accuracy": 0.7880457192659378, |
| "num_tokens": 11569377.0, |
| "step": 708 |
| }, |
| { |
| "entropy": 0.5424563735723495, |
| "epoch": 2.6455223880597014, |
| "grad_norm": 0.18578708171844482, |
| "learning_rate": 0.0002, |
| "loss": 0.5317046642303467, |
| "mean_token_accuracy": 0.7853426337242126, |
| "num_tokens": 11585781.0, |
| "step": 709 |
| }, |
| { |
| "entropy": 0.5125626623630524, |
| "epoch": 2.6492537313432836, |
| "grad_norm": 0.1740494817495346, |
| "learning_rate": 0.0002, |
| "loss": 0.5167580842971802, |
| "mean_token_accuracy": 0.7886417061090469, |
| "num_tokens": 11601941.0, |
| "step": 710 |
| }, |
| { |
| "entropy": 0.5200148671865463, |
| "epoch": 2.6529850746268657, |
| "grad_norm": 0.187382310628891, |
| "learning_rate": 0.0002, |
| "loss": 0.527021050453186, |
| "mean_token_accuracy": 0.7840719223022461, |
| "num_tokens": 11618412.0, |
| "step": 711 |
| }, |
| { |
| "entropy": 0.525070533156395, |
| "epoch": 2.656716417910448, |
| "grad_norm": 0.22577427327632904, |
| "learning_rate": 0.0002, |
| "loss": 0.5331640243530273, |
| "mean_token_accuracy": 0.7835032641887665, |
| "num_tokens": 11634853.0, |
| "step": 712 |
| }, |
| { |
| "entropy": 0.5288734957575798, |
| "epoch": 2.66044776119403, |
| "grad_norm": 0.18288232386112213, |
| "learning_rate": 0.0002, |
| "loss": 0.5265569090843201, |
| "mean_token_accuracy": 0.7865918427705765, |
| "num_tokens": 11651438.0, |
| "step": 713 |
| }, |
| { |
| "entropy": 0.5303667932748795, |
| "epoch": 2.664179104477612, |
| "grad_norm": 0.17751170694828033, |
| "learning_rate": 0.0002, |
| "loss": 0.5317604541778564, |
| "mean_token_accuracy": 0.785312294960022, |
| "num_tokens": 11667898.0, |
| "step": 714 |
| }, |
| { |
| "entropy": 0.5205241963267326, |
| "epoch": 2.667910447761194, |
| "grad_norm": 0.18675194680690765, |
| "learning_rate": 0.0002, |
| "loss": 0.5167180299758911, |
| "mean_token_accuracy": 0.7891979664564133, |
| "num_tokens": 11684358.0, |
| "step": 715 |
| }, |
| { |
| "entropy": 0.5435728430747986, |
| "epoch": 2.671641791044776, |
| "grad_norm": 0.15365327894687653, |
| "learning_rate": 0.0002, |
| "loss": 0.5367885828018188, |
| "mean_token_accuracy": 0.7829645127058029, |
| "num_tokens": 11700947.0, |
| "step": 716 |
| }, |
| { |
| "entropy": 0.5342584103345871, |
| "epoch": 2.675373134328358, |
| "grad_norm": 0.18714477121829987, |
| "learning_rate": 0.0002, |
| "loss": 0.5341162085533142, |
| "mean_token_accuracy": 0.7813986986875534, |
| "num_tokens": 11717361.0, |
| "step": 717 |
| }, |
| { |
| "entropy": 0.5180455446243286, |
| "epoch": 2.6791044776119404, |
| "grad_norm": 0.1737353354692459, |
| "learning_rate": 0.0002, |
| "loss": 0.5205020904541016, |
| "mean_token_accuracy": 0.7888380438089371, |
| "num_tokens": 11733633.0, |
| "step": 718 |
| }, |
| { |
| "entropy": 0.49537888169288635, |
| "epoch": 2.6828358208955225, |
| "grad_norm": 0.19078519940376282, |
| "learning_rate": 0.0002, |
| "loss": 0.5030867457389832, |
| "mean_token_accuracy": 0.7949226647615433, |
| "num_tokens": 11749756.0, |
| "step": 719 |
| }, |
| { |
| "entropy": 0.535558670759201, |
| "epoch": 2.6865671641791042, |
| "grad_norm": 0.1854591816663742, |
| "learning_rate": 0.0002, |
| "loss": 0.5402969717979431, |
| "mean_token_accuracy": 0.7801541537046432, |
