| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 234, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 1.223182126879692, |
| "epoch": 0.012903225806451613, |
| "grad_norm": 1.076210379600525, |
| "learning_rate": 0.0, |
| "loss": 2.058398723602295, |
| "mean_token_accuracy": 0.5399363860487938, |
| "num_tokens": 129656.0, |
| "step": 1 |
| }, |
| { |
| "entropy": 1.2220996767282486, |
| "epoch": 0.025806451612903226, |
| "grad_norm": 1.0572984218597412, |
| "learning_rate": 4.166666666666667e-06, |
| "loss": 2.070119857788086, |
| "mean_token_accuracy": 0.5379651635885239, |
| "num_tokens": 257608.0, |
| "step": 2 |
| }, |
| { |
| "entropy": 1.2825039327144623, |
| "epoch": 0.03870967741935484, |
| "grad_norm": 0.9764279723167419, |
| "learning_rate": 8.333333333333334e-06, |
| "loss": 2.0715339183807373, |
| "mean_token_accuracy": 0.5355395078659058, |
| "num_tokens": 385654.0, |
| "step": 3 |
| }, |
| { |
| "entropy": 1.3505332916975021, |
| "epoch": 0.05161290322580645, |
| "grad_norm": 0.8341186046600342, |
| "learning_rate": 1.25e-05, |
| "loss": 2.0449037551879883, |
| "mean_token_accuracy": 0.5337138548493385, |
| "num_tokens": 513578.0, |
| "step": 4 |
| }, |
| { |
| "entropy": 1.3795223087072372, |
| "epoch": 0.06451612903225806, |
| "grad_norm": 0.6299435496330261, |
| "learning_rate": 1.6666666666666667e-05, |
| "loss": 1.9157527685165405, |
| "mean_token_accuracy": 0.5517139434814453, |
| "num_tokens": 643891.0, |
| "step": 5 |
| }, |
| { |
| "entropy": 1.4815990179777145, |
| "epoch": 0.07741935483870968, |
| "grad_norm": 0.4900154173374176, |
| "learning_rate": 2.0833333333333336e-05, |
| "loss": 1.891552448272705, |
| "mean_token_accuracy": 0.5499126613140106, |
| "num_tokens": 773552.0, |
| "step": 6 |
| }, |
| { |
| "entropy": 1.5551793575286865, |
| "epoch": 0.09032258064516129, |
| "grad_norm": 0.36406657099723816, |
| "learning_rate": 2.5e-05, |
| "loss": 1.8251445293426514, |
| "mean_token_accuracy": 0.5556761026382446, |
| "num_tokens": 902676.0, |
| "step": 7 |
| }, |
| { |
| "entropy": 1.6218345165252686, |
| "epoch": 0.1032258064516129, |
| "grad_norm": 0.3063054084777832, |
| "learning_rate": 2.916666666666667e-05, |
| "loss": 1.7969532012939453, |
| "mean_token_accuracy": 0.5583265572786331, |
| "num_tokens": 1031062.0, |
| "step": 8 |
| }, |
| { |
| "entropy": 1.7121598720550537, |
| "epoch": 0.11612903225806452, |
| "grad_norm": 0.2525842785835266, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 1.7734124660491943, |
| "mean_token_accuracy": 0.563885897397995, |
| "num_tokens": 1159144.0, |
| "step": 9 |
| }, |
| { |
| "entropy": 1.7930369228124619, |
| "epoch": 0.12903225806451613, |
| "grad_norm": 0.24535015225410461, |
| "learning_rate": 3.7500000000000003e-05, |
| "loss": 1.7790138721466064, |
| "mean_token_accuracy": 0.5602867007255554, |
| "num_tokens": 1286047.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 1.8023179322481155, |
| "epoch": 0.14193548387096774, |
| "grad_norm": 0.2574515640735626, |
| "learning_rate": 4.166666666666667e-05, |
| "loss": 1.7038989067077637, |
| "mean_token_accuracy": 0.5719256922602654, |
| "num_tokens": 1414956.0, |
| "step": 11 |
| }, |
| { |
| "entropy": 1.8494196385145187, |
| "epoch": 0.15483870967741936, |
| "grad_norm": 0.28199130296707153, |
| "learning_rate": 4.5833333333333334e-05, |
| "loss": 1.6980609893798828, |
| "mean_token_accuracy": 0.5720911771059036, |
| "num_tokens": 1544083.0, |
| "step": 12 |
| }, |
| { |
| "entropy": 1.8534925431013107, |
| "epoch": 0.16774193548387098, |
| "grad_norm": 0.29593202471733093, |
| "learning_rate": 5e-05, |
| "loss": 1.6669628620147705, |
| "mean_token_accuracy": 0.5764533281326294, |
| "num_tokens": 1673817.0, |
| "step": 13 |
| }, |
| { |
| "entropy": 1.7742547988891602, |
| "epoch": 0.18064516129032257, |
| "grad_norm": 0.2752297818660736, |
| "learning_rate": 4.9997496794168726e-05, |
| "loss": 1.5782192945480347, |
| "mean_token_accuracy": 0.5955501049757004, |
| "num_tokens": 1801770.0, |
| "step": 14 |
| }, |
| { |
| "entropy": 1.8175705522298813, |
| "epoch": 0.1935483870967742, |
| "grad_norm": 0.2872096300125122, |
| "learning_rate": 4.998998767795805e-05, |
| "loss": 1.5999691486358643, |
| "mean_token_accuracy": 0.5888361930847168, |
| "num_tokens": 1931723.0, |
| "step": 15 |
| }, |
| { |
| "entropy": 1.7427806854248047, |
| "epoch": 0.2064516129032258, |
| "grad_norm": 0.2521703839302063, |
| "learning_rate": 4.9977474155117045e-05, |
| "loss": 1.5546669960021973, |
| "mean_token_accuracy": 0.5967967882752419, |
