| { |
| "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": 1.1289661526679993, |
| "epoch": 0.0037313432835820895, |
| "grad_norm": 1.718437910079956, |
| "learning_rate": 0.0002, |
| "loss": 2.463672637939453, |
| "mean_token_accuracy": 0.538365513086319, |
| "num_tokens": 16752.0, |
| "step": 1 |
| }, |
| { |
| "entropy": 1.2265157401561737, |
| "epoch": 0.007462686567164179, |
| "grad_norm": 1.4970091581344604, |
| "learning_rate": 0.0002, |
| "loss": 2.126779079437256, |
| "mean_token_accuracy": 0.5722294598817825, |
| "num_tokens": 33439.0, |
| "step": 2 |
| }, |
| { |
| "entropy": 1.3961938917636871, |
| "epoch": 0.011194029850746268, |
| "grad_norm": 1.1837635040283203, |
| "learning_rate": 0.0002, |
| "loss": 1.7183202505111694, |
| "mean_token_accuracy": 0.5992514342069626, |
| "num_tokens": 49806.0, |
| "step": 3 |
| }, |
| { |
| "entropy": 1.364193856716156, |
| "epoch": 0.014925373134328358, |
| "grad_norm": 0.9230232834815979, |
| "learning_rate": 0.0002, |
| "loss": 1.3841232061386108, |
| "mean_token_accuracy": 0.6459762454032898, |
| "num_tokens": 66146.0, |
| "step": 4 |
| }, |
| { |
| "entropy": 1.3363392651081085, |
| "epoch": 0.018656716417910446, |
| "grad_norm": 0.8856565952301025, |
| "learning_rate": 0.0002, |
| "loss": 1.2654755115509033, |
| "mean_token_accuracy": 0.6537224054336548, |
| "num_tokens": 82552.0, |
| "step": 5 |
| }, |
| { |
| "entropy": 1.2341538965702057, |
| "epoch": 0.022388059701492536, |
| "grad_norm": 0.44626009464263916, |
| "learning_rate": 0.0002, |
| "loss": 1.1672656536102295, |
| "mean_token_accuracy": 0.6582475453615189, |
| "num_tokens": 98836.0, |
| "step": 6 |
| }, |
| { |
| "entropy": 1.1661392152309418, |
| "epoch": 0.026119402985074626, |
| "grad_norm": 0.4053705036640167, |
| "learning_rate": 0.0002, |
| "loss": 1.0865505933761597, |
| "mean_token_accuracy": 0.6667926758527756, |
| "num_tokens": 115272.0, |
| "step": 7 |
| }, |
| { |
| "entropy": 1.072335958480835, |
| "epoch": 0.029850746268656716, |
| "grad_norm": 0.47601690888404846, |
| "learning_rate": 0.0002, |
| "loss": 1.008798599243164, |
| "mean_token_accuracy": 0.6827712208032608, |
| "num_tokens": 131747.0, |
| "step": 8 |
| }, |
| { |
| "entropy": 0.9832868427038193, |
| "epoch": 0.033582089552238806, |
| "grad_norm": 0.5788419246673584, |
| "learning_rate": 0.0002, |
| "loss": 0.9593731164932251, |
| "mean_token_accuracy": 0.6967775076627731, |
| "num_tokens": 147817.0, |
| "step": 9 |
| }, |
| { |
| "entropy": 0.972461149096489, |
| "epoch": 0.03731343283582089, |
| "grad_norm": 0.4150241017341614, |
| "learning_rate": 0.0002, |
| "loss": 0.8944523930549622, |
| "mean_token_accuracy": 0.7026021331548691, |
| "num_tokens": 164033.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 0.9064666777849197, |
| "epoch": 0.041044776119402986, |
| "grad_norm": 0.4159983992576599, |
| "learning_rate": 0.0002, |
| "loss": 0.8238236308097839, |
| "mean_token_accuracy": 0.7149031907320023, |
| "num_tokens": 180255.0, |
| "step": 11 |
| }, |
| { |
| "entropy": 0.8522350639104843, |
| "epoch": 0.04477611940298507, |
| "grad_norm": 0.4109551012516022, |
| "learning_rate": 0.0002, |
| "loss": 0.8041632175445557, |
| "mean_token_accuracy": 0.714429035782814, |
| "num_tokens": 196667.0, |
| "step": 12 |
| }, |
| { |
| "entropy": 0.7943563163280487, |
| "epoch": 0.048507462686567165, |
| "grad_norm": 4.692042350769043, |
| "learning_rate": 0.0002, |
| "loss": 0.7489398121833801, |
| "mean_token_accuracy": 0.7290935516357422, |
| "num_tokens": 213310.0, |
| "step": 13 |
| }, |
| { |
| "entropy": 0.7642933279275894, |
| "epoch": 0.05223880597014925, |
| "grad_norm": 0.4272930920124054, |
| "learning_rate": 0.0002, |
| "loss": 0.745248019695282, |
| "mean_token_accuracy": 0.7267377078533173, |
| "num_tokens": 229866.0, |
| "step": 14 |
| }, |
| { |
| "entropy": 0.7006226629018784, |
| "epoch": 0.055970149253731345, |
| "grad_norm": 0.4604073464870453, |
| "learning_rate": 0.0002, |
| "loss": 0.707587480545044, |
| "mean_token_accuracy": 0.7386381179094315, |
| "num_tokens": 246215.0, |
| "step": 15 |
| }, |
| { |
| "entropy": 0.6789494007825851, |
| "epoch": 0.05970149253731343, |
| "grad_norm": 0.3421825170516968, |
| "learning_rate": 0.0002, |
| "loss": 0.6623942255973816, |
| "mean_token_accuracy": 0.7504184693098068, |
| "num_tokens": 262578.0, |
| "step": 16 |
| }, |
| { |
| "entropy": 0.6900303512811661, |
| "epoch": 0.06343283582089553, |
| "grad_norm": 0.32081541419029236, |
| "learning_rate": 0.0002, |
| "loss": 0.6742128729820251, |
| "mean_token_accuracy": 0.7435187548398972, |
| "num_tokens": 279221.0, |
| "step": 17 |
| }, |
| { |
| "entropy": 0.6704058647155762, |
| "epoch": 0.06716417910447761, |
| "grad_norm": 0.3068050444126129, |
| "learning_rate": 0.0002, |
| "loss": 0.6692320108413696, |
| "mean_token_accuracy": 0.7405453622341156, |
| "num_tokens": 295744.0, |
| "step": 18 |
| }, |
| { |
| "entropy": 0.645032674074173, |
| "epoch": 0.0708955223880597, |
| "grad_norm": 0.3876055181026459, |
| "learning_rate": 0.0002, |
| "loss": 0.6497271656990051, |
| "mean_token_accuracy": 0.7474837154150009, |
| "num_tokens": 311941.0, |
| "step": 19 |
| }, |
| { |
| "entropy": 0.6437188982963562, |
| "epoch": 0.07462686567164178, |
| "grad_norm": 0.28225845098495483, |
| "learning_rate": 0.0002, |
| "loss": 0.6310586333274841, |
| "mean_token_accuracy": 0.7562051713466644, |
| "num_tokens": 328123.0, |
| "step": 20 |
| }, |
| { |
| "entropy": 0.6336151957511902, |
| "epoch": 0.07835820895522388, |
| "grad_norm": 0.2910671830177307, |
| "learning_rate": 0.0002, |
| "loss": 0.6111513376235962, |
| "mean_token_accuracy": 0.7640680223703384, |
| "num_tokens": 344551.0, |
| "step": 21 |
| }, |
| { |
| "entropy": 0.6192467957735062, |
| "epoch": 0.08208955223880597, |
| "grad_norm": 0.2633042633533478, |
| "learning_rate": 0.0002, |
| "loss": 0.6076130867004395, |
| "mean_token_accuracy": 0.7612886726856232, |
| "num_tokens": 360828.0, |
| "step": 22 |
| }, |
| { |
| "entropy": 0.6041840612888336, |
| "epoch": 0.08582089552238806, |
| "grad_norm": 0.25307416915893555, |
| "learning_rate": 0.0002, |
| "loss": 0.5986919403076172, |
| "mean_token_accuracy": 0.7661398947238922, |
| "num_tokens": 377228.0, |
| "step": 23 |
| }, |
| { |
| "entropy": 0.5882479846477509, |
| "epoch": 0.08955223880597014, |
| "grad_norm": 0.29383954405784607, |
| "learning_rate": 0.0002, |
| "loss": 0.5981481075286865, |
| "mean_token_accuracy": 0.7642848491668701, |
| "num_tokens": 393677.0, |
| "step": 24 |
| }, |
| { |
| "entropy": 0.5793564766645432, |
| "epoch": 0.09328358208955224, |
| "grad_norm": 0.2627723217010498, |
| "learning_rate": 0.0002, |
| "loss": 0.5741637349128723, |
| "mean_token_accuracy": 0.7727137804031372, |
| "num_tokens": 409970.0, |
| "step": 25 |
| }, |
| { |
| "entropy": 0.6003908663988113, |
| "epoch": 0.09701492537313433, |
| "grad_norm": 0.2566275894641876, |
| "learning_rate": 0.0002, |
| "loss": 0.5895748138427734, |
| "mean_token_accuracy": 0.7672757506370544, |
| "num_tokens": 426376.0, |
| "step": 26 |
| }, |
| { |
| "entropy": 0.5952489227056503, |
| "epoch": 0.10074626865671642, |
| "grad_norm": 0.2420552521944046, |
| "learning_rate": 0.0002, |
| "loss": 0.6007665991783142, |
| "mean_token_accuracy": 0.7637803256511688, |
| "num_tokens": 442546.0, |
| "step": 27 |
| }, |
| { |
| "entropy": 0.5743676871061325, |
| "epoch": 0.1044776119402985, |
| "grad_norm": 0.29494741559028625, |
| "learning_rate": 0.0002, |
| "loss": 0.5768784880638123, |
| "mean_token_accuracy": 0.7743212580680847, |
| "num_tokens": 458793.0, |
| "step": 28 |
| }, |
| { |
| "entropy": 0.5913154035806656, |
| "epoch": 0.10820895522388059, |
| "grad_norm": 0.22388432919979095, |
| "learning_rate": 0.0002, |
| "loss": 0.5951215624809265, |
| "mean_token_accuracy": 0.7636702209711075, |
| "num_tokens": 475104.0, |
| "step": 29 |
| }, |
| { |
| "entropy": 0.5590654462575912, |
| "epoch": 0.11194029850746269, |
| "grad_norm": 0.2290356606245041, |
| "learning_rate": 0.0002, |
| "loss": 0.5624232292175293, |
| "mean_token_accuracy": 0.777785912156105, |
| "num_tokens": 491297.0, |
| "step": 30 |
| }, |
| { |
| "entropy": 0.5694295465946198, |
| "epoch": 0.11567164179104478, |
| "grad_norm": 0.25151577591896057, |
| "learning_rate": 0.0002, |
| "loss": 0.5708881616592407, |
| "mean_token_accuracy": 0.7728395611047745, |
| "num_tokens": 507721.0, |
| "step": 31 |
| }, |
| { |
| "entropy": 0.5803322345018387, |
| "epoch": 0.11940298507462686, |
| "grad_norm": 0.22804486751556396, |
| "learning_rate": 0.0002, |
| "loss": 0.5754807591438293, |
| "mean_token_accuracy": 0.7712786793708801, |
| "num_tokens": 524178.0, |
| "step": 32 |
| }, |
| { |
| "entropy": 0.5787805169820786, |
| "epoch": 0.12313432835820895, |
| "grad_norm": 0.20522084832191467, |
| "learning_rate": 0.0002, |
| "loss": 0.5813344717025757, |
| "mean_token_accuracy": 0.7693952471017838, |
| "num_tokens": 540759.0, |
| "step": 33 |
| }, |
| { |
| "entropy": 0.5641594678163528, |
| "epoch": 0.12686567164179105, |
| "grad_norm": 0.22316089272499084, |
| "learning_rate": 0.0002, |
| "loss": 0.5667368769645691, |
| "mean_token_accuracy": 0.7733088880777359, |
| "num_tokens": 557098.0, |
| "step": 34 |
| }, |
| { |
| "entropy": 0.5698780119419098, |
| "epoch": 0.13059701492537312, |
| "grad_norm": 0.19682574272155762, |
| "learning_rate": 0.0002, |
| "loss": 0.5731198191642761, |
| "mean_token_accuracy": 0.7713790237903595, |
| "num_tokens": 573643.0, |
| "step": 35 |
| }, |
| { |
| "entropy": 0.5606762617826462, |
| "epoch": 0.13432835820895522, |
| "grad_norm": 0.18110722303390503, |
| "learning_rate": 0.0002, |
| "loss": 0.5680837035179138, |
| "mean_token_accuracy": 0.7729717791080475, |
| "num_tokens": 590055.0, |
| "step": 36 |
| }, |
| { |
| "entropy": 0.573099821805954, |
| "epoch": 0.13805970149253732, |
| "grad_norm": 0.1901063174009323, |
| "learning_rate": 0.0002, |
| "loss": 0.58585524559021, |
| "mean_token_accuracy": 0.7647827565670013, |
| "num_tokens": 606371.0, |
| "step": 37 |
| }, |
| { |
| "entropy": 0.5616094470024109, |
| "epoch": 0.1417910447761194, |
| "grad_norm": 0.16249483823776245, |
| "learning_rate": 0.0002, |
| "loss": 0.5683356523513794, |
| "mean_token_accuracy": 0.7730494290590286, |
| "num_tokens": 622407.0, |
| "step": 38 |
| }, |
| { |
| "entropy": 0.5745197981595993, |
| "epoch": 0.1455223880597015, |
| "grad_norm": 0.18366950750350952, |
| "learning_rate": 0.0002, |
| "loss": 0.5711386203765869, |
| "mean_token_accuracy": 0.7720607072114944, |
| "num_tokens": 638807.0, |
| "step": 39 |
| }, |
| { |
| "entropy": 0.5433095991611481, |
| "epoch": 0.14925373134328357, |
| "grad_norm": 0.16753046214580536, |
| "learning_rate": 0.0002, |
| "loss": 0.541424036026001, |
| "mean_token_accuracy": 0.7816750854253769, |
| "num_tokens": 655156.0, |
| "step": 40 |
| }, |
| { |
| "entropy": 0.577083632349968, |
| "epoch": 0.15298507462686567, |
| "grad_norm": 0.1564643234014511, |
| "learning_rate": 0.0002, |
| "loss": 0.5749148726463318, |
| "mean_token_accuracy": 0.7712480574846268, |
| "num_tokens": 671455.0, |
| "step": 41 |
| }, |
| { |
| "entropy": 0.5777066200971603, |
| "epoch": 0.15671641791044777, |
| "grad_norm": 0.15681707859039307, |
| "learning_rate": 0.0002, |
| "loss": 0.5710839629173279, |
| "mean_token_accuracy": 0.771970272064209, |
| "num_tokens": 687402.0, |
| "step": 42 |
| }, |
| { |
| "entropy": 0.5576052665710449, |
| "epoch": 0.16044776119402984, |
| "grad_norm": 0.1535220742225647, |
| "learning_rate": 0.0002, |
| "loss": 0.554729163646698, |
| "mean_token_accuracy": 0.7778889983892441, |
| "num_tokens": 703674.0, |
| "step": 43 |
| }, |
| { |
| "entropy": 0.568035364151001, |
| "epoch": 0.16417910447761194, |
| "grad_norm": 0.19506719708442688, |
| "learning_rate": 0.0002, |
| "loss": 0.563572883605957, |
| "mean_token_accuracy": 0.7732609957456589, |
| "num_tokens": 720028.0, |
| "step": 44 |
| }, |
| { |
| "entropy": 0.5528023689985275, |
| "epoch": 0.16791044776119404, |
| "grad_norm": 0.17355836927890778, |
| "learning_rate": 0.0002, |
| "loss": 0.5633578300476074, |
| "mean_token_accuracy": 0.7745559066534042, |
| "num_tokens": 736383.0, |
| "step": 45 |
| }, |
| { |
| "entropy": 0.5670178234577179, |
| "epoch": 0.17164179104477612, |
| "grad_norm": 0.15191075205802917, |
| "learning_rate": 0.0002, |
| "loss": 0.5678278207778931, |
| "mean_token_accuracy": 0.7719666659832001, |
| "num_tokens": 752674.0, |
| "step": 46 |
| }, |
| { |
| "entropy": 0.5755926370620728, |
| "epoch": 0.17537313432835822, |
| "grad_norm": 0.16460369527339935, |
| "learning_rate": 0.0002, |
| "loss": 0.5739490389823914, |
| "mean_token_accuracy": 0.7679776549339294, |
| "num_tokens": 768903.0, |
| "step": 47 |
| }, |
| { |
| "entropy": 0.5554705560207367, |
| "epoch": 0.1791044776119403, |
| "grad_norm": 0.18931463360786438, |
| "learning_rate": 0.0002, |
| "loss": 0.5547196865081787, |
| "mean_token_accuracy": 0.7758906781673431, |
| "num_tokens": 785118.0, |
| "step": 48 |
| }, |
| { |
| "entropy": 0.5702430158853531, |
| "epoch": 0.1828358208955224, |
| "grad_norm": 0.15216942131519318, |
| "learning_rate": 0.0002, |
| "loss": 0.5743824243545532, |
| "mean_token_accuracy": 0.7712646275758743, |
| "num_tokens": 801443.0, |
| "step": 49 |
| }, |
| { |
| "entropy": 0.5590359568595886, |
| "epoch": 0.1865671641791045, |
| "grad_norm": 0.1364562213420868, |
| "learning_rate": 0.0002, |
| "loss": 0.5621891617774963, |
| "mean_token_accuracy": 0.7768612504005432, |
| "num_tokens": 817953.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 0.5538916885852814, |
| "epoch": 0.19029850746268656, |
| "grad_norm": 0.15327665209770203, |
| "learning_rate": 0.0002, |
| "loss": 0.557817280292511, |
| "mean_token_accuracy": 0.77579165995121, |
| "num_tokens": 834179.0, |
| "step": 51 |
| }, |
| { |
| "entropy": 0.5548055320978165, |
| "epoch": 0.19402985074626866, |
| "grad_norm": 0.17109805345535278, |
| "learning_rate": 0.0002, |
| "loss": 0.5557324886322021, |
| "mean_token_accuracy": 0.7784830182790756, |
| "num_tokens": 850292.0, |
| "step": 52 |
| }, |
| { |
| "entropy": 0.5522786229848862, |
| "epoch": 0.19776119402985073, |
| "grad_norm": 0.13925932347774506, |
| "learning_rate": 0.0002, |
| "loss": 0.5462207198143005, |
| "mean_token_accuracy": 0.7795155495405197, |
| "num_tokens": 866921.0, |
| "step": 53 |
| }, |
| { |
| "entropy": 0.5618164092302322, |
| "epoch": 0.20149253731343283, |
| "grad_norm": 0.16067089140415192, |
| "learning_rate": 0.0002, |
| "loss": 0.5644089579582214, |
| "mean_token_accuracy": 0.7715546041727066, |
| "num_tokens": 883239.0, |
| "step": 54 |
| }, |
| { |
| "entropy": 0.5592249482870102, |
| "epoch": 0.20522388059701493, |
| "grad_norm": 0.15423332154750824, |
| "learning_rate": 0.0002, |
| "loss": 0.561421811580658, |
| "mean_token_accuracy": 0.7746220380067825, |
| "num_tokens": 899644.0, |
| "step": 55 |
| }, |
| { |
| "entropy": 0.5488702207803726, |
| "epoch": 0.208955223880597, |
| "grad_norm": 0.17080672085285187, |
| "learning_rate": 0.0002, |
| "loss": 0.5529103875160217, |
| "mean_token_accuracy": 0.7794950157403946, |
| "num_tokens": 915989.0, |
| "step": 56 |
| }, |
| { |
| "entropy": 0.5521678775548935, |
| "epoch": 0.2126865671641791, |
| "grad_norm": 0.15817587077617645, |
| "learning_rate": 0.0002, |
| "loss": 0.5538347363471985, |
| "mean_token_accuracy": 0.7747852057218552, |
| "num_tokens": 932345.0, |
| "step": 57 |
| }, |
| { |
| "entropy": 0.5373486876487732, |
| "epoch": 0.21641791044776118, |
| "grad_norm": 0.14603540301322937, |
| "learning_rate": 0.0002, |
| "loss": 0.5370327234268188, |
| "mean_token_accuracy": 0.7844787091016769, |
| "num_tokens": 948632.0, |
| "step": 58 |
| }, |
| { |
| "entropy": 0.5743934810161591, |
| "epoch": 0.22014925373134328, |
| "grad_norm": 0.15721800923347473, |
| "learning_rate": 0.0002, |
| "loss": 0.5750125050544739, |
| "mean_token_accuracy": 0.7708619683980942, |
| "num_tokens": 965036.0, |
| "step": 59 |
| }, |
| { |
| "entropy": 0.5666798055171967, |
| "epoch": 0.22388059701492538, |
| "grad_norm": 0.15671038627624512, |
| "learning_rate": 0.0002, |
| "loss": 0.5712930560112, |
| "mean_token_accuracy": 0.7729278206825256, |
| "num_tokens": 981532.0, |
| "step": 60 |
| }, |
| { |
| "entropy": 0.5513272732496262, |
| "epoch": 0.22761194029850745, |
| "grad_norm": 0.17748433351516724, |
| "learning_rate": 0.0002, |
| "loss": 0.5560383200645447, |
| "mean_token_accuracy": 0.7785970717668533, |
| "num_tokens": 997973.0, |
| "step": 61 |
| }, |
| { |
| "entropy": 0.5540748685598373, |
| "epoch": 0.23134328358208955, |
| "grad_norm": 0.16005375981330872, |
| "learning_rate": 0.0002, |
| "loss": 0.5532342195510864, |
| "mean_token_accuracy": 0.7789635509252548, |
| "num_tokens": 1014304.0, |
| "step": 62 |
| }, |
| { |
| "entropy": 0.5579517930746078, |
| "epoch": 0.23507462686567165, |
| "grad_norm": 0.18263301253318787, |
| "learning_rate": 0.0002, |
| "loss": 0.5565052032470703, |
| "mean_token_accuracy": 0.7755438834428787, |
| "num_tokens": 1030673.0, |
| "step": 63 |
| }, |
| { |
| "entropy": 0.5552463680505753, |
| "epoch": 0.23880597014925373, |
| "grad_norm": 0.1649768054485321, |
| "learning_rate": 0.0002, |
| "loss": 0.5620046257972717, |
| "mean_token_accuracy": 0.7743330150842667, |
| "num_tokens": 1047130.0, |
| "step": 64 |
| }, |
| { |
| "entropy": 0.5658495426177979, |
| "epoch": 0.24253731343283583, |
| "grad_norm": 0.14895500242710114, |
| "learning_rate": 0.0002, |
| "loss": 0.5690064430236816, |
| "mean_token_accuracy": 0.769889697432518, |
| "num_tokens": 1063267.0, |
| "step": 65 |
| }, |
| { |
| "entropy": 0.5476687997579575, |
| "epoch": 0.2462686567164179, |
| "grad_norm": 0.15621285140514374, |
| "learning_rate": 0.0002, |
| "loss": 0.5411933660507202, |
| "mean_token_accuracy": 0.7802412062883377, |
| "num_tokens": 1079489.0, |
| "step": 66 |
| }, |
| { |
| "entropy": 0.5770413428544998, |
| "epoch": 0.25, |
| "grad_norm": 0.17651045322418213, |
| "learning_rate": 0.0002, |
| "loss": 0.5727323293685913, |
| "mean_token_accuracy": 0.7670447826385498, |
| "num_tokens": 1096099.0, |
| "step": 67 |
| }, |
| { |
| "entropy": 0.5629345774650574, |
| "epoch": 0.2537313432835821, |
| "grad_norm": 0.14068245887756348, |
| "learning_rate": 0.0002, |
| "loss": 0.5644123554229736, |
| "mean_token_accuracy": 0.7756455391645432, |
| "num_tokens": 1112706.0, |
| "step": 68 |
| }, |
| { |
| "entropy": 0.5544387400150299, |
| "epoch": 0.2574626865671642, |
| "grad_norm": 0.17108768224716187, |
| "learning_rate": 0.0002, |
| "loss": 0.5581443309783936, |
| "mean_token_accuracy": 0.7782857865095139, |
| "num_tokens": 1128932.0, |
| "step": 69 |
| }, |
| { |
| "entropy": 0.5596695244312286, |
| "epoch": 0.26119402985074625, |
| "grad_norm": 0.19048558175563812, |
| "learning_rate": 0.0002, |
| "loss": 0.5650323629379272, |
| "mean_token_accuracy": 0.7726176232099533, |
| "num_tokens": 1145124.0, |
| "step": 70 |
| }, |
| { |
| "entropy": 0.5567205399274826, |
| "epoch": 0.26492537313432835, |
| "grad_norm": 0.13650791347026825, |
| "learning_rate": 0.0002, |
| "loss": 0.5617868900299072, |
| "mean_token_accuracy": 0.7734960317611694, |
| "num_tokens": 1161412.0, |
| "step": 71 |
| }, |
| { |
| "entropy": 0.5644008219242096, |
| "epoch": 0.26865671641791045, |
| "grad_norm": 0.155628502368927, |
| "learning_rate": 0.0002, |
| "loss": 0.5622598528862, |
| "mean_token_accuracy": 0.7751530855894089, |
| "num_tokens": 1177678.0, |
| "step": 72 |
| }, |
| { |
| "entropy": 0.5512420982122421, |
| "epoch": 0.27238805970149255, |
| "grad_norm": 0.15644431114196777, |
| "learning_rate": 0.0002, |
| "loss": 0.544489860534668, |
| "mean_token_accuracy": 0.7823818773031235, |
| "num_tokens": 1194203.0, |
| "step": 73 |
| }, |
| { |
| "entropy": 0.5527062118053436, |
| "epoch": 0.27611940298507465, |
| "grad_norm": 0.13635890185832977, |
| "learning_rate": 0.0002, |
| "loss": 0.5439632534980774, |
| "mean_token_accuracy": 0.778559997677803, |
| "num_tokens": 1210684.0, |
| "step": 74 |
| }, |
| { |
| "entropy": 0.5612697750329971, |
| "epoch": 0.2798507462686567, |
| "grad_norm": 0.12589991092681885, |
| "learning_rate": 0.0002, |
| "loss": 0.5658812522888184, |
| "mean_token_accuracy": 0.7703366130590439, |
| "num_tokens": 1226976.0, |
| "step": 75 |
| }, |
| { |
| "entropy": 0.5571960955858231, |
| "epoch": 0.2835820895522388, |
| "grad_norm": 0.14073754847049713, |
| "learning_rate": 0.0002, |
| "loss": 0.5620365142822266, |
| "mean_token_accuracy": 0.7720384001731873, |
| "num_tokens": 1243391.0, |
| "step": 76 |
| }, |
| { |
| "entropy": 0.5598266273736954, |
| "epoch": 0.2873134328358209, |
| "grad_norm": 0.15402883291244507, |
| "learning_rate": 0.0002, |
| "loss": 0.566253662109375, |
| "mean_token_accuracy": 0.7730027735233307, |
| "num_tokens": 1259839.0, |
| "step": 77 |
| }, |
| { |
| "entropy": 0.5466305911540985, |
| "epoch": 0.291044776119403, |
| "grad_norm": 0.1498635858297348, |
| "learning_rate": 0.0002, |
| "loss": 0.5497840642929077, |
| "mean_token_accuracy": 0.7795174568891525, |
| "num_tokens": 1276206.0, |
| "step": 78 |
| }, |
| { |
| "entropy": 0.5226401463150978, |
| "epoch": 0.2947761194029851, |
| "grad_norm": 0.14208680391311646, |
| "learning_rate": 0.0002, |
| "loss": 0.5317234992980957, |
| "mean_token_accuracy": 0.7878109961748123, |
| "num_tokens": 1292321.0, |
| "step": 79 |
| }, |
| { |
| "entropy": 0.5591273456811905, |
| "epoch": 0.29850746268656714, |
| "grad_norm": 0.16277118027210236, |
| "learning_rate": 0.0002, |
| "loss": 0.5597557425498962, |
| "mean_token_accuracy": 0.7736033499240875, |
| "num_tokens": 1308595.0, |
| "step": 80 |
| }, |
| { |
| "entropy": 0.5489696487784386, |
| "epoch": 0.30223880597014924, |
| "grad_norm": 0.15522730350494385, |
| "learning_rate": 0.0002, |
| "loss": 0.5473228693008423, |
| "mean_token_accuracy": 0.7793988287448883, |
| "num_tokens": 1324686.0, |
| "step": 81 |
| }, |
| { |
| "entropy": 0.5511604249477386, |
| "epoch": 0.30597014925373134, |
| "grad_norm": 0.1423621028661728, |
| "learning_rate": 0.0002, |
| "loss": 0.5471224784851074, |
| "mean_token_accuracy": 0.7808315306901932, |
| "num_tokens": 1340767.0, |
| "step": 82 |
| }, |
| { |
| "entropy": 0.535831555724144, |
| "epoch": 0.30970149253731344, |
| "grad_norm": 0.11497796326875687, |
| "learning_rate": 0.0002, |
| "loss": 0.5396604537963867, |
| "mean_token_accuracy": 0.7792594134807587, |
| "num_tokens": 1356840.0, |
| "step": 83 |
| }, |
| { |
| "entropy": 0.5524029284715652, |
| "epoch": 0.31343283582089554, |
| "grad_norm": 0.14306826889514923, |
| "learning_rate": 0.0002, |
| "loss": 0.554614782333374, |
| "mean_token_accuracy": 0.7765442132949829, |
| "num_tokens": 1373132.0, |
| "step": 84 |
| }, |
| { |
| "entropy": 0.5417301952838898, |
| "epoch": 0.31716417910447764, |
| "grad_norm": 0.14920470118522644, |
| "learning_rate": 0.0002, |
| "loss": 0.5464574098587036, |
| "mean_token_accuracy": 0.7781450152397156, |
| "num_tokens": 1389464.0, |
| "step": 85 |
| }, |
| { |
| "entropy": 0.5468066930770874, |
| "epoch": 0.3208955223880597, |
| "grad_norm": 0.1330336183309555, |
| "learning_rate": 0.0002, |
| "loss": 0.5496163368225098, |
| "mean_token_accuracy": 0.7773268073797226, |
| "num_tokens": 1405758.0, |
| "step": 86 |
| }, |
| { |
| "entropy": 0.5532258301973343, |
| "epoch": 0.3246268656716418, |
| "grad_norm": 0.14286059141159058, |
| "learning_rate": 0.0002, |
| "loss": 0.5587942004203796, |
| "mean_token_accuracy": 0.773719072341919, |
| "num_tokens": 1421983.0, |
| "step": 87 |
| }, |
| { |
| "entropy": 0.5505443513393402, |
| "epoch": 0.3283582089552239, |
| "grad_norm": 0.14466629922389984, |
| "learning_rate": 0.0002, |
| "loss": 0.5517881512641907, |
| "mean_token_accuracy": 0.7773502916097641, |
| "num_tokens": 1438290.0, |
| "step": 88 |
| }, |
| { |
| "entropy": 0.5580704063177109, |
| "epoch": 0.332089552238806, |
| "grad_norm": 0.14080838859081268, |
| "learning_rate": 0.0002, |
| "loss": 0.5504853129386902, |
| "mean_token_accuracy": 0.7808509767055511, |
| "num_tokens": 1454785.0, |
| "step": 89 |
| }, |
| { |
| "entropy": 0.5517671704292297, |
| "epoch": 0.3358208955223881, |
| "grad_norm": 0.13040079176425934, |
| "learning_rate": 0.0002, |
| "loss": 0.5536596179008484, |
| "mean_token_accuracy": 0.7774396985769272, |
| "num_tokens": 1471103.0, |
| "step": 90 |
| }, |
| { |
| "entropy": 0.5486855804920197, |
| "epoch": 0.33955223880597013, |
| "grad_norm": 0.13183721899986267, |
| "learning_rate": 0.0002, |
| "loss": 0.5515735149383545, |
| "mean_token_accuracy": 0.7787674814462662, |
| "num_tokens": 1487726.0, |
| "step": 91 |
| }, |
| { |
| "entropy": 0.5304955244064331, |
| "epoch": 0.34328358208955223, |
| "grad_norm": 0.14942337572574615, |
| "learning_rate": 0.0002, |
| "loss": 0.5404319167137146, |
| "mean_token_accuracy": 0.7821393609046936, |
| "num_tokens": 1503916.0, |
| "step": 92 |
| }, |
| { |
| "entropy": 0.5513530522584915, |
| "epoch": 0.34701492537313433, |
| "grad_norm": 0.14205244183540344, |
| "learning_rate": 0.0002, |
| "loss": 0.5578951239585876, |
| "mean_token_accuracy": 0.7760411649942398, |
| "num_tokens": 1520451.0, |
| "step": 93 |
| }, |
| { |
| "entropy": 0.5582473278045654, |
| "epoch": 0.35074626865671643, |
| "grad_norm": 0.14064031839370728, |
| "learning_rate": 0.0002, |
| "loss": 0.555766224861145, |
| "mean_token_accuracy": 0.7757732421159744, |
| "num_tokens": 1536703.0, |
| "step": 94 |
| }, |
| { |
| "entropy": 0.5676290094852448, |
| "epoch": 0.35447761194029853, |
| "grad_norm": 0.13484041392803192, |
| "learning_rate": 0.0002, |
| "loss": 0.5641413927078247, |
| "mean_token_accuracy": 0.7711052447557449, |
| "num_tokens": 1553019.0, |
| "step": 95 |
| }, |
| { |
| "entropy": 0.5447694808244705, |
| "epoch": 0.3582089552238806, |
| "grad_norm": 0.1363735944032669, |
| "learning_rate": 0.0002, |
| "loss": 0.550776481628418, |
| "mean_token_accuracy": 0.7794662415981293, |
| "num_tokens": 1569163.0, |
| "step": 96 |
| }, |
| { |
| "entropy": 0.5422163158655167, |
| "epoch": 0.3619402985074627, |
| "grad_norm": 0.16971470415592194, |
| "learning_rate": 0.0002, |
| "loss": 0.546565592288971, |
| "mean_token_accuracy": 0.7790998369455338, |
| "num_tokens": 1585441.0, |
| "step": 97 |
| }, |
| { |
| "entropy": 0.5433662682771683, |
| "epoch": 0.3656716417910448, |
| "grad_norm": 0.1288556158542633, |
| "learning_rate": 0.0002, |
| "loss": 0.542870819568634, |
| "mean_token_accuracy": 0.7825556546449661, |
| "num_tokens": 1601831.0, |
| "step": 98 |
| }, |
| { |
| "entropy": 0.5588658303022385, |
| "epoch": 0.3694029850746269, |
| "grad_norm": 0.13709332048892975, |
| "learning_rate": 0.0002, |
| "loss": 0.5542604923248291, |
| "mean_token_accuracy": 0.7753584235906601, |
| "num_tokens": 1618047.0, |
| "step": 99 |
| }, |
| { |
| "entropy": 0.5432140231132507, |
| "epoch": 0.373134328358209, |
| "grad_norm": 0.1292959600687027, |
| "learning_rate": 0.0002, |
| "loss": 0.5443875193595886, |
| "mean_token_accuracy": 0.7775225788354874, |
| "num_tokens": 1634357.0, |
| "step": 100 |
| }, |
| { |
| "entropy": 0.5512475073337555, |
| "epoch": 0.376865671641791, |
| "grad_norm": 0.13880467414855957, |
| "learning_rate": 0.0002, |
| "loss": 0.5502674579620361, |