| "num_tokens": 11766234.0, |
| "step": 720 |
| }, |
| { |
| "entropy": 0.530241534113884, |
| "epoch": 2.6902985074626864, |
| "grad_norm": 0.17487172782421112, |
| "learning_rate": 0.0002, |
| "loss": 0.5301569700241089, |
| "mean_token_accuracy": 0.7846524864435196, |
| "num_tokens": 11782477.0, |
| "step": 721 |
| }, |
| { |
| "entropy": 0.5191474407911301, |
| "epoch": 2.6940298507462686, |
| "grad_norm": 0.1899295300245285, |
| "learning_rate": 0.0002, |
| "loss": 0.5159591436386108, |
| "mean_token_accuracy": 0.7921349108219147, |
| "num_tokens": 11798654.0, |
| "step": 722 |
| }, |
| { |
| "entropy": 0.5308229029178619, |
| "epoch": 2.6977611940298507, |
| "grad_norm": 0.1881001889705658, |
| "learning_rate": 0.0002, |
| "loss": 0.5328470468521118, |
| "mean_token_accuracy": 0.7856848537921906, |
| "num_tokens": 11814732.0, |
| "step": 723 |
| }, |
| { |
| "entropy": 0.5103614181280136, |
| "epoch": 2.701492537313433, |
| "grad_norm": 0.18823736906051636, |
| "learning_rate": 0.0002, |
| "loss": 0.5120236277580261, |
| "mean_token_accuracy": 0.7926580309867859, |
| "num_tokens": 11830919.0, |
| "step": 724 |
| }, |
| { |
| "entropy": 0.5119433403015137, |
| "epoch": 2.705223880597015, |
| "grad_norm": 0.22159895300865173, |
| "learning_rate": 0.0002, |
| "loss": 0.5128073692321777, |
| "mean_token_accuracy": 0.7904396206140518, |
| "num_tokens": 11847221.0, |
| "step": 725 |
| }, |
| { |
| "entropy": 0.5431084483861923, |
| "epoch": 2.708955223880597, |
| "grad_norm": 0.19306734204292297, |
| "learning_rate": 0.0002, |
| "loss": 0.545830488204956, |
| "mean_token_accuracy": 0.7785494774580002, |
| "num_tokens": 11863612.0, |
| "step": 726 |
| }, |
| { |
| "entropy": 0.5449389517307281, |
| "epoch": 2.7126865671641793, |
| "grad_norm": 0.2331860363483429, |
| "learning_rate": 0.0002, |
| "loss": 0.5482600927352905, |
| "mean_token_accuracy": 0.7749331146478653, |
| "num_tokens": 11880013.0, |
| "step": 727 |
| }, |
| { |
| "entropy": 0.5157749727368355, |
| "epoch": 2.716417910447761, |
| "grad_norm": 0.18329618871212006, |
| "learning_rate": 0.0002, |
| "loss": 0.5160377025604248, |
| "mean_token_accuracy": 0.793632835149765, |
| "num_tokens": 11896283.0, |
| "step": 728 |
| }, |
| { |
| "entropy": 0.535910427570343, |
| "epoch": 2.720149253731343, |
| "grad_norm": 0.17993047833442688, |
| "learning_rate": 0.0002, |
| "loss": 0.5316116809844971, |
| "mean_token_accuracy": 0.7862441092729568, |
| "num_tokens": 11912618.0, |
| "step": 729 |
| }, |
| { |
| "entropy": 0.5266935378313065, |
| "epoch": 2.7238805970149254, |
| "grad_norm": 0.16241778433322906, |
| "learning_rate": 0.0002, |
| "loss": 0.5210563540458679, |
| "mean_token_accuracy": 0.7902451008558273, |
| "num_tokens": 11928944.0, |
| "step": 730 |
| }, |
| { |
| "entropy": 0.528913140296936, |
| "epoch": 2.7276119402985075, |
| "grad_norm": 0.16674327850341797, |
| "learning_rate": 0.0002, |
| "loss": 0.5289589166641235, |
| "mean_token_accuracy": 0.7847661525011063, |
| "num_tokens": 11945363.0, |
| "step": 731 |
| }, |
| { |
| "entropy": 0.5256128311157227, |
| "epoch": 2.7313432835820897, |
| "grad_norm": 0.16561084985733032, |
| "learning_rate": 0.0002, |
| "loss": 0.5275549292564392, |
| "mean_token_accuracy": 0.7886036038398743, |
| "num_tokens": 11961912.0, |