| "num_tokens": 2061345.0, |
| "step": 16 |
| }, |
| { |
| "entropy": 1.6578464657068253, |
| "epoch": 0.21935483870967742, |
| "grad_norm": 0.22542445361614227, |
| "learning_rate": 4.995995873155958e-05, |
| "loss": 1.5100972652435303, |
| "mean_token_accuracy": 0.6021811291575432, |
| "num_tokens": 2190508.0, |
| "step": 17 |
| }, |
| { |
| "entropy": 1.598375290632248, |
| "epoch": 0.23225806451612904, |
| "grad_norm": 0.1917019784450531, |
| "learning_rate": 4.99374449148625e-05, |
| "loss": 1.490499496459961, |
| "mean_token_accuracy": 0.60594841837883, |
| "num_tokens": 2318941.0, |
| "step": 18 |
| }, |
| { |
| "entropy": 1.5606479495763779, |
| "epoch": 0.24516129032258063, |
| "grad_norm": 0.1699151247739792, |
| "learning_rate": 4.9909937213563165e-05, |
| "loss": 1.480535626411438, |
| "mean_token_accuracy": 0.607219472527504, |
| "num_tokens": 2448059.0, |
| "step": 19 |
| }, |
| { |
| "entropy": 1.5005332827568054, |
| "epoch": 0.25806451612903225, |
| "grad_norm": 0.15443331003189087, |
| "learning_rate": 4.987744113625665e-05, |
| "loss": 1.4707814455032349, |
| "mean_token_accuracy": 0.6087440326809883, |
| "num_tokens": 2577375.0, |
| "step": 20 |
| }, |
| { |
| "entropy": 1.3930998891592026, |
| "epoch": 0.2709677419354839, |
| "grad_norm": 0.1559259444475174, |
| "learning_rate": 4.9839963190492576e-05, |
| "loss": 1.410855770111084, |
| "mean_token_accuracy": 0.6227314248681068, |
| "num_tokens": 2707055.0, |
| "step": 21 |
| }, |
| { |
| "entropy": 1.36322420835495, |
| "epoch": 0.2838709677419355, |
| "grad_norm": 0.20294561982154846, |
| "learning_rate": 4.979751088147192e-05, |
| "loss": 1.4284950494766235, |
| "mean_token_accuracy": 0.6158238276839256, |
| "num_tokens": 2836471.0, |
| "step": 22 |
| }, |
| { |
| "entropy": 1.3222410529851913, |
| "epoch": 0.2967741935483871, |
| "grad_norm": 0.22203199565410614, |
| "learning_rate": 4.975009271054409e-05, |
| "loss": 1.4026174545288086, |
| "mean_token_accuracy": 0.6221327260136604, |
| "num_tokens": 2967186.0, |
| "step": 23 |
| }, |
| { |
| "entropy": 1.3454352766275406, |
| "epoch": 0.3096774193548387, |
| "grad_norm": 0.2088484764099121, |
| "learning_rate": 4.969771817350445e-05, |
| "loss": 1.4195332527160645, |
| "mean_token_accuracy": 0.6193315461277962, |
| "num_tokens": 3091283.0, |
| "step": 24 |
| }, |
| { |
| "entropy": 1.3203742057085037, |
| "epoch": 0.3225806451612903, |
| "grad_norm": 0.1915750652551651, |
| "learning_rate": 4.9640397758692715e-05, |
| "loss": 1.3804551362991333, |
| "mean_token_accuracy": 0.626660019159317, |
| "num_tokens": 3221704.0, |
| "step": 25 |
| }, |
| { |
| "entropy": 1.3405092060565948, |
| "epoch": 0.33548387096774196, |
| "grad_norm": 0.16226191818714142, |
| "learning_rate": 4.957814294489261e-05, |
| "loss": 1.3678839206695557, |
| "mean_token_accuracy": 0.6271623075008392, |
| "num_tokens": 3351359.0, |
| "step": 26 |
| }, |
| { |
| "entropy": 1.3681351393461227, |
| "epoch": 0.34838709677419355, |
| "grad_norm": 0.15001052618026733, |
| "learning_rate": 4.9510966199033174e-05, |
| "loss": 1.3961801528930664, |
| "mean_token_accuracy": 0.6210252344608307, |
| "num_tokens": 3480058.0, |
| "step": 27 |
| }, |
| { |
| "entropy": 1.360452800989151, |
| "epoch": 0.36129032258064514, |
| "grad_norm": 0.13115695118904114, |
| "learning_rate": 4.943888097369216e-05, |
| "loss": 1.3473964929580688, |
| "mean_token_accuracy": 0.6314521729946136, |
| "num_tokens": 3610897.0, |
| "step": 28 |
| }, |
| { |
| "entropy": 1.3818826526403427, |
| "epoch": 0.3741935483870968, |
| "grad_norm": 0.12812234461307526, |
| "learning_rate": 4.936190170440208e-05, |
| "loss": 1.3602492809295654, |
| "mean_token_accuracy": 0.6298193782567978, |
| "num_tokens": 3740627.0, |
| "step": 29 |
| }, |
| { |
| "entropy": 1.3282616436481476, |
| "epoch": 0.3870967741935484, |
| "grad_norm": 0.12813468277454376, |
| "learning_rate": 4.928004380675941e-05, |
| "loss": 1.2889750003814697, |
| "mean_token_accuracy": 0.6441097930073738, |
| "num_tokens": 3869695.0, |
| "step": 30 |
| }, |
| { |
| "entropy": 1.3403072953224182, |
| "epoch": 0.4, |
| "grad_norm": 0.1254233419895172, |
| "learning_rate": 4.9193323673337476e-05, |
| "loss": 1.3034392595291138, |
| "mean_token_accuracy": 0.6405649855732918, |
| "num_tokens": 3998221.0, |
| "step": 31 |
| }, |
| { |
| "entropy": 1.3977190256118774, |
| "epoch": 0.4129032258064516, |
| "grad_norm": 0.13067315518856049, |
| "learning_rate": 4.910175867040377e-05, |
| "loss": 1.354722261428833, |