| "mean_token_accuracy": 0.7766819447278976, |
| "num_tokens": 1650447.0, |
| "step": 101 |
| }, |
| { |
| "entropy": 0.5448634326457977, |
| "epoch": 0.3805970149253731, |
| "grad_norm": 0.11999475210905075, |
| "learning_rate": 0.0002, |
| "loss": 0.5479167103767395, |
| "mean_token_accuracy": 0.7774510979652405, |
| "num_tokens": 1666715.0, |
| "step": 102 |
| }, |
| { |
| "entropy": 0.5404264181852341, |
| "epoch": 0.3843283582089552, |
| "grad_norm": 0.1147257462143898, |
| "learning_rate": 0.0002, |
| "loss": 0.5443326830863953, |
| "mean_token_accuracy": 0.7807854264974594, |
| "num_tokens": 1683048.0, |
| "step": 103 |
| }, |
| { |
| "entropy": 0.5706409513950348, |
| "epoch": 0.3880597014925373, |
| "grad_norm": 0.1385030895471573, |
| "learning_rate": 0.0002, |
| "loss": 0.5782899260520935, |
| "mean_token_accuracy": 0.7652212530374527, |
| "num_tokens": 1699325.0, |
| "step": 104 |
| }, |
| { |
| "entropy": 0.5571511834859848, |
| "epoch": 0.3917910447761194, |
| "grad_norm": 0.1369410902261734, |
| "learning_rate": 0.0002, |
| "loss": 0.5521953701972961, |
| "mean_token_accuracy": 0.7748987078666687, |
| "num_tokens": 1716057.0, |
| "step": 105 |
| }, |
| { |
| "entropy": 0.5631535947322845, |
| "epoch": 0.39552238805970147, |
| "grad_norm": 0.1280808299779892, |
| "learning_rate": 0.0002, |
| "loss": 0.5561803579330444, |
| "mean_token_accuracy": 0.775022104382515, |
| "num_tokens": 1732435.0, |
| "step": 106 |
| }, |
| { |
| "entropy": 0.5572030395269394, |
| "epoch": 0.39925373134328357, |
| "grad_norm": 0.12024517357349396, |
| "learning_rate": 0.0002, |
| "loss": 0.5535359382629395, |
| "mean_token_accuracy": 0.7766966223716736, |
| "num_tokens": 1748804.0, |
| "step": 107 |
| }, |
| { |
| "entropy": 0.5371659398078918, |
| "epoch": 0.40298507462686567, |
| "grad_norm": 0.13146717846393585, |
| "learning_rate": 0.0002, |
| "loss": 0.5349127650260925, |
| "mean_token_accuracy": 0.7823473811149597, |
| "num_tokens": 1765273.0, |
| "step": 108 |
| }, |
| { |
| "entropy": 0.5396981537342072, |
| "epoch": 0.40671641791044777, |
| "grad_norm": 0.14155176281929016, |
| "learning_rate": 0.0002, |
| "loss": 0.5501641035079956, |
| "mean_token_accuracy": 0.7808535546064377, |
| "num_tokens": 1781613.0, |
| "step": 109 |
| }, |
| { |
| "entropy": 0.55367811024189, |
| "epoch": 0.41044776119402987, |
| "grad_norm": 0.14105667173862457, |
| "learning_rate": 0.0002, |
| "loss": 0.5660677552223206, |
| "mean_token_accuracy": 0.7713736146688461, |
| "num_tokens": 1798051.0, |
| "step": 110 |
| }, |
| { |
| "entropy": 0.5674728751182556, |
| "epoch": 0.4141791044776119, |
| "grad_norm": 0.13329695165157318, |
| "learning_rate": 0.0002, |
| "loss": 0.5601462125778198, |
| "mean_token_accuracy": 0.7731436491012573, |
| "num_tokens": 1814790.0, |
| "step": 111 |
| }, |
| { |
| "entropy": 0.5627353489398956, |
| "epoch": 0.417910447761194, |
| "grad_norm": 0.12380664050579071, |
| "learning_rate": 0.0002, |
| "loss": 0.5507606863975525, |
| "mean_token_accuracy": 0.77576744556427, |
| "num_tokens": 1831494.0, |
| "step": 112 |
| }, |
| { |
| "entropy": 0.5607950538396835, |
| "epoch": 0.4216417910447761, |
| "grad_norm": 0.1340574473142624, |
| "learning_rate": 0.0002, |
| "loss": 0.5582605600357056, |
| "mean_token_accuracy": 0.7748961746692657, |
| "num_tokens": 1847954.0, |
| "step": 113 |
| }, |
| { |
| "entropy": 0.5448761284351349, |
| "epoch": 0.4253731343283582, |
| "grad_norm": 0.1381089985370636, |
| "learning_rate": 0.0002, |
| "loss": 0.5562179088592529, |
| "mean_token_accuracy": 0.77853924036026, |
| "num_tokens": 1864171.0, |
| "step": 114 |
| }, |
| { |
| "entropy": 0.5476966500282288, |
| "epoch": 0.4291044776119403, |
| "grad_norm": 0.17156046628952026, |
| "learning_rate": 0.0002, |
| "loss": 0.5621172189712524, |
| "mean_token_accuracy": 0.7726399302482605, |
| "num_tokens": 1880288.0, |
| "step": 115 |
| }, |
| { |
| "entropy": 0.536665678024292, |
| "epoch": 0.43283582089552236, |
| "grad_norm": 0.12497282028198242, |
| "learning_rate": 0.0002, |
| "loss": 0.5375184416770935, |
| "mean_token_accuracy": 0.7834422141313553, |
| "num_tokens": 1896645.0, |
| "step": 116 |
| }, |
| { |
| "entropy": 0.5514304488897324, |
| "epoch": 0.43656716417910446, |
| "grad_norm": 0.1161092147231102, |
| "learning_rate": 0.0002, |
| "loss": 0.544856071472168, |
| "mean_token_accuracy": 0.7797137200832367, |
| "num_tokens": 1912665.0, |
| "step": 117 |
| }, |
| { |
| "entropy": 0.5609152466058731, |
| "epoch": 0.44029850746268656, |
| "grad_norm": 0.13559550046920776, |
| "learning_rate": 0.0002, |
| "loss": 0.5554326176643372, |
| "mean_token_accuracy": 0.7768488228321075, |
| "num_tokens": 1929029.0, |
| "step": 118 |
| }, |
| { |
| "entropy": 0.5484367311000824, |
| "epoch": 0.44402985074626866, |
| "grad_norm": 0.1606493592262268, |
| "learning_rate": 0.0002, |
| "loss": 0.552499532699585, |
| "mean_token_accuracy": 0.7767489403486252, |
| "num_tokens": 1945411.0, |
| "step": 119 |
| }, |
| { |
| "entropy": 0.5383798032999039, |
| "epoch": 0.44776119402985076, |
| "grad_norm": 0.15001127123832703, |
| "learning_rate": 0.0002, |
| "loss": 0.5457225441932678, |
| "mean_token_accuracy": 0.781368225812912, |
| "num_tokens": 1961687.0, |
| "step": 120 |
| }, |
| { |
| "entropy": 0.556725487112999, |
| "epoch": 0.45149253731343286, |
| "grad_norm": 0.13887761533260345, |
| "learning_rate": 0.0002, |
| "loss": 0.5596432685852051, |
| "mean_token_accuracy": 0.7745788991451263, |
| "num_tokens": 1977970.0, |
| "step": 121 |
| }, |
| { |
| "entropy": 0.5471978932619095, |
| "epoch": 0.4552238805970149, |
| "grad_norm": 0.17769674956798553, |
| "learning_rate": 0.0002, |
| "loss": 0.548913836479187, |
| "mean_token_accuracy": 0.7780103981494904, |
| "num_tokens": 1994623.0, |
| "step": 122 |
| }, |
| { |
| "entropy": 0.5743421018123627, |
| "epoch": 0.458955223880597, |
| "grad_norm": 0.1550552397966385, |
| "learning_rate": 0.0002, |
| "loss": 0.5709196329116821, |
| "mean_token_accuracy": 0.7687129527330399, |
| "num_tokens": 2011220.0, |
| "step": 123 |
| }, |
| { |
| "entropy": 0.5476535260677338, |
| "epoch": 0.4626865671641791, |
| "grad_norm": 0.1717722862958908, |
| "learning_rate": 0.0002, |
| "loss": 0.5485281944274902, |
| "mean_token_accuracy": 0.7796104848384857, |
| "num_tokens": 2027592.0, |
| "step": 124 |
| }, |
| { |
| "entropy": 0.560809999704361, |
| "epoch": 0.4664179104477612, |
| "grad_norm": 0.13076141476631165, |
| "learning_rate": 0.0002, |
| "loss": 0.558412492275238, |
| "mean_token_accuracy": 0.7760445475578308, |
| "num_tokens": 2044027.0, |
| "step": 125 |
| }, |
| { |
| "entropy": 0.5596277713775635, |
| "epoch": 0.4701492537313433, |
| "grad_norm": 0.1541507989168167, |
| "learning_rate": 0.0002, |
| "loss": 0.5639489889144897, |
| "mean_token_accuracy": 0.773893877863884, |
| "num_tokens": 2060575.0, |
| "step": 126 |
| }, |
| { |
| "entropy": 0.5626689940690994, |
| "epoch": 0.47388059701492535, |
| "grad_norm": 0.13210763037204742, |
| "learning_rate": 0.0002, |
| "loss": 0.5666107535362244, |
| "mean_token_accuracy": 0.7723562121391296, |
| "num_tokens": 2077142.0, |
| "step": 127 |
| }, |
| { |
| "entropy": 0.5383650660514832, |
| "epoch": 0.47761194029850745, |
| "grad_norm": 0.144685760140419, |
| "learning_rate": 0.0002, |
| "loss": 0.5507121086120605, |
| "mean_token_accuracy": 0.7755688577890396, |
| "num_tokens": 2093476.0, |
| "step": 128 |
| }, |
| { |
| "entropy": 0.5625992119312286, |
| "epoch": 0.48134328358208955, |
| "grad_norm": 0.15112625062465668, |
| "learning_rate": 0.0002, |
| "loss": 0.5599629282951355, |
| "mean_token_accuracy": 0.7773216217756271, |
| "num_tokens": 2110065.0, |
| "step": 129 |
| }, |
| { |
| "entropy": 0.5618867576122284, |
| "epoch": 0.48507462686567165, |
| "grad_norm": 0.12856954336166382, |
| "learning_rate": 0.0002, |
| "loss": 0.5595183372497559, |
| "mean_token_accuracy": 0.770575687289238, |
| "num_tokens": 2126219.0, |
| "step": 130 |
| }, |
| { |
| "entropy": 0.5557905286550522, |
| "epoch": 0.48880597014925375, |
| "grad_norm": 0.13426126539707184, |
| "learning_rate": 0.0002, |
| "loss": 0.5510875582695007, |
| "mean_token_accuracy": 0.7762824147939682, |
| "num_tokens": 2142407.0, |
| "step": 131 |
| }, |
| { |
| "entropy": 0.5594918131828308, |
| "epoch": 0.4925373134328358, |
| "grad_norm": 0.12567119300365448, |
| "learning_rate": 0.0002, |
| "loss": 0.5540769100189209, |
| "mean_token_accuracy": 0.7767548561096191, |
| "num_tokens": 2158881.0, |
| "step": 132 |
| }, |
| { |
| "entropy": 0.5489580035209656, |
| "epoch": 0.4962686567164179, |
| "grad_norm": 0.12187269330024719, |
| "learning_rate": 0.0002, |
| "loss": 0.5511589050292969, |
| "mean_token_accuracy": 0.7775879800319672, |
| "num_tokens": 2175102.0, |
| "step": 133 |
| }, |
| { |
| "entropy": 0.5529372990131378, |
| "epoch": 0.5, |
| "grad_norm": 0.13277417421340942, |
| "learning_rate": 0.0002, |
| "loss": 0.5545541048049927, |
| "mean_token_accuracy": 0.7761681526899338, |
| "num_tokens": 2191435.0, |
| "step": 134 |
| }, |
| { |
| "entropy": 0.5319318771362305, |
| "epoch": 0.503731343283582, |
| "grad_norm": 0.11856169253587723, |
| "learning_rate": 0.0002, |
| "loss": 0.536462128162384, |
| "mean_token_accuracy": 0.7816974222660065, |
| "num_tokens": 2207643.0, |
| "step": 135 |
| }, |
| { |
| "entropy": 0.5471926778554916, |
| "epoch": 0.5074626865671642, |
| "grad_norm": 0.1309870183467865, |
| "learning_rate": 0.0002, |
| "loss": 0.5440844297409058, |
| "mean_token_accuracy": 0.7771536409854889, |
| "num_tokens": 2223878.0, |
| "step": 136 |
| }, |
| { |
| "entropy": 0.541624128818512, |
| "epoch": 0.5111940298507462, |
| "grad_norm": 0.12067677825689316, |
| "learning_rate": 0.0002, |
| "loss": 0.5402209758758545, |
| "mean_token_accuracy": 0.781082957983017, |
| "num_tokens": 2240317.0, |
| "step": 137 |
| }, |
| { |
| "entropy": 0.5479262322187424, |
| "epoch": 0.5149253731343284, |
| "grad_norm": 0.13173235952854156, |
| "learning_rate": 0.0002, |
| "loss": 0.5611056685447693, |
| "mean_token_accuracy": 0.7731286883354187, |
| "num_tokens": 2256845.0, |
| "step": 138 |
| }, |
| { |
| "entropy": 0.523705467581749, |
| "epoch": 0.5186567164179104, |
| "grad_norm": 0.13409246504306793, |
| "learning_rate": 0.0002, |
| "loss": 0.5309388041496277, |
| "mean_token_accuracy": 0.7845514416694641, |
| "num_tokens": 2273023.0, |
| "step": 139 |
| }, |
| { |
| "entropy": 0.5475854426622391, |
| "epoch": 0.5223880597014925, |
| "grad_norm": 0.12833888828754425, |
| "learning_rate": 0.0002, |
| "loss": 0.5475225448608398, |
| "mean_token_accuracy": 0.7781049013137817, |
| "num_tokens": 2289099.0, |
| "step": 140 |
| }, |
| { |
| "entropy": 0.5594592392444611, |
| "epoch": 0.5261194029850746, |
| "grad_norm": 0.15159712731838226, |
| "learning_rate": 0.0002, |
| "loss": 0.5624300837516785, |
| "mean_token_accuracy": 0.773489311337471, |
| "num_tokens": 2305531.0, |
| "step": 141 |
| }, |
| { |
| "entropy": 0.5404133200645447, |
| "epoch": 0.5298507462686567, |
| "grad_norm": 0.1435905247926712, |
| "learning_rate": 0.0002, |
| "loss": 0.545477569103241, |
| "mean_token_accuracy": 0.7806483060121536, |
| "num_tokens": 2321594.0, |
| "step": 142 |
| }, |
| { |
| "entropy": 0.539509728550911, |
| "epoch": 0.5335820895522388, |
| "grad_norm": 0.1423826515674591, |
| "learning_rate": 0.0002, |
| "loss": 0.5402405261993408, |
| "mean_token_accuracy": 0.7804411351680756, |
| "num_tokens": 2337786.0, |
| "step": 143 |
| }, |
| { |
| "entropy": 0.5538707077503204, |
| "epoch": 0.5373134328358209, |
| "grad_norm": 0.1418147087097168, |
| "learning_rate": 0.0002, |
| "loss": 0.5509767532348633, |
| "mean_token_accuracy": 0.7774711847305298, |
| "num_tokens": 2354213.0, |
| "step": 144 |
| }, |
| { |
| "entropy": 0.5350814312696457, |
| "epoch": 0.5410447761194029, |
| "grad_norm": 0.12177110463380814, |
| "learning_rate": 0.0002, |
| "loss": 0.5284251570701599, |
| "mean_token_accuracy": 0.7876058667898178, |
| "num_tokens": 2370593.0, |
| "step": 145 |
| }, |
| { |
| "entropy": 0.5710433572530746, |
| "epoch": 0.5447761194029851, |
| "grad_norm": 0.12272237241268158, |
| "learning_rate": 0.0002, |
| "loss": 0.5655312538146973, |
| "mean_token_accuracy": 0.7685508877038956, |
| "num_tokens": 2387165.0, |
| "step": 146 |
| }, |
| { |
| "entropy": 0.5458782464265823, |
| "epoch": 0.5485074626865671, |
| "grad_norm": 0.13536348938941956, |
| "learning_rate": 0.0002, |
| "loss": 0.5476084351539612, |
| "mean_token_accuracy": 0.7789230942726135, |
| "num_tokens": 2403521.0, |
| "step": 147 |
| }, |
| { |
| "entropy": 0.5447355061769485, |
| "epoch": 0.5522388059701493, |
| "grad_norm": 0.12205858528614044, |
| "learning_rate": 0.0002, |
| "loss": 0.5553078651428223, |
| "mean_token_accuracy": 0.7710840106010437, |
| "num_tokens": 2420233.0, |
| "step": 148 |
| }, |
| { |
| "entropy": 0.548275426030159, |
| "epoch": 0.5559701492537313, |
| "grad_norm": 0.14460232853889465, |
| "learning_rate": 0.0002, |
| "loss": 0.5450581908226013, |
| "mean_token_accuracy": 0.7800416350364685, |
| "num_tokens": 2436434.0, |
| "step": 149 |
| }, |
| { |
| "entropy": 0.5386362373828888, |
| "epoch": 0.5597014925373134, |
| "grad_norm": 0.1384345442056656, |
| "learning_rate": 0.0002, |
| "loss": 0.5451717376708984, |
| "mean_token_accuracy": 0.7785218209028244, |
| "num_tokens": 2452618.0, |
| "step": 150 |
| }, |
| { |
| "entropy": 0.5483503490686417, |
| "epoch": 0.5634328358208955, |
| "grad_norm": 0.1613372266292572, |
| "learning_rate": 0.0002, |
| "loss": 0.5606507658958435, |
| "mean_token_accuracy": 0.7739191055297852, |
| "num_tokens": 2468988.0, |
| "step": 151 |
| }, |
| { |
| "entropy": 0.5419003367424011, |
| "epoch": 0.5671641791044776, |
| "grad_norm": 0.13155998289585114, |
| "learning_rate": 0.0002, |
| "loss": 0.5469087362289429, |
| "mean_token_accuracy": 0.7772263735532761, |
| "num_tokens": 2485167.0, |
| "step": 152 |
| }, |
| { |
| "entropy": 0.5591682493686676, |
| "epoch": 0.5708955223880597, |
| "grad_norm": 0.1569778174161911, |
| "learning_rate": 0.0002, |
| "loss": 0.5541848540306091, |
| "mean_token_accuracy": 0.7757261842489243, |
| "num_tokens": 2501671.0, |
| "step": 153 |
| }, |
| { |
| "entropy": 0.5500394701957703, |
| "epoch": 0.5746268656716418, |
| "grad_norm": 0.12647314369678497, |
| "learning_rate": 0.0002, |
| "loss": 0.5490140318870544, |
| "mean_token_accuracy": 0.7743174433708191, |
| "num_tokens": 2518113.0, |
| "step": 154 |
| }, |
| { |
| "entropy": 0.5377467721700668, |
| "epoch": 0.5783582089552238, |
| "grad_norm": 0.1387450248003006, |
| "learning_rate": 0.0002, |
| "loss": 0.5413840413093567, |
| "mean_token_accuracy": 0.7787664234638214, |
| "num_tokens": 2534429.0, |
| "step": 155 |
| }, |
| { |
| "entropy": 0.5345519632101059, |
| "epoch": 0.582089552238806, |
| "grad_norm": 0.13808852434158325, |
| "learning_rate": 0.0002, |
| "loss": 0.5346741080284119, |
| "mean_token_accuracy": 0.7841156870126724, |
| "num_tokens": 2550605.0, |
| "step": 156 |
| }, |
| { |
| "entropy": 0.5536827743053436, |
| "epoch": 0.585820895522388, |
| "grad_norm": 0.12298566102981567, |
| "learning_rate": 0.0002, |
| "loss": 0.5540347099304199, |
| "mean_token_accuracy": 0.7765155583620071, |
| "num_tokens": 2566789.0, |
| "step": 157 |
| }, |
| { |
| "entropy": 0.577739804983139, |
| "epoch": 0.5895522388059702, |
| "grad_norm": 0.14150071144104004, |
| "learning_rate": 0.0002, |
| "loss": 0.573868453502655, |
| "mean_token_accuracy": 0.7681884914636612, |
| "num_tokens": 2583423.0, |
| "step": 158 |
| }, |
| { |
| "entropy": 0.5503116697072983, |
| "epoch": 0.5932835820895522, |
| "grad_norm": 0.14658614993095398, |
| "learning_rate": 0.0002, |
| "loss": 0.5575414896011353, |
| "mean_token_accuracy": 0.7734437137842178, |
| "num_tokens": 2599927.0, |
| "step": 159 |
| }, |
| { |
| "entropy": 0.5317959934473038, |
| "epoch": 0.5970149253731343, |
| "grad_norm": 0.12970751523971558, |
| "learning_rate": 0.0002, |
| "loss": 0.5374177098274231, |
| "mean_token_accuracy": 0.7817978262901306, |
| "num_tokens": 2616097.0, |
| "step": 160 |
| }, |
| { |
| "entropy": 0.546217069029808, |
| "epoch": 0.6007462686567164, |
| "grad_norm": 0.11546632647514343, |
| "learning_rate": 0.0002, |
| "loss": 0.543847918510437, |
| "mean_token_accuracy": 0.779498353600502, |
| "num_tokens": 2632552.0, |
| "step": 161 |
| }, |
| { |
| "entropy": 0.5548344850540161, |
| "epoch": 0.6044776119402985, |
| "grad_norm": 0.12414934486150742, |
| "learning_rate": 0.0002, |
| "loss": 0.5520914793014526, |
| "mean_token_accuracy": 0.7777125388383865, |
| "num_tokens": 2648869.0, |
| "step": 162 |
| }, |
| { |
| "entropy": 0.5547935217618942, |
| "epoch": 0.6082089552238806, |
| "grad_norm": 0.13000915944576263, |
| "learning_rate": 0.0002, |
| "loss": 0.551349401473999, |
| "mean_token_accuracy": 0.7783058136701584, |
| "num_tokens": 2665440.0, |
| "step": 163 |
| }, |
| { |
| "entropy": 0.5620521903038025, |
| "epoch": 0.6119402985074627, |
| "grad_norm": 0.13910441100597382, |
| "learning_rate": 0.0002, |
| "loss": 0.5739133358001709, |
| "mean_token_accuracy": 0.7670122534036636, |
| "num_tokens": 2681690.0, |
| "step": 164 |
| }, |
| { |
| "entropy": 0.5512259006500244, |
| "epoch": 0.6156716417910447, |
| "grad_norm": 0.13505348563194275, |
| "learning_rate": 0.0002, |
| "loss": 0.5533974170684814, |
| "mean_token_accuracy": 0.7787705659866333, |
| "num_tokens": 2698140.0, |
| "step": 165 |
| }, |
| { |
| "entropy": 0.5392219871282578, |
| "epoch": 0.6194029850746269, |
| "grad_norm": 0.11672961711883545, |
| "learning_rate": 0.0002, |
| "loss": 0.5463794469833374, |
| "mean_token_accuracy": 0.7788806110620499, |
| "num_tokens": 2714423.0, |
| "step": 166 |
| }, |
| { |
| "entropy": 0.5314094871282578, |
| "epoch": 0.6231343283582089, |
| "grad_norm": 0.12193512171506882, |
| "learning_rate": 0.0002, |
| "loss": 0.5372287631034851, |
| "mean_token_accuracy": 0.7841473966836929, |
| "num_tokens": 2730529.0, |
| "step": 167 |
| }, |
| { |
| "entropy": 0.5572375357151031, |
| "epoch": 0.6268656716417911, |
| "grad_norm": 0.11672478914260864, |
| "learning_rate": 0.0002, |
| "loss": 0.559344470500946, |
| "mean_token_accuracy": 0.773651733994484, |
| "num_tokens": 2746881.0, |
| "step": 168 |
| }, |
| { |
| "entropy": 0.5501056462526321, |
| "epoch": 0.6305970149253731, |
| "grad_norm": 0.12261555343866348, |
| "learning_rate": 0.0002, |
| "loss": 0.5473341345787048, |
| "mean_token_accuracy": 0.779707744717598, |
| "num_tokens": 2763164.0, |
| "step": 169 |
| }, |
| { |
| "entropy": 0.5318388938903809, |
| "epoch": 0.6343283582089553, |
| "grad_norm": 0.13955217599868774, |
| "learning_rate": 0.0002, |
| "loss": 0.5321835279464722, |
| "mean_token_accuracy": 0.7833937853574753, |
| "num_tokens": 2779479.0, |
| "step": 170 |
| }, |
| { |
| "entropy": 0.5511606186628342, |
| "epoch": 0.6380597014925373, |
| "grad_norm": 0.12771864235401154, |
| "learning_rate": 0.0002, |
| "loss": 0.5502902269363403, |
| "mean_token_accuracy": 0.7762105464935303, |
| "num_tokens": 2796021.0, |
| "step": 171 |
| }, |
| { |
| "entropy": 0.5423205345869064, |
| "epoch": 0.6417910447761194, |
| "grad_norm": 0.18375541269779205, |
| "learning_rate": 0.0002, |
| "loss": 0.5487872958183289, |
| "mean_token_accuracy": 0.7805365175008774, |
| "num_tokens": 2812472.0, |
| "step": 172 |
| }, |
| { |
| "entropy": 0.5469668656587601, |
| "epoch": 0.6455223880597015, |
| "grad_norm": 0.11199312657117844, |
| "learning_rate": 0.0002, |
| "loss": 0.5421779751777649, |
| "mean_token_accuracy": 0.781487375497818, |
| "num_tokens": 2829056.0, |
| "step": 173 |
| }, |
| { |
| "entropy": 0.5569621622562408, |
| "epoch": 0.6492537313432836, |
| "grad_norm": 0.12339774519205093, |
| "learning_rate": 0.0002, |
| "loss": 0.5471019744873047, |
| "mean_token_accuracy": 0.7775540947914124, |
| "num_tokens": 2845445.0, |
| "step": 174 |
| }, |
| { |
| "entropy": 0.5595368593931198, |
| "epoch": 0.6529850746268657, |
| "grad_norm": 0.1223224550485611, |
| "learning_rate": 0.0002, |
| "loss": 0.5516889095306396, |
| "mean_token_accuracy": 0.7772944271564484, |
| "num_tokens": 2861874.0, |
| "step": 175 |
| }, |
| { |
| "entropy": 0.5564417690038681, |
| "epoch": 0.6567164179104478, |
| "grad_norm": 0.12084439396858215, |
| "learning_rate": 0.0002, |
| "loss": 0.5609424710273743, |
| "mean_token_accuracy": 0.7732392102479935, |
| "num_tokens": 2878149.0, |
| "step": 176 |
| }, |
| { |
| "entropy": 0.5459808111190796, |
| "epoch": 0.6604477611940298, |
| "grad_norm": 0.1534433364868164, |
| "learning_rate": 0.0002, |
| "loss": 0.5631917715072632, |
| "mean_token_accuracy": 0.7739778012037277, |
| "num_tokens": 2894620.0, |
| "step": 177 |
| }, |
| { |
| "entropy": 0.5444875359535217, |
| "epoch": 0.664179104477612, |
| "grad_norm": 0.13410453498363495, |
| "learning_rate": 0.0002, |
| "loss": 0.5541073083877563, |
| "mean_token_accuracy": 0.7758855521678925, |
| "num_tokens": 2910969.0, |
| "step": 178 |
| }, |
| { |
| "entropy": 0.5505465567111969, |
| "epoch": 0.667910447761194, |
| "grad_norm": 0.12259754538536072, |
| "learning_rate": 0.0002, |
| "loss": 0.5456393361091614, |
| "mean_token_accuracy": 0.7777644842863083, |
| "num_tokens": 2927324.0, |
| "step": 179 |
| }, |
| { |
| "entropy": 0.5646703690290451, |
| "epoch": 0.6716417910447762, |
| "grad_norm": 0.12087544053792953, |
| "learning_rate": 0.0002, |
| "loss": 0.5554431676864624, |
| "mean_token_accuracy": 0.7750003635883331, |
| "num_tokens": 2943501.0, |
| "step": 180 |
| }, |
| { |
| "entropy": 0.5640924125909805, |
| "epoch": 0.6753731343283582, |
| "grad_norm": 0.1259244829416275, |
| "learning_rate": 0.0002, |
| "loss": 0.5662774443626404, |
| "mean_token_accuracy": 0.7718631774187088, |
| "num_tokens": 2959947.0, |
| "step": 181 |
| }, |
| { |
| "entropy": 0.5437904596328735, |
| "epoch": 0.6791044776119403, |
| "grad_norm": 0.11557884514331818, |
| "learning_rate": 0.0002, |
| "loss": 0.5454355478286743, |
| "mean_token_accuracy": 0.7810252904891968, |
| "num_tokens": 2976494.0, |
| "step": 182 |
| }, |
| { |
| "entropy": 0.5446734130382538, |
| "epoch": 0.6828358208955224, |
| "grad_norm": 0.1413925290107727, |
| "learning_rate": 0.0002, |
| "loss": 0.5507742166519165, |
| "mean_token_accuracy": 0.7776683568954468, |
| "num_tokens": 2992697.0, |
| "step": 183 |
| }, |
| { |
| "entropy": 0.539382815361023, |
| "epoch": 0.6865671641791045, |
| "grad_norm": 0.11271845549345016, |
| "learning_rate": 0.0002, |
| "loss": 0.5379137396812439, |
| "mean_token_accuracy": 0.7833002358675003, |
| "num_tokens": 3008951.0, |
| "step": 184 |
| }, |
| { |
| "entropy": 0.5536984205245972, |
| "epoch": 0.6902985074626866, |
| "grad_norm": 0.1399201899766922, |
| "learning_rate": 0.0002, |
| "loss": 0.5506386160850525, |
| "mean_token_accuracy": 0.7762731313705444, |
| "num_tokens": 3025159.0, |
| "step": 185 |
| }, |
| { |
| "entropy": 0.55257548391819, |
| "epoch": 0.6940298507462687, |
| "grad_norm": 0.12090768665075302, |
| "learning_rate": 0.0002, |
| "loss": 0.5477935075759888, |
| "mean_token_accuracy": 0.7796179801225662, |
| "num_tokens": 3041706.0, |
| "step": 186 |
| }, |
| { |
| "entropy": 0.537647157907486, |
| "epoch": 0.6977611940298507, |
| "grad_norm": 0.1375986784696579, |
| "learning_rate": 0.0002, |
| "loss": 0.5442407131195068, |
| "mean_token_accuracy": 0.7777736335992813, |
| "num_tokens": 3058097.0, |
| "step": 187 |
| }, |
| { |
| "entropy": 0.5462846904993057, |
| "epoch": 0.7014925373134329, |
| "grad_norm": 0.1281321495771408, |
| "learning_rate": 0.0002, |
| "loss": 0.5496324896812439, |
| "mean_token_accuracy": 0.7783989757299423, |
| "num_tokens": 3074344.0, |
| "step": 188 |
| }, |
| { |
| "entropy": 0.5602088421583176, |
| "epoch": 0.7052238805970149, |
| "grad_norm": 0.1293424814939499, |
| "learning_rate": 0.0002, |
| "loss": 0.5645491480827332, |
| "mean_token_accuracy": 0.7716221660375595, |
| "num_tokens": 3090993.0, |
| "step": 189 |
| }, |
| { |
| "entropy": 0.564358189702034, |
| "epoch": 0.7089552238805971, |
| "grad_norm": 0.11787773668766022, |
| "learning_rate": 0.0002, |
| "loss": 0.5615185499191284, |
| "mean_token_accuracy": 0.7737833112478256, |
| "num_tokens": 3107467.0, |
| "step": 190 |
| }, |
| { |
| "entropy": 0.5645042210817337, |
| "epoch": 0.7126865671641791, |
| "grad_norm": 0.13978245854377747, |
| "learning_rate": 0.0002, |
| "loss": 0.5676586627960205, |
| "mean_token_accuracy": 0.7713933438062668, |
| "num_tokens": 3123717.0, |
| "step": 191 |
| }, |
| { |
| "entropy": 0.552118331193924, |
| "epoch": 0.7164179104477612, |
| "grad_norm": 0.1480918973684311, |
| "learning_rate": 0.0002, |
| "loss": 0.5516392588615417, |
| "mean_token_accuracy": 0.7758712768554688, |
| "num_tokens": 3140195.0, |
| "step": 192 |
| }, |
| { |
| "entropy": 0.5298159420490265, |
| "epoch": 0.7201492537313433, |
| "grad_norm": 0.1216685101389885, |
| "learning_rate": 0.0002, |
| "loss": 0.5351110696792603, |
| "mean_token_accuracy": 0.7831089496612549, |
| "num_tokens": 3156383.0, |
| "step": 193 |
| }, |
| { |
| "entropy": 0.5307169109582901, |
| "epoch": 0.7238805970149254, |
| "grad_norm": 0.1356184482574463, |
| "learning_rate": 0.0002, |
| "loss": 0.5372255444526672, |
| "mean_token_accuracy": 0.7801680862903595, |
| "num_tokens": 3172647.0, |
| "step": 194 |
| }, |
| { |
| "entropy": 0.5488355308771133, |
| "epoch": 0.7276119402985075, |
| "grad_norm": 0.14287717640399933, |
| "learning_rate": 0.0002, |
| "loss": 0.5596861839294434, |
| "mean_token_accuracy": 0.7719696015119553, |
| "num_tokens": 3188955.0, |
| "step": 195 |
| }, |
| { |
| "entropy": 0.5424549728631973, |
| "epoch": 0.7313432835820896, |
| "grad_norm": 0.1282239407300949, |
| "learning_rate": 0.0002, |
| "loss": 0.5411726832389832, |
| "mean_token_accuracy": 0.7814428955316544, |
| "num_tokens": 3205176.0, |
| "step": 196 |
| }, |
| { |
| "entropy": 0.5679114013910294, |
| "epoch": 0.7350746268656716, |
| "grad_norm": 0.16656865179538727, |
| "learning_rate": 0.0002, |
| "loss": 0.5606438517570496, |
| "mean_token_accuracy": 0.7725225985050201, |
| "num_tokens": 3221268.0, |
| "step": 197 |
| }, |
| { |
| "entropy": 0.5471612960100174, |
| "epoch": 0.7388059701492538, |
| "grad_norm": 0.1200842633843422, |
| "learning_rate": 0.0002, |
| "loss": 0.5425546169281006, |
| "mean_token_accuracy": 0.7768001556396484, |
| "num_tokens": 3237597.0, |
| "step": 198 |
| }, |
| { |
| "entropy": 0.5599212646484375, |
| "epoch": 0.7425373134328358, |
| "grad_norm": 0.1369842141866684, |
| "learning_rate": 0.0002, |
| "loss": 0.5659201741218567, |
| "mean_token_accuracy": 0.7680574655532837, |
| "num_tokens": 3254052.0, |
| "step": 199 |
| }, |
| { |
| "entropy": 0.5361340939998627, |
| "epoch": 0.746268656716418, |
| "grad_norm": 0.155270054936409, |
| "learning_rate": 0.0002, |
| "loss": 0.5480148196220398, |
| "mean_token_accuracy": 0.7778600752353668, |
| "num_tokens": 3270107.0, |
| "step": 200 |
| }, |
| { |
| "entropy": 0.5407303869724274, |
| "epoch": 0.75, |
| "grad_norm": 0.11775724589824677, |
| "learning_rate": 0.0002, |
| "loss": 0.5463446974754333, |
| "mean_token_accuracy": 0.7780316770076752, |
| "num_tokens": 3286336.0, |
| "step": 201 |
| }, |
| { |
| "entropy": 0.5683784335851669, |
| "epoch": 0.753731343283582, |