| "step": 732 |
| }, |
| { |
| "entropy": 0.521274209022522, |
| "epoch": 2.7350746268656714, |
| "grad_norm": 0.19156470894813538, |
| "learning_rate": 0.0002, |
| "loss": 0.5302949547767639, |
| "mean_token_accuracy": 0.7860212177038193, |
| "num_tokens": 11978287.0, |
| "step": 733 |
| }, |
| { |
| "entropy": 0.5035324916243553, |
| "epoch": 2.7388059701492535, |
| "grad_norm": 0.1629370152950287, |
| "learning_rate": 0.0002, |
| "loss": 0.5045384764671326, |
| "mean_token_accuracy": 0.7970030307769775, |
| "num_tokens": 11994631.0, |
| "step": 734 |
| }, |
| { |
| "entropy": 0.523556262254715, |
| "epoch": 2.7425373134328357, |
| "grad_norm": 0.18451189994812012, |
| "learning_rate": 0.0002, |
| "loss": 0.5250605344772339, |
| "mean_token_accuracy": 0.7910588532686234, |
| "num_tokens": 12011220.0, |
| "step": 735 |
| }, |
| { |
| "entropy": 0.5444305688142776, |
| "epoch": 2.746268656716418, |
| "grad_norm": 0.17551295459270477, |
| "learning_rate": 0.0002, |
| "loss": 0.5424449443817139, |
| "mean_token_accuracy": 0.780817836523056, |
| "num_tokens": 12027915.0, |
| "step": 736 |
| }, |
| { |
| "entropy": 0.5146434158086777, |
| "epoch": 2.75, |
| "grad_norm": 0.17423537373542786, |
| "learning_rate": 0.0002, |
| "loss": 0.5176112055778503, |
| "mean_token_accuracy": 0.7910855561494827, |
| "num_tokens": 12044219.0, |
| "step": 737 |
| }, |
| { |
| "entropy": 0.510842576622963, |
| "epoch": 2.753731343283582, |
| "grad_norm": 0.2222961187362671, |
| "learning_rate": 0.0002, |
| "loss": 0.5182011723518372, |
| "mean_token_accuracy": 0.7897626310586929, |
| "num_tokens": 12060657.0, |
| "step": 738 |
| }, |
| { |
| "entropy": 0.5120789408683777, |
| "epoch": 2.7574626865671643, |
| "grad_norm": 0.2220395803451538, |
| "learning_rate": 0.0002, |
| "loss": 0.517307460308075, |
| "mean_token_accuracy": 0.7925999015569687, |
| "num_tokens": 12076873.0, |
| "step": 739 |
| }, |
| { |
| "entropy": 0.5197033733129501, |
| "epoch": 2.7611940298507465, |
| "grad_norm": 0.1659633219242096, |
| "learning_rate": 0.0002, |
| "loss": 0.5216593742370605, |
| "mean_token_accuracy": 0.7905697673559189, |
| "num_tokens": 12093114.0, |
| "step": 740 |
| }, |
| { |
| "entropy": 0.5399138480424881, |
| "epoch": 2.7649253731343286, |
| "grad_norm": 0.14747905731201172, |
| "learning_rate": 0.0002, |
| "loss": 0.5354295969009399, |
| "mean_token_accuracy": 0.782166376709938, |
| "num_tokens": 12109622.0, |
| "step": 741 |
| }, |
| { |
| "entropy": 0.528435692191124, |
| "epoch": 2.7686567164179103, |
| "grad_norm": 0.190764382481575, |
| "learning_rate": 0.0002, |
| "loss": 0.5308310985565186, |
| "mean_token_accuracy": 0.7865614742040634, |
| "num_tokens": 12125846.0, |
| "step": 742 |
| }, |
| { |
| "entropy": 0.5413566380739212, |
| "epoch": 2.7723880597014925, |
| "grad_norm": 0.1633787453174591, |
| "learning_rate": 0.0002, |
| "loss": 0.5384572148323059, |
| "mean_token_accuracy": 0.7836358845233917, |
| "num_tokens": 12142433.0, |
| "step": 743 |
| }, |
| { |
| "entropy": 0.5262139663100243, |
| "epoch": 2.7761194029850746, |
| "grad_norm": 0.17428120970726013, |
| "learning_rate": 0.0002, |
| "loss": 0.5261743664741516, |
| "mean_token_accuracy": 0.7889194637537003, |
| "num_tokens": 12158796.0, |
| "step": 744 |
| }, |
| { |