| "mean_token_accuracy": 0.6276756450533867, |
| "num_tokens": 4127108.0, |
| "step": 32 |
| }, |
| { |
| "entropy": 1.348634958267212, |
| "epoch": 0.4258064516129032, |
| "grad_norm": 0.12189042568206787, |
| "learning_rate": 4.9005367134442235e-05, |
| "loss": 1.3136909008026123, |
| "mean_token_accuracy": 0.6381376534700394, |
| "num_tokens": 4256994.0, |
| "step": 33 |
| }, |
| { |
| "entropy": 1.3185934275388718, |
| "epoch": 0.43870967741935485, |
| "grad_norm": 0.1224159300327301, |
| "learning_rate": 4.890416836848127e-05, |
| "loss": 1.2872580289840698, |
| "mean_token_accuracy": 0.6426139622926712, |
| "num_tokens": 4385244.0, |
| "step": 34 |
| }, |
| { |
| "entropy": 1.2890230417251587, |
| "epoch": 0.45161290322580644, |
| "grad_norm": 0.11730781197547913, |
| "learning_rate": 4.8798182638228166e-05, |
| "loss": 1.2566399574279785, |
| "mean_token_accuracy": 0.649329274892807, |
| "num_tokens": 4515175.0, |
| "step": 35 |
| }, |
| { |
| "entropy": 1.3161695450544357, |
| "epoch": 0.4645161290322581, |
| "grad_norm": 0.11564701795578003, |
| "learning_rate": 4.868743116801074e-05, |
| "loss": 1.2894011735916138, |
| "mean_token_accuracy": 0.6447330787777901, |
| "num_tokens": 4644464.0, |
| "step": 36 |
| }, |
| { |
| "entropy": 1.263451337814331, |
| "epoch": 0.4774193548387097, |
| "grad_norm": 0.11025005578994751, |
| "learning_rate": 4.857193613652711e-05, |
| "loss": 1.250872254371643, |
| "mean_token_accuracy": 0.6496427357196808, |
| "num_tokens": 4774388.0, |
| "step": 37 |
| }, |
| { |
| "entropy": 1.2831027507781982, |
| "epoch": 0.49032258064516127, |
| "grad_norm": 0.11225498467683792, |
| "learning_rate": 4.845172067240415e-05, |
| "loss": 1.2833701372146606, |
| "mean_token_accuracy": 0.642292931675911, |
| "num_tokens": 4903171.0, |
| "step": 38 |
| }, |
| { |
| "entropy": 1.28334479033947, |
| "epoch": 0.5032258064516129, |
| "grad_norm": 0.11390651762485504, |
| "learning_rate": 4.8326808849565936e-05, |
| "loss": 1.2927157878875732, |
| "mean_token_accuracy": 0.6402992084622383, |
| "num_tokens": 5033677.0, |
| "step": 39 |
| }, |
| { |
| "entropy": 1.2627993077039719, |
| "epoch": 0.5161290322580645, |
| "grad_norm": 0.1086907684803009, |
| "learning_rate": 4.819722568241274e-05, |
| "loss": 1.2574979066848755, |
| "mean_token_accuracy": 0.6465372666716576, |
| "num_tokens": 5163487.0, |
| "step": 40 |
| }, |
| { |
| "entropy": 1.2626460939645767, |
| "epoch": 0.5290322580645161, |
| "grad_norm": 0.10910395532846451, |
| "learning_rate": 4.806299712081172e-05, |
| "loss": 1.266538381576538, |
| "mean_token_accuracy": 0.6473062336444855, |
| "num_tokens": 5292899.0, |
| "step": 41 |
| }, |
| { |
| "entropy": 1.2527801245450974, |
| "epoch": 0.5419354838709678, |
| "grad_norm": 0.10939069092273712, |
| "learning_rate": 4.792415004490034e-05, |
| "loss": 1.2544794082641602, |
| "mean_token_accuracy": 0.6493285819888115, |
| "num_tokens": 5422025.0, |
| "step": 42 |
| }, |
| { |
| "entropy": 1.2684112191200256, |
| "epoch": 0.5548387096774193, |
| "grad_norm": 0.10955163091421127, |
| "learning_rate": 4.77807122597034e-05, |
| "loss": 1.2640540599822998, |
| "mean_token_accuracy": 0.6442403197288513, |
| "num_tokens": 5551149.0, |
| "step": 43 |
| }, |
| { |
| "entropy": 1.202114075422287, |
| "epoch": 0.567741935483871, |
| "grad_norm": 0.10252036899328232, |
| "learning_rate": 4.7632712489564926e-05, |
| "loss": 1.2032322883605957, |
| "mean_token_accuracy": 0.6615511402487755, |
| "num_tokens": 5680701.0, |
| "step": 44 |
| }, |
| { |
| "entropy": 1.2185258865356445, |
| "epoch": 0.5806451612903226, |
| "grad_norm": 0.10858958959579468, |
| "learning_rate": 4.748018037239592e-05, |
| "loss": 1.2210724353790283, |
| "mean_token_accuracy": 0.6543648615479469, |
| "num_tokens": 5808493.0, |
| "step": 45 |
| }, |
| { |
| "entropy": 1.2259098291397095, |
| "epoch": 0.5935483870967742, |
| "grad_norm": 0.10566595196723938, |
| "learning_rate": 4.732314645373921e-05, |
| "loss": 1.2279314994812012, |
| "mean_token_accuracy": 0.6541318669915199, |
| "num_tokens": 5938296.0, |
| "step": 46 |
| }, |
| { |
| "entropy": 1.217906042933464, |
| "epoch": 0.6064516129032258, |
| "grad_norm": 0.10399080067873001, |
| "learning_rate": 4.7161642180652464e-05, |
| "loss": 1.2170512676239014, |
| "mean_token_accuracy": 0.6552224531769753, |
| "num_tokens": 6067439.0, |
| "step": 47 |
| }, |
| { |
| "entropy": 1.243887796998024, |
| "epoch": 0.6193548387096774, |
| "grad_norm": 0.10374640673398972, |
| "learning_rate": 4.699569989541074e-05, |
| "loss": 1.2446861267089844, |