| "grad_norm": 0.13120947778224945, |
| "learning_rate": 0.0002, |
| "loss": 0.5636997222900391, |
| "mean_token_accuracy": 0.7720665782690048, |
| "num_tokens": 3302752.0, |
| "step": 202 |
| }, |
| { |
| "entropy": 0.5629799664020538, |
| "epoch": 0.7574626865671642, |
| "grad_norm": 0.11005634069442749, |
| "learning_rate": 0.0002, |
| "loss": 0.5560387969017029, |
| "mean_token_accuracy": 0.774502158164978, |
| "num_tokens": 3319195.0, |
| "step": 203 |
| }, |
| { |
| "entropy": 0.5276861786842346, |
| "epoch": 0.7611940298507462, |
| "grad_norm": 0.11525508016347885, |
| "learning_rate": 0.0002, |
| "loss": 0.5282235145568848, |
| "mean_token_accuracy": 0.7834585458040237, |
| "num_tokens": 3335515.0, |
| "step": 204 |
| }, |
| { |
| "entropy": 0.5502845495939255, |
| "epoch": 0.7649253731343284, |
| "grad_norm": 0.16224226355552673, |
| "learning_rate": 0.0002, |
| "loss": 0.5616753101348877, |
| "mean_token_accuracy": 0.7725106775760651, |
| "num_tokens": 3352133.0, |
| "step": 205 |
| }, |
| { |
| "entropy": 0.5353530049324036, |
| "epoch": 0.7686567164179104, |
| "grad_norm": 0.10722214728593826, |
| "learning_rate": 0.0002, |
| "loss": 0.5364400148391724, |
| "mean_token_accuracy": 0.7824194133281708, |
| "num_tokens": 3368339.0, |
| "step": 206 |
| }, |
| { |
| "entropy": 0.5563006103038788, |
| "epoch": 0.7723880597014925, |
| "grad_norm": 0.10849201679229736, |
| "learning_rate": 0.0002, |
| "loss": 0.5509206056594849, |
| "mean_token_accuracy": 0.7798264473676682, |
| "num_tokens": 3385107.0, |
| "step": 207 |
| }, |
| { |
| "entropy": 0.5372148305177689, |
| "epoch": 0.7761194029850746, |
| "grad_norm": 0.1064474806189537, |
| "learning_rate": 0.0002, |
| "loss": 0.5339787602424622, |
| "mean_token_accuracy": 0.7819695770740509, |
| "num_tokens": 3401375.0, |
| "step": 208 |
| }, |
| { |
| "entropy": 0.5600335597991943, |
| "epoch": 0.7798507462686567, |
| "grad_norm": 0.14489714801311493, |
| "learning_rate": 0.0002, |
| "loss": 0.557947039604187, |
| "mean_token_accuracy": 0.7752352505922318, |
| "num_tokens": 3417716.0, |
| "step": 209 |
| }, |
| { |
| "entropy": 0.5391388982534409, |
| "epoch": 0.7835820895522388, |
| "grad_norm": 0.11322993040084839, |
| "learning_rate": 0.0002, |
| "loss": 0.542580783367157, |
| "mean_token_accuracy": 0.7812723368406296, |
| "num_tokens": 3434079.0, |
| "step": 210 |
| }, |
| { |
| "entropy": 0.5447981357574463, |
| "epoch": 0.7873134328358209, |
| "grad_norm": 0.1646254062652588, |
| "learning_rate": 0.0002, |
| "loss": 0.5561512112617493, |
| "mean_token_accuracy": 0.7761420905590057, |
| "num_tokens": 3450406.0, |
| "step": 211 |
| }, |
| { |
| "entropy": 0.5546468645334244, |
| "epoch": 0.7910447761194029, |
| "grad_norm": 0.15984156727790833, |
| "learning_rate": 0.0002, |
| "loss": 0.5689921379089355, |
| "mean_token_accuracy": 0.77018703520298, |
| "num_tokens": 3466969.0, |
| "step": 212 |
| }, |
| { |
| "entropy": 0.551989957690239, |
| "epoch": 0.7947761194029851, |
| "grad_norm": 0.18132156133651733, |
| "learning_rate": 0.0002, |
| "loss": 0.5496206283569336, |
| "mean_token_accuracy": 0.7776729613542557, |
| "num_tokens": 3483581.0, |
| "step": 213 |
| }, |
| { |
| "entropy": 0.5667679309844971, |
| "epoch": 0.7985074626865671, |
| "grad_norm": 0.1400090903043747, |
| "learning_rate": 0.0002, |
| "loss": 0.556699275970459, |
| "mean_token_accuracy": 0.7745833098888397, |
| "num_tokens": 3499917.0, |
| "step": 214 |
| }, |
| { |
| "entropy": 0.5755820423364639, |
| "epoch": 0.8022388059701493, |
| "grad_norm": 0.16247980296611786, |
| "learning_rate": 0.0002, |
| "loss": 0.566421627998352, |
| "mean_token_accuracy": 0.7716336101293564, |
| "num_tokens": 3516249.0, |
| "step": 215 |
| }, |
| { |
| "entropy": 0.5313844755291939, |
| "epoch": 0.8059701492537313, |
| "grad_norm": 0.1498187929391861, |
| "learning_rate": 0.0002, |
| "loss": 0.5304653644561768, |
| "mean_token_accuracy": 0.7861770987510681, |
| "num_tokens": 3532751.0, |
| "step": 216 |
| }, |
| { |
| "entropy": 0.5405164808034897, |
| "epoch": 0.8097014925373134, |
| "grad_norm": 0.12809698283672333, |
| "learning_rate": 0.0002, |
| "loss": 0.5482773780822754, |
| "mean_token_accuracy": 0.7805600017309189, |
| "num_tokens": 3548864.0, |
| "step": 217 |
| }, |
| { |
| "entropy": 0.5404932796955109, |
| "epoch": 0.8134328358208955, |
| "grad_norm": 0.17795848846435547, |
| "learning_rate": 0.0002, |
| "loss": 0.5554847717285156, |
| "mean_token_accuracy": 0.773003101348877, |
| "num_tokens": 3565510.0, |
| "step": 218 |
| }, |
| { |
| "entropy": 0.5378199517726898, |
| "epoch": 0.8171641791044776, |
| "grad_norm": 0.1491861194372177, |
| "learning_rate": 0.0002, |
| "loss": 0.5462876558303833, |
| "mean_token_accuracy": 0.7820324152708054, |
| "num_tokens": 3581905.0, |
| "step": 219 |
| }, |
| { |
| "entropy": 0.5617736428976059, |
| "epoch": 0.8208955223880597, |
| "grad_norm": 0.1128775104880333, |
| "learning_rate": 0.0002, |
| "loss": 0.5518558621406555, |
| "mean_token_accuracy": 0.7750371694564819, |
| "num_tokens": 3598465.0, |
| "step": 220 |
| }, |
| { |
| "entropy": 0.5712319910526276, |
| "epoch": 0.8246268656716418, |
| "grad_norm": 0.17724420130252838, |
| "learning_rate": 0.0002, |
| "loss": 0.5522560477256775, |
| "mean_token_accuracy": 0.777231901884079, |
| "num_tokens": 3615143.0, |
| "step": 221 |
| }, |
| { |
| "entropy": 0.5571258962154388, |
| "epoch": 0.8283582089552238, |
| "grad_norm": 0.13079975545406342, |
| "learning_rate": 0.0002, |
| "loss": 0.5471462607383728, |
| "mean_token_accuracy": 0.7803215682506561, |
| "num_tokens": 3631537.0, |
| "step": 222 |
| }, |
| { |
| "entropy": 0.5514252334833145, |
| "epoch": 0.832089552238806, |
| "grad_norm": 0.11742964386940002, |
| "learning_rate": 0.0002, |
| "loss": 0.5558452606201172, |
| "mean_token_accuracy": 0.7774627059698105, |
| "num_tokens": 3648189.0, |
| "step": 223 |
| }, |
| { |
| "entropy": 0.5301423668861389, |
| "epoch": 0.835820895522388, |
| "grad_norm": 0.19299449026584625, |
| "learning_rate": 0.0002, |
| "loss": 0.5539587140083313, |
| "mean_token_accuracy": 0.7765046209096909, |
| "num_tokens": 3664675.0, |
| "step": 224 |
| }, |
| { |
| "entropy": 0.5480137765407562, |
| "epoch": 0.8395522388059702, |
| "grad_norm": 0.1241627112030983, |
| "learning_rate": 0.0002, |
| "loss": 0.560308039188385, |
| "mean_token_accuracy": 0.7730884552001953, |
| "num_tokens": 3681234.0, |
| "step": 225 |
| }, |
| { |
| "entropy": 0.5727380067110062, |
| "epoch": 0.8432835820895522, |
| "grad_norm": 0.13619816303253174, |
| "learning_rate": 0.0002, |
| "loss": 0.5722546577453613, |
| "mean_token_accuracy": 0.7690231055021286, |
| "num_tokens": 3697702.0, |
| "step": 226 |
| }, |
| { |
| "entropy": 0.5443355441093445, |
| "epoch": 0.8470149253731343, |
| "grad_norm": 0.12818409502506256, |
| "learning_rate": 0.0002, |
| "loss": 0.5364972352981567, |
| "mean_token_accuracy": 0.7826599627733231, |
| "num_tokens": 3714023.0, |
| "step": 227 |
| }, |
| { |
| "entropy": 0.5638679265975952, |
| "epoch": 0.8507462686567164, |
| "grad_norm": 0.12638136744499207, |
| "learning_rate": 0.0002, |
| "loss": 0.541628360748291, |
| "mean_token_accuracy": 0.7827154844999313, |
| "num_tokens": 3730782.0, |
| "step": 228 |
| }, |
| { |
| "entropy": 0.544154703617096, |
| "epoch": 0.8544776119402985, |
| "grad_norm": 0.13112476468086243, |
| "learning_rate": 0.0002, |
| "loss": 0.536247193813324, |
| "mean_token_accuracy": 0.7804847210645676, |
| "num_tokens": 3746769.0, |
| "step": 229 |
| }, |
| { |
| "entropy": 0.5337965190410614, |
| "epoch": 0.8582089552238806, |
| "grad_norm": 0.1358417123556137, |
| "learning_rate": 0.0002, |
| "loss": 0.5434447526931763, |
| "mean_token_accuracy": 0.7823351621627808, |
| "num_tokens": 3762746.0, |
| "step": 230 |
| }, |
| { |
| "entropy": 0.5315578505396843, |
| "epoch": 0.8619402985074627, |
| "grad_norm": 0.14817467331886292, |
| "learning_rate": 0.0002, |
| "loss": 0.5455387234687805, |
| "mean_token_accuracy": 0.7773294299840927, |
| "num_tokens": 3779028.0, |
| "step": 231 |
| }, |
| { |
| "entropy": 0.5409719198942184, |
| "epoch": 0.8656716417910447, |
| "grad_norm": 0.16679254174232483, |
| "learning_rate": 0.0002, |
| "loss": 0.5536785125732422, |
| "mean_token_accuracy": 0.7771536558866501, |
| "num_tokens": 3795256.0, |
| "step": 232 |
| }, |
| { |
| "entropy": 0.5579944103956223, |
| "epoch": 0.8694029850746269, |
| "grad_norm": 0.12268655002117157, |
| "learning_rate": 0.0002, |
| "loss": 0.5481241345405579, |
| "mean_token_accuracy": 0.7788999974727631, |
| "num_tokens": 3811660.0, |
| "step": 233 |
| }, |
| { |
| "entropy": 0.5501740872859955, |
| "epoch": 0.8731343283582089, |
| "grad_norm": 0.13782234489917755, |
| "learning_rate": 0.0002, |
| "loss": 0.5376328229904175, |
| "mean_token_accuracy": 0.7825577855110168, |
| "num_tokens": 3828068.0, |
| "step": 234 |
| }, |
| { |
| "entropy": 0.548073410987854, |
| "epoch": 0.8768656716417911, |
| "grad_norm": 0.12561145424842834, |
| "learning_rate": 0.0002, |
| "loss": 0.5418543815612793, |
| "mean_token_accuracy": 0.7788865119218826, |
| "num_tokens": 3844507.0, |
| "step": 235 |
| }, |
| { |
| "entropy": 0.5608464628458023, |
| "epoch": 0.8805970149253731, |
| "grad_norm": 0.1355101317167282, |
| "learning_rate": 0.0002, |
| "loss": 0.5593248605728149, |
| "mean_token_accuracy": 0.7745541632175446, |
| "num_tokens": 3860678.0, |
| "step": 236 |
| }, |
| { |
| "entropy": 0.5360798388719559, |
| "epoch": 0.8843283582089553, |
| "grad_norm": 0.142546147108078, |
| "learning_rate": 0.0002, |
| "loss": 0.5447651743888855, |
| "mean_token_accuracy": 0.780293807387352, |
| "num_tokens": 3876972.0, |
| "step": 237 |
| }, |
| { |
| "entropy": 0.5576356202363968, |
| "epoch": 0.8880597014925373, |
| "grad_norm": 0.12002276629209518, |
| "learning_rate": 0.0002, |
| "loss": 0.5670543909072876, |
| "mean_token_accuracy": 0.77015221118927, |
| "num_tokens": 3893064.0, |
| "step": 238 |
| }, |
| { |
| "entropy": 0.5523956120014191, |
| "epoch": 0.8917910447761194, |
| "grad_norm": 0.13991399109363556, |
| "learning_rate": 0.0002, |
| "loss": 0.5598673820495605, |
| "mean_token_accuracy": 0.772214338183403, |
| "num_tokens": 3909613.0, |
| "step": 239 |
| }, |
| { |
| "entropy": 0.535386249423027, |
| "epoch": 0.8955223880597015, |
| "grad_norm": 0.11688131093978882, |
| "learning_rate": 0.0002, |
| "loss": 0.5338555574417114, |
| "mean_token_accuracy": 0.785940408706665, |
| "num_tokens": 3926029.0, |
| "step": 240 |
| }, |
| { |
| "entropy": 0.5517598241567612, |
| "epoch": 0.8992537313432836, |
| "grad_norm": 0.11504597216844559, |
| "learning_rate": 0.0002, |
| "loss": 0.5484194159507751, |
| "mean_token_accuracy": 0.7777102142572403, |
| "num_tokens": 3942449.0, |
| "step": 241 |
| }, |
| { |
| "entropy": 0.5596148073673248, |
| "epoch": 0.9029850746268657, |
| "grad_norm": 0.12677527964115143, |
| "learning_rate": 0.0002, |
| "loss": 0.5552861094474792, |
| "mean_token_accuracy": 0.7738935798406601, |
| "num_tokens": 3958753.0, |
| "step": 242 |
| }, |
| { |
| "entropy": 0.5394274592399597, |
| "epoch": 0.9067164179104478, |
| "grad_norm": 0.11295556277036667, |
| "learning_rate": 0.0002, |
| "loss": 0.5421245098114014, |
| "mean_token_accuracy": 0.7797911465167999, |
| "num_tokens": 3975112.0, |
| "step": 243 |
| }, |
| { |
| "entropy": 0.5412910431623459, |
| "epoch": 0.9104477611940298, |
| "grad_norm": 0.11529767513275146, |
| "learning_rate": 0.0002, |
| "loss": 0.5420047044754028, |
| "mean_token_accuracy": 0.7779449224472046, |
| "num_tokens": 3991367.0, |
| "step": 244 |
| }, |
| { |
| "entropy": 0.5418308526277542, |
| "epoch": 0.914179104477612, |
| "grad_norm": 0.1123286783695221, |
| "learning_rate": 0.0002, |
| "loss": 0.5436584949493408, |
| "mean_token_accuracy": 0.7798446863889694, |
| "num_tokens": 4007860.0, |
| "step": 245 |
| }, |
| { |
| "entropy": 0.5526231080293655, |
| "epoch": 0.917910447761194, |
| "grad_norm": 0.11229414492845535, |
| "learning_rate": 0.0002, |
| "loss": 0.5495740175247192, |
| "mean_token_accuracy": 0.7787007689476013, |
| "num_tokens": 4024105.0, |
| "step": 246 |
| }, |
| { |
| "entropy": 0.540853813290596, |
| "epoch": 0.9216417910447762, |
| "grad_norm": 0.132887601852417, |
| "learning_rate": 0.0002, |
| "loss": 0.5415008664131165, |
| "mean_token_accuracy": 0.7791140973567963, |
| "num_tokens": 4040534.0, |
| "step": 247 |
| }, |
| { |
| "entropy": 0.5326784551143646, |
| "epoch": 0.9253731343283582, |
| "grad_norm": 0.12400668859481812, |
| "learning_rate": 0.0002, |
| "loss": 0.5335761904716492, |
| "mean_token_accuracy": 0.7853088229894638, |
| "num_tokens": 4056527.0, |
| "step": 248 |
| }, |
| { |
| "entropy": 0.5596267133951187, |
| "epoch": 0.9291044776119403, |
| "grad_norm": 0.12875378131866455, |
| "learning_rate": 0.0002, |
| "loss": 0.5666757822036743, |
| "mean_token_accuracy": 0.7693292647600174, |
| "num_tokens": 4072911.0, |
| "step": 249 |
| }, |
| { |
| "entropy": 0.5215249359607697, |
| "epoch": 0.9328358208955224, |
| "grad_norm": 0.12209980189800262, |
| "learning_rate": 0.0002, |
| "loss": 0.5284324884414673, |
| "mean_token_accuracy": 0.7845395058393478, |
| "num_tokens": 4089163.0, |
| "step": 250 |
| }, |
| { |
| "entropy": 0.5523748248815536, |
| "epoch": 0.9365671641791045, |
| "grad_norm": 0.1122996062040329, |
| "learning_rate": 0.0002, |
| "loss": 0.550143837928772, |
| "mean_token_accuracy": 0.7775111645460129, |
| "num_tokens": 4105446.0, |
| "step": 251 |
| }, |
| { |
| "entropy": 0.5454890429973602, |
| "epoch": 0.9402985074626866, |
| "grad_norm": 0.12437989562749863, |
| "learning_rate": 0.0002, |
| "loss": 0.5460339784622192, |
| "mean_token_accuracy": 0.7767636179924011, |
| "num_tokens": 4121779.0, |
| "step": 252 |
| }, |
| { |
| "entropy": 0.5656173974275589, |
| "epoch": 0.9440298507462687, |
| "grad_norm": 0.1343945562839508, |
| "learning_rate": 0.0002, |
| "loss": 0.5615634322166443, |
| "mean_token_accuracy": 0.7717313021421432, |
| "num_tokens": 4138153.0, |
| "step": 253 |
| }, |
| { |
| "entropy": 0.5611940026283264, |
| "epoch": 0.9477611940298507, |
| "grad_norm": 0.12788742780685425, |
| "learning_rate": 0.0002, |
| "loss": 0.5537964701652527, |
| "mean_token_accuracy": 0.7758807390928268, |
| "num_tokens": 4154310.0, |
| "step": 254 |
| }, |
| { |
| "entropy": 0.5482861697673798, |
| "epoch": 0.9514925373134329, |
| "grad_norm": 0.12935073673725128, |
| "learning_rate": 0.0002, |
| "loss": 0.5483288168907166, |
| "mean_token_accuracy": 0.7791451960802078, |
| "num_tokens": 4170799.0, |
| "step": 255 |
| }, |
| { |
| "entropy": 0.5527377128601074, |
| "epoch": 0.9552238805970149, |
| "grad_norm": 0.11660388857126236, |
| "learning_rate": 0.0002, |
| "loss": 0.5535370707511902, |
| "mean_token_accuracy": 0.7748463898897171, |
| "num_tokens": 4187287.0, |
| "step": 256 |
| }, |
| { |
| "entropy": 0.5318783521652222, |
| "epoch": 0.9589552238805971, |
| "grad_norm": 0.1454961895942688, |
| "learning_rate": 0.0002, |
| "loss": 0.5430982112884521, |
| "mean_token_accuracy": 0.7797283381223679, |
| "num_tokens": 4203767.0, |
| "step": 257 |
| }, |
| { |
| "entropy": 0.5481456965208054, |
| "epoch": 0.9626865671641791, |
| "grad_norm": 0.15091487765312195, |
| "learning_rate": 0.0002, |
| "loss": 0.564013659954071, |
| "mean_token_accuracy": 0.773566260933876, |
| "num_tokens": 4219886.0, |
| "step": 258 |
| }, |
| { |
| "entropy": 0.5531263202428818, |
| "epoch": 0.9664179104477612, |
| "grad_norm": 0.10883932560682297, |
| "learning_rate": 0.0002, |
| "loss": 0.5547791719436646, |
| "mean_token_accuracy": 0.7741214781999588, |
| "num_tokens": 4236258.0, |
| "step": 259 |
| }, |
| { |
| "entropy": 0.5522076636552811, |
| "epoch": 0.9701492537313433, |
| "grad_norm": 0.1252211630344391, |
| "learning_rate": 0.0002, |
| "loss": 0.5378358960151672, |
| "mean_token_accuracy": 0.783813551068306, |
| "num_tokens": 4252596.0, |
| "step": 260 |
| }, |
| { |
| "entropy": 0.5805730819702148, |
| "epoch": 0.9738805970149254, |
| "grad_norm": 0.12375251203775406, |
| "learning_rate": 0.0002, |
| "loss": 0.5674760937690735, |
| "mean_token_accuracy": 0.7704650014638901, |
| "num_tokens": 4268928.0, |
| "step": 261 |
| }, |
| { |
| "entropy": 0.5665071904659271, |
| "epoch": 0.9776119402985075, |
| "grad_norm": 0.10372231155633926, |
| "learning_rate": 0.0002, |
| "loss": 0.559476912021637, |
| "mean_token_accuracy": 0.7720057666301727, |
| "num_tokens": 4285468.0, |
| "step": 262 |
| }, |
| { |
| "entropy": 0.5560015141963959, |
| "epoch": 0.9813432835820896, |
| "grad_norm": 0.12143128365278244, |
| "learning_rate": 0.0002, |
| "loss": 0.555933952331543, |
| "mean_token_accuracy": 0.7722462862730026, |
| "num_tokens": 4301940.0, |
| "step": 263 |
| }, |
| { |
| "entropy": 0.5471072793006897, |
| "epoch": 0.9850746268656716, |
| "grad_norm": 0.15810711681842804, |
| "learning_rate": 0.0002, |
| "loss": 0.5585564970970154, |
| "mean_token_accuracy": 0.7753822505474091, |
| "num_tokens": 4318195.0, |
| "step": 264 |
| }, |
| { |
| "entropy": 0.5270911604166031, |
| "epoch": 0.9888059701492538, |
| "grad_norm": 0.14716827869415283, |
| "learning_rate": 0.0002, |
| "loss": 0.5458887219429016, |
| "mean_token_accuracy": 0.7786976844072342, |
| "num_tokens": 4334329.0, |
| "step": 265 |
| }, |
| { |
| "entropy": 0.5411859452724457, |
| "epoch": 0.9925373134328358, |
| "grad_norm": 0.11300450563430786, |
| "learning_rate": 0.0002, |
| "loss": 0.5447648763656616, |
| "mean_token_accuracy": 0.7797644585371017, |
| "num_tokens": 4350572.0, |
| "step": 266 |
| }, |
| { |
| "entropy": 0.5404697358608246, |
| "epoch": 0.996268656716418, |
| "grad_norm": 0.11449640244245529, |
| "learning_rate": 0.0002, |
| "loss": 0.5386698246002197, |
| "mean_token_accuracy": 0.7809340059757233, |
| "num_tokens": 4366907.0, |
| "step": 267 |
| }, |
| { |
| "entropy": 0.53959159553051, |
| "epoch": 1.0, |
| "grad_norm": 0.10758668184280396, |
| "learning_rate": 0.0002, |
| "loss": 0.5358680486679077, |
| "mean_token_accuracy": 0.7795725017786026, |
| "num_tokens": 4382925.0, |
| "step": 268 |
| }, |
| { |
| "entropy": 0.5795807391405106, |
| "epoch": 1.0037313432835822, |
| "grad_norm": 0.1371837854385376, |
| "learning_rate": 0.0002, |
| "loss": 0.5600798726081848, |
| "mean_token_accuracy": 0.7725576758384705, |
| "num_tokens": 4399277.0, |
| "step": 269 |
| }, |
| { |
| "entropy": 0.533683717250824, |
| "epoch": 1.007462686567164, |
| "grad_norm": 0.12005309760570526, |
| "learning_rate": 0.0002, |
| "loss": 0.5225374698638916, |
| "mean_token_accuracy": 0.7902077585458755, |
| "num_tokens": 4415424.0, |
| "step": 270 |
| }, |
| { |
| "entropy": 0.5298184454441071, |
| "epoch": 1.0111940298507462, |
| "grad_norm": 0.1209864467382431, |
| "learning_rate": 0.0002, |
| "loss": 0.5334348082542419, |
| "mean_token_accuracy": 0.7835809886455536, |
| "num_tokens": 4431694.0, |
| "step": 271 |
| }, |
| { |
| "entropy": 0.5239971578121185, |
| "epoch": 1.0149253731343284, |
| "grad_norm": 0.1776454895734787, |
| "learning_rate": 0.0002, |
| "loss": 0.5432223677635193, |
| "mean_token_accuracy": 0.7807145714759827, |
| "num_tokens": 4448074.0, |
| "step": 272 |
| }, |
| { |
| "entropy": 0.5392177700996399, |
| "epoch": 1.0186567164179103, |
| "grad_norm": 0.15443317592144012, |
| "learning_rate": 0.0002, |
| "loss": 0.5447742342948914, |
| "mean_token_accuracy": 0.7797702848911285, |
| "num_tokens": 4464550.0, |
| "step": 273 |
| }, |
| { |
| "entropy": 0.5439985394477844, |
| "epoch": 1.0223880597014925, |
| "grad_norm": 0.11803331971168518, |
| "learning_rate": 0.0002, |
| "loss": 0.5395654439926147, |
| "mean_token_accuracy": 0.7830762416124344, |
| "num_tokens": 4480864.0, |
| "step": 274 |
| }, |
| { |
| "entropy": 0.5342804938554764, |
| "epoch": 1.0261194029850746, |
| "grad_norm": 0.1339092254638672, |
| "learning_rate": 0.0002, |
| "loss": 0.5320309996604919, |
| "mean_token_accuracy": 0.7823790609836578, |
| "num_tokens": 4497225.0, |
| "step": 275 |
| }, |
| { |
| "entropy": 0.5354204773902893, |
| "epoch": 1.0298507462686568, |
| "grad_norm": 0.1276242434978485, |
| "learning_rate": 0.0002, |
| "loss": 0.5391862392425537, |
| "mean_token_accuracy": 0.7798895090818405, |
| "num_tokens": 4513595.0, |
| "step": 276 |
| }, |
| { |
| "entropy": 0.5347974300384521, |
| "epoch": 1.0335820895522387, |
| "grad_norm": 0.1352418214082718, |
| "learning_rate": 0.0002, |
| "loss": 0.5331315994262695, |
| "mean_token_accuracy": 0.781826838850975, |
| "num_tokens": 4529760.0, |
| "step": 277 |
| }, |
| { |
| "entropy": 0.5466842651367188, |
| "epoch": 1.037313432835821, |
| "grad_norm": 0.1697050780057907, |
| "learning_rate": 0.0002, |
| "loss": 0.5440285205841064, |
| "mean_token_accuracy": 0.7792473882436752, |
| "num_tokens": 4546029.0, |
| "step": 278 |
| }, |
| { |
| "entropy": 0.5333380401134491, |
| "epoch": 1.041044776119403, |
| "grad_norm": 0.1413269191980362, |
| "learning_rate": 0.0002, |
| "loss": 0.5399320125579834, |
| "mean_token_accuracy": 0.7796883285045624, |
| "num_tokens": 4562279.0, |
| "step": 279 |
| }, |
| { |
| "entropy": 0.5452618151903152, |
| "epoch": 1.044776119402985, |
| "grad_norm": 0.1672191619873047, |
| "learning_rate": 0.0002, |
| "loss": 0.546228289604187, |
| "mean_token_accuracy": 0.784556120634079, |
| "num_tokens": 4578733.0, |
| "step": 280 |
| }, |
| { |
| "entropy": 0.5418536514043808, |
| "epoch": 1.0485074626865671, |
| "grad_norm": 0.13942968845367432, |
| "learning_rate": 0.0002, |
| "loss": 0.542955219745636, |
| "mean_token_accuracy": 0.778509721159935, |
| "num_tokens": 4595306.0, |
| "step": 281 |
| }, |
| { |
| "entropy": 0.5325378477573395, |
| "epoch": 1.0522388059701493, |
| "grad_norm": 0.12303755432367325, |
| "learning_rate": 0.0002, |
| "loss": 0.5271491408348083, |
| "mean_token_accuracy": 0.7890959829092026, |
| "num_tokens": 4611614.0, |
| "step": 282 |
| }, |
| { |
| "entropy": 0.5226758569478989, |
| "epoch": 1.0559701492537314, |
| "grad_norm": 0.15698690712451935, |
| "learning_rate": 0.0002, |
| "loss": 0.5240474939346313, |
| "mean_token_accuracy": 0.7859134376049042, |
| "num_tokens": 4628039.0, |
| "step": 283 |
| }, |
| { |
| "entropy": 0.5174808949232101, |
| "epoch": 1.0597014925373134, |
| "grad_norm": 0.14522448182106018, |
| "learning_rate": 0.0002, |
| "loss": 0.5214486122131348, |
| "mean_token_accuracy": 0.789116695523262, |
| "num_tokens": 4644188.0, |
| "step": 284 |
| }, |
| { |
| "entropy": 0.5484358072280884, |
| "epoch": 1.0634328358208955, |
| "grad_norm": 0.21348708868026733, |
| "learning_rate": 0.0002, |
| "loss": 0.545887291431427, |
| "mean_token_accuracy": 0.7767468988895416, |
| "num_tokens": 4660571.0, |
| "step": 285 |
| }, |
| { |
| "entropy": 0.5461400300264359, |
| "epoch": 1.0671641791044777, |
| "grad_norm": 0.12773112952709198, |
| "learning_rate": 0.0002, |
| "loss": 0.5430867671966553, |
| "mean_token_accuracy": 0.780292809009552, |
| "num_tokens": 4677015.0, |
| "step": 286 |
| }, |
| { |
| "entropy": 0.528187945485115, |
| "epoch": 1.0708955223880596, |
| "grad_norm": 0.15882739424705505, |
| "learning_rate": 0.0002, |
| "loss": 0.5334241390228271, |
| "mean_token_accuracy": 0.7845441102981567, |
| "num_tokens": 4693215.0, |
| "step": 287 |
| }, |
| { |
| "entropy": 0.5439321994781494, |
| "epoch": 1.0746268656716418, |
| "grad_norm": 0.4617445766925812, |
| "learning_rate": 0.0002, |
| "loss": 0.5486345291137695, |
| "mean_token_accuracy": 0.7790203094482422, |
| "num_tokens": 4709306.0, |
| "step": 288 |
| }, |
| { |
| "entropy": 0.544179305434227, |
| "epoch": 1.078358208955224, |
| "grad_norm": 0.17263422906398773, |
| "learning_rate": 0.0002, |
| "loss": 0.5484040379524231, |
| "mean_token_accuracy": 0.780149906873703, |
| "num_tokens": 4725638.0, |
| "step": 289 |
| }, |
| { |
| "entropy": 0.5383714884519577, |
| "epoch": 1.0820895522388059, |
| "grad_norm": 0.2244713455438614, |
| "learning_rate": 0.0002, |
| "loss": 0.544658899307251, |
| "mean_token_accuracy": 0.7811738103628159, |
| "num_tokens": 4742155.0, |
| "step": 290 |
| }, |
| { |
| "entropy": 0.5565983057022095, |
| "epoch": 1.085820895522388, |
| "grad_norm": 0.19952508807182312, |
| "learning_rate": 0.0002, |
| "loss": 0.5595170259475708, |
| "mean_token_accuracy": 0.7736999839544296, |
| "num_tokens": 4758517.0, |
| "step": 291 |
| }, |
| { |
| "entropy": 0.5434303134679794, |
| "epoch": 1.0895522388059702, |
| "grad_norm": 0.14544866979122162, |
| "learning_rate": 0.0002, |
| "loss": 0.5393437147140503, |
| "mean_token_accuracy": 0.7856098413467407, |
| "num_tokens": 4774762.0, |
| "step": 292 |
| }, |
| { |
| "entropy": 0.5319772362709045, |
| "epoch": 1.0932835820895523, |
| "grad_norm": 0.14283113181591034, |
| "learning_rate": 0.0002, |
| "loss": 0.526218056678772, |
| "mean_token_accuracy": 0.7870162725448608, |
| "num_tokens": 4790999.0, |
| "step": 293 |
| }, |
| { |
| "entropy": 0.5434096455574036, |
| "epoch": 1.0970149253731343, |
| "grad_norm": 0.15626703202724457, |
| "learning_rate": 0.0002, |
| "loss": 0.5425883531570435, |
| "mean_token_accuracy": 0.7799723148345947, |
| "num_tokens": 4807355.0, |
| "step": 294 |
| }, |
| { |
| "entropy": 0.5354667901992798, |
| "epoch": 1.1007462686567164, |
| "grad_norm": 0.14570565521717072, |
| "learning_rate": 0.0002, |
| "loss": 0.534758448600769, |
| "mean_token_accuracy": 0.7837725728750229, |
| "num_tokens": 4823630.0, |
| "step": 295 |
| }, |
| { |
| "entropy": 0.5123852044343948, |
| "epoch": 1.1044776119402986, |
| "grad_norm": 0.160378098487854, |
| "learning_rate": 0.0002, |
| "loss": 0.5198788642883301, |
| "mean_token_accuracy": 0.7897140234708786, |
| "num_tokens": 4839823.0, |
| "step": 296 |
| }, |
| { |
| "entropy": 0.5153655484318733, |
| "epoch": 1.1082089552238805, |
| "grad_norm": 0.12454921752214432, |
| "learning_rate": 0.0002, |
| "loss": 0.5199008584022522, |
| "mean_token_accuracy": 0.788884624838829, |
| "num_tokens": 4856035.0, |
| "step": 297 |
| }, |
| { |
| "entropy": 0.5461432039737701, |
| "epoch": 1.1119402985074627, |
| "grad_norm": 0.1544659435749054, |
| "learning_rate": 0.0002, |
| "loss": 0.5452744364738464, |
| "mean_token_accuracy": 0.7795560359954834, |
| "num_tokens": 4872220.0, |
| "step": 298 |
| }, |
| { |
| "entropy": 0.5625067204236984, |
| "epoch": 1.1156716417910448, |
| "grad_norm": 0.13766349852085114, |
| "learning_rate": 0.0002, |
| "loss": 0.5540031790733337, |
| "mean_token_accuracy": 0.7744271457195282, |
| "num_tokens": 4888763.0, |
| "step": 299 |
| }, |
| { |
| "entropy": 0.5349690914154053, |
| "epoch": 1.1194029850746268, |
| "grad_norm": 0.12119746953248978, |
| "learning_rate": 0.0002, |
| "loss": 0.5328707695007324, |
| "mean_token_accuracy": 0.786256805062294, |
| "num_tokens": 4904934.0, |
| "step": 300 |
| }, |
| { |
| "entropy": 0.5442438572645187, |
| "epoch": 1.123134328358209, |
| "grad_norm": 0.1483428031206131, |
| "learning_rate": 0.0002, |
| "loss": 0.5394157767295837, |
| "mean_token_accuracy": 0.7828674614429474, |
| "num_tokens": 4921449.0, |
| "step": 301 |
| }, |
| { |
| "entropy": 0.5480814874172211, |
| "epoch": 1.126865671641791, |
| "grad_norm": 0.12111463397741318, |
| "learning_rate": 0.0002, |
| "loss": 0.5459335446357727, |
| "mean_token_accuracy": 0.7798201739788055, |