| "entropy": 0.5228346884250641, |
| "epoch": 2.779850746268657, |
| "grad_norm": 0.17859239876270294, |
| "learning_rate": 0.0002, |
| "loss": 0.5259703397750854, |
| "mean_token_accuracy": 0.7865621894598007, |
| "num_tokens": 12174955.0, |
| "step": 745 |
| }, |
| { |
| "entropy": 0.523474931716919, |
| "epoch": 2.783582089552239, |
| "grad_norm": 0.19062267243862152, |
| "learning_rate": 0.0002, |
| "loss": 0.5315964221954346, |
| "mean_token_accuracy": 0.7831311523914337, |
| "num_tokens": 12191460.0, |
| "step": 746 |
| }, |
| { |
| "entropy": 0.5175044983625412, |
| "epoch": 2.7873134328358207, |
| "grad_norm": 0.17256957292556763, |
| "learning_rate": 0.0002, |
| "loss": 0.516089141368866, |
| "mean_token_accuracy": 0.7927580624818802, |
| "num_tokens": 12207740.0, |
| "step": 747 |
| }, |
| { |
| "entropy": 0.5287255048751831, |
| "epoch": 2.791044776119403, |
| "grad_norm": 0.1659696400165558, |
| "learning_rate": 0.0002, |
| "loss": 0.5232484936714172, |
| "mean_token_accuracy": 0.7907352447509766, |
| "num_tokens": 12224042.0, |
| "step": 748 |
| }, |
| { |
| "entropy": 0.5305596143007278, |
| "epoch": 2.794776119402985, |
| "grad_norm": 0.14449246227741241, |
| "learning_rate": 0.0002, |
| "loss": 0.5185768604278564, |
| "mean_token_accuracy": 0.7900068461894989, |
| "num_tokens": 12240465.0, |
| "step": 749 |
| }, |
| { |
| "entropy": 0.5211694538593292, |
| "epoch": 2.798507462686567, |
| "grad_norm": 0.174103781580925, |
| "learning_rate": 0.0002, |
| "loss": 0.517880916595459, |
| "mean_token_accuracy": 0.7911041378974915, |
| "num_tokens": 12256960.0, |
| "step": 750 |
| }, |
| { |
| "entropy": 0.5136962980031967, |
| "epoch": 2.8022388059701493, |
| "grad_norm": 0.17864161729812622, |
| "learning_rate": 0.0002, |
| "loss": 0.5226247310638428, |
| "mean_token_accuracy": 0.7884148061275482, |
| "num_tokens": 12273387.0, |
| "step": 751 |
| }, |
| { |
| "entropy": 0.5268662720918655, |
| "epoch": 2.8059701492537314, |
| "grad_norm": 0.1835167109966278, |
| "learning_rate": 0.0002, |
| "loss": 0.536668062210083, |
| "mean_token_accuracy": 0.7853374630212784, |
| "num_tokens": 12289834.0, |
| "step": 752 |
| }, |
| { |
| "entropy": 0.5391030460596085, |
| "epoch": 2.8097014925373136, |
| "grad_norm": 0.16024722158908844, |
| "learning_rate": 0.0002, |
| "loss": 0.5422932505607605, |
| "mean_token_accuracy": 0.7793518453836441, |
| "num_tokens": 12306528.0, |
| "step": 753 |
| }, |
| { |
| "entropy": 0.5161868035793304, |
| "epoch": 2.8134328358208958, |
| "grad_norm": 0.16897249221801758, |
| "learning_rate": 0.0002, |
| "loss": 0.5165775418281555, |
| "mean_token_accuracy": 0.7907373309135437, |
| "num_tokens": 12322734.0, |
| "step": 754 |
| }, |
| { |
| "entropy": 0.5141005516052246, |
| "epoch": 2.8171641791044775, |
| "grad_norm": 0.15342213213443756, |
| "learning_rate": 0.0002, |
| "loss": 0.5110867619514465, |
| "mean_token_accuracy": 0.7936585545539856, |
| "num_tokens": 12338965.0, |
| "step": 755 |
| }, |
| { |
| "entropy": 0.5136059522628784, |
| "epoch": 2.8208955223880596, |
| "grad_norm": 0.1845058798789978, |
| "learning_rate": 0.0002, |
| "loss": 0.5135921835899353, |
| "mean_token_accuracy": 0.7938182055950165, |
| "num_tokens": 12355201.0, |
| "step": 756 |
| }, |
| { |
| "entropy": 0.5416870564222336, |