| "mean_token_accuracy": 0.6509256213903427, |
| "num_tokens": 6197510.0, |
| "step": 48 |
| }, |
| { |
| "entropy": 1.2262021899223328, |
| "epoch": 0.632258064516129, |
| "grad_norm": 0.10401046276092529, |
| "learning_rate": 4.6825352829029705e-05, |
| "loss": 1.2263641357421875, |
| "mean_token_accuracy": 0.6529856100678444, |
| "num_tokens": 6327768.0, |
| "step": 49 |
| }, |
| { |
| "entropy": 1.1782560497522354, |
| "epoch": 0.6451612903225806, |
| "grad_norm": 0.10297931730747223, |
| "learning_rate": 4.665063509461097e-05, |
| "loss": 1.1814297437667847, |
| "mean_token_accuracy": 0.6635062471032143, |
| "num_tokens": 6455846.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 1.2240826934576035, |
| "epoch": 0.6580645161290323, |
| "grad_norm": 0.10559607297182083, |
| "learning_rate": 4.647158168051066e-05, |
| "loss": 1.2128801345825195, |
| "mean_token_accuracy": 0.659131720662117, |
| "num_tokens": 6585457.0, |
| "step": 51 |
| }, |
| { |
| "entropy": 1.2306331396102905, |
| "epoch": 0.6709677419354839, |
| "grad_norm": 0.10558925569057465, |
| "learning_rate": 4.628822844333278e-05, |
| "loss": 1.2250795364379883, |
| "mean_token_accuracy": 0.6541951075196266, |
| "num_tokens": 6716096.0, |
| "step": 52 |
| }, |
| { |
| "entropy": 1.2307018637657166, |
| "epoch": 0.6838709677419355, |
| "grad_norm": 0.106507308781147, |
| "learning_rate": 4.6100612100748765e-05, |
| "loss": 1.216687798500061, |
| "mean_token_accuracy": 0.657420352101326, |
| "num_tokens": 6844341.0, |
| "step": 53 |
| }, |
| { |
| "entropy": 1.1905661970376968, |
| "epoch": 0.6967741935483871, |
| "grad_norm": 0.1018037423491478, |
| "learning_rate": 4.59087702241444e-05, |
| "loss": 1.1824817657470703, |
| "mean_token_accuracy": 0.6638368740677834, |
| "num_tokens": 6971794.0, |
| "step": 54 |
| }, |
| { |
| "entropy": 1.2321506142616272, |
| "epoch": 0.7096774193548387, |
| "grad_norm": 0.1053023412823677, |
| "learning_rate": 4.571274123109606e-05, |
| "loss": 1.2273911237716675, |
| "mean_token_accuracy": 0.6531050652265549, |
| "num_tokens": 7100353.0, |
| "step": 55 |
| }, |
| { |
| "entropy": 1.1877244710922241, |
| "epoch": 0.7225806451612903, |
| "grad_norm": 0.10472644120454788, |
| "learning_rate": 4.551256437767719e-05, |
| "loss": 1.1830646991729736, |
| "mean_token_accuracy": 0.662447988986969, |
| "num_tokens": 7230177.0, |
| "step": 56 |
| }, |
| { |
| "entropy": 1.1354379504919052, |
| "epoch": 0.7354838709677419, |
| "grad_norm": 0.10116837918758392, |
| "learning_rate": 4.530827975059715e-05, |
| "loss": 1.1367874145507812, |
| "mean_token_accuracy": 0.6742443069815636, |
| "num_tokens": 7359042.0, |
| "step": 57 |
| }, |
| { |
| "entropy": 1.1323172450065613, |
| "epoch": 0.7483870967741936, |
| "grad_norm": 0.10149563103914261, |
| "learning_rate": 4.5099928259173516e-05, |
| "loss": 1.1368333101272583, |
| "mean_token_accuracy": 0.6757072061300278, |
| "num_tokens": 7488137.0, |
| "step": 58 |
| }, |
| { |
| "entropy": 1.1689679026603699, |
| "epoch": 0.7612903225806451, |
| "grad_norm": 0.10289032757282257, |
| "learning_rate": 4.488755162713975e-05, |
| "loss": 1.170515775680542, |
| "mean_token_accuracy": 0.6659915670752525, |
| "num_tokens": 7618282.0, |
| "step": 59 |
| }, |
| { |
| "entropy": 1.1511125713586807, |
| "epoch": 0.7741935483870968, |
| "grad_norm": 0.10344893485307693, |
| "learning_rate": 4.467119238428975e-05, |
| "loss": 1.1578235626220703, |
| "mean_token_accuracy": 0.6681751757860184, |
| "num_tokens": 7748017.0, |
| "step": 60 |
| }, |
| { |
| "entropy": 1.15065398812294, |
| "epoch": 0.7870967741935484, |
| "grad_norm": 0.10410141944885254, |
| "learning_rate": 4.445089385796099e-05, |
| "loss": 1.1545982360839844, |
| "mean_token_accuracy": 0.6693510711193085, |
| "num_tokens": 7876986.0, |
| "step": 61 |
| }, |
| { |
| "entropy": 1.1854369789361954, |
| "epoch": 0.8, |
| "grad_norm": 0.10658932477235794, |
| "learning_rate": 4.422670016435792e-05, |
| "loss": 1.1886390447616577, |
| "mean_token_accuracy": 0.6610049903392792, |
| "num_tokens": 8006794.0, |
| "step": 62 |
| }, |
| { |
| "entropy": 1.1734878718852997, |
| "epoch": 0.8129032258064516, |
| "grad_norm": 0.0999564528465271, |
| "learning_rate": 4.3998656199717435e-05, |
| "loss": 1.1779112815856934, |
| "mean_token_accuracy": 0.6633528992533684, |
| "num_tokens": 8135408.0, |
| "step": 63 |
| }, |
| { |
| "entropy": 1.1888367980718613, |
| "epoch": 0.8258064516129032, |
| "grad_norm": 0.1022685319185257, |
| "learning_rate": 4.3766807631318106e-05, |