| "num_tokens": 4937927.0, |
| "step": 302 |
| }, |
| { |
| "entropy": 0.5204553231596947, |
| "epoch": 1.1305970149253732, |
| "grad_norm": 0.14064359664916992, |
| "learning_rate": 0.0002, |
| "loss": 0.5259119868278503, |
| "mean_token_accuracy": 0.7859820872545242, |
| "num_tokens": 4953963.0, |
| "step": 303 |
| }, |
| { |
| "entropy": 0.5364374965429306, |
| "epoch": 1.1343283582089552, |
| "grad_norm": 0.13243189454078674, |
| "learning_rate": 0.0002, |
| "loss": 0.5326945781707764, |
| "mean_token_accuracy": 0.7844381481409073, |
| "num_tokens": 4970415.0, |
| "step": 304 |
| }, |
| { |
| "entropy": 0.5407220274209976, |
| "epoch": 1.1380597014925373, |
| "grad_norm": 0.12492922693490982, |
| "learning_rate": 0.0002, |
| "loss": 0.5424169301986694, |
| "mean_token_accuracy": 0.7811987847089767, |
| "num_tokens": 4986668.0, |
| "step": 305 |
| }, |
| { |
| "entropy": 0.5520765632390976, |
| "epoch": 1.1417910447761195, |
| "grad_norm": 0.14284519851207733, |
| "learning_rate": 0.0002, |
| "loss": 0.5543367862701416, |
| "mean_token_accuracy": 0.7787054628133774, |
| "num_tokens": 5003033.0, |
| "step": 306 |
| }, |
| { |
| "entropy": 0.523719884455204, |
| "epoch": 1.1455223880597014, |
| "grad_norm": 0.14955952763557434, |
| "learning_rate": 0.0002, |
| "loss": 0.5386480093002319, |
| "mean_token_accuracy": 0.7809686362743378, |
| "num_tokens": 5019039.0, |
| "step": 307 |
| }, |
| { |
| "entropy": 0.5446151494979858, |
| "epoch": 1.1492537313432836, |
| "grad_norm": 0.13584887981414795, |
| "learning_rate": 0.0002, |
| "loss": 0.5464479327201843, |
| "mean_token_accuracy": 0.7785664796829224, |
| "num_tokens": 5035543.0, |
| "step": 308 |
| }, |
| { |
| "entropy": 0.56036277115345, |
| "epoch": 1.1529850746268657, |
| "grad_norm": 0.15630215406417847, |
| "learning_rate": 0.0002, |
| "loss": 0.5526530742645264, |
| "mean_token_accuracy": 0.7781243026256561, |
| "num_tokens": 5052230.0, |
| "step": 309 |
| }, |
| { |
| "entropy": 0.5558945387601852, |
| "epoch": 1.1567164179104479, |
| "grad_norm": 0.1377703845500946, |
| "learning_rate": 0.0002, |
| "loss": 0.5451952815055847, |
| "mean_token_accuracy": 0.7807501256465912, |
| "num_tokens": 5068729.0, |
| "step": 310 |
| }, |
| { |
| "entropy": 0.5357001423835754, |
| "epoch": 1.1604477611940298, |
| "grad_norm": 0.15856942534446716, |
| "learning_rate": 0.0002, |
| "loss": 0.5353619456291199, |
| "mean_token_accuracy": 0.7824000269174576, |
| "num_tokens": 5085182.0, |
| "step": 311 |
| }, |
| { |
| "entropy": 0.5403632968664169, |
| "epoch": 1.164179104477612, |
| "grad_norm": 0.1401129812002182, |
| "learning_rate": 0.0002, |
| "loss": 0.5430052876472473, |
| "mean_token_accuracy": 0.7785370498895645, |
| "num_tokens": 5101581.0, |
| "step": 312 |
| }, |
| { |
| "entropy": 0.5525769144296646, |
| "epoch": 1.1679104477611941, |
| "grad_norm": 0.18710924685001373, |
| "learning_rate": 0.0002, |
| "loss": 0.5602273941040039, |
| "mean_token_accuracy": 0.7721119523048401, |
| "num_tokens": 5117991.0, |
| "step": 313 |
| }, |
| { |
| "entropy": 0.5405965894460678, |
| "epoch": 1.171641791044776, |
| "grad_norm": 0.13541167974472046, |
| "learning_rate": 0.0002, |
| "loss": 0.5374094843864441, |
| "mean_token_accuracy": 0.7825052738189697, |
| "num_tokens": 5134527.0, |
| "step": 314 |
| }, |
| { |
| "entropy": 0.5242538601160049, |
| "epoch": 1.1753731343283582, |
| "grad_norm": 0.14658832550048828, |
| "learning_rate": 0.0002, |
| "loss": 0.5233728289604187, |
| "mean_token_accuracy": 0.7873149216175079, |
| "num_tokens": 5150786.0, |
| "step": 315 |
| }, |
| { |
| "entropy": 0.5385556519031525, |
| "epoch": 1.1791044776119404, |
| "grad_norm": 0.1504085808992386, |
| "learning_rate": 0.0002, |
| "loss": 0.5342796444892883, |
| "mean_token_accuracy": 0.7851303815841675, |
| "num_tokens": 5167236.0, |
| "step": 316 |
| }, |
| { |
| "entropy": 0.5199088305234909, |
| "epoch": 1.1828358208955223, |
| "grad_norm": 0.12961594760417938, |
| "learning_rate": 0.0002, |
| "loss": 0.5229104161262512, |
| "mean_token_accuracy": 0.7855532914400101, |
| "num_tokens": 5183611.0, |
| "step": 317 |
| }, |
| { |
| "entropy": 0.5421285480260849, |
| "epoch": 1.1865671641791045, |
| "grad_norm": 0.1630048155784607, |
| "learning_rate": 0.0002, |
| "loss": 0.5512990951538086, |
| "mean_token_accuracy": 0.7758335471153259, |
| "num_tokens": 5199999.0, |
| "step": 318 |
| }, |
| { |
| "entropy": 0.5308284014463425, |
| "epoch": 1.1902985074626866, |
| "grad_norm": 0.12485714256763458, |
| "learning_rate": 0.0002, |
| "loss": 0.5404457449913025, |
| "mean_token_accuracy": 0.782282680273056, |
| "num_tokens": 5216339.0, |
| "step": 319 |
| }, |
| { |
| "entropy": 0.5173521861433983, |
| "epoch": 1.1940298507462686, |
| "grad_norm": 0.13365958631038666, |
| "learning_rate": 0.0002, |
| "loss": 0.5198112726211548, |
| "mean_token_accuracy": 0.7871741354465485, |
| "num_tokens": 5232624.0, |
| "step": 320 |
| }, |
| { |
| "entropy": 0.536166213452816, |
| "epoch": 1.1977611940298507, |
| "grad_norm": 0.1480405628681183, |
| "learning_rate": 0.0002, |
| "loss": 0.5324058532714844, |
| "mean_token_accuracy": 0.7836772352457047, |
| "num_tokens": 5248769.0, |
| "step": 321 |
| }, |
| { |
| "entropy": 0.5278853923082352, |
| "epoch": 1.2014925373134329, |
| "grad_norm": 0.11620926111936569, |
| "learning_rate": 0.0002, |
| "loss": 0.5210928320884705, |
| "mean_token_accuracy": 0.7879270166158676, |
| "num_tokens": 5265103.0, |
| "step": 322 |
| }, |
| { |
| "entropy": 0.5473660826683044, |
| "epoch": 1.205223880597015, |
| "grad_norm": 0.14534439146518707, |
| "learning_rate": 0.0002, |
| "loss": 0.5495036840438843, |
| "mean_token_accuracy": 0.7784842550754547, |
| "num_tokens": 5281566.0, |
| "step": 323 |
| }, |
| { |
| "entropy": 0.5377688258886337, |
| "epoch": 1.208955223880597, |
| "grad_norm": 0.12136119604110718, |
| "learning_rate": 0.0002, |
| "loss": 0.5339184999465942, |
| "mean_token_accuracy": 0.7866815328598022, |
| "num_tokens": 5297908.0, |
| "step": 324 |
| }, |
| { |
| "entropy": 0.5164415165781975, |
| "epoch": 1.212686567164179, |
| "grad_norm": 0.12826436758041382, |
| "learning_rate": 0.0002, |
| "loss": 0.5172092914581299, |
| "mean_token_accuracy": 0.7894498109817505, |
| "num_tokens": 5314098.0, |
| "step": 325 |
| }, |
| { |
| "entropy": 0.530172199010849, |
| "epoch": 1.2164179104477613, |
| "grad_norm": 0.1333148181438446, |
| "learning_rate": 0.0002, |
| "loss": 0.5356741547584534, |
| "mean_token_accuracy": 0.782715454697609, |
| "num_tokens": 5330692.0, |
| "step": 326 |
| }, |
| { |
| "entropy": 0.5366138964891434, |
| "epoch": 1.2201492537313432, |
| "grad_norm": 0.13149604201316833, |
| "learning_rate": 0.0002, |
| "loss": 0.540725827217102, |
| "mean_token_accuracy": 0.778188943862915, |
| "num_tokens": 5346807.0, |
| "step": 327 |
| }, |
| { |
| "entropy": 0.5387064814567566, |
| "epoch": 1.2238805970149254, |
| "grad_norm": 0.11986811459064484, |
| "learning_rate": 0.0002, |
| "loss": 0.5362977385520935, |
| "mean_token_accuracy": 0.7805480509996414, |
| "num_tokens": 5363204.0, |
| "step": 328 |
| }, |
| { |
| "entropy": 0.5309393405914307, |
| "epoch": 1.2276119402985075, |
| "grad_norm": 0.15663830935955048, |
| "learning_rate": 0.0002, |
| "loss": 0.5344343185424805, |
| "mean_token_accuracy": 0.7852894812822342, |
| "num_tokens": 5379443.0, |
| "step": 329 |
| }, |
| { |
| "entropy": 0.5188804268836975, |
| "epoch": 1.2313432835820897, |
| "grad_norm": 0.13876301050186157, |
| "learning_rate": 0.0002, |
| "loss": 0.5226371884346008, |
| "mean_token_accuracy": 0.7869541347026825, |
| "num_tokens": 5395899.0, |
| "step": 330 |
| }, |
| { |
| "entropy": 0.5370157659053802, |
| "epoch": 1.2350746268656716, |
| "grad_norm": 0.1468764841556549, |
| "learning_rate": 0.0002, |
| "loss": 0.5368411540985107, |
| "mean_token_accuracy": 0.782823771238327, |
| "num_tokens": 5412330.0, |
| "step": 331 |
| }, |
| { |
| "entropy": 0.53305783867836, |
| "epoch": 1.2388059701492538, |
| "grad_norm": 0.7343654036521912, |
| "learning_rate": 0.0002, |
| "loss": 0.5325803160667419, |
| "mean_token_accuracy": 0.786160409450531, |
| "num_tokens": 5428623.0, |
| "step": 332 |
| }, |
| { |
| "entropy": 0.5495659112930298, |
| "epoch": 1.242537313432836, |
| "grad_norm": 0.1761074662208557, |
| "learning_rate": 0.0002, |
| "loss": 0.5617696642875671, |
| "mean_token_accuracy": 0.7767286598682404, |
| "num_tokens": 5444935.0, |
| "step": 333 |
| }, |
| { |
| "entropy": 0.5243020802736282, |
| "epoch": 1.2462686567164178, |
| "grad_norm": 0.2371833771467209, |
| "learning_rate": 0.0002, |
| "loss": 0.533098578453064, |
| "mean_token_accuracy": 0.7883012443780899, |
| "num_tokens": 5461199.0, |
| "step": 334 |
| }, |
| { |
| "entropy": 0.5307088941335678, |
| "epoch": 1.25, |
| "grad_norm": 0.18113981187343597, |
| "learning_rate": 0.0002, |
| "loss": 0.545291543006897, |
| "mean_token_accuracy": 0.7803493738174438, |
| "num_tokens": 5477497.0, |
| "step": 335 |
| }, |
| { |
| "entropy": 0.555059015750885, |
| "epoch": 1.2537313432835822, |
| "grad_norm": 0.15813486278057098, |
| "learning_rate": 0.0002, |
| "loss": 0.5573302507400513, |
| "mean_token_accuracy": 0.7767059653997421, |
| "num_tokens": 5493899.0, |
| "step": 336 |
| }, |
| { |
| "entropy": 0.5521019399166107, |
| "epoch": 1.2574626865671643, |
| "grad_norm": 0.1451314091682434, |
| "learning_rate": 0.0002, |
| "loss": 0.5429173707962036, |
| "mean_token_accuracy": 0.781745970249176, |
| "num_tokens": 5510416.0, |
| "step": 337 |
| }, |
| { |
| "entropy": 0.5308272391557693, |
| "epoch": 1.2611940298507462, |
| "grad_norm": 0.13935986161231995, |
| "learning_rate": 0.0002, |
| "loss": 0.521798849105835, |
| "mean_token_accuracy": 0.7906093895435333, |
| "num_tokens": 5526560.0, |
| "step": 338 |
| }, |
| { |
| "entropy": 0.5415322780609131, |
| "epoch": 1.2649253731343284, |
| "grad_norm": 0.13424275815486908, |
| "learning_rate": 0.0002, |
| "loss": 0.5343063473701477, |
| "mean_token_accuracy": 0.7824369817972183, |
| "num_tokens": 5542960.0, |
| "step": 339 |
| }, |
| { |
| "entropy": 0.522081658244133, |
| "epoch": 1.2686567164179103, |
| "grad_norm": 0.15974028408527374, |
| "learning_rate": 0.0002, |
| "loss": 0.5269800424575806, |
| "mean_token_accuracy": 0.7839764058589935, |
| "num_tokens": 5559214.0, |
| "step": 340 |
| }, |
| { |
| "entropy": 0.5425546318292618, |
| "epoch": 1.2723880597014925, |
| "grad_norm": 0.1437254548072815, |
| "learning_rate": 0.0002, |
| "loss": 0.5448679327964783, |
| "mean_token_accuracy": 0.7786598205566406, |
| "num_tokens": 5575630.0, |
| "step": 341 |
| }, |
| { |
| "entropy": 0.5436711013317108, |
| "epoch": 1.2761194029850746, |
| "grad_norm": 0.1429026871919632, |
| "learning_rate": 0.0002, |
| "loss": 0.5388238430023193, |
| "mean_token_accuracy": 0.784403070807457, |
| "num_tokens": 5591920.0, |
| "step": 342 |
| }, |
| { |
| "entropy": 0.5507813543081284, |
| "epoch": 1.2798507462686568, |
| "grad_norm": 0.14362995326519012, |
| "learning_rate": 0.0002, |
| "loss": 0.5431510210037231, |
| "mean_token_accuracy": 0.7801653742790222, |
| "num_tokens": 5608239.0, |
| "step": 343 |
| }, |
| { |
| "entropy": 0.526011124253273, |
| "epoch": 1.2835820895522387, |
| "grad_norm": 0.13371744751930237, |
| "learning_rate": 0.0002, |
| "loss": 0.5243735313415527, |
| "mean_token_accuracy": 0.7876265347003937, |
| "num_tokens": 5624776.0, |
| "step": 344 |
| }, |
| { |
| "entropy": 0.546712264418602, |
| "epoch": 1.287313432835821, |
| "grad_norm": 0.13483010232448578, |
| "learning_rate": 0.0002, |
| "loss": 0.5509325861930847, |
| "mean_token_accuracy": 0.7768485099077225, |
| "num_tokens": 5641387.0, |
| "step": 345 |
| }, |
| { |
| "entropy": 0.5187881886959076, |
| "epoch": 1.291044776119403, |
| "grad_norm": 0.16521677374839783, |
| "learning_rate": 0.0002, |
| "loss": 0.5272278785705566, |
| "mean_token_accuracy": 0.7863399684429169, |
| "num_tokens": 5657696.0, |
| "step": 346 |
| }, |
| { |
| "entropy": 0.5431257635354996, |
| "epoch": 1.294776119402985, |
| "grad_norm": 0.1433476358652115, |
| "learning_rate": 0.0002, |
| "loss": 0.544238269329071, |
| "mean_token_accuracy": 0.7789204865694046, |
| "num_tokens": 5674118.0, |
| "step": 347 |
| }, |
| { |
| "entropy": 0.5423388481140137, |
| "epoch": 1.2985074626865671, |
| "grad_norm": 0.18153057992458344, |
| "learning_rate": 0.0002, |
| "loss": 0.5453824996948242, |
| "mean_token_accuracy": 0.7768147736787796, |
| "num_tokens": 5690497.0, |
| "step": 348 |
| }, |
| { |
| "entropy": 0.5282611399888992, |
| "epoch": 1.3022388059701493, |
| "grad_norm": 0.1320338100194931, |
| "learning_rate": 0.0002, |
| "loss": 0.52436363697052, |
| "mean_token_accuracy": 0.7850473374128342, |
| "num_tokens": 5706707.0, |
| "step": 349 |
| }, |
| { |
| "entropy": 0.554891362786293, |
| "epoch": 1.3059701492537314, |
| "grad_norm": 0.17498286068439484, |
| "learning_rate": 0.0002, |
| "loss": 0.5602602362632751, |
| "mean_token_accuracy": 0.7726856172084808, |
| "num_tokens": 5722957.0, |
| "step": 350 |
| }, |
| { |
| "entropy": 0.5311142429709435, |
| "epoch": 1.3097014925373134, |
| "grad_norm": 0.13096287846565247, |
| "learning_rate": 0.0002, |
| "loss": 0.5347020030021667, |
| "mean_token_accuracy": 0.782605841755867, |
| "num_tokens": 5739444.0, |
| "step": 351 |
| }, |
| { |
| "entropy": 0.5453475713729858, |
| "epoch": 1.3134328358208955, |
| "grad_norm": 0.1644972562789917, |
| "learning_rate": 0.0002, |
| "loss": 0.5561221241950989, |
| "mean_token_accuracy": 0.7715690732002258, |
| "num_tokens": 5755735.0, |
| "step": 352 |
| }, |
| { |
| "entropy": 0.5426347702741623, |
| "epoch": 1.3171641791044777, |
| "grad_norm": 0.15120083093643188, |
| "learning_rate": 0.0002, |
| "loss": 0.5344815850257874, |
| "mean_token_accuracy": 0.7845005393028259, |
| "num_tokens": 5772199.0, |
| "step": 353 |
| }, |
| { |
| "entropy": 0.5419983565807343, |
| "epoch": 1.3208955223880596, |
| "grad_norm": 0.1761469691991806, |
| "learning_rate": 0.0002, |
| "loss": 0.537039577960968, |
| "mean_token_accuracy": 0.7818126231431961, |
| "num_tokens": 5788675.0, |
| "step": 354 |
| }, |
| { |
| "entropy": 0.552616760134697, |
| "epoch": 1.3246268656716418, |
| "grad_norm": 0.14121757447719574, |
| "learning_rate": 0.0002, |
| "loss": 0.5478329062461853, |
| "mean_token_accuracy": 0.7794584184885025, |
| "num_tokens": 5805184.0, |
| "step": 355 |
| }, |
| { |
| "entropy": 0.5541802197694778, |
| "epoch": 1.328358208955224, |
| "grad_norm": 0.1597132384777069, |
| "learning_rate": 0.0002, |
| "loss": 0.5552881360054016, |
| "mean_token_accuracy": 0.7760720700025558, |
| "num_tokens": 5821800.0, |
| "step": 356 |
| }, |
| { |
| "entropy": 0.5311779379844666, |
| "epoch": 1.332089552238806, |
| "grad_norm": 0.14419205486774445, |
| "learning_rate": 0.0002, |
| "loss": 0.5361248850822449, |
| "mean_token_accuracy": 0.7849418371915817, |
| "num_tokens": 5837920.0, |
| "step": 357 |
| }, |
| { |
| "entropy": 0.5202493965625763, |
| "epoch": 1.335820895522388, |
| "grad_norm": 0.1753031611442566, |
| "learning_rate": 0.0002, |
| "loss": 0.5250152349472046, |
| "mean_token_accuracy": 0.7846049815416336, |
| "num_tokens": 5853986.0, |
| "step": 358 |
| }, |
| { |
| "entropy": 0.5305204391479492, |
| "epoch": 1.3395522388059702, |
| "grad_norm": 0.13069619238376617, |
| "learning_rate": 0.0002, |
| "loss": 0.5352439284324646, |
| "mean_token_accuracy": 0.7837421298027039, |
| "num_tokens": 5870201.0, |
| "step": 359 |
| }, |
| { |
| "entropy": 0.5199942141771317, |
| "epoch": 1.3432835820895521, |
| "grad_norm": 0.12522701919078827, |
| "learning_rate": 0.0002, |
| "loss": 0.522696852684021, |
| "mean_token_accuracy": 0.7883526384830475, |
| "num_tokens": 5886521.0, |
| "step": 360 |
| }, |
| { |
| "entropy": 0.5446951240301132, |
| "epoch": 1.3470149253731343, |
| "grad_norm": 0.12352673709392548, |
| "learning_rate": 0.0002, |
| "loss": 0.5464925765991211, |
| "mean_token_accuracy": 0.7775059789419174, |
| "num_tokens": 5902854.0, |
| "step": 361 |
| }, |
| { |
| "entropy": 0.5462271720170975, |
| "epoch": 1.3507462686567164, |
| "grad_norm": 0.12150366604328156, |
| "learning_rate": 0.0002, |
| "loss": 0.5447920560836792, |
| "mean_token_accuracy": 0.7786460071802139, |
| "num_tokens": 5919263.0, |
| "step": 362 |
| }, |
| { |
| "entropy": 0.5448370575904846, |
| "epoch": 1.3544776119402986, |
| "grad_norm": 0.1430087685585022, |
| "learning_rate": 0.0002, |
| "loss": 0.5400609970092773, |
| "mean_token_accuracy": 0.7802611738443375, |
| "num_tokens": 5935619.0, |
| "step": 363 |
| }, |
| { |
| "entropy": 0.5544243305921555, |
| "epoch": 1.3582089552238805, |
| "grad_norm": 0.1183784082531929, |
| "learning_rate": 0.0002, |
| "loss": 0.5504992008209229, |
| "mean_token_accuracy": 0.7777380645275116, |
| "num_tokens": 5952004.0, |
| "step": 364 |
| }, |
| { |
| "entropy": 0.5417809635400772, |
| "epoch": 1.3619402985074627, |
| "grad_norm": 0.14860908687114716, |
| "learning_rate": 0.0002, |
| "loss": 0.5398492813110352, |
| "mean_token_accuracy": 0.7835634648799896, |
| "num_tokens": 5968408.0, |
| "step": 365 |
| }, |
| { |
| "entropy": 0.54038967192173, |
| "epoch": 1.3656716417910448, |
| "grad_norm": 0.1280207335948944, |
| "learning_rate": 0.0002, |
| "loss": 0.5439375638961792, |
| "mean_token_accuracy": 0.7803472131490707, |
| "num_tokens": 5984523.0, |
| "step": 366 |
| }, |
| { |
| "entropy": 0.5312757939100266, |
| "epoch": 1.3694029850746268, |
| "grad_norm": 0.12786155939102173, |
| "learning_rate": 0.0002, |
| "loss": 0.537388265132904, |
| "mean_token_accuracy": 0.7846339344978333, |
| "num_tokens": 6001152.0, |
| "step": 367 |
| }, |
| { |
| "entropy": 0.5325536578893661, |
| "epoch": 1.373134328358209, |
| "grad_norm": 0.14665193855762482, |
| "learning_rate": 0.0002, |
| "loss": 0.5409241914749146, |
| "mean_token_accuracy": 0.7798537611961365, |
| "num_tokens": 6017461.0, |
| "step": 368 |
| }, |
| { |
| "entropy": 0.5438549816608429, |
| "epoch": 1.376865671641791, |
| "grad_norm": 0.15340304374694824, |
| "learning_rate": 0.0002, |
| "loss": 0.547132134437561, |
| "mean_token_accuracy": 0.7798985242843628, |
| "num_tokens": 6034010.0, |
| "step": 369 |
| }, |
| { |
| "entropy": 0.5280237346887589, |
| "epoch": 1.3805970149253732, |
| "grad_norm": 0.12335757911205292, |
| "learning_rate": 0.0002, |
| "loss": 0.5288500189781189, |
| "mean_token_accuracy": 0.7849439233541489, |
| "num_tokens": 6050449.0, |
| "step": 370 |
| }, |
| { |
| "entropy": 0.5389716774225235, |
| "epoch": 1.3843283582089552, |
| "grad_norm": 0.14379094541072845, |
| "learning_rate": 0.0002, |
| "loss": 0.5319365859031677, |
| "mean_token_accuracy": 0.7839574217796326, |
| "num_tokens": 6066773.0, |
| "step": 371 |
| }, |
| { |
| "entropy": 0.5398078411817551, |
| "epoch": 1.3880597014925373, |
| "grad_norm": 0.125816211104393, |
| "learning_rate": 0.0002, |
| "loss": 0.5355566740036011, |
| "mean_token_accuracy": 0.782632440328598, |
| "num_tokens": 6083144.0, |
| "step": 372 |
| }, |
| { |
| "entropy": 0.5222254693508148, |
| "epoch": 1.3917910447761195, |
| "grad_norm": 0.13074038922786713, |
| "learning_rate": 0.0002, |
| "loss": 0.5234925746917725, |
| "mean_token_accuracy": 0.7849694788455963, |
| "num_tokens": 6099504.0, |
| "step": 373 |
| }, |
| { |
| "entropy": 0.5394090265035629, |
| "epoch": 1.3955223880597014, |
| "grad_norm": 0.14279109239578247, |
| "learning_rate": 0.0002, |
| "loss": 0.5467327237129211, |
| "mean_token_accuracy": 0.7787034064531326, |
| "num_tokens": 6115915.0, |
| "step": 374 |
| }, |
| { |
| "entropy": 0.5503050237894058, |
| "epoch": 1.3992537313432836, |
| "grad_norm": 0.13877107203006744, |
| "learning_rate": 0.0002, |
| "loss": 0.5478618144989014, |
| "mean_token_accuracy": 0.7787372469902039, |
| "num_tokens": 6132294.0, |
| "step": 375 |
| }, |
| { |
| "entropy": 0.5493099391460419, |
| "epoch": 1.4029850746268657, |
| "grad_norm": 0.13642564415931702, |
| "learning_rate": 0.0002, |
| "loss": 0.5501952171325684, |
| "mean_token_accuracy": 0.7771935015916824, |
| "num_tokens": 6148603.0, |
| "step": 376 |
| }, |
| { |
| "entropy": 0.5462473034858704, |
| "epoch": 1.4067164179104479, |
| "grad_norm": 0.12655094265937805, |
| "learning_rate": 0.0002, |
| "loss": 0.5428159832954407, |
| "mean_token_accuracy": 0.7779795825481415, |
| "num_tokens": 6165118.0, |
| "step": 377 |
| }, |
| { |
| "entropy": 0.5256887674331665, |
| "epoch": 1.4104477611940298, |
| "grad_norm": 0.14916951954364777, |
| "learning_rate": 0.0002, |
| "loss": 0.527644157409668, |
| "mean_token_accuracy": 0.788107380270958, |
| "num_tokens": 6181375.0, |
| "step": 378 |
| }, |
| { |
| "entropy": 0.5180016905069351, |
| "epoch": 1.414179104477612, |
| "grad_norm": 0.15282602608203888, |
| "learning_rate": 0.0002, |
| "loss": 0.5270644426345825, |
| "mean_token_accuracy": 0.7877923846244812, |
| "num_tokens": 6197579.0, |
| "step": 379 |
| }, |
| { |
| "entropy": 0.5399880707263947, |
| "epoch": 1.417910447761194, |
| "grad_norm": 0.13323858380317688, |
| "learning_rate": 0.0002, |
| "loss": 0.5470925569534302, |
| "mean_token_accuracy": 0.7769253998994827, |
| "num_tokens": 6213930.0, |
| "step": 380 |
| }, |
| { |
| "entropy": 0.5487040579319, |
| "epoch": 1.421641791044776, |
| "grad_norm": 0.13869382441043854, |
| "learning_rate": 0.0002, |
| "loss": 0.5484498739242554, |
| "mean_token_accuracy": 0.7771484106779099, |
| "num_tokens": 6230279.0, |
| "step": 381 |
| }, |
| { |
| "entropy": 0.5512665659189224, |
| "epoch": 1.4253731343283582, |
| "grad_norm": 0.12661167979240417, |
| "learning_rate": 0.0002, |
| "loss": 0.5482139587402344, |
| "mean_token_accuracy": 0.7779690474271774, |
| "num_tokens": 6246836.0, |
| "step": 382 |
| }, |
| { |
| "entropy": 0.5149375051259995, |
| "epoch": 1.4291044776119404, |
| "grad_norm": 0.12929636240005493, |
| "learning_rate": 0.0002, |
| "loss": 0.51515793800354, |
| "mean_token_accuracy": 0.7905084192752838, |
| "num_tokens": 6263027.0, |
| "step": 383 |
| }, |
| { |
| "entropy": 0.5514957904815674, |
| "epoch": 1.4328358208955223, |
| "grad_norm": 0.13133598864078522, |
| "learning_rate": 0.0002, |
| "loss": 0.5495380163192749, |
| "mean_token_accuracy": 0.7770676761865616, |
| "num_tokens": 6279290.0, |
| "step": 384 |
| }, |
| { |
| "entropy": 0.5408458113670349, |
| "epoch": 1.4365671641791045, |
| "grad_norm": 0.15077555179595947, |
| "learning_rate": 0.0002, |
| "loss": 0.5422307252883911, |
| "mean_token_accuracy": 0.7783090472221375, |
| "num_tokens": 6295777.0, |
| "step": 385 |
| }, |
| { |
| "entropy": 0.520571157336235, |
| "epoch": 1.4402985074626866, |
| "grad_norm": 0.13069279491901398, |
| "learning_rate": 0.0002, |
| "loss": 0.5223069190979004, |
| "mean_token_accuracy": 0.7897206395864487, |
| "num_tokens": 6312226.0, |
| "step": 386 |
| }, |
| { |
| "entropy": 0.555729016661644, |
| "epoch": 1.4440298507462686, |
| "grad_norm": 0.12705039978027344, |
| "learning_rate": 0.0002, |
| "loss": 0.5552259087562561, |
| "mean_token_accuracy": 0.7751185745000839, |
| "num_tokens": 6328727.0, |
| "step": 387 |
| }, |
| { |
| "entropy": 0.534821942448616, |
| "epoch": 1.4477611940298507, |
| "grad_norm": 0.16326452791690826, |
| "learning_rate": 0.0002, |
| "loss": 0.5358320474624634, |
| "mean_token_accuracy": 0.7829154431819916, |
| "num_tokens": 6345104.0, |
| "step": 388 |
| }, |
| { |
| "entropy": 0.5430563241243362, |
| "epoch": 1.4514925373134329, |
| "grad_norm": 0.1356133371591568, |
| "learning_rate": 0.0002, |
| "loss": 0.5396363735198975, |
| "mean_token_accuracy": 0.7828508615493774, |
| "num_tokens": 6361601.0, |
| "step": 389 |
| }, |
| { |
| "entropy": 0.5201783627271652, |
| "epoch": 1.455223880597015, |
| "grad_norm": 0.15094102919101715, |
| "learning_rate": 0.0002, |
| "loss": 0.5216266512870789, |
| "mean_token_accuracy": 0.7902540266513824, |
| "num_tokens": 6377866.0, |
| "step": 390 |
| }, |
| { |
| "entropy": 0.5517327636480331, |
| "epoch": 1.458955223880597, |
| "grad_norm": 0.13916830718517303, |
| "learning_rate": 0.0002, |
| "loss": 0.5561582446098328, |
| "mean_token_accuracy": 0.7718836516141891, |
| "num_tokens": 6394257.0, |
| "step": 391 |
| }, |
| { |
| "entropy": 0.5622112900018692, |
| "epoch": 1.462686567164179, |
| "grad_norm": 0.13867150247097015, |
| "learning_rate": 0.0002, |
| "loss": 0.5616392493247986, |
| "mean_token_accuracy": 0.7720617204904556, |
| "num_tokens": 6410728.0, |
| "step": 392 |
| }, |
| { |
| "entropy": 0.5276502966880798, |
| "epoch": 1.4664179104477613, |
| "grad_norm": 0.13475503027439117, |
| "learning_rate": 0.0002, |
| "loss": 0.5214023590087891, |
| "mean_token_accuracy": 0.7917980551719666, |
| "num_tokens": 6427103.0, |
| "step": 393 |
| }, |
| { |
| "entropy": 0.5384048223495483, |
| "epoch": 1.4701492537313432, |
| "grad_norm": 0.15797017514705658, |
| "learning_rate": 0.0002, |
| "loss": 0.5402668714523315, |
| "mean_token_accuracy": 0.7805082350969315, |
| "num_tokens": 6443429.0, |
| "step": 394 |
| }, |
| { |
| "entropy": 0.5475383549928665, |
| "epoch": 1.4738805970149254, |
| "grad_norm": 0.13803258538246155, |
| "learning_rate": 0.0002, |
| "loss": 0.549871563911438, |
| "mean_token_accuracy": 0.7778583019971848, |
| "num_tokens": 6459834.0, |
| "step": 395 |
| }, |
| { |
| "entropy": 0.5315697863698006, |
| "epoch": 1.4776119402985075, |
| "grad_norm": 0.14121446013450623, |
| "learning_rate": 0.0002, |
| "loss": 0.536948561668396, |
| "mean_token_accuracy": 0.7810053825378418, |
| "num_tokens": 6476130.0, |
| "step": 396 |
| }, |
| { |
| "entropy": 0.5273994207382202, |
| "epoch": 1.4813432835820897, |
| "grad_norm": 0.15222403407096863, |
| "learning_rate": 0.0002, |
| "loss": 0.5290229916572571, |
| "mean_token_accuracy": 0.7844912558794022, |
| "num_tokens": 6492517.0, |
| "step": 397 |
| }, |
| { |
| "entropy": 0.5295314341783524, |
| "epoch": 1.4850746268656716, |
| "grad_norm": 0.1473362147808075, |
| "learning_rate": 0.0002, |
| "loss": 0.5299125909805298, |
| "mean_token_accuracy": 0.7843508124351501, |
| "num_tokens": 6508820.0, |
| "step": 398 |
| }, |
| { |
| "entropy": 0.5375467240810394, |
| "epoch": 1.4888059701492538, |
| "grad_norm": 0.15435679256916046, |
| "learning_rate": 0.0002, |
| "loss": 0.5364446043968201, |
| "mean_token_accuracy": 0.7816187143325806, |
| "num_tokens": 6524991.0, |
| "step": 399 |
| }, |
| { |
| "entropy": 0.552648514509201, |
| "epoch": 1.4925373134328357, |
| "grad_norm": 0.13747446238994598, |
| "learning_rate": 0.0002, |
| "loss": 0.5507781505584717, |
| "mean_token_accuracy": 0.7755608707666397, |
| "num_tokens": 6541349.0, |
| "step": 400 |
| }, |
| { |
| "entropy": 0.514685332775116, |
| "epoch": 1.4962686567164178, |
| "grad_norm": 0.15152879059314728, |
| "learning_rate": 0.0002, |
| "loss": 0.5196027755737305, |
| "mean_token_accuracy": 0.7910663783550262, |
| "num_tokens": 6557571.0, |
| "step": 401 |
| }, |
| { |
| "entropy": 0.5485993921756744, |
| "epoch": 1.5, |
| "grad_norm": 0.12553729116916656, |
| "learning_rate": 0.0002, |
| "loss": 0.548511266708374, |
| "mean_token_accuracy": 0.7769753634929657, |
| "num_tokens": 6573960.0, |
| "step": 402 |
| }, |
| { |
| "entropy": 0.5424423962831497, |
| "epoch": 1.5037313432835822, |
| "grad_norm": 0.16526827216148376, |
| "learning_rate": 0.0002, |