| "epoch": 2.824626865671642, |
| "grad_norm": 0.1709318608045578, |
| "learning_rate": 0.0002, |
| "loss": 0.5426878929138184, |
| "mean_token_accuracy": 0.7789145410060883, |
| "num_tokens": 12371703.0, |
| "step": 757 |
| }, |
| { |
| "entropy": 0.5359257012605667, |
| "epoch": 2.828358208955224, |
| "grad_norm": 0.18052268028259277, |
| "learning_rate": 0.0002, |
| "loss": 0.5371591448783875, |
| "mean_token_accuracy": 0.7839593291282654, |
| "num_tokens": 12387929.0, |
| "step": 758 |
| }, |
| { |
| "entropy": 0.5421824306249619, |
| "epoch": 2.832089552238806, |
| "grad_norm": 0.20184674859046936, |
| "learning_rate": 0.0002, |
| "loss": 0.5447945594787598, |
| "mean_token_accuracy": 0.77911476790905, |
| "num_tokens": 12404484.0, |
| "step": 759 |
| }, |
| { |
| "entropy": 0.5263776183128357, |
| "epoch": 2.835820895522388, |
| "grad_norm": 0.14825916290283203, |
| "learning_rate": 0.0002, |
| "loss": 0.522606372833252, |
| "mean_token_accuracy": 0.7873242050409317, |
| "num_tokens": 12420919.0, |
| "step": 760 |
| }, |
| { |
| "entropy": 0.5179624557495117, |
| "epoch": 2.83955223880597, |
| "grad_norm": 0.17371687293052673, |
| "learning_rate": 0.0002, |
| "loss": 0.5137609243392944, |
| "mean_token_accuracy": 0.7907534688711166, |
| "num_tokens": 12437125.0, |
| "step": 761 |
| }, |
| { |
| "entropy": 0.524615615606308, |
| "epoch": 2.843283582089552, |
| "grad_norm": 0.16056205332279205, |
| "learning_rate": 0.0002, |
| "loss": 0.5198151469230652, |
| "mean_token_accuracy": 0.7898595035076141, |
| "num_tokens": 12453472.0, |
| "step": 762 |
| }, |
| { |
| "entropy": 0.5239430665969849, |
| "epoch": 2.8470149253731343, |
| "grad_norm": 0.16611787676811218, |
| "learning_rate": 0.0002, |
| "loss": 0.5254291296005249, |
| "mean_token_accuracy": 0.7856629192829132, |
| "num_tokens": 12469596.0, |
| "step": 763 |
| }, |
| { |
| "entropy": 0.5066717937588692, |
| "epoch": 2.8507462686567164, |
| "grad_norm": 0.17863133549690247, |
| "learning_rate": 0.0002, |
| "loss": 0.5125826001167297, |
| "mean_token_accuracy": 0.7925843596458435, |
| "num_tokens": 12485953.0, |
| "step": 764 |
| }, |
| { |
| "entropy": 0.4955884516239166, |
| "epoch": 2.8544776119402986, |
| "grad_norm": 0.20588912069797516, |
| "learning_rate": 0.0002, |
| "loss": 0.5022555589675903, |
| "mean_token_accuracy": 0.7975597530603409, |
| "num_tokens": 12502277.0, |
| "step": 765 |
| }, |
| { |
| "entropy": 0.5196300745010376, |
| "epoch": 2.8582089552238807, |
| "grad_norm": 0.16237229108810425, |
| "learning_rate": 0.0002, |
| "loss": 0.5216930508613586, |
| "mean_token_accuracy": 0.7879622578620911, |
| "num_tokens": 12518709.0, |
| "step": 766 |
| }, |
| { |
| "entropy": 0.5230744481086731, |
| "epoch": 2.861940298507463, |
| "grad_norm": 0.171110138297081, |
| "learning_rate": 0.0002, |
| "loss": 0.5227325558662415, |
| "mean_token_accuracy": 0.7877098172903061, |
| "num_tokens": 12535094.0, |
| "step": 767 |
| }, |
| { |
| "entropy": 0.5051610618829727, |
| "epoch": 2.8656716417910446, |
| "grad_norm": 0.18448050320148468, |
| "learning_rate": 0.0002, |
| "loss": 0.5110284686088562, |
| "mean_token_accuracy": 0.7944174855947495, |
| "num_tokens": 12551166.0, |
| "step": 768 |
| }, |
| { |
| "entropy": 0.5255183726549149, |
| "epoch": 2.8694029850746268, |