| "loss": 1.1841375827789307, |
| "mean_token_accuracy": 0.6636051461100578, |
| "num_tokens": 8265182.0, |
| "step": 64 |
| }, |
| { |
| "entropy": 1.1773615032434464, |
| "epoch": 0.8387096774193549, |
| "grad_norm": 0.10359368473291397, |
| "learning_rate": 4.353120088833501e-05, |
| "loss": 1.1596578359603882, |
| "mean_token_accuracy": 0.6664805710315704, |
| "num_tokens": 8395710.0, |
| "step": 65 |
| }, |
| { |
| "entropy": 1.1735037863254547, |
| "epoch": 0.8516129032258064, |
| "grad_norm": 0.10424409806728363, |
| "learning_rate": 4.329188315254196e-05, |
| "loss": 1.1645269393920898, |
| "mean_token_accuracy": 0.6646556481719017, |
| "num_tokens": 8525026.0, |
| "step": 66 |
| }, |
| { |
| "entropy": 1.1600711345672607, |
| "epoch": 0.864516129032258, |
| "grad_norm": 0.10298816114664078, |
| "learning_rate": 4.3048902348863116e-05, |
| "loss": 1.146191120147705, |
| "mean_token_accuracy": 0.6732870414853096, |
| "num_tokens": 8655176.0, |
| "step": 67 |
| }, |
| { |
| "entropy": 1.1675972044467926, |
| "epoch": 0.8774193548387097, |
| "grad_norm": 0.09964212030172348, |
| "learning_rate": 4.280230713577564e-05, |
| "loss": 1.1639752388000488, |
| "mean_token_accuracy": 0.6678973436355591, |
| "num_tokens": 8784950.0, |
| "step": 68 |
| }, |
| { |
| "entropy": 1.1486363634467125, |
| "epoch": 0.8903225806451613, |
| "grad_norm": 0.10526347905397415, |
| "learning_rate": 4.255214689556557e-05, |
| "loss": 1.1550880670547485, |
| "mean_token_accuracy": 0.669487789273262, |
| "num_tokens": 8915424.0, |
| "step": 69 |
| }, |
| { |
| "entropy": 1.1960512697696686, |
| "epoch": 0.9032258064516129, |
| "grad_norm": 0.10434431582689285, |
| "learning_rate": 4.229847172443866e-05, |
| "loss": 1.195779800415039, |
| "mean_token_accuracy": 0.6591227054595947, |
| "num_tokens": 9043958.0, |
| "step": 70 |
| }, |
| { |
| "entropy": 1.1383194029331207, |
| "epoch": 0.9161290322580645, |
| "grad_norm": 0.10281933099031448, |
| "learning_rate": 4.204133242248832e-05, |
| "loss": 1.1457536220550537, |
| "mean_token_accuracy": 0.670663595199585, |
| "num_tokens": 9173238.0, |
| "step": 71 |
| }, |
| { |
| "entropy": 1.1284168064594269, |
| "epoch": 0.9290322580645162, |
| "grad_norm": 0.10491844266653061, |
| "learning_rate": 4.1780780483522575e-05, |
| "loss": 1.1363515853881836, |
| "mean_token_accuracy": 0.6729972660541534, |
| "num_tokens": 9303178.0, |
| "step": 72 |
| }, |
| { |
| "entropy": 1.155638337135315, |
| "epoch": 0.9419354838709677, |
| "grad_norm": 0.10739096254110336, |
| "learning_rate": 4.151686808475204e-05, |
| "loss": 1.1668245792388916, |
| "mean_token_accuracy": 0.6647603213787079, |
| "num_tokens": 9432086.0, |
| "step": 73 |
| }, |
| { |
| "entropy": 1.1737090498209, |
| "epoch": 0.9548387096774194, |
| "grad_norm": 0.10476558655500412, |
| "learning_rate": 4.1249648076341165e-05, |
| "loss": 1.1709017753601074, |
| "mean_token_accuracy": 0.6655773147940636, |
| "num_tokens": 9560333.0, |
| "step": 74 |
| }, |
| { |
| "entropy": 1.1429373025894165, |
| "epoch": 0.967741935483871, |
| "grad_norm": 0.09973709285259247, |
| "learning_rate": 4.0979173970824626e-05, |
| "loss": 1.1408506631851196, |
| "mean_token_accuracy": 0.6709853634238243, |
| "num_tokens": 9689775.0, |
| "step": 75 |
| }, |
| { |
| "entropy": 1.131405919790268, |
| "epoch": 0.9806451612903225, |
| "grad_norm": 0.10272659361362457, |
| "learning_rate": 4.070549993239106e-05, |
| "loss": 1.1342134475708008, |
| "mean_token_accuracy": 0.6737439185380936, |
| "num_tokens": 9818901.0, |
| "step": 76 |
| }, |
| { |
| "entropy": 1.1382378786802292, |
| "epoch": 0.9935483870967742, |
| "grad_norm": 0.10625957697629929, |
| "learning_rate": 4.0428680766036384e-05, |
| "loss": 1.1314501762390137, |
| "mean_token_accuracy": 0.6726028546690941, |
| "num_tokens": 9948460.0, |
| "step": 77 |
| }, |
| { |
| "entropy": 1.1366769075393677, |
| "epoch": 1.0, |
| "grad_norm": 0.14248473942279816, |
| "learning_rate": 4.0148771906588706e-05, |
| "loss": 1.120863676071167, |
| "mean_token_accuracy": 0.6762505769729614, |
| "num_tokens": 9997067.0, |
| "step": 78 |
| }, |
| { |
| "entropy": 1.1518085598945618, |
| "epoch": 1.0129032258064516, |
| "grad_norm": 0.10363268852233887, |
| "learning_rate": 3.986582940760717e-05, |
| "loss": 1.1300816535949707, |
| "mean_token_accuracy": 0.6724538877606392, |
| "num_tokens": 10126462.0, |
| "step": 79 |
| }, |
| { |
| "entropy": 1.1565421894192696, |
| "epoch": 1.0258064516129033, |
| "grad_norm": 0.10230233520269394, |