| "loss": 0.5419015288352966, |
| "mean_token_accuracy": 0.7792991548776627, |
| "num_tokens": 6590090.0, |
| "step": 403 |
| }, |
| { |
| "entropy": 0.5306361317634583, |
| "epoch": 1.5074626865671643, |
| "grad_norm": 0.13779371976852417, |
| "learning_rate": 0.0002, |
| "loss": 0.5375878214836121, |
| "mean_token_accuracy": 0.7820742130279541, |
| "num_tokens": 6606560.0, |
| "step": 404 |
| }, |
| { |
| "entropy": 0.5300803333520889, |
| "epoch": 1.5111940298507462, |
| "grad_norm": 0.15327152609825134, |
| "learning_rate": 0.0002, |
| "loss": 0.5330384373664856, |
| "mean_token_accuracy": 0.7848233580589294, |
| "num_tokens": 6622555.0, |
| "step": 405 |
| }, |
| { |
| "entropy": 0.5627156347036362, |
| "epoch": 1.5149253731343284, |
| "grad_norm": 0.14609600603580475, |
| "learning_rate": 0.0002, |
| "loss": 0.561301589012146, |
| "mean_token_accuracy": 0.7721252292394638, |
| "num_tokens": 6639061.0, |
| "step": 406 |
| }, |
| { |
| "entropy": 0.5461866706609726, |
| "epoch": 1.5186567164179103, |
| "grad_norm": 0.16535943746566772, |
| "learning_rate": 0.0002, |
| "loss": 0.5418128967285156, |
| "mean_token_accuracy": 0.7805300354957581, |
| "num_tokens": 6655328.0, |
| "step": 407 |
| }, |
| { |
| "entropy": 0.5484707355499268, |
| "epoch": 1.5223880597014925, |
| "grad_norm": 0.13302011787891388, |
| "learning_rate": 0.0002, |
| "loss": 0.5458552837371826, |
| "mean_token_accuracy": 0.7797780781984329, |
| "num_tokens": 6671803.0, |
| "step": 408 |
| }, |
| { |
| "entropy": 0.5416560918092728, |
| "epoch": 1.5261194029850746, |
| "grad_norm": 0.1602572798728943, |
| "learning_rate": 0.0002, |
| "loss": 0.5427152514457703, |
| "mean_token_accuracy": 0.7791958302259445, |
| "num_tokens": 6688051.0, |
| "step": 409 |
| }, |
| { |
| "entropy": 0.5331416875123978, |
| "epoch": 1.5298507462686568, |
| "grad_norm": 0.19099944829940796, |
| "learning_rate": 0.0002, |
| "loss": 0.5434013605117798, |
| "mean_token_accuracy": 0.7788519859313965, |
| "num_tokens": 6704217.0, |
| "step": 410 |
| }, |
| { |
| "entropy": 0.5284256190061569, |
| "epoch": 1.533582089552239, |
| "grad_norm": 0.14738844335079193, |
| "learning_rate": 0.0002, |
| "loss": 0.5317047834396362, |
| "mean_token_accuracy": 0.7858552485704422, |
| "num_tokens": 6720200.0, |
| "step": 411 |
| }, |
| { |
| "entropy": 0.5176631659269333, |
| "epoch": 1.537313432835821, |
| "grad_norm": 0.15669815242290497, |
| "learning_rate": 0.0002, |
| "loss": 0.5124083757400513, |
| "mean_token_accuracy": 0.7932737022638321, |
| "num_tokens": 6736383.0, |
| "step": 412 |
| }, |
| { |
| "entropy": 0.5400972962379456, |
| "epoch": 1.5410447761194028, |
| "grad_norm": 0.13705363869667053, |
| "learning_rate": 0.0002, |
| "loss": 0.5268256664276123, |
| "mean_token_accuracy": 0.7893208563327789, |
| "num_tokens": 6752760.0, |
| "step": 413 |
| }, |
| { |
| "entropy": 0.5178179070353508, |
| "epoch": 1.544776119402985, |
| "grad_norm": 0.19731254875659943, |
| "learning_rate": 0.0002, |
| "loss": 0.5257001519203186, |
| "mean_token_accuracy": 0.787686675786972, |
| "num_tokens": 6768766.0, |
| "step": 414 |
| }, |
| { |
| "entropy": 0.5451741069555283, |
| "epoch": 1.5485074626865671, |
| "grad_norm": 0.15194211900234222, |
| "learning_rate": 0.0002, |
| "loss": 0.5515379905700684, |
| "mean_token_accuracy": 0.7795265913009644, |
| "num_tokens": 6785171.0, |
| "step": 415 |
| }, |
| { |
| "entropy": 0.5419858694076538, |
| "epoch": 1.5522388059701493, |
| "grad_norm": 0.17340968549251556, |
| "learning_rate": 0.0002, |
| "loss": 0.545304536819458, |
| "mean_token_accuracy": 0.7808218151330948, |
| "num_tokens": 6801630.0, |
| "step": 416 |
| }, |
| { |
| "entropy": 0.5443240851163864, |
| "epoch": 1.5559701492537314, |
| "grad_norm": 0.15292493999004364, |
| "learning_rate": 0.0002, |
| "loss": 0.5419030785560608, |
| "mean_token_accuracy": 0.7798885256052017, |
| "num_tokens": 6818090.0, |
| "step": 417 |
| }, |
| { |
| "entropy": 0.5471833944320679, |
| "epoch": 1.5597014925373134, |
| "grad_norm": 0.12805797159671783, |
| "learning_rate": 0.0002, |
| "loss": 0.5408046841621399, |
| "mean_token_accuracy": 0.782907098531723, |
| "num_tokens": 6834509.0, |
| "step": 418 |
| }, |
| { |
| "entropy": 0.5420715063810349, |
| "epoch": 1.5634328358208955, |
| "grad_norm": 0.162551149725914, |
| "learning_rate": 0.0002, |
| "loss": 0.5513861775398254, |
| "mean_token_accuracy": 0.7757697552442551, |
| "num_tokens": 6850861.0, |
| "step": 419 |
| }, |
| { |
| "entropy": 0.5393735766410828, |
| "epoch": 1.5671641791044775, |
| "grad_norm": 0.14343798160552979, |
| "learning_rate": 0.0002, |
| "loss": 0.5458438992500305, |
| "mean_token_accuracy": 0.7787589132785797, |
| "num_tokens": 6867458.0, |
| "step": 420 |
| }, |
| { |
| "entropy": 0.5417635887861252, |
| "epoch": 1.5708955223880596, |
| "grad_norm": 0.13028287887573242, |
| "learning_rate": 0.0002, |
| "loss": 0.5405986309051514, |
| "mean_token_accuracy": 0.7784676849842072, |
| "num_tokens": 6883876.0, |
| "step": 421 |
| }, |
| { |
| "entropy": 0.5441770106554031, |
| "epoch": 1.5746268656716418, |
| "grad_norm": 0.15801310539245605, |
| "learning_rate": 0.0002, |
| "loss": 0.5400066375732422, |
| "mean_token_accuracy": 0.7833662182092667, |
| "num_tokens": 6900212.0, |
| "step": 422 |
| }, |
| { |
| "entropy": 0.5527145117521286, |
| "epoch": 1.578358208955224, |
| "grad_norm": 0.13147710263729095, |
| "learning_rate": 0.0002, |
| "loss": 0.5493002533912659, |
| "mean_token_accuracy": 0.7745068222284317, |
| "num_tokens": 6916546.0, |
| "step": 423 |
| }, |
| { |
| "entropy": 0.5173420310020447, |
| "epoch": 1.582089552238806, |
| "grad_norm": 0.18176275491714478, |
| "learning_rate": 0.0002, |
| "loss": 0.518753707408905, |
| "mean_token_accuracy": 0.7889157682657242, |
| "num_tokens": 6932687.0, |
| "step": 424 |
| }, |
| { |
| "entropy": 0.5411906540393829, |
| "epoch": 1.585820895522388, |
| "grad_norm": 0.15723790228366852, |
| "learning_rate": 0.0002, |
| "loss": 0.5488603711128235, |
| "mean_token_accuracy": 0.7769431620836258, |
| "num_tokens": 6948980.0, |
| "step": 425 |
| }, |
| { |
| "entropy": 0.5203953087329865, |
| "epoch": 1.5895522388059702, |
| "grad_norm": 0.18141059577465057, |
| "learning_rate": 0.0002, |
| "loss": 0.5299071669578552, |
| "mean_token_accuracy": 0.784531980752945, |
| "num_tokens": 6965149.0, |
| "step": 426 |
| }, |
| { |
| "entropy": 0.5436441600322723, |
| "epoch": 1.5932835820895521, |
| "grad_norm": 0.18633973598480225, |
| "learning_rate": 0.0002, |
| "loss": 0.5423316955566406, |
| "mean_token_accuracy": 0.7788860648870468, |
| "num_tokens": 6981508.0, |
| "step": 427 |
| }, |
| { |
| "entropy": 0.5343156158924103, |
| "epoch": 1.5970149253731343, |
| "grad_norm": 0.14471854269504547, |
| "learning_rate": 0.0002, |
| "loss": 0.5336286425590515, |
| "mean_token_accuracy": 0.7826142609119415, |
| "num_tokens": 6997863.0, |
| "step": 428 |
| }, |
| { |
| "entropy": 0.5323745012283325, |
| "epoch": 1.6007462686567164, |
| "grad_norm": 0.15250997245311737, |
| "learning_rate": 0.0002, |
| "loss": 0.5297402739524841, |
| "mean_token_accuracy": 0.7861441671848297, |
| "num_tokens": 7014123.0, |
| "step": 429 |
| }, |
| { |
| "entropy": 0.5268867313861847, |
| "epoch": 1.6044776119402986, |
| "grad_norm": 0.11837883293628693, |
| "learning_rate": 0.0002, |
| "loss": 0.5201472640037537, |
| "mean_token_accuracy": 0.7883018255233765, |
| "num_tokens": 7030343.0, |
| "step": 430 |
| }, |
| { |
| "entropy": 0.5492458641529083, |
| "epoch": 1.6082089552238807, |
| "grad_norm": 0.14543312788009644, |
| "learning_rate": 0.0002, |
| "loss": 0.5491319894790649, |
| "mean_token_accuracy": 0.7765375375747681, |
| "num_tokens": 7046798.0, |
| "step": 431 |
| }, |
| { |
| "entropy": 0.5376308560371399, |
| "epoch": 1.6119402985074627, |
| "grad_norm": 0.13925957679748535, |
| "learning_rate": 0.0002, |
| "loss": 0.5396914482116699, |
| "mean_token_accuracy": 0.7817218601703644, |
| "num_tokens": 7063145.0, |
| "step": 432 |
| }, |
| { |
| "entropy": 0.5356453359127045, |
| "epoch": 1.6156716417910446, |
| "grad_norm": 0.1521977186203003, |
| "learning_rate": 0.0002, |
| "loss": 0.5444437265396118, |
| "mean_token_accuracy": 0.7794919908046722, |
| "num_tokens": 7079368.0, |
| "step": 433 |
| }, |
| { |
| "entropy": 0.5201334357261658, |
| "epoch": 1.6194029850746268, |
| "grad_norm": 0.15561066567897797, |
| "learning_rate": 0.0002, |
| "loss": 0.5289233326911926, |
| "mean_token_accuracy": 0.784171000123024, |
| "num_tokens": 7095616.0, |
| "step": 434 |
| }, |
| { |
| "entropy": 0.5571893453598022, |
| "epoch": 1.623134328358209, |
| "grad_norm": 0.1300196349620819, |
| "learning_rate": 0.0002, |
| "loss": 0.555545449256897, |
| "mean_token_accuracy": 0.775547206401825, |
| "num_tokens": 7111874.0, |
| "step": 435 |
| }, |
| { |
| "entropy": 0.5312858074903488, |
| "epoch": 1.626865671641791, |
| "grad_norm": 0.1330934464931488, |
| "learning_rate": 0.0002, |
| "loss": 0.5261718034744263, |
| "mean_token_accuracy": 0.786922961473465, |
| "num_tokens": 7128145.0, |
| "step": 436 |
| }, |
| { |
| "entropy": 0.5281410962343216, |
| "epoch": 1.6305970149253732, |
| "grad_norm": 0.14317038655281067, |
| "learning_rate": 0.0002, |
| "loss": 0.5306646823883057, |
| "mean_token_accuracy": 0.7834247648715973, |
| "num_tokens": 7144132.0, |
| "step": 437 |
| }, |
| { |
| "entropy": 0.5431696772575378, |
| "epoch": 1.6343283582089554, |
| "grad_norm": 0.13157254457473755, |
| "learning_rate": 0.0002, |
| "loss": 0.5454980731010437, |
| "mean_token_accuracy": 0.777852326631546, |
| "num_tokens": 7160608.0, |
| "step": 438 |
| }, |
| { |
| "entropy": 0.5354062467813492, |
| "epoch": 1.6380597014925373, |
| "grad_norm": 0.13746564090251923, |
| "learning_rate": 0.0002, |
| "loss": 0.5435372591018677, |
| "mean_token_accuracy": 0.7808448374271393, |
| "num_tokens": 7177069.0, |
| "step": 439 |
| }, |
| { |
| "entropy": 0.5201321840286255, |
| "epoch": 1.6417910447761193, |
| "grad_norm": 0.1284942626953125, |
| "learning_rate": 0.0002, |
| "loss": 0.5289615392684937, |
| "mean_token_accuracy": 0.7847140729427338, |
| "num_tokens": 7193361.0, |
| "step": 440 |
| }, |
| { |
| "entropy": 0.5350640714168549, |
| "epoch": 1.6455223880597014, |
| "grad_norm": 0.1171712875366211, |
| "learning_rate": 0.0002, |
| "loss": 0.5357374548912048, |
| "mean_token_accuracy": 0.7836005985736847, |
| "num_tokens": 7209654.0, |
| "step": 441 |
| }, |
| { |
| "entropy": 0.5668849945068359, |
| "epoch": 1.6492537313432836, |
| "grad_norm": 0.13492390513420105, |
| "learning_rate": 0.0002, |
| "loss": 0.5561244487762451, |
| "mean_token_accuracy": 0.7765070199966431, |
| "num_tokens": 7226064.0, |
| "step": 442 |
| }, |
| { |
| "entropy": 0.5396825820207596, |
| "epoch": 1.6529850746268657, |
| "grad_norm": 0.12974844872951508, |
| "learning_rate": 0.0002, |
| "loss": 0.537752628326416, |
| "mean_token_accuracy": 0.7787812352180481, |
| "num_tokens": 7242367.0, |
| "step": 443 |
| }, |
| { |
| "entropy": 0.5502779334783554, |
| "epoch": 1.6567164179104479, |
| "grad_norm": 0.12517166137695312, |
| "learning_rate": 0.0002, |
| "loss": 0.5454338788986206, |
| "mean_token_accuracy": 0.7793845534324646, |
| "num_tokens": 7258783.0, |
| "step": 444 |
| }, |
| { |
| "entropy": 0.5294174402952194, |
| "epoch": 1.6604477611940298, |
| "grad_norm": 0.13836665451526642, |
| "learning_rate": 0.0002, |
| "loss": 0.5331920981407166, |
| "mean_token_accuracy": 0.7824013829231262, |
| "num_tokens": 7274967.0, |
| "step": 445 |
| }, |
| { |
| "entropy": 0.5410277545452118, |
| "epoch": 1.664179104477612, |
| "grad_norm": 0.1432313323020935, |
| "learning_rate": 0.0002, |
| "loss": 0.5498407483100891, |
| "mean_token_accuracy": 0.7790577262639999, |
| "num_tokens": 7291356.0, |
| "step": 446 |
| }, |
| { |
| "entropy": 0.539034441113472, |
| "epoch": 1.667910447761194, |
| "grad_norm": 0.1445050835609436, |
| "learning_rate": 0.0002, |
| "loss": 0.5430982708930969, |
| "mean_token_accuracy": 0.7781680226325989, |
| "num_tokens": 7307779.0, |
| "step": 447 |
| }, |
| { |
| "entropy": 0.55336594581604, |
| "epoch": 1.671641791044776, |
| "grad_norm": 0.13109669089317322, |
| "learning_rate": 0.0002, |
| "loss": 0.5499248504638672, |
| "mean_token_accuracy": 0.776648998260498, |
| "num_tokens": 7324273.0, |
| "step": 448 |
| }, |
| { |
| "entropy": 0.5568288266658783, |
| "epoch": 1.6753731343283582, |
| "grad_norm": 0.14090794324874878, |
| "learning_rate": 0.0002, |
| "loss": 0.5547531247138977, |
| "mean_token_accuracy": 0.7766285985708237, |
| "num_tokens": 7340593.0, |
| "step": 449 |
| }, |
| { |
| "entropy": 0.5353512465953827, |
| "epoch": 1.6791044776119404, |
| "grad_norm": 0.1307251751422882, |
| "learning_rate": 0.0002, |
| "loss": 0.5386269688606262, |
| "mean_token_accuracy": 0.7805867791175842, |
| "num_tokens": 7356753.0, |
| "step": 450 |
| }, |
| { |
| "entropy": 0.5661828964948654, |
| "epoch": 1.6828358208955225, |
| "grad_norm": 0.11857535690069199, |
| "learning_rate": 0.0002, |
| "loss": 0.5659854412078857, |
| "mean_token_accuracy": 0.77124984562397, |
| "num_tokens": 7373256.0, |
| "step": 451 |
| }, |
| { |
| "entropy": 0.5539843142032623, |
| "epoch": 1.6865671641791045, |
| "grad_norm": 0.14917944371700287, |
| "learning_rate": 0.0002, |
| "loss": 0.5583715438842773, |
| "mean_token_accuracy": 0.7743902951478958, |
| "num_tokens": 7389489.0, |
| "step": 452 |
| }, |
| { |
| "entropy": 0.5351207703351974, |
| "epoch": 1.6902985074626866, |
| "grad_norm": 0.14221763610839844, |
| "learning_rate": 0.0002, |
| "loss": 0.5404794812202454, |
| "mean_token_accuracy": 0.7832664251327515, |
| "num_tokens": 7406229.0, |
| "step": 453 |
| }, |
| { |
| "entropy": 0.5356936901807785, |
| "epoch": 1.6940298507462686, |
| "grad_norm": 0.12946124374866486, |
| "learning_rate": 0.0002, |
| "loss": 0.5352929830551147, |
| "mean_token_accuracy": 0.7790337800979614, |
| "num_tokens": 7422650.0, |
| "step": 454 |
| }, |
| { |
| "entropy": 0.5387227535247803, |
| "epoch": 1.6977611940298507, |
| "grad_norm": 0.11507748067378998, |
| "learning_rate": 0.0002, |
| "loss": 0.5424814224243164, |
| "mean_token_accuracy": 0.7787957936525345, |
| "num_tokens": 7439177.0, |
| "step": 455 |
| }, |
| { |
| "entropy": 0.549864336848259, |
| "epoch": 1.7014925373134329, |
| "grad_norm": 0.14885613322257996, |
| "learning_rate": 0.0002, |
| "loss": 0.5519541501998901, |
| "mean_token_accuracy": 0.7762247025966644, |
| "num_tokens": 7455565.0, |
| "step": 456 |
| }, |
| { |
| "entropy": 0.5486273765563965, |
| "epoch": 1.705223880597015, |
| "grad_norm": 0.15473784506320953, |
| "learning_rate": 0.0002, |
| "loss": 0.5463945865631104, |
| "mean_token_accuracy": 0.7785002291202545, |
| "num_tokens": 7471822.0, |
| "step": 457 |
| }, |
| { |
| "entropy": 0.5466701537370682, |
| "epoch": 1.7089552238805972, |
| "grad_norm": 0.1299288123846054, |
| "learning_rate": 0.0002, |
| "loss": 0.5443429350852966, |
| "mean_token_accuracy": 0.7762390524148941, |
| "num_tokens": 7488133.0, |
| "step": 458 |
| }, |
| { |
| "entropy": 0.5391920059919357, |
| "epoch": 1.712686567164179, |
| "grad_norm": 0.14679183065891266, |
| "learning_rate": 0.0002, |
| "loss": 0.5397407412528992, |
| "mean_token_accuracy": 0.7831064164638519, |
| "num_tokens": 7504230.0, |
| "step": 459 |
| }, |
| { |
| "entropy": 0.5521973818540573, |
| "epoch": 1.716417910447761, |
| "grad_norm": 0.1218586266040802, |
| "learning_rate": 0.0002, |
| "loss": 0.5458081364631653, |
| "mean_token_accuracy": 0.7785947620868683, |
| "num_tokens": 7520842.0, |
| "step": 460 |
| }, |
| { |
| "entropy": 0.5177743285894394, |
| "epoch": 1.7201492537313432, |
| "grad_norm": 0.14107051491737366, |
| "learning_rate": 0.0002, |
| "loss": 0.5207897424697876, |
| "mean_token_accuracy": 0.786453366279602, |
| "num_tokens": 7537369.0, |
| "step": 461 |
| }, |
| { |
| "entropy": 0.515509620308876, |
| "epoch": 1.7238805970149254, |
| "grad_norm": 0.1282530128955841, |
| "learning_rate": 0.0002, |
| "loss": 0.5195788741111755, |
| "mean_token_accuracy": 0.7888242304325104, |
| "num_tokens": 7553604.0, |
| "step": 462 |
| }, |
| { |
| "entropy": 0.5109505727887154, |
| "epoch": 1.7276119402985075, |
| "grad_norm": 0.1323649287223816, |
| "learning_rate": 0.0002, |
| "loss": 0.5134848952293396, |
| "mean_token_accuracy": 0.789066269993782, |
| "num_tokens": 7569940.0, |
| "step": 463 |
| }, |
| { |
| "entropy": 0.5281020551919937, |
| "epoch": 1.7313432835820897, |
| "grad_norm": 0.12885527312755585, |
| "learning_rate": 0.0002, |
| "loss": 0.5273661017417908, |
| "mean_token_accuracy": 0.789619505405426, |
| "num_tokens": 7586233.0, |
| "step": 464 |
| }, |
| { |
| "entropy": 0.5342904329299927, |
| "epoch": 1.7350746268656716, |
| "grad_norm": 0.12585751712322235, |
| "learning_rate": 0.0002, |
| "loss": 0.5354442000389099, |
| "mean_token_accuracy": 0.7830105870962143, |
| "num_tokens": 7602674.0, |
| "step": 465 |
| }, |
| { |
| "entropy": 0.543620765209198, |
| "epoch": 1.7388059701492538, |
| "grad_norm": 0.15376721322536469, |
| "learning_rate": 0.0002, |
| "loss": 0.5442280769348145, |
| "mean_token_accuracy": 0.780307799577713, |
| "num_tokens": 7618748.0, |
| "step": 466 |
| }, |
| { |
| "entropy": 0.5452436953783035, |
| "epoch": 1.7425373134328357, |
| "grad_norm": 0.12279915064573288, |
| "learning_rate": 0.0002, |
| "loss": 0.5382248163223267, |
| "mean_token_accuracy": 0.7808591425418854, |
| "num_tokens": 7635224.0, |
| "step": 467 |
| }, |
| { |
| "entropy": 0.5412160456180573, |
| "epoch": 1.7462686567164178, |
| "grad_norm": 0.1339152455329895, |
| "learning_rate": 0.0002, |
| "loss": 0.5462720990180969, |
| "mean_token_accuracy": 0.7800054550170898, |
| "num_tokens": 7651597.0, |
| "step": 468 |
| }, |
| { |
| "entropy": 0.5364412665367126, |
| "epoch": 1.75, |
| "grad_norm": 0.14334280788898468, |
| "learning_rate": 0.0002, |
| "loss": 0.5434943437576294, |
| "mean_token_accuracy": 0.779253676533699, |
| "num_tokens": 7668155.0, |
| "step": 469 |
| }, |
| { |
| "entropy": 0.5545109361410141, |
| "epoch": 1.7537313432835822, |
| "grad_norm": 0.15890227258205414, |
| "learning_rate": 0.0002, |
| "loss": 0.5469630360603333, |
| "mean_token_accuracy": 0.7731442898511887, |
| "num_tokens": 7684818.0, |
| "step": 470 |
| }, |
| { |
| "entropy": 0.5490809381008148, |
| "epoch": 1.7574626865671643, |
| "grad_norm": 0.13309617340564728, |
| "learning_rate": 0.0002, |
| "loss": 0.5500892996788025, |
| "mean_token_accuracy": 0.7770658880472183, |
| "num_tokens": 7701219.0, |
| "step": 471 |
| }, |
| { |
| "entropy": 0.5305235236883163, |
| "epoch": 1.7611940298507462, |
| "grad_norm": 0.16258549690246582, |
| "learning_rate": 0.0002, |
| "loss": 0.5388149619102478, |
| "mean_token_accuracy": 0.7829635441303253, |
| "num_tokens": 7717582.0, |
| "step": 472 |
| }, |
| { |
| "entropy": 0.5585267692804337, |
| "epoch": 1.7649253731343284, |
| "grad_norm": 0.11873357743024826, |
| "learning_rate": 0.0002, |
| "loss": 0.5577584505081177, |
| "mean_token_accuracy": 0.7762050777673721, |
| "num_tokens": 7734324.0, |
| "step": 473 |
| }, |
| { |
| "entropy": 0.5489350706338882, |
| "epoch": 1.7686567164179103, |
| "grad_norm": 0.12332171201705933, |
| "learning_rate": 0.0002, |
| "loss": 0.5449402332305908, |
| "mean_token_accuracy": 0.7781216353178024, |
| "num_tokens": 7750752.0, |
| "step": 474 |
| }, |
| { |
| "entropy": 0.5424219220876694, |
| "epoch": 1.7723880597014925, |
| "grad_norm": 0.14421363174915314, |
| "learning_rate": 0.0002, |
| "loss": 0.5385311841964722, |
| "mean_token_accuracy": 0.7787967473268509, |
| "num_tokens": 7767226.0, |
| "step": 475 |
| }, |
| { |
| "entropy": 0.5521616637706757, |
| "epoch": 1.7761194029850746, |
| "grad_norm": 0.1186925396323204, |
| "learning_rate": 0.0002, |
| "loss": 0.5526041984558105, |
| "mean_token_accuracy": 0.7767607420682907, |
| "num_tokens": 7783682.0, |
| "step": 476 |
| }, |
| { |
| "entropy": 0.5158545449376106, |
| "epoch": 1.7798507462686568, |
| "grad_norm": 0.18216553330421448, |
| "learning_rate": 0.0002, |
| "loss": 0.5199044942855835, |
| "mean_token_accuracy": 0.7856768816709518, |
| "num_tokens": 7800030.0, |
| "step": 477 |
| }, |
| { |
| "entropy": 0.5443078428506851, |
| "epoch": 1.783582089552239, |
| "grad_norm": 0.14375311136245728, |
| "learning_rate": 0.0002, |
| "loss": 0.5509768724441528, |
| "mean_token_accuracy": 0.775581955909729, |
| "num_tokens": 7816522.0, |
| "step": 478 |
| }, |
| { |
| "entropy": 0.5413143634796143, |
| "epoch": 1.787313432835821, |
| "grad_norm": 0.18410946428775787, |
| "learning_rate": 0.0002, |
| "loss": 0.5492492914199829, |
| "mean_token_accuracy": 0.7783028930425644, |
| "num_tokens": 7832550.0, |
| "step": 479 |
| }, |
| { |
| "entropy": 0.5406689345836639, |
| "epoch": 1.7910447761194028, |
| "grad_norm": 0.14112934470176697, |
| "learning_rate": 0.0002, |
| "loss": 0.5439832806587219, |
| "mean_token_accuracy": 0.779539629817009, |
| "num_tokens": 7848776.0, |
| "step": 480 |
| }, |
| { |
| "entropy": 0.5413185209035873, |
| "epoch": 1.794776119402985, |
| "grad_norm": 0.15361003577709198, |
| "learning_rate": 0.0002, |
| "loss": 0.5352233648300171, |
| "mean_token_accuracy": 0.7820680886507034, |
| "num_tokens": 7865105.0, |
| "step": 481 |
| }, |
| { |
| "entropy": 0.5401637256145477, |
| "epoch": 1.7985074626865671, |
| "grad_norm": 0.1404116302728653, |
| "learning_rate": 0.0002, |
| "loss": 0.5335552096366882, |
| "mean_token_accuracy": 0.7834560424089432, |
| "num_tokens": 7881356.0, |
| "step": 482 |
| }, |
| { |
| "entropy": 0.5421462655067444, |
| "epoch": 1.8022388059701493, |
| "grad_norm": 0.13059787452220917, |
| "learning_rate": 0.0002, |
| "loss": 0.5401331782341003, |
| "mean_token_accuracy": 0.7803400605916977, |
| "num_tokens": 7897808.0, |
| "step": 483 |
| }, |
| { |
| "entropy": 0.5413605570793152, |
| "epoch": 1.8059701492537314, |
| "grad_norm": 0.18282194435596466, |
| "learning_rate": 0.0002, |
| "loss": 0.5493237376213074, |
| "mean_token_accuracy": 0.7789726853370667, |
| "num_tokens": 7914142.0, |
| "step": 484 |
| }, |
| { |
| "entropy": 0.5435532331466675, |
| "epoch": 1.8097014925373134, |
| "grad_norm": 0.13297522068023682, |
| "learning_rate": 0.0002, |
| "loss": 0.5454325675964355, |
| "mean_token_accuracy": 0.7815843522548676, |
| "num_tokens": 7930683.0, |
| "step": 485 |
| }, |
| { |
| "entropy": 0.5448514670133591, |
| "epoch": 1.8134328358208955, |
| "grad_norm": 0.17432713508605957, |
| "learning_rate": 0.0002, |
| "loss": 0.556286096572876, |
| "mean_token_accuracy": 0.7757316827774048, |
| "num_tokens": 7947064.0, |
| "step": 486 |
| }, |
| { |
| "entropy": 0.5413680523633957, |
| "epoch": 1.8171641791044775, |
| "grad_norm": 0.16253697872161865, |
| "learning_rate": 0.0002, |
| "loss": 0.5410704016685486, |
| "mean_token_accuracy": 0.7813205868005753, |
| "num_tokens": 7963261.0, |
| "step": 487 |
| }, |
| { |
| "entropy": 0.5359946191310883, |
| "epoch": 1.8208955223880596, |
| "grad_norm": 0.12221310287714005, |
| "learning_rate": 0.0002, |
| "loss": 0.5314027667045593, |
| "mean_token_accuracy": 0.7841240018606186, |
| "num_tokens": 7979773.0, |
| "step": 488 |
| }, |
| { |
| "entropy": 0.5420530661940575, |
| "epoch": 1.8246268656716418, |
| "grad_norm": 0.15669137239456177, |
| "learning_rate": 0.0002, |
| "loss": 0.5438501834869385, |
| "mean_token_accuracy": 0.7811977416276932, |
| "num_tokens": 7995987.0, |
| "step": 489 |
| }, |
| { |
| "entropy": 0.5264635682106018, |
| "epoch": 1.828358208955224, |
| "grad_norm": 0.1370009481906891, |
| "learning_rate": 0.0002, |
| "loss": 0.52957683801651, |
| "mean_token_accuracy": 0.7815753519535065, |
| "num_tokens": 8012440.0, |
| "step": 490 |
| }, |
| { |
| "entropy": 0.5173354893922806, |
| "epoch": 1.832089552238806, |
| "grad_norm": 0.13682052493095398, |
| "learning_rate": 0.0002, |
| "loss": 0.5175887942314148, |
| "mean_token_accuracy": 0.7895816564559937, |
| "num_tokens": 8028910.0, |
| "step": 491 |
| }, |
| { |
| "entropy": 0.5401716083288193, |
| "epoch": 1.835820895522388, |
| "grad_norm": 0.15775182843208313, |
| "learning_rate": 0.0002, |
| "loss": 0.5398913621902466, |
| "mean_token_accuracy": 0.7796313166618347, |
| "num_tokens": 8045307.0, |
| "step": 492 |
| }, |
| { |
| "entropy": 0.531095527112484, |
| "epoch": 1.8395522388059702, |
| "grad_norm": 0.1412198394536972, |
| "learning_rate": 0.0002, |
| "loss": 0.5365026593208313, |
| "mean_token_accuracy": 0.7815003246068954, |
| "num_tokens": 8061629.0, |
| "step": 493 |
| }, |
| { |
| "entropy": 0.528749480843544, |
| "epoch": 1.8432835820895521, |
| "grad_norm": 0.1595659852027893, |
| "learning_rate": 0.0002, |
| "loss": 0.5356355905532837, |
| "mean_token_accuracy": 0.7825777232646942, |
| "num_tokens": 8078090.0, |
| "step": 494 |
| }, |
| { |
| "entropy": 0.5317548662424088, |
| "epoch": 1.8470149253731343, |
| "grad_norm": 0.166373610496521, |
| "learning_rate": 0.0002, |
| "loss": 0.5332224369049072, |
| "mean_token_accuracy": 0.7848176658153534, |
| "num_tokens": 8094140.0, |
| "step": 495 |
| }, |
| { |
| "entropy": 0.5490619540214539, |
| "epoch": 1.8507462686567164, |
| "grad_norm": 0.13089962303638458, |
| "learning_rate": 0.0002, |
| "loss": 0.5390321612358093, |
| "mean_token_accuracy": 0.7814900130033493, |
| "num_tokens": 8110622.0, |
| "step": 496 |
| }, |
| { |
| "entropy": 0.5394901782274246, |
| "epoch": 1.8544776119402986, |
| "grad_norm": 0.11591363698244095, |
| "learning_rate": 0.0002, |
| "loss": 0.5375248193740845, |
| "mean_token_accuracy": 0.7814390808343887, |
| "num_tokens": 8126876.0, |
| "step": 497 |
| }, |
| { |
| "entropy": 0.5381087958812714, |
| "epoch": 1.8582089552238807, |
| "grad_norm": 0.1456560492515564, |
| "learning_rate": 0.0002, |
| "loss": 0.5411711931228638, |
| "mean_token_accuracy": 0.7816133350133896, |
| "num_tokens": 8143274.0, |
| "step": 498 |
| }, |
| { |
| "entropy": 0.5220907032489777, |
| "epoch": 1.8619402985074627, |
| "grad_norm": 0.13956928253173828, |
| "learning_rate": 0.0002, |
| "loss": 0.523941159248352, |
| "mean_token_accuracy": 0.784881204366684, |
| "num_tokens": 8159277.0, |
| "step": 499 |
| }, |
| { |
| "entropy": 0.5485254973173141, |
| "epoch": 1.8656716417910446, |
| "grad_norm": 0.14179295301437378, |
| "learning_rate": 0.0002, |
| "loss": 0.5531203150749207, |
| "mean_token_accuracy": 0.7753941714763641, |
| "num_tokens": 8175748.0, |
| "step": 500 |
| }, |
| { |
| "entropy": 0.5228838473558426, |
| "epoch": 1.8694029850746268, |
| "grad_norm": 0.13817176222801208, |
| "learning_rate": 0.0002, |
| "loss": 0.5194221138954163, |
| "mean_token_accuracy": 0.7881438136100769, |
| "num_tokens": 8192024.0, |
| "step": 501 |
| }, |
| { |
| "entropy": 0.5568139851093292, |
| "epoch": 1.873134328358209, |
| "grad_norm": 0.12931230664253235, |
| "learning_rate": 0.0002, |
| "loss": 0.556110143661499, |
| "mean_token_accuracy": 0.7763972878456116, |
| "num_tokens": 8208619.0, |
| "step": 502 |
| }, |
| { |
| "entropy": 0.5371456891298294, |
| "epoch": 1.876865671641791, |
| "grad_norm": 0.1403176635503769, |
| "learning_rate": 0.0002, |
| "loss": 0.5337600111961365, |
| "mean_token_accuracy": 0.7836433202028275, |
| "num_tokens": 8225153.0, |
| "step": 503 |
| }, |
| { |