| "grad_norm": 0.20434531569480896, |
| "learning_rate": 0.0002, |
| "loss": 0.5285360217094421, |
| "mean_token_accuracy": 0.7865411043167114, |
| "num_tokens": 12567631.0, |
| "step": 769 |
| }, |
| { |
| "entropy": 0.545948937535286, |
| "epoch": 2.873134328358209, |
| "grad_norm": 0.17558202147483826, |
| "learning_rate": 0.0002, |
| "loss": 0.5451335310935974, |
| "mean_token_accuracy": 0.779512420296669, |
| "num_tokens": 12584015.0, |
| "step": 770 |
| }, |
| { |
| "entropy": 0.5129513889551163, |
| "epoch": 2.876865671641791, |
| "grad_norm": 0.16112232208251953, |
| "learning_rate": 0.0002, |
| "loss": 0.5147193670272827, |
| "mean_token_accuracy": 0.7902137041091919, |
| "num_tokens": 12600358.0, |
| "step": 771 |
| }, |
| { |
| "entropy": 0.5109254121780396, |
| "epoch": 2.8805970149253732, |
| "grad_norm": 0.1734379678964615, |
| "learning_rate": 0.0002, |
| "loss": 0.5135535597801208, |
| "mean_token_accuracy": 0.79263935983181, |
| "num_tokens": 12616657.0, |
| "step": 772 |
| }, |
| { |
| "entropy": 0.5341281741857529, |
| "epoch": 2.8843283582089554, |
| "grad_norm": 0.15875209867954254, |
| "learning_rate": 0.0002, |
| "loss": 0.5292481780052185, |
| "mean_token_accuracy": 0.7863804548978806, |
| "num_tokens": 12633100.0, |
| "step": 773 |
| }, |
| { |
| "entropy": 0.517389640212059, |
| "epoch": 2.888059701492537, |
| "grad_norm": 0.15992122888565063, |
| "learning_rate": 0.0002, |
| "loss": 0.5166742205619812, |
| "mean_token_accuracy": 0.7887596189975739, |
| "num_tokens": 12649385.0, |
| "step": 774 |
| }, |
| { |
| "entropy": 0.5102578699588776, |
| "epoch": 2.8917910447761193, |
| "grad_norm": 0.18349410593509674, |
| "learning_rate": 0.0002, |
| "loss": 0.5076138973236084, |
| "mean_token_accuracy": 0.795178085565567, |
| "num_tokens": 12665525.0, |
| "step": 775 |
| }, |
| { |
| "entropy": 0.5299288779497147, |
| "epoch": 2.8955223880597014, |
| "grad_norm": 0.16424435377120972, |
| "learning_rate": 0.0002, |
| "loss": 0.5284433364868164, |
| "mean_token_accuracy": 0.786581739783287, |
| "num_tokens": 12681803.0, |
| "step": 776 |
| }, |
| { |
| "entropy": 0.5181921571493149, |
| "epoch": 2.8992537313432836, |
| "grad_norm": 0.15228402614593506, |
| "learning_rate": 0.0002, |
| "loss": 0.5196937918663025, |
| "mean_token_accuracy": 0.7886471450328827, |
| "num_tokens": 12698173.0, |
| "step": 777 |
| }, |
| { |
| "entropy": 0.5215725898742676, |
| "epoch": 2.9029850746268657, |
| "grad_norm": 0.2131892293691635, |
| "learning_rate": 0.0002, |
| "loss": 0.5307268500328064, |
| "mean_token_accuracy": 0.78591388463974, |
| "num_tokens": 12714463.0, |
| "step": 778 |
| }, |
| { |
| "entropy": 0.5362919270992279, |
| "epoch": 2.906716417910448, |
| "grad_norm": 0.17817635834217072, |
| "learning_rate": 0.0002, |
| "loss": 0.5401370525360107, |
| "mean_token_accuracy": 0.7808279395103455, |
| "num_tokens": 12730720.0, |
| "step": 779 |
| }, |
| { |
| "entropy": 0.5322705805301666, |
| "epoch": 2.91044776119403, |
| "grad_norm": 0.1678716540336609, |
| "learning_rate": 0.0002, |
| "loss": 0.5257270336151123, |
| "mean_token_accuracy": 0.7859293818473816, |
| "num_tokens": 12747091.0, |
| "step": 780 |
| }, |
| { |
| "entropy": 0.520588606595993, |
| "epoch": 2.914179104477612, |
| "grad_norm": 0.18254685401916504, |