| "learning_rate": 3.957990993015683e-05, |
| "loss": 1.150430679321289, |
| "mean_token_accuracy": 0.6694934591650963, |
| "num_tokens": 10256580.0, |
| "step": 80 |
| }, |
| { |
| "entropy": 1.1469500064849854, |
| "epoch": 1.038709677419355, |
| "grad_norm": 0.1017085388302803, |
| "learning_rate": 3.929107073146197e-05, |
| "loss": 1.137932300567627, |
| "mean_token_accuracy": 0.672937422990799, |
| "num_tokens": 10385670.0, |
| "step": 81 |
| }, |
| { |
| "entropy": 1.1146536320447922, |
| "epoch": 1.0516129032258064, |
| "grad_norm": 0.10386557132005692, |
| "learning_rate": 3.899936965343989e-05, |
| "loss": 1.1186662912368774, |
| "mean_token_accuracy": 0.6774236634373665, |
| "num_tokens": 10515880.0, |
| "step": 82 |
| }, |
| { |
| "entropy": 1.1311339735984802, |
| "epoch": 1.064516129032258, |
| "grad_norm": 0.10529699176549911, |
| "learning_rate": 3.8704865111117746e-05, |
| "loss": 1.1309411525726318, |
| "mean_token_accuracy": 0.6742902398109436, |
| "num_tokens": 10645214.0, |
| "step": 83 |
| }, |
| { |
| "entropy": 1.0882018506526947, |
| "epoch": 1.0774193548387097, |
| "grad_norm": 0.1024845689535141, |
| "learning_rate": 3.840761608093456e-05, |
| "loss": 1.0901994705200195, |
| "mean_token_accuracy": 0.6838363260030746, |
| "num_tokens": 10775324.0, |
| "step": 84 |
| }, |
| { |
| "entropy": 1.081175297498703, |
| "epoch": 1.0903225806451613, |
| "grad_norm": 0.10421576350927353, |
| "learning_rate": 3.8107682088930794e-05, |
| "loss": 1.083613395690918, |
| "mean_token_accuracy": 0.6847718432545662, |
| "num_tokens": 10906115.0, |
| "step": 85 |
| }, |
| { |
| "entropy": 1.1237317472696304, |
| "epoch": 1.103225806451613, |
| "grad_norm": 0.10275532305240631, |
| "learning_rate": 3.7805123198827857e-05, |
| "loss": 1.1233375072479248, |
| "mean_token_accuracy": 0.673041544854641, |
| "num_tokens": 11036082.0, |
| "step": 86 |
| }, |
| { |
| "entropy": 1.1282892972230911, |
| "epoch": 1.1161290322580646, |
| "grad_norm": 0.11031878739595413, |
| "learning_rate": 3.7500000000000003e-05, |
| "loss": 1.134421467781067, |
| "mean_token_accuracy": 0.6718096882104874, |
| "num_tokens": 11166308.0, |
| "step": 87 |
| }, |
| { |
| "entropy": 1.1246851980686188, |
| "epoch": 1.129032258064516, |
| "grad_norm": 0.10738931596279144, |
| "learning_rate": 3.719237359534087e-05, |
| "loss": 1.1162521839141846, |
| "mean_token_accuracy": 0.6750943064689636, |
| "num_tokens": 11296038.0, |
| "step": 88 |
| }, |
| { |
| "entropy": 1.091427892446518, |
| "epoch": 1.1419354838709677, |
| "grad_norm": 0.1043296754360199, |
| "learning_rate": 3.688230558902725e-05, |
| "loss": 1.0911470651626587, |
| "mean_token_accuracy": 0.6818756312131882, |
| "num_tokens": 11424449.0, |
| "step": 89 |
| }, |
| { |
| "entropy": 1.0753950253129005, |
| "epoch": 1.1548387096774193, |
| "grad_norm": 0.10350479930639267, |
| "learning_rate": 3.656985807418248e-05, |
| "loss": 1.07297682762146, |
| "mean_token_accuracy": 0.6874061748385429, |
| "num_tokens": 11553352.0, |
| "step": 90 |
| }, |
| { |
| "entropy": 1.0837179571390152, |
| "epoch": 1.167741935483871, |
| "grad_norm": 0.10422831773757935, |
| "learning_rate": 3.6255093620441834e-05, |
| "loss": 1.0784122943878174, |
| "mean_token_accuracy": 0.6853957697749138, |
| "num_tokens": 11683188.0, |
| "step": 91 |
| }, |
| { |
| "entropy": 1.0955706387758255, |
| "epoch": 1.1806451612903226, |
| "grad_norm": 0.1034531518816948, |
| "learning_rate": 3.593807526142261e-05, |
| "loss": 1.0929460525512695, |
| "mean_token_accuracy": 0.680936798453331, |
| "num_tokens": 11812927.0, |
| "step": 92 |
| }, |
| { |
| "entropy": 1.1230056285858154, |
| "epoch": 1.1935483870967742, |
| "grad_norm": 0.10683950036764145, |
| "learning_rate": 3.56188664821012e-05, |
| "loss": 1.1296939849853516, |
| "mean_token_accuracy": 0.6739164963364601, |
| "num_tokens": 11941868.0, |
| "step": 93 |
| }, |
| { |
| "entropy": 1.0906171947717667, |
| "epoch": 1.206451612903226, |
| "grad_norm": 0.11000493913888931, |
| "learning_rate": 3.529753120609982e-05, |
| "loss": 1.1027157306671143, |
| "mean_token_accuracy": 0.6794363781809807, |
| "num_tokens": 12070500.0, |
| "step": 94 |
| }, |
| { |
| "entropy": 1.1029838472604752, |
| "epoch": 1.2193548387096773, |
| "grad_norm": 0.10395485907793045, |
| "learning_rate": 3.497413378288541e-05, |
| "loss": 1.1018798351287842, |
| "mean_token_accuracy": 0.6790261566638947, |
| "num_tokens": 12199259.0, |
| "step": 95 |
| }, |
| { |
| "entropy": 1.0792984515428543, |
| "epoch": 1.232258064516129, |
| "grad_norm": 0.10340157896280289, |