| "entropy": 0.5494351089000702, |
| "epoch": 1.8805970149253732, |
| "grad_norm": 0.13375559449195862, |
| "learning_rate": 0.0002, |
| "loss": 0.5488487482070923, |
| "mean_token_accuracy": 0.7738263159990311, |
| "num_tokens": 8241540.0, |
| "step": 504 |
| }, |
| { |
| "entropy": 0.5478385984897614, |
| "epoch": 1.8843283582089554, |
| "grad_norm": 0.1508444994688034, |
| "learning_rate": 0.0002, |
| "loss": 0.5490124225616455, |
| "mean_token_accuracy": 0.7773222625255585, |
| "num_tokens": 8258088.0, |
| "step": 505 |
| }, |
| { |
| "entropy": 0.5380401015281677, |
| "epoch": 1.8880597014925373, |
| "grad_norm": 0.16321228444576263, |
| "learning_rate": 0.0002, |
| "loss": 0.5464720726013184, |
| "mean_token_accuracy": 0.7815645039081573, |
| "num_tokens": 8274722.0, |
| "step": 506 |
| }, |
| { |
| "entropy": 0.5183184295892715, |
| "epoch": 1.8917910447761193, |
| "grad_norm": 0.1558491438627243, |
| "learning_rate": 0.0002, |
| "loss": 0.53003990650177, |
| "mean_token_accuracy": 0.7835704982280731, |
| "num_tokens": 8290836.0, |
| "step": 507 |
| }, |
| { |
| "entropy": 0.5319181531667709, |
| "epoch": 1.8955223880597014, |
| "grad_norm": 0.15235044062137604, |
| "learning_rate": 0.0002, |
| "loss": 0.5381399393081665, |
| "mean_token_accuracy": 0.7818045765161514, |
| "num_tokens": 8307219.0, |
| "step": 508 |
| }, |
| { |
| "entropy": 0.5494637489318848, |
| "epoch": 1.8992537313432836, |
| "grad_norm": 0.13539130985736847, |
| "learning_rate": 0.0002, |
| "loss": 0.5432940721511841, |
| "mean_token_accuracy": 0.779973179101944, |
| "num_tokens": 8323506.0, |
| "step": 509 |
| }, |
| { |
| "entropy": 0.5507510900497437, |
| "epoch": 1.9029850746268657, |
| "grad_norm": 0.13247814774513245, |
| "learning_rate": 0.0002, |
| "loss": 0.5390299558639526, |
| "mean_token_accuracy": 0.7806130647659302, |
| "num_tokens": 8340032.0, |
| "step": 510 |
| }, |
| { |
| "entropy": 0.5482463240623474, |
| "epoch": 1.9067164179104479, |
| "grad_norm": 0.11802904307842255, |
| "learning_rate": 0.0002, |
| "loss": 0.5383414030075073, |
| "mean_token_accuracy": 0.7824697196483612, |
| "num_tokens": 8356588.0, |
| "step": 511 |
| }, |
| { |
| "entropy": 0.5249346122145653, |
| "epoch": 1.9104477611940298, |
| "grad_norm": 0.13017453253269196, |
| "learning_rate": 0.0002, |
| "loss": 0.5275671482086182, |
| "mean_token_accuracy": 0.7869113087654114, |
| "num_tokens": 8372913.0, |
| "step": 512 |
| }, |
| { |
| "entropy": 0.5295490026473999, |
| "epoch": 1.914179104477612, |
| "grad_norm": 0.1681528389453888, |
| "learning_rate": 0.0002, |
| "loss": 0.5436277389526367, |
| "mean_token_accuracy": 0.7807879447937012, |
| "num_tokens": 8389280.0, |
| "step": 513 |
| }, |
| { |
| "entropy": 0.5379057079553604, |
| "epoch": 1.917910447761194, |
| "grad_norm": 0.1375591903924942, |
| "learning_rate": 0.0002, |
| "loss": 0.549224853515625, |
| "mean_token_accuracy": 0.7795612812042236, |
| "num_tokens": 8405794.0, |
| "step": 514 |
| }, |
| { |
| "entropy": 0.5255391150712967, |
| "epoch": 1.921641791044776, |
| "grad_norm": 0.14476200938224792, |
| "learning_rate": 0.0002, |
| "loss": 0.5203375220298767, |
| "mean_token_accuracy": 0.7901246547698975, |
| "num_tokens": 8422115.0, |
| "step": 515 |
| }, |
| { |
| "entropy": 0.5440230965614319, |
| "epoch": 1.9253731343283582, |
| "grad_norm": 0.13710729777812958, |
| "learning_rate": 0.0002, |
| "loss": 0.5400455594062805, |
| "mean_token_accuracy": 0.7826576679944992, |
| "num_tokens": 8438475.0, |
| "step": 516 |
| }, |
| { |
| "entropy": 0.5594098567962646, |
| "epoch": 1.9291044776119404, |
| "grad_norm": 0.15048064291477203, |
| "learning_rate": 0.0002, |
| "loss": 0.5556347966194153, |
| "mean_token_accuracy": 0.775066465139389, |
| "num_tokens": 8455137.0, |
| "step": 517 |
| }, |
| { |
| "entropy": 0.5417518466711044, |
| "epoch": 1.9328358208955225, |
| "grad_norm": 0.11550929397344589, |
| "learning_rate": 0.0002, |
| "loss": 0.537165105342865, |
| "mean_token_accuracy": 0.7795901298522949, |
| "num_tokens": 8471783.0, |
| "step": 518 |
| }, |
| { |
| "entropy": 0.5307828038930893, |
| "epoch": 1.9365671641791045, |
| "grad_norm": 0.1507074385881424, |
| "learning_rate": 0.0002, |
| "loss": 0.5322086811065674, |
| "mean_token_accuracy": 0.7824592143297195, |
| "num_tokens": 8488077.0, |
| "step": 519 |
| }, |
| { |
| "entropy": 0.5303423702716827, |
| "epoch": 1.9402985074626866, |
| "grad_norm": 0.14603017270565033, |
| "learning_rate": 0.0002, |
| "loss": 0.5419748425483704, |
| "mean_token_accuracy": 0.7797867804765701, |
| "num_tokens": 8504575.0, |
| "step": 520 |
| }, |
| { |
| "entropy": 0.5456606447696686, |
| "epoch": 1.9440298507462686, |
| "grad_norm": 0.13237862288951874, |
| "learning_rate": 0.0002, |
| "loss": 0.5428569316864014, |
| "mean_token_accuracy": 0.7818800657987595, |
| "num_tokens": 8520967.0, |
| "step": 521 |
| }, |
| { |
| "entropy": 0.5310875177383423, |
| "epoch": 1.9477611940298507, |
| "grad_norm": 0.13525272905826569, |
| "learning_rate": 0.0002, |
| "loss": 0.5283735990524292, |
| "mean_token_accuracy": 0.786258190870285, |
| "num_tokens": 8537319.0, |
| "step": 522 |
| }, |
| { |
| "entropy": 0.5379719585180283, |
| "epoch": 1.9514925373134329, |
| "grad_norm": 0.15432380139827728, |
| "learning_rate": 0.0002, |
| "loss": 0.5408097505569458, |
| "mean_token_accuracy": 0.7781657874584198, |
| "num_tokens": 8553448.0, |
| "step": 523 |
| }, |
| { |
| "entropy": 0.5481258481740952, |
| "epoch": 1.955223880597015, |
| "grad_norm": 0.12797947227954865, |
| "learning_rate": 0.0002, |
| "loss": 0.5464990735054016, |
| "mean_token_accuracy": 0.778485506772995, |
| "num_tokens": 8570325.0, |
| "step": 524 |
| }, |
| { |
| "entropy": 0.5342290997505188, |
| "epoch": 1.9589552238805972, |
| "grad_norm": 0.16300323605537415, |
| "learning_rate": 0.0002, |
| "loss": 0.5419365763664246, |
| "mean_token_accuracy": 0.7765484899282455, |
| "num_tokens": 8586528.0, |
| "step": 525 |
| }, |
| { |
| "entropy": 0.5183306038379669, |
| "epoch": 1.962686567164179, |
| "grad_norm": 0.1349683552980423, |
| "learning_rate": 0.0002, |
| "loss": 0.5252315402030945, |
| "mean_token_accuracy": 0.7851862013339996, |
| "num_tokens": 8602731.0, |
| "step": 526 |
| }, |
| { |
| "entropy": 0.5346875190734863, |
| "epoch": 1.966417910447761, |
| "grad_norm": 0.15960031747817993, |
| "learning_rate": 0.0002, |
| "loss": 0.5396409034729004, |
| "mean_token_accuracy": 0.7812920063734055, |
| "num_tokens": 8619025.0, |
| "step": 527 |
| }, |
| { |
| "entropy": 0.5321638286113739, |
| "epoch": 1.9701492537313432, |
| "grad_norm": 0.12743237614631653, |
| "learning_rate": 0.0002, |
| "loss": 0.5324144959449768, |
| "mean_token_accuracy": 0.7834001034498215, |
| "num_tokens": 8635321.0, |
| "step": 528 |
| }, |
| { |
| "entropy": 0.5459233373403549, |
| "epoch": 1.9738805970149254, |
| "grad_norm": 0.15017178654670715, |
| "learning_rate": 0.0002, |
| "loss": 0.5493046045303345, |
| "mean_token_accuracy": 0.7773318439722061, |
| "num_tokens": 8651440.0, |
| "step": 529 |
| }, |
| { |
| "entropy": 0.5471896231174469, |
| "epoch": 1.9776119402985075, |
| "grad_norm": 0.1409200131893158, |
| "learning_rate": 0.0002, |
| "loss": 0.5477155447006226, |
| "mean_token_accuracy": 0.7782939076423645, |
| "num_tokens": 8667677.0, |
| "step": 530 |
| }, |
| { |
| "entropy": 0.54158616065979, |
| "epoch": 1.9813432835820897, |
| "grad_norm": 0.15108433365821838, |
| "learning_rate": 0.0002, |
| "loss": 0.5398797988891602, |
| "mean_token_accuracy": 0.780155286192894, |
| "num_tokens": 8684082.0, |
| "step": 531 |
| }, |
| { |
| "entropy": 0.559661254286766, |
| "epoch": 1.9850746268656716, |
| "grad_norm": 0.16502220928668976, |
| "learning_rate": 0.0002, |
| "loss": 0.560107946395874, |
| "mean_token_accuracy": 0.7700088769197464, |
| "num_tokens": 8700430.0, |
| "step": 532 |
| }, |
| { |
| "entropy": 0.5411800444126129, |
| "epoch": 1.9888059701492538, |
| "grad_norm": 0.16169190406799316, |
| "learning_rate": 0.0002, |
| "loss": 0.5391537547111511, |
| "mean_token_accuracy": 0.7833402901887894, |
| "num_tokens": 8716668.0, |
| "step": 533 |
| }, |
| { |
| "entropy": 0.5470827370882034, |
| "epoch": 1.9925373134328357, |
| "grad_norm": 0.1543496996164322, |
| "learning_rate": 0.0002, |
| "loss": 0.5461235642433167, |
| "mean_token_accuracy": 0.7778415530920029, |
| "num_tokens": 8733026.0, |
| "step": 534 |
| }, |
| { |
| "entropy": 0.5324201732873917, |
| "epoch": 1.9962686567164178, |
| "grad_norm": 0.16016018390655518, |
| "learning_rate": 0.0002, |
| "loss": 0.5389805436134338, |
| "mean_token_accuracy": 0.7803365737199783, |
| "num_tokens": 8749311.0, |
| "step": 535 |
| }, |
| { |
| "entropy": 0.5435256808996201, |
| "epoch": 2.0, |
| "grad_norm": 0.14572884142398834, |
| "learning_rate": 0.0002, |
| "loss": 0.5441113710403442, |
| "mean_token_accuracy": 0.7785479575395584, |
| "num_tokens": 8765777.0, |
| "step": 536 |
| }, |
| { |
| "entropy": 0.5407584756612778, |
| "epoch": 2.003731343283582, |
| "grad_norm": 0.13617859780788422, |
| "learning_rate": 0.0002, |
| "loss": 0.5282794833183289, |
| "mean_token_accuracy": 0.7869160920381546, |
| "num_tokens": 8781980.0, |
| "step": 537 |
| }, |
| { |
| "entropy": 0.5350850969552994, |
| "epoch": 2.0074626865671643, |
| "grad_norm": 0.1447509527206421, |
| "learning_rate": 0.0002, |
| "loss": 0.5275791883468628, |
| "mean_token_accuracy": 0.785736083984375, |
| "num_tokens": 8798371.0, |
| "step": 538 |
| }, |
| { |
| "entropy": 0.51067965477705, |
| "epoch": 2.0111940298507465, |
| "grad_norm": 0.14436857402324677, |
| "learning_rate": 0.0002, |
| "loss": 0.510128378868103, |
| "mean_token_accuracy": 0.7941802889108658, |
| "num_tokens": 8814829.0, |
| "step": 539 |
| }, |
| { |
| "entropy": 0.5066168382763863, |
| "epoch": 2.014925373134328, |
| "grad_norm": 0.20557339489459991, |
| "learning_rate": 0.0002, |
| "loss": 0.5192297697067261, |
| "mean_token_accuracy": 0.7901676893234253, |
| "num_tokens": 8830864.0, |
| "step": 540 |
| }, |
| { |
| "entropy": 0.5086682066321373, |
| "epoch": 2.0186567164179103, |
| "grad_norm": 0.151071235537529, |
| "learning_rate": 0.0002, |
| "loss": 0.5170693397521973, |
| "mean_token_accuracy": 0.7896369844675064, |
| "num_tokens": 8847274.0, |
| "step": 541 |
| }, |
| { |
| "entropy": 0.5096391588449478, |
| "epoch": 2.0223880597014925, |
| "grad_norm": 0.1753709316253662, |
| "learning_rate": 0.0002, |
| "loss": 0.5102881193161011, |
| "mean_token_accuracy": 0.7923690527677536, |
| "num_tokens": 8863512.0, |
| "step": 542 |
| }, |
| { |
| "entropy": 0.5296002924442291, |
| "epoch": 2.0261194029850746, |
| "grad_norm": 0.1462300568819046, |
| "learning_rate": 0.0002, |
| "loss": 0.5223501920700073, |
| "mean_token_accuracy": 0.7873635143041611, |
| "num_tokens": 8879908.0, |
| "step": 543 |
| }, |
| { |
| "entropy": 0.5155584290623665, |
| "epoch": 2.029850746268657, |
| "grad_norm": 0.14320869743824005, |
| "learning_rate": 0.0002, |
| "loss": 0.5057611465454102, |
| "mean_token_accuracy": 0.7949195951223373, |
| "num_tokens": 8896298.0, |
| "step": 544 |
| }, |
| { |
| "entropy": 0.5321292579174042, |
| "epoch": 2.033582089552239, |
| "grad_norm": 0.16136051714420319, |
| "learning_rate": 0.0002, |
| "loss": 0.5260882377624512, |
| "mean_token_accuracy": 0.7870594561100006, |
| "num_tokens": 8912695.0, |
| "step": 545 |
| }, |
| { |
| "entropy": 0.5038010776042938, |
| "epoch": 2.0373134328358207, |
| "grad_norm": 0.14799539744853973, |
| "learning_rate": 0.0002, |
| "loss": 0.5066463947296143, |
| "mean_token_accuracy": 0.7916280180215836, |
| "num_tokens": 8929001.0, |
| "step": 546 |
| }, |
| { |
| "entropy": 0.5048325732350349, |
| "epoch": 2.041044776119403, |
| "grad_norm": 0.1580689251422882, |
| "learning_rate": 0.0002, |
| "loss": 0.5141686201095581, |
| "mean_token_accuracy": 0.7914908081293106, |
| "num_tokens": 8945457.0, |
| "step": 547 |
| }, |
| { |
| "entropy": 0.49788908660411835, |
| "epoch": 2.044776119402985, |
| "grad_norm": 0.14763985574245453, |
| "learning_rate": 0.0002, |
| "loss": 0.5052313208580017, |
| "mean_token_accuracy": 0.7970555871725082, |
| "num_tokens": 8961982.0, |
| "step": 548 |
| }, |
| { |
| "entropy": 0.5149217396974564, |
| "epoch": 2.048507462686567, |
| "grad_norm": 0.14633412659168243, |
| "learning_rate": 0.0002, |
| "loss": 0.5154003500938416, |
| "mean_token_accuracy": 0.7911371290683746, |
| "num_tokens": 8978415.0, |
| "step": 549 |
| }, |
| { |
| "entropy": 0.5206630527973175, |
| "epoch": 2.0522388059701493, |
| "grad_norm": 0.16220484673976898, |
| "learning_rate": 0.0002, |
| "loss": 0.517713725566864, |
| "mean_token_accuracy": 0.790251299738884, |
| "num_tokens": 8994915.0, |
| "step": 550 |
| }, |
| { |
| "entropy": 0.5112492591142654, |
| "epoch": 2.0559701492537314, |
| "grad_norm": 0.14196157455444336, |
| "learning_rate": 0.0002, |
| "loss": 0.5108572840690613, |
| "mean_token_accuracy": 0.7943962514400482, |
| "num_tokens": 9011333.0, |
| "step": 551 |
| }, |
| { |
| "entropy": 0.5131144821643829, |
| "epoch": 2.0597014925373136, |
| "grad_norm": 0.13064007461071014, |
| "learning_rate": 0.0002, |
| "loss": 0.5118117332458496, |
| "mean_token_accuracy": 0.7943043112754822, |
| "num_tokens": 9027587.0, |
| "step": 552 |
| }, |
| { |
| "entropy": 0.501186303794384, |
| "epoch": 2.0634328358208953, |
| "grad_norm": 0.14956530928611755, |
| "learning_rate": 0.0002, |
| "loss": 0.5043509006500244, |
| "mean_token_accuracy": 0.7948697656393051, |
| "num_tokens": 9043894.0, |
| "step": 553 |
| }, |
| { |
| "entropy": 0.5232811272144318, |
| "epoch": 2.0671641791044775, |
| "grad_norm": 0.15405148267745972, |
| "learning_rate": 0.0002, |
| "loss": 0.5297489166259766, |
| "mean_token_accuracy": 0.7905055433511734, |
| "num_tokens": 9060242.0, |
| "step": 554 |
| }, |
| { |
| "entropy": 0.5105090290307999, |
| "epoch": 2.0708955223880596, |
| "grad_norm": 0.14629869163036346, |
| "learning_rate": 0.0002, |
| "loss": 0.5100098848342896, |
| "mean_token_accuracy": 0.7926841229200363, |
| "num_tokens": 9076814.0, |
| "step": 555 |
| }, |
| { |
| "entropy": 0.518320694565773, |
| "epoch": 2.074626865671642, |
| "grad_norm": 0.14312250912189484, |
| "learning_rate": 0.0002, |
| "loss": 0.5099379420280457, |
| "mean_token_accuracy": 0.7933275699615479, |
| "num_tokens": 9092816.0, |
| "step": 556 |
| }, |
| { |
| "entropy": 0.521616593003273, |
| "epoch": 2.078358208955224, |
| "grad_norm": 0.17455337941646576, |
| "learning_rate": 0.0002, |
| "loss": 0.5177799463272095, |
| "mean_token_accuracy": 0.7904378324747086, |
| "num_tokens": 9109206.0, |
| "step": 557 |
| }, |
| { |
| "entropy": 0.5203812420368195, |
| "epoch": 2.082089552238806, |
| "grad_norm": 0.18107342720031738, |
| "learning_rate": 0.0002, |
| "loss": 0.5183897018432617, |
| "mean_token_accuracy": 0.7922575920820236, |
| "num_tokens": 9125950.0, |
| "step": 558 |
| }, |
| { |
| "entropy": 0.5026596710085869, |
| "epoch": 2.0858208955223883, |
| "grad_norm": 0.17266131937503815, |
| "learning_rate": 0.0002, |
| "loss": 0.5088356137275696, |
| "mean_token_accuracy": 0.7916382253170013, |
| "num_tokens": 9142305.0, |
| "step": 559 |
| }, |
| { |
| "entropy": 0.511992484331131, |
| "epoch": 2.08955223880597, |
| "grad_norm": 0.2052612006664276, |
| "learning_rate": 0.0002, |
| "loss": 0.5229610204696655, |
| "mean_token_accuracy": 0.7856646925210953, |
| "num_tokens": 9158606.0, |
| "step": 560 |
| }, |
| { |
| "entropy": 0.5073496028780937, |
| "epoch": 2.093283582089552, |
| "grad_norm": 0.1473969966173172, |
| "learning_rate": 0.0002, |
| "loss": 0.5062639117240906, |
| "mean_token_accuracy": 0.7944897413253784, |
| "num_tokens": 9175124.0, |
| "step": 561 |
| }, |
| { |
| "entropy": 0.5431516319513321, |
| "epoch": 2.0970149253731343, |
| "grad_norm": 0.19707000255584717, |
| "learning_rate": 0.0002, |
| "loss": 0.5428797006607056, |
| "mean_token_accuracy": 0.7825317233800888, |
| "num_tokens": 9191532.0, |
| "step": 562 |
| }, |
| { |
| "entropy": 0.5471702218055725, |
| "epoch": 2.1007462686567164, |
| "grad_norm": 0.18265855312347412, |
| "learning_rate": 0.0002, |
| "loss": 0.5425987839698792, |
| "mean_token_accuracy": 0.7799271047115326, |
| "num_tokens": 9207916.0, |
| "step": 563 |
| }, |
| { |
| "entropy": 0.5444347113370895, |
| "epoch": 2.1044776119402986, |
| "grad_norm": 0.16828271746635437, |
| "learning_rate": 0.0002, |
| "loss": 0.5345572233200073, |
| "mean_token_accuracy": 0.782006174325943, |
| "num_tokens": 9224333.0, |
| "step": 564 |
| }, |
| { |
| "entropy": 0.5277058333158493, |
| "epoch": 2.1082089552238807, |
| "grad_norm": 0.1713986098766327, |
| "learning_rate": 0.0002, |
| "loss": 0.5258783102035522, |
| "mean_token_accuracy": 0.7864782810211182, |
| "num_tokens": 9240798.0, |
| "step": 565 |
| }, |
| { |
| "entropy": 0.5058989822864532, |
| "epoch": 2.111940298507463, |
| "grad_norm": 0.1589066982269287, |
| "learning_rate": 0.0002, |
| "loss": 0.5111018419265747, |
| "mean_token_accuracy": 0.7933597713708878, |
| "num_tokens": 9257202.0, |
| "step": 566 |
| }, |
| { |
| "entropy": 0.5076189562678337, |
| "epoch": 2.1156716417910446, |
| "grad_norm": 0.19917325675487518, |
| "learning_rate": 0.0002, |
| "loss": 0.5177862644195557, |
| "mean_token_accuracy": 0.792441338300705, |
| "num_tokens": 9273939.0, |
| "step": 567 |
| }, |
| { |
| "entropy": 0.508878193795681, |
| "epoch": 2.1194029850746268, |
| "grad_norm": 0.19606716930866241, |
| "learning_rate": 0.0002, |
| "loss": 0.5253061652183533, |
| "mean_token_accuracy": 0.7870957255363464, |
| "num_tokens": 9290296.0, |
| "step": 568 |
| }, |
| { |
| "entropy": 0.5359541177749634, |
| "epoch": 2.123134328358209, |
| "grad_norm": 0.16361179947853088, |
| "learning_rate": 0.0002, |
| "loss": 0.5309543609619141, |
| "mean_token_accuracy": 0.7845293134450912, |
| "num_tokens": 9306839.0, |
| "step": 569 |
| }, |
| { |
| "entropy": 0.5252948701381683, |
| "epoch": 2.126865671641791, |
| "grad_norm": 0.14921948313713074, |
| "learning_rate": 0.0002, |
| "loss": 0.5221210718154907, |
| "mean_token_accuracy": 0.7899912744760513, |
| "num_tokens": 9323010.0, |
| "step": 570 |
| }, |
| { |
| "entropy": 0.5450704097747803, |
| "epoch": 2.1305970149253732, |
| "grad_norm": 0.15373222529888153, |
| "learning_rate": 0.0002, |
| "loss": 0.5332466959953308, |
| "mean_token_accuracy": 0.7840565890073776, |
| "num_tokens": 9339451.0, |
| "step": 571 |
| }, |
| { |
| "entropy": 0.5429719239473343, |
| "epoch": 2.1343283582089554, |
| "grad_norm": 0.19419997930526733, |
| "learning_rate": 0.0002, |
| "loss": 0.5410496592521667, |
| "mean_token_accuracy": 0.7834058254957199, |
| "num_tokens": 9355647.0, |
| "step": 572 |
| }, |
| { |
| "entropy": 0.5368043184280396, |
| "epoch": 2.138059701492537, |
| "grad_norm": 0.15381263196468353, |
| "learning_rate": 0.0002, |
| "loss": 0.5375343561172485, |
| "mean_token_accuracy": 0.7806866466999054, |
| "num_tokens": 9372231.0, |
| "step": 573 |
| }, |
| { |
| "entropy": 0.4968769699335098, |
| "epoch": 2.1417910447761193, |
| "grad_norm": 0.16035689413547516, |
| "learning_rate": 0.0002, |
| "loss": 0.502482533454895, |
| "mean_token_accuracy": 0.797141045331955, |
| "num_tokens": 9388484.0, |
| "step": 574 |
| }, |
| { |
| "entropy": 0.5311544984579086, |
| "epoch": 2.1455223880597014, |
| "grad_norm": 0.17108048498630524, |
| "learning_rate": 0.0002, |
| "loss": 0.5366680026054382, |
| "mean_token_accuracy": 0.7843577861785889, |
| "num_tokens": 9404966.0, |
| "step": 575 |
| }, |
| { |
| "entropy": 0.5274676531553268, |
| "epoch": 2.1492537313432836, |
| "grad_norm": 0.17156817018985748, |
| "learning_rate": 0.0002, |
| "loss": 0.5321662425994873, |
| "mean_token_accuracy": 0.7839924246072769, |
| "num_tokens": 9420975.0, |
| "step": 576 |
| }, |
| { |
| "entropy": 0.5465158075094223, |
| "epoch": 2.1529850746268657, |
| "grad_norm": 0.14162594079971313, |
| "learning_rate": 0.0002, |
| "loss": 0.5368850231170654, |
| "mean_token_accuracy": 0.784740686416626, |
| "num_tokens": 9437472.0, |
| "step": 577 |
| }, |
| { |
| "entropy": 0.5229951590299606, |
| "epoch": 2.156716417910448, |
| "grad_norm": 0.169818714261055, |
| "learning_rate": 0.0002, |
| "loss": 0.5167170763015747, |
| "mean_token_accuracy": 0.7908326238393784, |
| "num_tokens": 9454013.0, |
| "step": 578 |
| }, |
| { |
| "entropy": 0.5185272470116615, |
| "epoch": 2.16044776119403, |
| "grad_norm": 0.1582489162683487, |
| "learning_rate": 0.0002, |
| "loss": 0.5142561197280884, |
| "mean_token_accuracy": 0.7913820296525955, |
| "num_tokens": 9470337.0, |
| "step": 579 |
| }, |
| { |
| "entropy": 0.5035977885127068, |
| "epoch": 2.1641791044776117, |
| "grad_norm": 0.20573090016841888, |
| "learning_rate": 0.0002, |
| "loss": 0.5119897723197937, |
| "mean_token_accuracy": 0.7940754294395447, |
| "num_tokens": 9486716.0, |
| "step": 580 |
| }, |
| { |
| "entropy": 0.5165989696979523, |
| "epoch": 2.167910447761194, |
| "grad_norm": 0.1757967472076416, |
| "learning_rate": 0.0002, |
| "loss": 0.5256104469299316, |
| "mean_token_accuracy": 0.7866527140140533, |
| "num_tokens": 9503146.0, |
| "step": 581 |
| }, |
| { |
| "entropy": 0.49958640336990356, |
| "epoch": 2.171641791044776, |
| "grad_norm": 0.1906362771987915, |
| "learning_rate": 0.0002, |
| "loss": 0.5054171681404114, |
| "mean_token_accuracy": 0.7944374829530716, |
| "num_tokens": 9519678.0, |
| "step": 582 |
| }, |
| { |
| "entropy": 0.5284804850816727, |
| "epoch": 2.175373134328358, |
| "grad_norm": 0.16591541469097137, |
| "learning_rate": 0.0002, |
| "loss": 0.5342270135879517, |
| "mean_token_accuracy": 0.7828827947378159, |
| "num_tokens": 9536031.0, |
| "step": 583 |
| }, |
| { |
| "entropy": 0.5156923532485962, |
| "epoch": 2.1791044776119404, |
| "grad_norm": 0.15790575742721558, |
| "learning_rate": 0.0002, |
| "loss": 0.5130570530891418, |
| "mean_token_accuracy": 0.7916172742843628, |
| "num_tokens": 9552366.0, |
| "step": 584 |
| }, |
| { |
| "entropy": 0.5417519062757492, |
| "epoch": 2.1828358208955225, |
| "grad_norm": 0.15677741169929504, |
| "learning_rate": 0.0002, |
| "loss": 0.534090518951416, |
| "mean_token_accuracy": 0.7819975167512894, |
| "num_tokens": 9568710.0, |
| "step": 585 |
| }, |
| { |
| "entropy": 0.5222856551408768, |
| "epoch": 2.1865671641791047, |
| "grad_norm": 0.1677142083644867, |
| "learning_rate": 0.0002, |
| "loss": 0.518591582775116, |
| "mean_token_accuracy": 0.7905530035495758, |
| "num_tokens": 9584984.0, |
| "step": 586 |
| }, |
| { |
| "entropy": 0.513166107237339, |
| "epoch": 2.1902985074626864, |
| "grad_norm": 0.2066265344619751, |
| "learning_rate": 0.0002, |
| "loss": 0.5180418491363525, |
| "mean_token_accuracy": 0.7926081568002701, |
| "num_tokens": 9601365.0, |
| "step": 587 |
| }, |
| { |
| "entropy": 0.5247017592191696, |
| "epoch": 2.1940298507462686, |
| "grad_norm": 0.21200427412986755, |
| "learning_rate": 0.0002, |
| "loss": 0.5376954078674316, |
| "mean_token_accuracy": 0.7840185910463333, |
| "num_tokens": 9617777.0, |
| "step": 588 |
| }, |
| { |
| "entropy": 0.5115050971508026, |
| "epoch": 2.1977611940298507, |
| "grad_norm": 0.1946049928665161, |
| "learning_rate": 0.0002, |
| "loss": 0.5207458734512329, |
| "mean_token_accuracy": 0.7890399694442749, |
| "num_tokens": 9634302.0, |
| "step": 589 |
| }, |
| { |
| "entropy": 0.5331281796097755, |
| "epoch": 2.201492537313433, |
| "grad_norm": 0.1675325483083725, |
| "learning_rate": 0.0002, |
| "loss": 0.5338683128356934, |
| "mean_token_accuracy": 0.7848098576068878, |
| "num_tokens": 9650709.0, |
| "step": 590 |
| }, |
| { |
| "entropy": 0.5316061452031136, |
| "epoch": 2.205223880597015, |
| "grad_norm": 0.17890526354312897, |
| "learning_rate": 0.0002, |
| "loss": 0.5230383276939392, |
| "mean_token_accuracy": 0.7875192016363144, |
| "num_tokens": 9666971.0, |
| "step": 591 |
| }, |
| { |
| "entropy": 0.5452000200748444, |
| "epoch": 2.208955223880597, |
| "grad_norm": 0.16008353233337402, |
| "learning_rate": 0.0002, |
| "loss": 0.5330168008804321, |
| "mean_token_accuracy": 0.7828583419322968, |
| "num_tokens": 9683552.0, |
| "step": 592 |
| }, |
| { |
| "entropy": 0.5236563384532928, |
| "epoch": 2.2126865671641793, |
| "grad_norm": 0.16508641839027405, |
| "learning_rate": 0.0002, |
| "loss": 0.521411120891571, |
| "mean_token_accuracy": 0.7873115092515945, |
| "num_tokens": 9700133.0, |
| "step": 593 |
| }, |
| { |
| "entropy": 0.521051436662674, |
| "epoch": 2.216417910447761, |
| "grad_norm": 0.22689642012119293, |
| "learning_rate": 0.0002, |
| "loss": 0.5271427035331726, |
| "mean_token_accuracy": 0.7868362218141556, |
| "num_tokens": 9716404.0, |
| "step": 594 |
| }, |
| { |
| "entropy": 0.5046728923916817, |
| "epoch": 2.220149253731343, |
| "grad_norm": 0.18618735671043396, |
| "learning_rate": 0.0002, |
| "loss": 0.5110145211219788, |
| "mean_token_accuracy": 0.7930623292922974, |
| "num_tokens": 9732582.0, |
| "step": 595 |
| }, |
| { |
| "entropy": 0.5012746602296829, |
| "epoch": 2.2238805970149254, |
| "grad_norm": 0.23272092640399933, |
| "learning_rate": 0.0002, |
| "loss": 0.5122671127319336, |
| "mean_token_accuracy": 0.7920441031455994, |
| "num_tokens": 9748891.0, |
| "step": 596 |
| }, |
| { |
| "entropy": 0.5166770666837692, |
| "epoch": 2.2276119402985075, |
| "grad_norm": 0.20147265493869781, |
| "learning_rate": 0.0002, |
| "loss": 0.5181618928909302, |
| "mean_token_accuracy": 0.789498507976532, |
| "num_tokens": 9765041.0, |
| "step": 597 |
| }, |
| { |
| "entropy": 0.5235425978899002, |
| "epoch": 2.2313432835820897, |
| "grad_norm": 0.16453935205936432, |
| "learning_rate": 0.0002, |
| "loss": 0.5197381973266602, |
| "mean_token_accuracy": 0.7904594093561172, |
| "num_tokens": 9781488.0, |
| "step": 598 |
| }, |
| { |
| "entropy": 0.5257585048675537, |
| "epoch": 2.235074626865672, |
| "grad_norm": 0.172663152217865, |
| "learning_rate": 0.0002, |
| "loss": 0.5165783762931824, |
| "mean_token_accuracy": 0.7900519222021103, |
| "num_tokens": 9797642.0, |
| "step": 599 |
| }, |
| { |
| "entropy": 0.5365807116031647, |
| "epoch": 2.2388059701492535, |
| "grad_norm": 0.1422445923089981, |
| "learning_rate": 0.0002, |
| "loss": 0.5346869230270386, |
| "mean_token_accuracy": 0.7834084630012512, |
| "num_tokens": 9813892.0, |
| "step": 600 |
| }, |
| { |
| "entropy": 0.5064356029033661, |
| "epoch": 2.2425373134328357, |
| "grad_norm": 0.19735611975193024, |
| "learning_rate": 0.0002, |
| "loss": 0.5157118439674377, |
| "mean_token_accuracy": 0.7920048385858536, |
| "num_tokens": 9830479.0, |
| "step": 601 |
| }, |
| { |
| "entropy": 0.5215098932385445, |
| "epoch": 2.246268656716418, |
| "grad_norm": 0.17668649554252625, |
| "learning_rate": 0.0002, |
| "loss": 0.5273607969284058, |
| "mean_token_accuracy": 0.7887186706066132, |
| "num_tokens": 9846617.0, |
| "step": 602 |
| }, |
| { |
| "entropy": 0.5240141153335571, |
| "epoch": 2.25, |
| "grad_norm": 0.16985413432121277, |
| "learning_rate": 0.0002, |
| "loss": 0.5232423543930054, |
| "mean_token_accuracy": 0.7894934117794037, |
| "num_tokens": 9862817.0, |
| "step": 603 |
| }, |
| { |
| "entropy": 0.5239729583263397, |
| "epoch": 2.253731343283582, |
| "grad_norm": 0.1715954691171646, |
| "learning_rate": 0.0002, |
| "loss": 0.5240473747253418, |
| "mean_token_accuracy": 0.7884418070316315, |