| "learning_rate": 0.0002, |
| "loss": 0.5188682079315186, |
| "mean_token_accuracy": 0.7932563871145248, |
| "num_tokens": 12763613.0, |
| "step": 781 |
| }, |
| { |
| "entropy": 0.5269717872142792, |
| "epoch": 2.917910447761194, |
| "grad_norm": 0.16678710281848907, |
| "learning_rate": 0.0002, |
| "loss": 0.5248956084251404, |
| "mean_token_accuracy": 0.790144070982933, |
| "num_tokens": 12780171.0, |
| "step": 782 |
| }, |
| { |
| "entropy": 0.5182164311408997, |
| "epoch": 2.921641791044776, |
| "grad_norm": 0.18318307399749756, |
| "learning_rate": 0.0002, |
| "loss": 0.5204554796218872, |
| "mean_token_accuracy": 0.787908211350441, |
| "num_tokens": 12796553.0, |
| "step": 783 |
| }, |
| { |
| "entropy": 0.5233607739210129, |
| "epoch": 2.925373134328358, |
| "grad_norm": 0.2030373364686966, |
| "learning_rate": 0.0002, |
| "loss": 0.5296039581298828, |
| "mean_token_accuracy": 0.7844000309705734, |
| "num_tokens": 12812947.0, |
| "step": 784 |
| }, |
| { |
| "entropy": 0.5187854021787643, |
| "epoch": 2.9291044776119404, |
| "grad_norm": 0.18503431975841522, |
| "learning_rate": 0.0002, |
| "loss": 0.5259944200515747, |
| "mean_token_accuracy": 0.7895472347736359, |
| "num_tokens": 12829211.0, |
| "step": 785 |
| }, |
| { |
| "entropy": 0.5311631262302399, |
| "epoch": 2.9328358208955225, |
| "grad_norm": 0.2229471653699875, |
| "learning_rate": 0.0002, |
| "loss": 0.5318973064422607, |
| "mean_token_accuracy": 0.7854189872741699, |
| "num_tokens": 12845800.0, |
| "step": 786 |
| }, |
| { |
| "entropy": 0.5326709896326065, |
| "epoch": 2.9365671641791042, |
| "grad_norm": 0.1797013282775879, |
| "learning_rate": 0.0002, |
| "loss": 0.5260239243507385, |
| "mean_token_accuracy": 0.7882365137338638, |
| "num_tokens": 12862175.0, |
| "step": 787 |
| }, |
| { |
| "entropy": 0.5253183990716934, |
| "epoch": 2.9402985074626864, |
| "grad_norm": 0.184711292386055, |
| "learning_rate": 0.0002, |
| "loss": 0.5227702856063843, |
| "mean_token_accuracy": 0.786175325512886, |
| "num_tokens": 12878599.0, |
| "step": 788 |
| }, |
| { |
| "entropy": 0.5101964995265007, |
| "epoch": 2.9440298507462686, |
| "grad_norm": 0.16542410850524902, |
| "learning_rate": 0.0002, |
| "loss": 0.5139442682266235, |
| "mean_token_accuracy": 0.7908255755901337, |
| "num_tokens": 12894876.0, |
| "step": 789 |
| }, |
| { |
| "entropy": 0.5281920284032822, |
| "epoch": 2.9477611940298507, |
| "grad_norm": 0.197799414396286, |
| "learning_rate": 0.0002, |
| "loss": 0.5309633016586304, |
| "mean_token_accuracy": 0.786136269569397, |
| "num_tokens": 12911306.0, |
| "step": 790 |
| }, |
| { |
| "entropy": 0.5293130129575729, |
| "epoch": 2.951492537313433, |
| "grad_norm": 0.18718501925468445, |
| "learning_rate": 0.0002, |
| "loss": 0.5343748331069946, |
| "mean_token_accuracy": 0.7822940051555634, |
| "num_tokens": 12927467.0, |
| "step": 791 |
| }, |
| { |
| "entropy": 0.5448336452245712, |
| "epoch": 2.955223880597015, |
| "grad_norm": 0.19536060094833374, |
| "learning_rate": 0.0002, |
| "loss": 0.5406786799430847, |
| "mean_token_accuracy": 0.7815372794866562, |
| "num_tokens": 12943686.0, |
| "step": 792 |
| }, |
| { |
| "entropy": 0.5320895612239838, |
| "epoch": 2.958955223880597, |
| "grad_norm": 0.16376431286334991, |
| "learning_rate": 0.0002, |