| "learning_rate": 3.464873897488322e-05, |
| "loss": 1.0742807388305664, |
| "mean_token_accuracy": 0.6854443848133087, |
| "num_tokens": 12327381.0, |
| "step": 96 |
| }, |
| { |
| "entropy": 1.1040336340665817, |
| "epoch": 1.2451612903225806, |
| "grad_norm": 0.1052948608994484, |
| "learning_rate": 3.432141194450772e-05, |
| "loss": 1.1013096570968628, |
| "mean_token_accuracy": 0.6796243190765381, |
| "num_tokens": 12457229.0, |
| "step": 97 |
| }, |
| { |
| "entropy": 1.0985784828662872, |
| "epoch": 1.2580645161290323, |
| "grad_norm": 0.10637353360652924, |
| "learning_rate": 3.39922182411134e-05, |
| "loss": 1.092590570449829, |
| "mean_token_accuracy": 0.6829387545585632, |
| "num_tokens": 12587371.0, |
| "step": 98 |
| }, |
| { |
| "entropy": 1.108673334121704, |
| "epoch": 1.270967741935484, |
| "grad_norm": 0.1088114008307457, |
| "learning_rate": 3.3661223787868094e-05, |
| "loss": 1.1037486791610718, |
| "mean_token_accuracy": 0.6788453385233879, |
| "num_tokens": 12714956.0, |
| "step": 99 |
| }, |
| { |
| "entropy": 1.116018533706665, |
| "epoch": 1.2838709677419355, |
| "grad_norm": 0.10825629532337189, |
| "learning_rate": 3.332849486855144e-05, |
| "loss": 1.1191405057907104, |
| "mean_token_accuracy": 0.6735457330942154, |
| "num_tokens": 12845041.0, |
| "step": 100 |
| }, |
| { |
| "entropy": 1.0860655605793, |
| "epoch": 1.2967741935483872, |
| "grad_norm": 0.104007288813591, |
| "learning_rate": 3.2994098114281134e-05, |
| "loss": 1.0827304124832153, |
| "mean_token_accuracy": 0.6839027926325798, |
| "num_tokens": 12974429.0, |
| "step": 101 |
| }, |
| { |
| "entropy": 1.0645690262317657, |
| "epoch": 1.3096774193548386, |
| "grad_norm": 0.10804564505815506, |
| "learning_rate": 3.265810049016959e-05, |
| "loss": 1.0671439170837402, |
| "mean_token_accuracy": 0.6886417642235756, |
| "num_tokens": 13103925.0, |
| "step": 102 |
| }, |
| { |
| "entropy": 1.1119411289691925, |
| "epoch": 1.3225806451612903, |
| "grad_norm": 0.107361800968647, |
| "learning_rate": 3.232056928191376e-05, |
| "loss": 1.1194833517074585, |
| "mean_token_accuracy": 0.6785841062664986, |
| "num_tokens": 13232750.0, |
| "step": 103 |
| }, |
| { |
| "entropy": 1.0839634910225868, |
| "epoch": 1.335483870967742, |
| "grad_norm": 0.10487478226423264, |
| "learning_rate": 3.1981572082320756e-05, |
| "loss": 1.0855300426483154, |
| "mean_token_accuracy": 0.6837950944900513, |
| "num_tokens": 13362678.0, |
| "step": 104 |
| }, |
| { |
| "entropy": 1.0855423361063004, |
| "epoch": 1.3483870967741935, |
| "grad_norm": 0.10489385575056076, |
| "learning_rate": 3.164117677777191e-05, |
| "loss": 1.0878322124481201, |
| "mean_token_accuracy": 0.6815162599086761, |
| "num_tokens": 13493019.0, |
| "step": 105 |
| }, |
| { |
| "entropy": 1.0708462968468666, |
| "epoch": 1.3612903225806452, |
| "grad_norm": 0.10663817077875137, |
| "learning_rate": 3.1299451534628135e-05, |
| "loss": 1.0679532289505005, |
| "mean_token_accuracy": 0.686631441116333, |
| "num_tokens": 13622495.0, |
| "step": 106 |
| }, |
| { |
| "entropy": 1.0779114365577698, |
| "epoch": 1.3741935483870968, |
| "grad_norm": 0.1084500178694725, |
| "learning_rate": 3.0956464785579124e-05, |
| "loss": 1.0651929378509521, |
| "mean_token_accuracy": 0.6884163245558739, |
| "num_tokens": 13751405.0, |
| "step": 107 |
| }, |
| { |
| "entropy": 1.0858594700694084, |
| "epoch": 1.3870967741935485, |
| "grad_norm": 0.10940396040678024, |
| "learning_rate": 3.061228521593931e-05, |
| "loss": 1.0804402828216553, |
| "mean_token_accuracy": 0.6820845901966095, |
| "num_tokens": 13881358.0, |
| "step": 108 |
| }, |
| { |
| "entropy": 1.0628213062882423, |
| "epoch": 1.4, |
| "grad_norm": 0.10861281305551529, |
| "learning_rate": 3.0266981749893157e-05, |
| "loss": 1.0724735260009766, |
| "mean_token_accuracy": 0.6882258728146553, |
| "num_tokens": 14010084.0, |
| "step": 109 |
| }, |
| { |
| "entropy": 1.0851275622844696, |
| "epoch": 1.4129032258064516, |
| "grad_norm": 0.1063976064324379, |
| "learning_rate": 2.9920623536692638e-05, |
| "loss": 1.0848662853240967, |
| "mean_token_accuracy": 0.6824500113725662, |
| "num_tokens": 14139791.0, |
| "step": 110 |
| }, |
| { |
| "entropy": 1.06889808177948, |
| "epoch": 1.4258064516129032, |
| "grad_norm": 0.1091022938489914, |
| "learning_rate": 2.9573279936809667e-05, |
| "loss": 1.071213960647583, |
| "mean_token_accuracy": 0.6864099279046059, |
| "num_tokens": 14270212.0, |
| "step": 111 |
| }, |
| { |
| "entropy": 1.0951210632920265, |