| "num_tokens": 9878927.0, |
| "step": 604 |
| }, |
| { |
| "entropy": 0.5237741768360138, |
| "epoch": 2.2574626865671643, |
| "grad_norm": 0.15604214370250702, |
| "learning_rate": 0.0002, |
| "loss": 0.5224798321723938, |
| "mean_token_accuracy": 0.7926197052001953, |
| "num_tokens": 9895193.0, |
| "step": 605 |
| }, |
| { |
| "entropy": 0.5215341970324516, |
| "epoch": 2.2611940298507465, |
| "grad_norm": 0.18307483196258545, |
| "learning_rate": 0.0002, |
| "loss": 0.5196058750152588, |
| "mean_token_accuracy": 0.7899859100580215, |
| "num_tokens": 9911470.0, |
| "step": 606 |
| }, |
| { |
| "entropy": 0.5101677626371384, |
| "epoch": 2.264925373134328, |
| "grad_norm": 0.16780704259872437, |
| "learning_rate": 0.0002, |
| "loss": 0.5195671916007996, |
| "mean_token_accuracy": 0.7892895489931107, |
| "num_tokens": 9927284.0, |
| "step": 607 |
| }, |
| { |
| "entropy": 0.5224899798631668, |
| "epoch": 2.2686567164179103, |
| "grad_norm": 0.18420308828353882, |
| "learning_rate": 0.0002, |
| "loss": 0.531579852104187, |
| "mean_token_accuracy": 0.7860321253538132, |
| "num_tokens": 9943602.0, |
| "step": 608 |
| }, |
| { |
| "entropy": 0.5314477235078812, |
| "epoch": 2.2723880597014925, |
| "grad_norm": 0.1823703646659851, |
| "learning_rate": 0.0002, |
| "loss": 0.5303313136100769, |
| "mean_token_accuracy": 0.784063383936882, |
| "num_tokens": 9959912.0, |
| "step": 609 |
| }, |
| { |
| "entropy": 0.5216669738292694, |
| "epoch": 2.2761194029850746, |
| "grad_norm": 0.1986614167690277, |
| "learning_rate": 0.0002, |
| "loss": 0.520351231098175, |
| "mean_token_accuracy": 0.7891969978809357, |
| "num_tokens": 9976090.0, |
| "step": 610 |
| }, |
| { |
| "entropy": 0.5096594169735909, |
| "epoch": 2.279850746268657, |
| "grad_norm": 0.16256451606750488, |
| "learning_rate": 0.0002, |
| "loss": 0.5053468942642212, |
| "mean_token_accuracy": 0.7961113899946213, |
| "num_tokens": 9992579.0, |
| "step": 611 |
| }, |
| { |
| "entropy": 0.5227770209312439, |
| "epoch": 2.283582089552239, |
| "grad_norm": 0.16831491887569427, |
| "learning_rate": 0.0002, |
| "loss": 0.5214449763298035, |
| "mean_token_accuracy": 0.7893294245004654, |
| "num_tokens": 10008977.0, |
| "step": 612 |
| }, |
| { |
| "entropy": 0.5172739624977112, |
| "epoch": 2.2873134328358207, |
| "grad_norm": 0.17745047807693481, |
| "learning_rate": 0.0002, |
| "loss": 0.5269317626953125, |
| "mean_token_accuracy": 0.787940725684166, |
| "num_tokens": 10024928.0, |
| "step": 613 |
| }, |
| { |
| "entropy": 0.5238304883241653, |
| "epoch": 2.291044776119403, |
| "grad_norm": 0.20205368101596832, |
| "learning_rate": 0.0002, |
| "loss": 0.5278552174568176, |
| "mean_token_accuracy": 0.7878326773643494, |
| "num_tokens": 10041222.0, |
| "step": 614 |
| }, |
| { |
| "entropy": 0.5256803333759308, |
| "epoch": 2.294776119402985, |
| "grad_norm": 0.1830967366695404, |
| "learning_rate": 0.0002, |
| "loss": 0.525160014629364, |
| "mean_token_accuracy": 0.7900779247283936, |
| "num_tokens": 10057436.0, |
| "step": 615 |
| }, |
| { |
| "entropy": 0.5254340618848801, |
| "epoch": 2.298507462686567, |
| "grad_norm": 0.20681993663311005, |
| "learning_rate": 0.0002, |
| "loss": 0.5216285586357117, |
| "mean_token_accuracy": 0.7884407341480255, |
| "num_tokens": 10073805.0, |
| "step": 616 |
| }, |
| { |
| "entropy": 0.5348054766654968, |
| "epoch": 2.3022388059701493, |
| "grad_norm": 0.15202976763248444, |
| "learning_rate": 0.0002, |
| "loss": 0.5264104008674622, |
| "mean_token_accuracy": 0.7864205688238144, |
| "num_tokens": 10090260.0, |
| "step": 617 |
| }, |
| { |
| "entropy": 0.5313213914632797, |
| "epoch": 2.3059701492537314, |
| "grad_norm": 0.19644394516944885, |
| "learning_rate": 0.0002, |
| "loss": 0.5291533470153809, |
| "mean_token_accuracy": 0.7862230539321899, |
| "num_tokens": 10106429.0, |
| "step": 618 |
| }, |
| { |
| "entropy": 0.5121608376502991, |
| "epoch": 2.3097014925373136, |
| "grad_norm": 0.1715804934501648, |
| "learning_rate": 0.0002, |
| "loss": 0.5171452760696411, |
| "mean_token_accuracy": 0.7932174503803253, |
| "num_tokens": 10122447.0, |
| "step": 619 |
| }, |
| { |
| "entropy": 0.508171834051609, |
| "epoch": 2.3134328358208958, |
| "grad_norm": 0.2214709371328354, |
| "learning_rate": 0.0002, |
| "loss": 0.5216375589370728, |
| "mean_token_accuracy": 0.7893238961696625, |
| "num_tokens": 10138948.0, |
| "step": 620 |
| }, |
| { |
| "entropy": 0.5181078910827637, |
| "epoch": 2.3171641791044775, |
| "grad_norm": 0.16204653680324554, |
| "learning_rate": 0.0002, |
| "loss": 0.5239478945732117, |
| "mean_token_accuracy": 0.7869942486286163, |
| "num_tokens": 10154976.0, |
| "step": 621 |
| }, |
| { |
| "entropy": 0.5260960906744003, |
| "epoch": 2.3208955223880596, |
| "grad_norm": 0.20417559146881104, |
| "learning_rate": 0.0002, |
| "loss": 0.5243396162986755, |
| "mean_token_accuracy": 0.789090171456337, |
| "num_tokens": 10171368.0, |
| "step": 622 |
| }, |
| { |
| "entropy": 0.5246789902448654, |
| "epoch": 2.324626865671642, |
| "grad_norm": 0.1666366308927536, |
| "learning_rate": 0.0002, |
| "loss": 0.5118212103843689, |
| "mean_token_accuracy": 0.793223962187767, |
| "num_tokens": 10188079.0, |
| "step": 623 |
| }, |
| { |
| "entropy": 0.5107671171426773, |
| "epoch": 2.328358208955224, |
| "grad_norm": 0.16232071816921234, |
| "learning_rate": 0.0002, |
| "loss": 0.5079004764556885, |
| "mean_token_accuracy": 0.7950920611619949, |
| "num_tokens": 10204456.0, |
| "step": 624 |
| }, |
| { |
| "entropy": 0.525738425552845, |
| "epoch": 2.332089552238806, |
| "grad_norm": 0.19880948960781097, |
| "learning_rate": 0.0002, |
| "loss": 0.530964195728302, |
| "mean_token_accuracy": 0.7846823483705521, |
| "num_tokens": 10220760.0, |
| "step": 625 |
| }, |
| { |
| "entropy": 0.5123703628778458, |
| "epoch": 2.3358208955223883, |
| "grad_norm": 0.20241215825080872, |
| "learning_rate": 0.0002, |
| "loss": 0.5237905383110046, |
| "mean_token_accuracy": 0.7908910661935806, |
| "num_tokens": 10237210.0, |
| "step": 626 |
| }, |
| { |
| "entropy": 0.521447092294693, |
| "epoch": 2.33955223880597, |
| "grad_norm": 0.1650668829679489, |
| "learning_rate": 0.0002, |
| "loss": 0.52762770652771, |
| "mean_token_accuracy": 0.7868582457304001, |
| "num_tokens": 10253625.0, |
| "step": 627 |
| }, |
| { |
| "entropy": 0.5237598270177841, |
| "epoch": 2.343283582089552, |
| "grad_norm": 0.15874698758125305, |
| "learning_rate": 0.0002, |
| "loss": 0.5160398483276367, |
| "mean_token_accuracy": 0.7931548953056335, |
| "num_tokens": 10269840.0, |
| "step": 628 |
| }, |
| { |
| "entropy": 0.5428738445043564, |
| "epoch": 2.3470149253731343, |
| "grad_norm": 0.15867970883846283, |
| "learning_rate": 0.0002, |
| "loss": 0.5387794971466064, |
| "mean_token_accuracy": 0.7846502065658569, |
| "num_tokens": 10286038.0, |
| "step": 629 |
| }, |
| { |
| "entropy": 0.5283751711249352, |
| "epoch": 2.3507462686567164, |
| "grad_norm": 0.1641656756401062, |
| "learning_rate": 0.0002, |
| "loss": 0.5256651639938354, |
| "mean_token_accuracy": 0.7867411226034164, |
| "num_tokens": 10302400.0, |
| "step": 630 |
| }, |
| { |
| "entropy": 0.5286802500486374, |
| "epoch": 2.3544776119402986, |
| "grad_norm": 0.17140311002731323, |
| "learning_rate": 0.0002, |
| "loss": 0.5293422937393188, |
| "mean_token_accuracy": 0.7854064255952835, |
| "num_tokens": 10318570.0, |
| "step": 631 |
| }, |
| { |
| "entropy": 0.5182445719838142, |
| "epoch": 2.3582089552238807, |
| "grad_norm": 0.21388016641139984, |
| "learning_rate": 0.0002, |
| "loss": 0.5371419787406921, |
| "mean_token_accuracy": 0.7856151163578033, |
| "num_tokens": 10334733.0, |
| "step": 632 |
| }, |
| { |
| "entropy": 0.5193633660674095, |
| "epoch": 2.361940298507463, |
| "grad_norm": 0.166620671749115, |
| "learning_rate": 0.0002, |
| "loss": 0.5231353640556335, |
| "mean_token_accuracy": 0.7889625281095505, |
| "num_tokens": 10351120.0, |
| "step": 633 |
| }, |
| { |
| "entropy": 0.5205678045749664, |
| "epoch": 2.3656716417910446, |
| "grad_norm": 0.1603280007839203, |
| "learning_rate": 0.0002, |
| "loss": 0.5198505520820618, |
| "mean_token_accuracy": 0.7884901314973831, |
| "num_tokens": 10367368.0, |
| "step": 634 |
| }, |
| { |
| "entropy": 0.5235021561384201, |
| "epoch": 2.3694029850746268, |
| "grad_norm": 0.18468010425567627, |
| "learning_rate": 0.0002, |
| "loss": 0.5170429348945618, |
| "mean_token_accuracy": 0.7903261333703995, |
| "num_tokens": 10383725.0, |
| "step": 635 |
| }, |
| { |
| "entropy": 0.5374963581562042, |
| "epoch": 2.373134328358209, |
| "grad_norm": 0.1840977519750595, |
| "learning_rate": 0.0002, |
| "loss": 0.5311538577079773, |
| "mean_token_accuracy": 0.7850894927978516, |
| "num_tokens": 10400048.0, |
| "step": 636 |
| }, |
| { |
| "entropy": 0.5280650407075882, |
| "epoch": 2.376865671641791, |
| "grad_norm": 0.17973721027374268, |
| "learning_rate": 0.0002, |
| "loss": 0.526053249835968, |
| "mean_token_accuracy": 0.7874976396560669, |
| "num_tokens": 10416395.0, |
| "step": 637 |
| }, |
| { |
| "entropy": 0.5327761918306351, |
| "epoch": 2.3805970149253732, |
| "grad_norm": 0.19733701646327972, |
| "learning_rate": 0.0002, |
| "loss": 0.5317797660827637, |
| "mean_token_accuracy": 0.7845488339662552, |
| "num_tokens": 10432915.0, |
| "step": 638 |
| }, |
| { |
| "entropy": 0.5275843441486359, |
| "epoch": 2.3843283582089554, |
| "grad_norm": 0.19057615101337433, |
| "learning_rate": 0.0002, |
| "loss": 0.5404111742973328, |
| "mean_token_accuracy": 0.7797352522611618, |
| "num_tokens": 10449217.0, |
| "step": 639 |
| }, |
| { |
| "entropy": 0.521431528031826, |
| "epoch": 2.388059701492537, |
| "grad_norm": 0.19880267977714539, |
| "learning_rate": 0.0002, |
| "loss": 0.5202227830886841, |
| "mean_token_accuracy": 0.789102628827095, |
| "num_tokens": 10465744.0, |
| "step": 640 |
| }, |
| { |
| "entropy": 0.5066538602113724, |
| "epoch": 2.3917910447761193, |
| "grad_norm": 0.17598935961723328, |
| "learning_rate": 0.0002, |
| "loss": 0.5071350932121277, |
| "mean_token_accuracy": 0.7931433022022247, |
| "num_tokens": 10482003.0, |
| "step": 641 |
| }, |
| { |
| "entropy": 0.5253507941961288, |
| "epoch": 2.3955223880597014, |
| "grad_norm": 0.1882835030555725, |
| "learning_rate": 0.0002, |
| "loss": 0.5254237651824951, |
| "mean_token_accuracy": 0.7863857597112656, |
| "num_tokens": 10498238.0, |
| "step": 642 |
| }, |
| { |
| "entropy": 0.47529489547014236, |
| "epoch": 2.3992537313432836, |
| "grad_norm": 0.19731156527996063, |
| "learning_rate": 0.0002, |
| "loss": 0.49018487334251404, |
| "mean_token_accuracy": 0.8020434677600861, |
| "num_tokens": 10514120.0, |
| "step": 643 |
| }, |
| { |
| "entropy": 0.5133585780858994, |
| "epoch": 2.4029850746268657, |
| "grad_norm": 0.17020277678966522, |
| "learning_rate": 0.0002, |
| "loss": 0.5182552337646484, |
| "mean_token_accuracy": 0.790691927075386, |
| "num_tokens": 10530480.0, |
| "step": 644 |
| }, |
| { |
| "entropy": 0.5060104876756668, |
| "epoch": 2.406716417910448, |
| "grad_norm": 0.17196904122829437, |
| "learning_rate": 0.0002, |
| "loss": 0.505009651184082, |
| "mean_token_accuracy": 0.7953106015920639, |
| "num_tokens": 10546804.0, |
| "step": 645 |
| }, |
| { |
| "entropy": 0.5243590921163559, |
| "epoch": 2.41044776119403, |
| "grad_norm": 0.14876312017440796, |
| "learning_rate": 0.0002, |
| "loss": 0.5192916393280029, |
| "mean_token_accuracy": 0.7894758582115173, |
| "num_tokens": 10563176.0, |
| "step": 646 |
| }, |
| { |
| "entropy": 0.5320051163434982, |
| "epoch": 2.4141791044776117, |
| "grad_norm": 0.19245290756225586, |
| "learning_rate": 0.0002, |
| "loss": 0.5289613604545593, |
| "mean_token_accuracy": 0.7869962006807327, |
| "num_tokens": 10579442.0, |
| "step": 647 |
| }, |
| { |
| "entropy": 0.5280356630682945, |
| "epoch": 2.417910447761194, |
| "grad_norm": 0.16865810751914978, |
| "learning_rate": 0.0002, |
| "loss": 0.5280870199203491, |
| "mean_token_accuracy": 0.7860658317804337, |
| "num_tokens": 10595777.0, |
| "step": 648 |
| }, |
| { |
| "entropy": 0.5159407258033752, |
| "epoch": 2.421641791044776, |
| "grad_norm": 0.18313923478126526, |
| "learning_rate": 0.0002, |
| "loss": 0.5199831128120422, |
| "mean_token_accuracy": 0.7879379093647003, |
| "num_tokens": 10612052.0, |
| "step": 649 |
| }, |
| { |
| "entropy": 0.5115545094013214, |
| "epoch": 2.425373134328358, |
| "grad_norm": 0.2015586644411087, |
| "learning_rate": 0.0002, |
| "loss": 0.5117849707603455, |
| "mean_token_accuracy": 0.7927766442298889, |
| "num_tokens": 10628351.0, |
| "step": 650 |
| }, |
| { |
| "entropy": 0.5246743187308311, |
| "epoch": 2.4291044776119404, |
| "grad_norm": 0.2073381245136261, |
| "learning_rate": 0.0002, |
| "loss": 0.5250370502471924, |
| "mean_token_accuracy": 0.7853521555662155, |
| "num_tokens": 10644550.0, |
| "step": 651 |
| }, |
| { |
| "entropy": 0.5212004333734512, |
| "epoch": 2.4328358208955225, |
| "grad_norm": 0.15271975100040436, |
| "learning_rate": 0.0002, |
| "loss": 0.5190944671630859, |
| "mean_token_accuracy": 0.7887966483831406, |
| "num_tokens": 10660975.0, |
| "step": 652 |
| }, |
| { |
| "entropy": 0.5326541215181351, |
| "epoch": 2.4365671641791042, |
| "grad_norm": 0.17628662288188934, |
| "learning_rate": 0.0002, |
| "loss": 0.5344939231872559, |
| "mean_token_accuracy": 0.7855707108974457, |
| "num_tokens": 10677340.0, |
| "step": 653 |
| }, |
| { |
| "entropy": 0.5556225478649139, |
| "epoch": 2.4402985074626864, |
| "grad_norm": 0.16658253967761993, |
| "learning_rate": 0.0002, |
| "loss": 0.5535020232200623, |
| "mean_token_accuracy": 0.7763145864009857, |
| "num_tokens": 10693876.0, |
| "step": 654 |
| }, |
| { |
| "entropy": 0.5162215456366539, |
| "epoch": 2.4440298507462686, |
| "grad_norm": 0.1736278086900711, |
| "learning_rate": 0.0002, |
| "loss": 0.5170564651489258, |
| "mean_token_accuracy": 0.7914817482233047, |
| "num_tokens": 10710134.0, |
| "step": 655 |
| }, |
| { |
| "entropy": 0.5131185948848724, |
| "epoch": 2.4477611940298507, |
| "grad_norm": 0.1758628785610199, |
| "learning_rate": 0.0002, |
| "loss": 0.5182158946990967, |
| "mean_token_accuracy": 0.7907793819904327, |
| "num_tokens": 10726547.0, |
| "step": 656 |
| }, |
| { |
| "entropy": 0.5195021033287048, |
| "epoch": 2.451492537313433, |
| "grad_norm": 0.1745452880859375, |
| "learning_rate": 0.0002, |
| "loss": 0.5191912651062012, |
| "mean_token_accuracy": 0.7899110168218613, |
| "num_tokens": 10742949.0, |
| "step": 657 |
| }, |
| { |
| "entropy": 0.5168969482183456, |
| "epoch": 2.455223880597015, |
| "grad_norm": 0.1855829358100891, |
| "learning_rate": 0.0002, |
| "loss": 0.5224817395210266, |
| "mean_token_accuracy": 0.7883941829204559, |
| "num_tokens": 10759113.0, |
| "step": 658 |
| }, |
| { |
| "entropy": 0.5249419063329697, |
| "epoch": 2.458955223880597, |
| "grad_norm": 0.21612296998500824, |
| "learning_rate": 0.0002, |
| "loss": 0.5325984954833984, |
| "mean_token_accuracy": 0.7871971130371094, |
| "num_tokens": 10775376.0, |
| "step": 659 |
| }, |
| { |
| "entropy": 0.5371896326541901, |
| "epoch": 2.4626865671641793, |
| "grad_norm": 0.1624351292848587, |
| "learning_rate": 0.0002, |
| "loss": 0.5361514091491699, |
| "mean_token_accuracy": 0.7826291769742966, |
| "num_tokens": 10791927.0, |
| "step": 660 |
| }, |
| { |
| "entropy": 0.5091428160667419, |
| "epoch": 2.466417910447761, |
| "grad_norm": 0.20327496528625488, |
| "learning_rate": 0.0002, |
| "loss": 0.5073671340942383, |
| "mean_token_accuracy": 0.794013112783432, |
| "num_tokens": 10808312.0, |
| "step": 661 |
| }, |
| { |
| "entropy": 0.5260773003101349, |
| "epoch": 2.470149253731343, |
| "grad_norm": 0.17028173804283142, |
| "learning_rate": 0.0002, |
| "loss": 0.5245232582092285, |
| "mean_token_accuracy": 0.788914829492569, |
| "num_tokens": 10824704.0, |
| "step": 662 |
| }, |
| { |
| "entropy": 0.5280766487121582, |
| "epoch": 2.4738805970149254, |
| "grad_norm": 0.18212343752384186, |
| "learning_rate": 0.0002, |
| "loss": 0.5301048159599304, |
| "mean_token_accuracy": 0.7843264639377594, |
| "num_tokens": 10840802.0, |
| "step": 663 |
| }, |
| { |
| "entropy": 0.5124288499355316, |
| "epoch": 2.4776119402985075, |
| "grad_norm": 0.17330721020698547, |
| "learning_rate": 0.0002, |
| "loss": 0.513626217842102, |
| "mean_token_accuracy": 0.7946698069572449, |
| "num_tokens": 10857261.0, |
| "step": 664 |
| }, |
| { |
| "entropy": 0.5110838413238525, |
| "epoch": 2.4813432835820897, |
| "grad_norm": 0.1706920862197876, |
| "learning_rate": 0.0002, |
| "loss": 0.5125702619552612, |
| "mean_token_accuracy": 0.7929413467645645, |
| "num_tokens": 10873658.0, |
| "step": 665 |
| }, |
| { |
| "entropy": 0.5205335915088654, |
| "epoch": 2.485074626865672, |
| "grad_norm": 0.1893186867237091, |
| "learning_rate": 0.0002, |
| "loss": 0.5249273180961609, |
| "mean_token_accuracy": 0.7878608405590057, |
| "num_tokens": 10890234.0, |
| "step": 666 |
| }, |
| { |
| "entropy": 0.5158488675951958, |
| "epoch": 2.4888059701492535, |
| "grad_norm": 0.17255286872386932, |
| "learning_rate": 0.0002, |
| "loss": 0.5161062479019165, |
| "mean_token_accuracy": 0.7902019917964935, |
| "num_tokens": 10906581.0, |
| "step": 667 |
| }, |
| { |
| "entropy": 0.5348800271749496, |
| "epoch": 2.4925373134328357, |
| "grad_norm": 0.16027338802814484, |
| "learning_rate": 0.0002, |
| "loss": 0.531215488910675, |
| "mean_token_accuracy": 0.785172164440155, |
| "num_tokens": 10923077.0, |
| "step": 668 |
| }, |
| { |
| "entropy": 0.5348771065473557, |
| "epoch": 2.496268656716418, |
| "grad_norm": 0.19097019731998444, |
| "learning_rate": 0.0002, |
| "loss": 0.5368809103965759, |
| "mean_token_accuracy": 0.7817152440547943, |
| "num_tokens": 10939475.0, |
| "step": 669 |
| }, |
| { |
| "entropy": 0.5455515533685684, |
| "epoch": 2.5, |
| "grad_norm": 0.16083452105522156, |
| "learning_rate": 0.0002, |
| "loss": 0.5379430055618286, |
| "mean_token_accuracy": 0.7795073390007019, |
| "num_tokens": 10956069.0, |
| "step": 670 |
| }, |
| { |
| "entropy": 0.5262513160705566, |
| "epoch": 2.503731343283582, |
| "grad_norm": 0.1948131024837494, |
| "learning_rate": 0.0002, |
| "loss": 0.5257157683372498, |
| "mean_token_accuracy": 0.7863384336233139, |
| "num_tokens": 10972316.0, |
| "step": 671 |
| }, |
| { |
| "entropy": 0.5327911078929901, |
| "epoch": 2.5074626865671643, |
| "grad_norm": 0.1680261194705963, |
| "learning_rate": 0.0002, |
| "loss": 0.5309050679206848, |
| "mean_token_accuracy": 0.7858748435974121, |
| "num_tokens": 10988636.0, |
| "step": 672 |
| }, |
| { |
| "entropy": 0.5200925022363663, |
| "epoch": 2.5111940298507465, |
| "grad_norm": 0.18088939785957336, |
| "learning_rate": 0.0002, |
| "loss": 0.5156010985374451, |
| "mean_token_accuracy": 0.7923842370510101, |
| "num_tokens": 11004858.0, |
| "step": 673 |
| }, |
| { |
| "entropy": 0.5215509980916977, |
| "epoch": 2.5149253731343286, |
| "grad_norm": 0.1766502559185028, |
| "learning_rate": 0.0002, |
| "loss": 0.5266660451889038, |
| "mean_token_accuracy": 0.7856778204441071, |
| "num_tokens": 11021111.0, |
| "step": 674 |
| }, |
| { |
| "entropy": 0.5079243779182434, |
| "epoch": 2.5186567164179103, |
| "grad_norm": 0.22624646127223969, |
| "learning_rate": 0.0002, |
| "loss": 0.5187743902206421, |
| "mean_token_accuracy": 0.7883740961551666, |
| "num_tokens": 11037460.0, |
| "step": 675 |
| }, |
| { |
| "entropy": 0.5214747488498688, |
| "epoch": 2.5223880597014925, |
| "grad_norm": 0.17487084865570068, |
| "learning_rate": 0.0002, |
| "loss": 0.5319433212280273, |
| "mean_token_accuracy": 0.7836728990077972, |
| "num_tokens": 11054112.0, |
| "step": 676 |
| }, |
| { |
| "entropy": 0.526528537273407, |
| "epoch": 2.5261194029850746, |
| "grad_norm": 0.1606326848268509, |
| "learning_rate": 0.0002, |
| "loss": 0.5325278043746948, |
| "mean_token_accuracy": 0.7849267572164536, |
| "num_tokens": 11070430.0, |
| "step": 677 |
| }, |
| { |
| "entropy": 0.5388126075267792, |
| "epoch": 2.529850746268657, |
| "grad_norm": 0.1730964034795761, |
| "learning_rate": 0.0002, |
| "loss": 0.5314829349517822, |
| "mean_token_accuracy": 0.7852486819028854, |
| "num_tokens": 11086959.0, |
| "step": 678 |
| }, |
| { |
| "entropy": 0.5306697189807892, |
| "epoch": 2.533582089552239, |
| "grad_norm": 0.18857303261756897, |
| "learning_rate": 0.0002, |
| "loss": 0.5244256258010864, |
| "mean_token_accuracy": 0.789952889084816, |
| "num_tokens": 11103447.0, |
| "step": 679 |
| }, |
| { |
| "entropy": 0.5247458964586258, |
| "epoch": 2.5373134328358207, |
| "grad_norm": 0.15421876311302185, |
| "learning_rate": 0.0002, |
| "loss": 0.5182734727859497, |
| "mean_token_accuracy": 0.7895084470510483, |
| "num_tokens": 11119898.0, |
| "step": 680 |
| }, |
| { |
| "entropy": 0.5156458765268326, |
| "epoch": 2.541044776119403, |
| "grad_norm": 0.19100499153137207, |
| "learning_rate": 0.0002, |
| "loss": 0.5198882818222046, |
| "mean_token_accuracy": 0.7881297767162323, |
| "num_tokens": 11136050.0, |
| "step": 681 |
| }, |
| { |
| "entropy": 0.525128647685051, |
| "epoch": 2.544776119402985, |
| "grad_norm": 0.17779041826725006, |
| "learning_rate": 0.0002, |
| "loss": 0.5317760109901428, |
| "mean_token_accuracy": 0.7860094010829926, |
| "num_tokens": 11152415.0, |
| "step": 682 |
| }, |
| { |
| "entropy": 0.5388829410076141, |
| "epoch": 2.548507462686567, |
| "grad_norm": 0.22449658811092377, |
| "learning_rate": 0.0002, |
| "loss": 0.5407117605209351, |
| "mean_token_accuracy": 0.7809988707304001, |
| "num_tokens": 11168704.0, |
| "step": 683 |
| }, |
| { |
| "entropy": 0.5210283547639847, |
| "epoch": 2.5522388059701493, |
| "grad_norm": 0.18301711976528168, |
| "learning_rate": 0.0002, |
| "loss": 0.5191092491149902, |
| "mean_token_accuracy": 0.7936272472143173, |
| "num_tokens": 11185399.0, |
| "step": 684 |
| }, |
| { |
| "entropy": 0.5333351492881775, |
| "epoch": 2.5559701492537314, |
| "grad_norm": 0.18689635396003723, |
| "learning_rate": 0.0002, |
| "loss": 0.5363100171089172, |
| "mean_token_accuracy": 0.7819992452859879, |
| "num_tokens": 11201660.0, |
| "step": 685 |
| }, |
| { |
| "entropy": 0.5189471021294594, |
| "epoch": 2.5597014925373136, |
| "grad_norm": 0.1866644024848938, |
| "learning_rate": 0.0002, |
| "loss": 0.5156103372573853, |
| "mean_token_accuracy": 0.7902535796165466, |
| "num_tokens": 11218050.0, |
| "step": 686 |
| }, |
| { |
| "entropy": 0.517949178814888, |
| "epoch": 2.5634328358208958, |
| "grad_norm": 0.17216302454471588, |
| "learning_rate": 0.0002, |
| "loss": 0.5179208517074585, |
| "mean_token_accuracy": 0.7918720543384552, |
| "num_tokens": 11234443.0, |
| "step": 687 |
| }, |
| { |
| "entropy": 0.5244702845811844, |
| "epoch": 2.5671641791044775, |
| "grad_norm": 0.18239498138427734, |
| "learning_rate": 0.0002, |
| "loss": 0.5227185487747192, |
| "mean_token_accuracy": 0.7892958074808121, |
| "num_tokens": 11250689.0, |
| "step": 688 |
| }, |
| { |
| "entropy": 0.5216506868600845, |
| "epoch": 2.5708955223880596, |
| "grad_norm": 0.14987768232822418, |
| "learning_rate": 0.0002, |
| "loss": 0.5201072692871094, |
| "mean_token_accuracy": 0.7904810160398483, |
| "num_tokens": 11267135.0, |
| "step": 689 |
| }, |
| { |
| "entropy": 0.5279186367988586, |
| "epoch": 2.574626865671642, |
| "grad_norm": 0.15889248251914978, |
| "learning_rate": 0.0002, |
| "loss": 0.5293627977371216, |
| "mean_token_accuracy": 0.7903176248073578, |
| "num_tokens": 11283800.0, |
| "step": 690 |
| }, |
| { |
| "entropy": 0.5287537425756454, |
| "epoch": 2.578358208955224, |
| "grad_norm": 0.18124715983867645, |
| "learning_rate": 0.0002, |
| "loss": 0.5371734499931335, |
| "mean_token_accuracy": 0.7816613614559174, |
| "num_tokens": 11300158.0, |
| "step": 691 |
| }, |
| { |
| "entropy": 0.5387821942567825, |
| "epoch": 2.582089552238806, |
| "grad_norm": 0.16657379269599915, |
| "learning_rate": 0.0002, |
| "loss": 0.5370945334434509, |
| "mean_token_accuracy": 0.7830782383680344, |
| "num_tokens": 11316832.0, |
| "step": 692 |
| }, |
| { |
| "entropy": 0.54594786465168, |
| "epoch": 2.585820895522388, |
| "grad_norm": 0.17614276707172394, |
| "learning_rate": 0.0002, |
| "loss": 0.5447899103164673, |
| "mean_token_accuracy": 0.7781383395195007, |
| "num_tokens": 11333247.0, |
| "step": 693 |
| }, |
| { |
| "entropy": 0.5267602428793907, |
| "epoch": 2.58955223880597, |
| "grad_norm": 0.17958366870880127, |
| "learning_rate": 0.0002, |
| "loss": 0.5313481688499451, |
| "mean_token_accuracy": 0.784763902425766, |
| "num_tokens": 11349641.0, |
| "step": 694 |
| }, |
| { |
| "entropy": 0.5402519404888153, |
| "epoch": 2.593283582089552, |
| "grad_norm": 0.19503135979175568, |
| "learning_rate": 0.0002, |
| "loss": 0.5412020683288574, |
| "mean_token_accuracy": 0.7823947221040726, |
| "num_tokens": 11366177.0, |
| "step": 695 |
| }, |
| { |
| "entropy": 0.5195119678974152, |
| "epoch": 2.5970149253731343, |
| "grad_norm": 0.16940443217754364, |
| "learning_rate": 0.0002, |
| "loss": 0.5163792967796326, |
| "mean_token_accuracy": 0.7890198975801468, |
| "num_tokens": 11382650.0, |
| "step": 696 |
| }, |
| { |
| "entropy": 0.5336590185761452, |
| "epoch": 2.6007462686567164, |
| "grad_norm": 0.17626972496509552, |
| "learning_rate": 0.0002, |
| "loss": 0.538517415523529, |
| "mean_token_accuracy": 0.7853260338306427, |
| "num_tokens": 11399476.0, |
| "step": 697 |
| }, |
| { |
| "entropy": 0.5293844193220139, |
| "epoch": 2.6044776119402986, |
| "grad_norm": 0.15218769013881683, |
| "learning_rate": 0.0002, |
| "loss": 0.5309358835220337, |
| "mean_token_accuracy": 0.7850868999958038, |
| "num_tokens": 11415593.0, |
| "step": 698 |
| }, |
| { |
| "entropy": 0.5104136094450951, |
| "epoch": 2.6082089552238807, |
| "grad_norm": 0.1675557941198349, |
| "learning_rate": 0.0002, |
| "loss": 0.5115703344345093, |
| "mean_token_accuracy": 0.7928510010242462, |
| "num_tokens": 11432000.0, |
| "step": 699 |
| }, |
| { |
| "entropy": 0.5213690474629402, |
| "epoch": 2.611940298507463, |
| "grad_norm": 0.15365014970302582, |
| "learning_rate": 0.0002, |
| "loss": 0.523728609085083, |
| "mean_token_accuracy": 0.7880403846502304, |
| "num_tokens": 11448459.0, |
| "step": 700 |
| }, |
| { |
| "entropy": 0.5225105360150337, |
| "epoch": 2.6156716417910446, |
| "grad_norm": 0.15121756494045258, |
| "learning_rate": 0.0002, |
| "loss": 0.524882435798645, |
| "mean_token_accuracy": 0.7873550206422806, |
| "num_tokens": 11464817.0, |
| "step": 701 |
| }, |
| { |
| "entropy": 0.5064144358038902, |
| "epoch": 2.6194029850746268, |
| "grad_norm": 0.16306865215301514, |
| "learning_rate": 0.0002, |
| "loss": 0.5103060007095337, |
| "mean_token_accuracy": 0.7935118228197098, |
| "num_tokens": 11481058.0, |
| "step": 702 |
| }, |
| { |
| "entropy": 0.5091907754540443, |
| "epoch": 2.623134328358209, |
| "grad_norm": 0.1607798933982849, |
| "learning_rate": 0.0002, |
| "loss": 0.5074288845062256, |
| "mean_token_accuracy": 0.793415904045105, |
| "num_tokens": 11497176.0, |
| "step": 703 |
| }, |
| { |
| "entropy": 0.5329691767692566, |
| "epoch": 2.626865671641791, |
| "grad_norm": 0.16253986954689026, |
| "learning_rate": 0.0002, |
| "loss": 0.5319289565086365, |
| "mean_token_accuracy": 0.7833495289087296, |
| "num_tokens": 11513787.0, |
| "step": 704 |
| }, |
| { |