| "loss": 0.5267434120178223, |
| "mean_token_accuracy": 0.7898588627576828, |
| "num_tokens": 12960051.0, |
| "step": 793 |
| }, |
| { |
| "entropy": 0.5325825065374374, |
| "epoch": 2.9626865671641793, |
| "grad_norm": 0.1873481571674347, |
| "learning_rate": 0.0002, |
| "loss": 0.5352177619934082, |
| "mean_token_accuracy": 0.7856618016958237, |
| "num_tokens": 12976566.0, |
| "step": 794 |
| }, |
| { |
| "entropy": 0.5237977653741837, |
| "epoch": 2.966417910447761, |
| "grad_norm": 0.1605473905801773, |
| "learning_rate": 0.0002, |
| "loss": 0.5246574878692627, |
| "mean_token_accuracy": 0.7903333604335785, |
| "num_tokens": 12993008.0, |
| "step": 795 |
| }, |
| { |
| "entropy": 0.5212627202272415, |
| "epoch": 2.970149253731343, |
| "grad_norm": 0.1664198637008667, |
| "learning_rate": 0.0002, |
| "loss": 0.5198924541473389, |
| "mean_token_accuracy": 0.7895936667919159, |
| "num_tokens": 13009296.0, |
| "step": 796 |
| }, |
| { |
| "entropy": 0.522112712264061, |
| "epoch": 2.9738805970149254, |
| "grad_norm": 0.16731607913970947, |
| "learning_rate": 0.0002, |
| "loss": 0.5291344523429871, |
| "mean_token_accuracy": 0.7837257832288742, |
| "num_tokens": 13025655.0, |
| "step": 797 |
| }, |
| { |
| "entropy": 0.5294683575630188, |
| "epoch": 2.9776119402985075, |
| "grad_norm": 0.16451914608478546, |
| "learning_rate": 0.0002, |
| "loss": 0.5247352123260498, |
| "mean_token_accuracy": 0.7870377004146576, |
| "num_tokens": 13042200.0, |
| "step": 798 |
| }, |
| { |
| "entropy": 0.5064173713326454, |
| "epoch": 2.9813432835820897, |
| "grad_norm": 0.19790644943714142, |
| "learning_rate": 0.0002, |
| "loss": 0.505647599697113, |
| "mean_token_accuracy": 0.7952451556921005, |
| "num_tokens": 13058310.0, |
| "step": 799 |
| }, |
| { |
| "entropy": 0.5241806209087372, |
| "epoch": 2.9850746268656714, |
| "grad_norm": 0.16203707456588745, |
| "learning_rate": 0.0002, |
| "loss": 0.5258848071098328, |
| "mean_token_accuracy": 0.7872522622346878, |
| "num_tokens": 13074393.0, |
| "step": 800 |
| }, |
| { |
| "entropy": 0.5231702029705048, |
| "epoch": 2.9888059701492535, |
| "grad_norm": 0.1862519532442093, |
| "learning_rate": 0.0002, |
| "loss": 0.5240829586982727, |
| "mean_token_accuracy": 0.7857110947370529, |
| "num_tokens": 13090929.0, |
| "step": 801 |
| }, |
| { |
| "entropy": 0.5257306396961212, |
| "epoch": 2.9925373134328357, |
| "grad_norm": 0.17041750252246857, |
| "learning_rate": 0.0002, |
| "loss": 0.5312814116477966, |
| "mean_token_accuracy": 0.7858880013227463, |
| "num_tokens": 13107504.0, |
| "step": 802 |
| }, |
| { |
| "entropy": 0.5197731107473373, |
| "epoch": 2.996268656716418, |
| "grad_norm": 0.18611328303813934, |
| "learning_rate": 0.0002, |
| "loss": 0.5225716829299927, |
| "mean_token_accuracy": 0.7895954698324203, |
| "num_tokens": 13123863.0, |
| "step": 803 |
| }, |
| { |
| "entropy": 0.532523974776268, |
| "epoch": 3.0, |
| "grad_norm": 0.17180706560611725, |
| "learning_rate": 0.0002, |
| "loss": 0.5359570980072021, |
| "mean_token_accuracy": 0.7822570651769638, |
| "num_tokens": 13140456.0, |
| "step": 804 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 804, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.2246358802919588e+18, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