| "entropy": 0.5169994980096817, |
| "epoch": 2.6305970149253732, |
| "grad_norm": 0.166827991604805, |
| "learning_rate": 0.0002, |
| "loss": 0.514173150062561, |
| "mean_token_accuracy": 0.7923637479543686, |
| "num_tokens": 11529946.0, |
| "step": 705 |
| }, |
| { |
| "entropy": 0.5249803811311722, |
| "epoch": 2.6343283582089554, |
| "grad_norm": 0.18918156623840332, |
| "learning_rate": 0.0002, |
| "loss": 0.5305459499359131, |
| "mean_token_accuracy": 0.7855891734361649, |
| "num_tokens": 11546180.0, |
| "step": 706 |
| }, |
| { |
| "entropy": 0.5436136573553085, |
| "epoch": 2.638059701492537, |
| "grad_norm": 0.15825380384922028, |
| "learning_rate": 0.0002, |
| "loss": 0.5421342849731445, |
| "mean_token_accuracy": 0.7830293327569962, |
| "num_tokens": 11562766.0, |
| "step": 707 |
| }, |
| { |
| "entropy": 0.533930666744709, |
| "epoch": 2.6417910447761193, |
| "grad_norm": 0.16911564767360687, |
| "learning_rate": 0.0002, |
| "loss": 0.5309953093528748, |
| "mean_token_accuracy": 0.7851850688457489, |
| "num_tokens": 11579311.0, |
| "step": 708 |
| }, |
| { |
| "entropy": 0.5336024761199951, |
| "epoch": 2.6455223880597014, |
| "grad_norm": 0.1647675782442093, |
| "learning_rate": 0.0002, |
| "loss": 0.5363572835922241, |
| "mean_token_accuracy": 0.7814708352088928, |
| "num_tokens": 11595904.0, |
| "step": 709 |
| }, |
| { |
| "entropy": 0.5240837708115578, |
| "epoch": 2.6492537313432836, |
| "grad_norm": 0.1759306639432907, |
| "learning_rate": 0.0002, |
| "loss": 0.5229705572128296, |
| "mean_token_accuracy": 0.7879683673381805, |
| "num_tokens": 11612320.0, |
| "step": 710 |
| }, |
| { |
| "entropy": 0.5113276243209839, |
| "epoch": 2.6529850746268657, |
| "grad_norm": 0.17536085844039917, |
| "learning_rate": 0.0002, |
| "loss": 0.5122668743133545, |
| "mean_token_accuracy": 0.7900424748659134, |
| "num_tokens": 11628434.0, |
| "step": 711 |
| }, |
| { |
| "entropy": 0.5328988134860992, |
| "epoch": 2.656716417910448, |
| "grad_norm": 0.19648663699626923, |
| "learning_rate": 0.0002, |
| "loss": 0.5327026844024658, |
| "mean_token_accuracy": 0.7865282148122787, |
| "num_tokens": 11644931.0, |
| "step": 712 |
| }, |
| { |
| "entropy": 0.5325882881879807, |
| "epoch": 2.66044776119403, |
| "grad_norm": 0.1875704824924469, |
| "learning_rate": 0.0002, |
| "loss": 0.5385427474975586, |
| "mean_token_accuracy": 0.7826512157917023, |
| "num_tokens": 11661147.0, |
| "step": 713 |
| }, |
| { |
| "entropy": 0.523619219660759, |
| "epoch": 2.664179104477612, |
| "grad_norm": 0.19794964790344238, |
| "learning_rate": 0.0002, |
| "loss": 0.5301916599273682, |
| "mean_token_accuracy": 0.7857156097888947, |
| "num_tokens": 11677373.0, |
| "step": 714 |
| }, |
| { |
| "entropy": 0.5147494375705719, |
| "epoch": 2.667910447761194, |
| "grad_norm": 0.18202298879623413, |
| "learning_rate": 0.0002, |
| "loss": 0.5198902487754822, |
| "mean_token_accuracy": 0.7907700091600418, |
| "num_tokens": 11693785.0, |
| "step": 715 |
| }, |
| { |
| "entropy": 0.533778190612793, |
| "epoch": 2.671641791044776, |
| "grad_norm": 0.17280054092407227, |
| "learning_rate": 0.0002, |
| "loss": 0.5362057685852051, |
| "mean_token_accuracy": 0.7827749103307724, |
| "num_tokens": 11710037.0, |
| "step": 716 |
| }, |
| { |
| "entropy": 0.5145204812288284, |
| "epoch": 2.675373134328358, |
| "grad_norm": 0.1686772257089615, |
| "learning_rate": 0.0002, |
| "loss": 0.5137688517570496, |
| "mean_token_accuracy": 0.7919251918792725, |
| "num_tokens": 11726618.0, |
| "step": 717 |
| }, |
| { |
| "entropy": 0.5260500907897949, |
| "epoch": 2.6791044776119404, |
| "grad_norm": 0.16683246195316315, |
| "learning_rate": 0.0002, |
| "loss": 0.5206961035728455, |
| "mean_token_accuracy": 0.7881253212690353, |
| "num_tokens": 11742916.0, |
| "step": 718 |
| }, |
| { |
| "entropy": 0.5424181371927261, |
| "epoch": 2.6828358208955225, |
| "grad_norm": 0.18321530520915985, |
| "learning_rate": 0.0002, |
| "loss": 0.5383980870246887, |
| "mean_token_accuracy": 0.7830944657325745, |
| "num_tokens": 11759115.0, |
| "step": 719 |
| }, |
| { |
| "entropy": 0.5491459220647812, |
| "epoch": 2.6865671641791042, |
| "grad_norm": 0.186932772397995, |
| "learning_rate": 0.0002, |
| "loss": 0.55148845911026, |
| "mean_token_accuracy": 0.7760913968086243, |
| "num_tokens": 11775484.0, |
| "step": 720 |
| }, |
| { |
| "entropy": 0.5309914946556091, |
| "epoch": 2.6902985074626864, |
| "grad_norm": 0.21945525705814362, |
| "learning_rate": 0.0002, |
| "loss": 0.53412926197052, |
| "mean_token_accuracy": 0.7859860062599182, |
| "num_tokens": 11791788.0, |
| "step": 721 |
| }, |
| { |
| "entropy": 0.5386980175971985, |
| "epoch": 2.6940298507462686, |
| "grad_norm": 0.1695859432220459, |
| "learning_rate": 0.0002, |
| "loss": 0.5400834083557129, |
| "mean_token_accuracy": 0.7796564400196075, |
| "num_tokens": 11807991.0, |
| "step": 722 |
| }, |
| { |
| "entropy": 0.5350251346826553, |
| "epoch": 2.6977611940298507, |
| "grad_norm": 0.2208118885755539, |
| "learning_rate": 0.0002, |
| "loss": 0.5410833358764648, |
| "mean_token_accuracy": 0.782024547457695, |
| "num_tokens": 11824364.0, |
| "step": 723 |
| }, |
| { |
| "entropy": 0.5189235359430313, |
| "epoch": 2.701492537313433, |
| "grad_norm": 0.16592693328857422, |
| "learning_rate": 0.0002, |
| "loss": 0.5192176103591919, |
| "mean_token_accuracy": 0.7880906909704208, |
| "num_tokens": 11840550.0, |
| "step": 724 |
| }, |
| { |
| "entropy": 0.5217519178986549, |
| "epoch": 2.705223880597015, |
| "grad_norm": 0.1565801054239273, |
| "learning_rate": 0.0002, |
| "loss": 0.5177676677703857, |
| "mean_token_accuracy": 0.7897888571023941, |
| "num_tokens": 11856956.0, |
| "step": 725 |
| }, |
| { |
| "entropy": 0.5270403623580933, |
| "epoch": 2.708955223880597, |
| "grad_norm": 0.20207525789737701, |
| "learning_rate": 0.0002, |
| "loss": 0.5202967524528503, |
| "mean_token_accuracy": 0.7888121604919434, |
| "num_tokens": 11873182.0, |
| "step": 726 |
| }, |
| { |
| "entropy": 0.5294585078954697, |
| "epoch": 2.7126865671641793, |
| "grad_norm": 0.1684177815914154, |
| "learning_rate": 0.0002, |
| "loss": 0.5281128287315369, |
| "mean_token_accuracy": 0.7869527190923691, |
| "num_tokens": 11889574.0, |
| "step": 727 |
| }, |
| { |
| "entropy": 0.532532662153244, |
| "epoch": 2.716417910447761, |
| "grad_norm": 0.22012768685817719, |
| "learning_rate": 0.0002, |
| "loss": 0.5416509509086609, |
| "mean_token_accuracy": 0.7810279577970505, |
| "num_tokens": 11906123.0, |
| "step": 728 |
| }, |
| { |
| "entropy": 0.5120967701077461, |
| "epoch": 2.720149253731343, |
| "grad_norm": 0.1947070211172104, |
| "learning_rate": 0.0002, |
| "loss": 0.5236059427261353, |
| "mean_token_accuracy": 0.7891417741775513, |
| "num_tokens": 11922608.0, |
| "step": 729 |
| }, |
| { |
| "entropy": 0.5193630754947662, |
| "epoch": 2.7238805970149254, |
| "grad_norm": 0.20312415063381195, |
| "learning_rate": 0.0002, |
| "loss": 0.5255002975463867, |
| "mean_token_accuracy": 0.7891178727149963, |
| "num_tokens": 11938915.0, |
| "step": 730 |
| }, |
| { |
| "entropy": 0.5322999209165573, |
| "epoch": 2.7276119402985075, |
| "grad_norm": 0.17771463096141815, |
| "learning_rate": 0.0002, |
| "loss": 0.5273772478103638, |
| "mean_token_accuracy": 0.7864169478416443, |
| "num_tokens": 11955111.0, |
| "step": 731 |
| }, |
| { |
| "entropy": 0.5383205115795135, |
| "epoch": 2.7313432835820897, |
| "grad_norm": 0.15980955958366394, |
| "learning_rate": 0.0002, |
| "loss": 0.5272043943405151, |
| "mean_token_accuracy": 0.7863987386226654, |
| "num_tokens": 11971376.0, |
| "step": 732 |
| }, |
| { |
| "entropy": 0.5206317976117134, |
| "epoch": 2.7350746268656714, |
| "grad_norm": 0.20390352606773376, |
| "learning_rate": 0.0002, |
| "loss": 0.5193040370941162, |
| "mean_token_accuracy": 0.7907106280326843, |
| "num_tokens": 11987514.0, |
| "step": 733 |
| }, |
| { |
| "entropy": 0.5251932889223099, |
| "epoch": 2.7388059701492535, |
| "grad_norm": 0.18475037813186646, |
| "learning_rate": 0.0002, |
| "loss": 0.5309616327285767, |
| "mean_token_accuracy": 0.7846813350915909, |
| "num_tokens": 12003877.0, |
| "step": 734 |
| }, |
| { |
| "entropy": 0.5320010930299759, |
| "epoch": 2.7425373134328357, |
| "grad_norm": 0.1740889698266983, |
| "learning_rate": 0.0002, |
| "loss": 0.5323460102081299, |
| "mean_token_accuracy": 0.7841763645410538, |
| "num_tokens": 12020670.0, |
| "step": 735 |
| }, |
| { |
| "entropy": 0.5126636326313019, |
| "epoch": 2.746268656716418, |
| "grad_norm": 0.16782669723033905, |
| "learning_rate": 0.0002, |
| "loss": 0.5191040635108948, |
| "mean_token_accuracy": 0.790853887796402, |
| "num_tokens": 12037086.0, |
| "step": 736 |
| }, |
| { |
| "entropy": 0.5052774623036385, |
| "epoch": 2.75, |
| "grad_norm": 0.19401201605796814, |
| "learning_rate": 0.0002, |
| "loss": 0.5102320909500122, |
| "mean_token_accuracy": 0.7947344183921814, |
| "num_tokens": 12053495.0, |
| "step": 737 |
| }, |
| { |
| "entropy": 0.5399646162986755, |
| "epoch": 2.753731343283582, |
| "grad_norm": 0.1827477216720581, |
| "learning_rate": 0.0002, |
| "loss": 0.5355514287948608, |
| "mean_token_accuracy": 0.7817161232233047, |
| "num_tokens": 12069931.0, |
| "step": 738 |
| }, |
| { |
| "entropy": 0.5407079011201859, |
| "epoch": 2.7574626865671643, |
| "grad_norm": 0.18165452778339386, |
| "learning_rate": 0.0002, |
| "loss": 0.532011866569519, |
| "mean_token_accuracy": 0.7855027616024017, |
| "num_tokens": 12086130.0, |
| "step": 739 |
| }, |
| { |
| "entropy": 0.542558565735817, |
| "epoch": 2.7611940298507465, |
| "grad_norm": 0.19525423645973206, |
| "learning_rate": 0.0002, |
| "loss": 0.5496971011161804, |
| "mean_token_accuracy": 0.7777255475521088, |
| "num_tokens": 12102368.0, |
| "step": 740 |
| }, |
| { |
| "entropy": 0.5062952637672424, |
| "epoch": 2.7649253731343286, |
| "grad_norm": 0.1739565134048462, |
| "learning_rate": 0.0002, |
| "loss": 0.5101356506347656, |
| "mean_token_accuracy": 0.7917449921369553, |
| "num_tokens": 12118457.0, |
| "step": 741 |
| }, |
| { |
| "entropy": 0.5223133414983749, |
| "epoch": 2.7686567164179103, |
| "grad_norm": 0.1621006429195404, |
| "learning_rate": 0.0002, |
| "loss": 0.5182772874832153, |
| "mean_token_accuracy": 0.7910286039113998, |
| "num_tokens": 12134963.0, |
| "step": 742 |
| }, |
| { |
| "entropy": 0.5320105403661728, |
| "epoch": 2.7723880597014925, |
| "grad_norm": 0.15907934308052063, |
| "learning_rate": 0.0002, |
| "loss": 0.5291880369186401, |
| "mean_token_accuracy": 0.7847632467746735, |
| "num_tokens": 12151254.0, |
| "step": 743 |
| }, |
| { |
| "entropy": 0.5349166542291641, |
| "epoch": 2.7761194029850746, |
| "grad_norm": 0.16063399612903595, |
| "learning_rate": 0.0002, |
| "loss": 0.5322758555412292, |
| "mean_token_accuracy": 0.7834458947181702, |
| "num_tokens": 12167646.0, |
| "step": 744 |
| }, |
| { |
| "entropy": 0.5386681109666824, |
| "epoch": 2.779850746268657, |
| "grad_norm": 0.16322869062423706, |
| "learning_rate": 0.0002, |
| "loss": 0.5323781371116638, |
| "mean_token_accuracy": 0.7845006138086319, |
| "num_tokens": 12183991.0, |
| "step": 745 |
| }, |
| { |
| "entropy": 0.5194026827812195, |
| "epoch": 2.783582089552239, |
| "grad_norm": 0.16580648720264435, |
| "learning_rate": 0.0002, |
| "loss": 0.5227853655815125, |
| "mean_token_accuracy": 0.7889015525579453, |
| "num_tokens": 12200382.0, |
| "step": 746 |
| }, |
| { |
| "entropy": 0.5212684720754623, |
| "epoch": 2.7873134328358207, |
| "grad_norm": 0.17125697433948517, |
| "learning_rate": 0.0002, |
| "loss": 0.5213700532913208, |
| "mean_token_accuracy": 0.7878117114305496, |
| "num_tokens": 12216713.0, |
| "step": 747 |
| }, |
| { |
| "entropy": 0.5110637918114662, |
| "epoch": 2.791044776119403, |
| "grad_norm": 0.16389493644237518, |
| "learning_rate": 0.0002, |
| "loss": 0.5169628858566284, |
| "mean_token_accuracy": 0.7910058498382568, |
| "num_tokens": 12233133.0, |
| "step": 748 |
| }, |
| { |
| "entropy": 0.5152159035205841, |
| "epoch": 2.794776119402985, |
| "grad_norm": 0.16831059753894806, |
| "learning_rate": 0.0002, |
| "loss": 0.5198533535003662, |
| "mean_token_accuracy": 0.7916101217269897, |
| "num_tokens": 12249285.0, |
| "step": 749 |
| }, |
| { |
| "entropy": 0.5124340429902077, |
| "epoch": 2.798507462686567, |
| "grad_norm": 0.19946205615997314, |
| "learning_rate": 0.0002, |
| "loss": 0.5169686079025269, |
| "mean_token_accuracy": 0.7913795113563538, |
| "num_tokens": 12265342.0, |
| "step": 750 |
| }, |
| { |
| "entropy": 0.5103273987770081, |
| "epoch": 2.8022388059701493, |
| "grad_norm": 0.21263223886489868, |
| "learning_rate": 0.0002, |
| "loss": 0.513588547706604, |
| "mean_token_accuracy": 0.7936588376760483, |
| "num_tokens": 12281678.0, |
| "step": 751 |
| }, |
| { |
| "entropy": 0.5249412059783936, |
| "epoch": 2.8059701492537314, |
| "grad_norm": 0.19252505898475647, |
| "learning_rate": 0.0002, |
| "loss": 0.5297028422355652, |
| "mean_token_accuracy": 0.7838840335607529, |
| "num_tokens": 12298088.0, |
| "step": 752 |
| }, |
| { |
| "entropy": 0.5274306833744049, |
| "epoch": 2.8097014925373136, |
| "grad_norm": 0.21943122148513794, |
| "learning_rate": 0.0002, |
| "loss": 0.5324361324310303, |
| "mean_token_accuracy": 0.7866558879613876, |
| "num_tokens": 12314471.0, |
| "step": 753 |
| }, |
| { |
| "entropy": 0.5557888448238373, |
| "epoch": 2.8134328358208958, |
| "grad_norm": 0.20434771478176117, |
| "learning_rate": 0.0002, |
| "loss": 0.5516470670700073, |
| "mean_token_accuracy": 0.7786602973937988, |
| "num_tokens": 12330874.0, |
| "step": 754 |
| }, |
| { |
| "entropy": 0.5457594841718674, |
| "epoch": 2.8171641791044775, |
| "grad_norm": 0.20885495841503143, |
| "learning_rate": 0.0002, |
| "loss": 0.545055091381073, |
| "mean_token_accuracy": 0.7783315926790237, |
| "num_tokens": 12347480.0, |
| "step": 755 |
| }, |
| { |
| "entropy": 0.5113869160413742, |
| "epoch": 2.8208955223880596, |
| "grad_norm": 0.18535853922367096, |
| "learning_rate": 0.0002, |
| "loss": 0.5093449354171753, |
| "mean_token_accuracy": 0.7951165586709976, |
| "num_tokens": 12363508.0, |
| "step": 756 |
| }, |
| { |
| "entropy": 0.515239879488945, |
| "epoch": 2.824626865671642, |
| "grad_norm": 0.1622360795736313, |
| "learning_rate": 0.0002, |
| "loss": 0.5141258239746094, |
| "mean_token_accuracy": 0.7911748439073563, |
| "num_tokens": 12379741.0, |
| "step": 757 |
| }, |
| { |
| "entropy": 0.5246733874082565, |
| "epoch": 2.828358208955224, |
| "grad_norm": 0.19015957415103912, |
| "learning_rate": 0.0002, |
| "loss": 0.5263366103172302, |
| "mean_token_accuracy": 0.7880817353725433, |
| "num_tokens": 12396070.0, |
| "step": 758 |
| }, |
| { |
| "entropy": 0.5205621868371964, |
| "epoch": 2.832089552238806, |
| "grad_norm": 0.1685044765472412, |
| "learning_rate": 0.0002, |
| "loss": 0.5285319685935974, |
| "mean_token_accuracy": 0.7902275174856186, |
| "num_tokens": 12412370.0, |
| "step": 759 |
| }, |
| { |
| "entropy": 0.5027724280953407, |
| "epoch": 2.835820895522388, |
| "grad_norm": 0.19229774177074432, |
| "learning_rate": 0.0002, |
| "loss": 0.50963294506073, |
| "mean_token_accuracy": 0.7949718832969666, |
| "num_tokens": 12428444.0, |
| "step": 760 |
| }, |
| { |
| "entropy": 0.5407818704843521, |
| "epoch": 2.83955223880597, |
| "grad_norm": 0.16733434796333313, |
| "learning_rate": 0.0002, |
| "loss": 0.5386614203453064, |
| "mean_token_accuracy": 0.7833600640296936, |
| "num_tokens": 12444688.0, |
| "step": 761 |
| }, |
| { |
| "entropy": 0.5310073494911194, |
| "epoch": 2.843283582089552, |
| "grad_norm": 0.15908770263195038, |
| "learning_rate": 0.0002, |
| "loss": 0.5266772508621216, |
| "mean_token_accuracy": 0.7857619971036911, |
| "num_tokens": 12461184.0, |
| "step": 762 |
| }, |
| { |
| "entropy": 0.5239167958498001, |
| "epoch": 2.8470149253731343, |
| "grad_norm": 0.20775766670703888, |
| "learning_rate": 0.0002, |
| "loss": 0.521652102470398, |
| "mean_token_accuracy": 0.7865601778030396, |
| "num_tokens": 12477433.0, |
| "step": 763 |
| }, |
| { |
| "entropy": 0.5286514759063721, |
| "epoch": 2.8507462686567164, |
| "grad_norm": 0.16723480820655823, |
| "learning_rate": 0.0002, |
| "loss": 0.5282317996025085, |
| "mean_token_accuracy": 0.7867786735296249, |
| "num_tokens": 12493871.0, |
| "step": 764 |
| }, |
| { |
| "entropy": 0.5268006846308708, |
| "epoch": 2.8544776119402986, |
| "grad_norm": 0.19454815983772278, |
| "learning_rate": 0.0002, |
| "loss": 0.5339269042015076, |
| "mean_token_accuracy": 0.7830109596252441, |
| "num_tokens": 12510041.0, |
| "step": 765 |
| }, |
| { |
| "entropy": 0.5250748991966248, |
| "epoch": 2.8582089552238807, |
| "grad_norm": 0.1809191107749939, |
| "learning_rate": 0.0002, |
| "loss": 0.5232853293418884, |
| "mean_token_accuracy": 0.788041427731514, |
| "num_tokens": 12526385.0, |
| "step": 766 |
| }, |
| { |
| "entropy": 0.5170865803956985, |
| "epoch": 2.861940298507463, |
| "grad_norm": 0.17149843275547028, |
| "learning_rate": 0.0002, |
| "loss": 0.5131306648254395, |
| "mean_token_accuracy": 0.7915859073400497, |
| "num_tokens": 12542670.0, |
| "step": 767 |
| }, |
| { |
| "entropy": 0.5146245658397675, |
| "epoch": 2.8656716417910446, |
| "grad_norm": 0.16911906003952026, |
| "learning_rate": 0.0002, |
| "loss": 0.5146507024765015, |
| "mean_token_accuracy": 0.7927059978246689, |
| "num_tokens": 12558877.0, |
| "step": 768 |
| }, |
| { |
| "entropy": 0.5112384557723999, |
| "epoch": 2.8694029850746268, |
| "grad_norm": 0.1961306780576706, |
| "learning_rate": 0.0002, |
| "loss": 0.5158634185791016, |
| "mean_token_accuracy": 0.7926837652921677, |
| "num_tokens": 12575080.0, |
| "step": 769 |
| }, |
| { |
| "entropy": 0.514963909983635, |
| "epoch": 2.873134328358209, |
| "grad_norm": 0.17623412609100342, |
| "learning_rate": 0.0002, |
| "loss": 0.5148130655288696, |
| "mean_token_accuracy": 0.7924610674381256, |
| "num_tokens": 12591601.0, |
| "step": 770 |
| }, |
| { |
| "entropy": 0.5089290961623192, |
| "epoch": 2.876865671641791, |
| "grad_norm": 0.16756275296211243, |
| "learning_rate": 0.0002, |
| "loss": 0.5092620253562927, |
| "mean_token_accuracy": 0.7940432131290436, |
| "num_tokens": 12607845.0, |
| "step": 771 |
| }, |
| { |
| "entropy": 0.5286067128181458, |
| "epoch": 2.8805970149253732, |
| "grad_norm": 0.16941910982131958, |
| "learning_rate": 0.0002, |
| "loss": 0.5317263603210449, |
| "mean_token_accuracy": 0.7845069319009781, |
| "num_tokens": 12624201.0, |
| "step": 772 |
| }, |
| { |
| "entropy": 0.5381678640842438, |
| "epoch": 2.8843283582089554, |
| "grad_norm": 0.1873699575662613, |
| "learning_rate": 0.0002, |
| "loss": 0.5410081744194031, |
| "mean_token_accuracy": 0.78157077729702, |
| "num_tokens": 12640644.0, |
| "step": 773 |
| }, |
| { |
| "entropy": 0.5046384260058403, |
| "epoch": 2.888059701492537, |
| "grad_norm": 0.17775684595108032, |
| "learning_rate": 0.0002, |
| "loss": 0.5106587409973145, |
| "mean_token_accuracy": 0.7930926978588104, |
| "num_tokens": 12656793.0, |
| "step": 774 |
| }, |
| { |
| "entropy": 0.5368884801864624, |
| "epoch": 2.8917910447761193, |
| "grad_norm": 0.18547044694423676, |
| "learning_rate": 0.0002, |
| "loss": 0.537592887878418, |
| "mean_token_accuracy": 0.7825702279806137, |
| "num_tokens": 12673196.0, |
| "step": 775 |
| }, |
| { |
| "entropy": 0.5347525924444199, |
| "epoch": 2.8955223880597014, |
| "grad_norm": 0.16764505207538605, |
| "learning_rate": 0.0002, |
| "loss": 0.539687991142273, |
| "mean_token_accuracy": 0.782211497426033, |
| "num_tokens": 12689581.0, |
| "step": 776 |
| }, |
| { |
| "entropy": 0.534941777586937, |
| "epoch": 2.8992537313432836, |
| "grad_norm": 0.1721573919057846, |
| "learning_rate": 0.0002, |
| "loss": 0.532742440700531, |
| "mean_token_accuracy": 0.7852998971939087, |
| "num_tokens": 12705990.0, |
| "step": 777 |
| }, |
| { |
| "entropy": 0.5300178974866867, |
| "epoch": 2.9029850746268657, |
| "grad_norm": 0.1695830523967743, |
| "learning_rate": 0.0002, |
| "loss": 0.5286327600479126, |
| "mean_token_accuracy": 0.786633312702179, |
| "num_tokens": 12722378.0, |
| "step": 778 |
| }, |
| { |
| "entropy": 0.5177266895771027, |
| "epoch": 2.906716417910448, |
| "grad_norm": 0.17715924978256226, |
| "learning_rate": 0.0002, |
| "loss": 0.5200332999229431, |
| "mean_token_accuracy": 0.7898508906364441, |
| "num_tokens": 12738959.0, |
| "step": 779 |
| }, |
| { |
| "entropy": 0.5274980813264847, |
| "epoch": 2.91044776119403, |
| "grad_norm": 0.16362538933753967, |
| "learning_rate": 0.0002, |
| "loss": 0.5244265794754028, |
| "mean_token_accuracy": 0.7883569002151489, |
| "num_tokens": 12755523.0, |
| "step": 780 |
| }, |
| { |
| "entropy": 0.5399365872144699, |
| "epoch": 2.914179104477612, |
| "grad_norm": 0.1771351546049118, |
| "learning_rate": 0.0002, |
| "loss": 0.5386828780174255, |
| "mean_token_accuracy": 0.781811535358429, |
| "num_tokens": 12771668.0, |
| "step": 781 |
| }, |
| { |
| "entropy": 0.5337410122156143, |
| "epoch": 2.917910447761194, |
| "grad_norm": 0.17401181161403656, |
| "learning_rate": 0.0002, |
| "loss": 0.5312663316726685, |
| "mean_token_accuracy": 0.784951314330101, |
| "num_tokens": 12788069.0, |
| "step": 782 |
| }, |
| { |
| "entropy": 0.5464458763599396, |
| "epoch": 2.921641791044776, |
| "grad_norm": 0.16721892356872559, |
| "learning_rate": 0.0002, |
| "loss": 0.5472561717033386, |
| "mean_token_accuracy": 0.7816298007965088, |
| "num_tokens": 12804638.0, |
| "step": 783 |
| }, |
| { |
| "entropy": 0.52312833070755, |
| "epoch": 2.925373134328358, |
| "grad_norm": 0.17951072752475739, |
| "learning_rate": 0.0002, |
| "loss": 0.5250601172447205, |
| "mean_token_accuracy": 0.789758563041687, |
| "num_tokens": 12820972.0, |
| "step": 784 |
| }, |
| { |
| "entropy": 0.5356441885232925, |
| "epoch": 2.9291044776119404, |
| "grad_norm": 0.1617494523525238, |
| "learning_rate": 0.0002, |
| "loss": 0.5411362648010254, |
| "mean_token_accuracy": 0.7789859026670456, |
| "num_tokens": 12837494.0, |
| "step": 785 |
| }, |
| { |
| "entropy": 0.5268202722072601, |
| "epoch": 2.9328358208955225, |
| "grad_norm": 0.16186217963695526, |
| "learning_rate": 0.0002, |
| "loss": 0.5264756083488464, |
| "mean_token_accuracy": 0.789272665977478, |
| "num_tokens": 12854115.0, |
| "step": 786 |
| }, |
| { |
| "entropy": 0.5226016044616699, |
| "epoch": 2.9365671641791042, |
| "grad_norm": 0.19670139253139496, |
| "learning_rate": 0.0002, |
| "loss": 0.5276767611503601, |
| "mean_token_accuracy": 0.7866577953100204, |
| "num_tokens": 12870494.0, |
| "step": 787 |
| }, |
| { |
| "entropy": 0.5186894088983536, |
| "epoch": 2.9402985074626864, |
| "grad_norm": 0.16058312356472015, |
| "learning_rate": 0.0002, |
| "loss": 0.5187162756919861, |
| "mean_token_accuracy": 0.7928062081336975, |
| "num_tokens": 12886770.0, |
| "step": 788 |
| }, |
| { |
| "entropy": 0.5392257422208786, |
| "epoch": 2.9440298507462686, |
| "grad_norm": 0.1552664190530777, |
| "learning_rate": 0.0002, |
| "loss": 0.5362218618392944, |
| "mean_token_accuracy": 0.7850502282381058, |
| "num_tokens": 12903294.0, |
| "step": 789 |
| }, |
| { |
| "entropy": 0.5480213761329651, |
| "epoch": 2.9477611940298507, |
| "grad_norm": 0.1846192330121994, |
| "learning_rate": 0.0002, |
| "loss": 0.5483019351959229, |
| "mean_token_accuracy": 0.7795610278844833, |
| "num_tokens": 12919876.0, |
| "step": 790 |
| }, |
| { |
| "entropy": 0.5139886289834976, |
| "epoch": 2.951492537313433, |
| "grad_norm": 0.1738010048866272, |
| "learning_rate": 0.0002, |
| "loss": 0.5166212320327759, |
| "mean_token_accuracy": 0.7915662527084351, |
| "num_tokens": 12936424.0, |
| "step": 791 |
| }, |
| { |
| "entropy": 0.5372511297464371, |
| "epoch": 2.955223880597015, |
| "grad_norm": 0.1778755784034729, |
| "learning_rate": 0.0002, |
| "loss": 0.5388936400413513, |
| "mean_token_accuracy": 0.7815490961074829, |
| "num_tokens": 12952795.0, |
| "step": 792 |
| }, |
| { |
| "entropy": 0.5021091029047966, |
| "epoch": 2.958955223880597, |
| "grad_norm": 0.1743546724319458, |
| "learning_rate": 0.0002, |
| "loss": 0.5121240019798279, |
| "mean_token_accuracy": 0.7943727374076843, |
| "num_tokens": 12969020.0, |
| "step": 793 |
| }, |
| { |
| "entropy": 0.5160349309444427, |
| "epoch": 2.9626865671641793, |
| "grad_norm": 0.15199200809001923, |
| "learning_rate": 0.0002, |
| "loss": 0.5135658383369446, |
| "mean_token_accuracy": 0.7924719452857971, |
| "num_tokens": 12985168.0, |
| "step": 794 |
| }, |
| { |
| "entropy": 0.5263677388429642, |
| "epoch": 2.966417910447761, |
| "grad_norm": 0.15799324214458466, |
| "learning_rate": 0.0002, |
| "loss": 0.5285534262657166, |
| "mean_token_accuracy": 0.7850258648395538, |
| "num_tokens": 13001492.0, |
| "step": 795 |
| }, |
| { |
| "entropy": 0.5156804472208023, |
| "epoch": 2.970149253731343, |
| "grad_norm": 0.15779782831668854, |
| "learning_rate": 0.0002, |
| "loss": 0.5143563747406006, |
| "mean_token_accuracy": 0.7892374396324158, |
| "num_tokens": 13017803.0, |
| "step": 796 |
| }, |
| { |
| "entropy": 0.5375271290540695, |
| "epoch": 2.9738805970149254, |
| "grad_norm": 0.1739465594291687, |
| "learning_rate": 0.0002, |
| "loss": 0.5337483882904053, |
| "mean_token_accuracy": 0.7839883714914322, |
| "num_tokens": 13034208.0, |
| "step": 797 |
| }, |
| { |
| "entropy": 0.5115648582577705, |
| "epoch": 2.9776119402985075, |
| "grad_norm": 0.2207818180322647, |
| "learning_rate": 0.0002, |
| "loss": 0.5210124254226685, |
| "mean_token_accuracy": 0.7909902632236481, |
| "num_tokens": 13050550.0, |
| "step": 798 |
| }, |
| { |
| "entropy": 0.5307280570268631, |
| "epoch": 2.9813432835820897, |
| "grad_norm": 0.19369612634181976, |
| "learning_rate": 0.0002, |
| "loss": 0.5399501323699951, |
| "mean_token_accuracy": 0.7819292396306992, |
| "num_tokens": 13066782.0, |
| "step": 799 |
| }, |
| { |
| "entropy": 0.5347567945718765, |
| "epoch": 2.9850746268656714, |
| "grad_norm": 0.23637999594211578, |
| "learning_rate": 0.0002, |
| "loss": 0.5361707210540771, |
| "mean_token_accuracy": 0.7847548425197601, |
| "num_tokens": 13083205.0, |
| "step": 800 |
| }, |
| { |
| "entropy": 0.5297493487596512, |
| "epoch": 2.9888059701492535, |
| "grad_norm": 0.1621111035346985, |
| "learning_rate": 0.0002, |
| "loss": 0.5200226306915283, |
| "mean_token_accuracy": 0.7869951725006104, |
| "num_tokens": 13099509.0, |
| "step": 801 |
| }, |
| { |
| "entropy": 0.5386456996202469, |
| "epoch": 2.9925373134328357, |
| "grad_norm": 0.1582663208246231, |
| "learning_rate": 0.0002, |
| "loss": 0.529798686504364, |
| "mean_token_accuracy": 0.7863951772451401, |
| "num_tokens": 13115830.0, |
| "step": 802 |
| }, |
| { |
| "entropy": 0.5255069807171822, |
| "epoch": 2.996268656716418, |
| "grad_norm": 0.16664133965969086, |
| "learning_rate": 0.0002, |
| "loss": 0.5226195454597473, |
| "mean_token_accuracy": 0.7878010272979736, |
| "num_tokens": 13132297.0, |
| "step": 803 |
| }, |
| { |
| "entropy": 0.5108897686004639, |
| "epoch": 3.0, |
| "grad_norm": 0.1584617644548416, |
| "learning_rate": 0.0002, |
| "loss": 0.513727605342865, |
| "mean_token_accuracy": 0.791055291891098, |
| "num_tokens": 13148695.0, |
| "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": 1.2253067331114107e+18, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