| "epoch": 1.4387096774193548, |
| "grad_norm": 0.10497217625379562, |
| "learning_rate": 2.9225020508046232e-05, |
| "loss": 1.090355396270752, |
| "mean_token_accuracy": 0.6813758462667465, |
| "num_tokens": 14400115.0, |
| "step": 112 |
| }, |
| { |
| "entropy": 1.1012007743120193, |
| "epoch": 1.4516129032258065, |
| "grad_norm": 0.11282135546207428, |
| "learning_rate": 2.8875914991604948e-05, |
| "loss": 1.0943909883499146, |
| "mean_token_accuracy": 0.6812350302934647, |
| "num_tokens": 14530182.0, |
| "step": 113 |
| }, |
| { |
| "entropy": 1.0668123438954353, |
| "epoch": 1.4645161290322581, |
| "grad_norm": 0.10792876034975052, |
| "learning_rate": 2.8526033298122985e-05, |
| "loss": 1.0663881301879883, |
| "mean_token_accuracy": 0.6888832896947861, |
| "num_tokens": 14658760.0, |
| "step": 114 |
| }, |
| { |
| "entropy": 1.075245887041092, |
| "epoch": 1.4774193548387098, |
| "grad_norm": 0.10725358873605728, |
| "learning_rate": 2.8175445493671972e-05, |
| "loss": 1.0732371807098389, |
| "mean_token_accuracy": 0.6830701306462288, |
| "num_tokens": 14787887.0, |
| "step": 115 |
| }, |
| { |
| "entropy": 1.080723062157631, |
| "epoch": 1.4903225806451612, |
| "grad_norm": 0.11148032546043396, |
| "learning_rate": 2.782422178572682e-05, |
| "loss": 1.080810308456421, |
| "mean_token_accuracy": 0.6856769248843193, |
| "num_tokens": 14917268.0, |
| "step": 116 |
| }, |
| { |
| "entropy": 1.0670917555689812, |
| "epoch": 1.5032258064516129, |
| "grad_norm": 0.10839603841304779, |
| "learning_rate": 2.7472432509106248e-05, |
| "loss": 1.0708037614822388, |
| "mean_token_accuracy": 0.6860948503017426, |
| "num_tokens": 15044663.0, |
| "step": 117 |
| }, |
| { |
| "entropy": 1.0836158990859985, |
| "epoch": 1.5161290322580645, |
| "grad_norm": 0.10698815435171127, |
| "learning_rate": 2.7120148111887732e-05, |
| "loss": 1.0807759761810303, |
| "mean_token_accuracy": 0.6842784956097603, |
| "num_tokens": 15174619.0, |
| "step": 118 |
| }, |
| { |
| "entropy": 1.0987706929445267, |
| "epoch": 1.5290322580645161, |
| "grad_norm": 0.10540509968996048, |
| "learning_rate": 2.6767439141299865e-05, |
| "loss": 1.1040892601013184, |
| "mean_token_accuracy": 0.6808092296123505, |
| "num_tokens": 15304197.0, |
| "step": 119 |
| }, |
| { |
| "entropy": 1.047809176146984, |
| "epoch": 1.5419354838709678, |
| "grad_norm": 0.1058097556233406, |
| "learning_rate": 2.6414376229594813e-05, |
| "loss": 1.0483499765396118, |
| "mean_token_accuracy": 0.6921439915895462, |
| "num_tokens": 15432579.0, |
| "step": 120 |
| }, |
| { |
| "entropy": 1.0963650196790695, |
| "epoch": 1.5548387096774192, |
| "grad_norm": 0.11119414865970612, |
| "learning_rate": 2.606103007990371e-05, |
| "loss": 1.0984492301940918, |
| "mean_token_accuracy": 0.6789131611585617, |
| "num_tokens": 15561722.0, |
| "step": 121 |
| }, |
| { |
| "entropy": 1.0872581899166107, |
| "epoch": 1.567741935483871, |
| "grad_norm": 0.10610063374042511, |
| "learning_rate": 2.570747145207796e-05, |
| "loss": 1.098354697227478, |
| "mean_token_accuracy": 0.6784585490822792, |
| "num_tokens": 15691958.0, |
| "step": 122 |
| }, |
| { |
| "entropy": 1.0838341489434242, |
| "epoch": 1.5806451612903225, |
| "grad_norm": 0.10991805791854858, |
| "learning_rate": 2.5353771148519057e-05, |
| "loss": 1.0900540351867676, |
| "mean_token_accuracy": 0.6810095012187958, |
| "num_tokens": 15821165.0, |
| "step": 123 |
| }, |
| { |
| "entropy": 1.056675523519516, |
| "epoch": 1.5935483870967742, |
| "grad_norm": 0.10874482244253159, |
| "learning_rate": 2.5e-05, |
| "loss": 1.0548217296600342, |
| "mean_token_accuracy": 0.6896284446120262, |
| "num_tokens": 15949216.0, |
| "step": 124 |
| }, |
| { |
| "entropy": 1.061226338148117, |
| "epoch": 1.6064516129032258, |
| "grad_norm": 0.10914712399244308, |
| "learning_rate": 2.4646228851480956e-05, |
| "loss": 1.061427354812622, |
| "mean_token_accuracy": 0.687263511121273, |
| "num_tokens": 16078522.0, |
| "step": 125 |
| }, |
| { |
| "entropy": 1.0842180401086807, |
| "epoch": 1.6193548387096774, |
| "grad_norm": 0.10912276804447174, |
| "learning_rate": 2.429252854792205e-05, |
| "loss": 1.0773967504501343, |
| "mean_token_accuracy": 0.6844106987118721, |
| "num_tokens": 16208166.0, |
| "step": 126 |
| }, |
| { |
| "entropy": 1.0762254372239113, |
| "epoch": 1.632258064516129, |
| "grad_norm": 0.10727284848690033, |
| "learning_rate": 2.39389699200963e-05, |
| "loss": 1.074779987335205, |
| "mean_token_accuracy": 0.684668280184269, |
| "num_tokens": 16338202.0, |
| "step": 127 |
| }, |
| { |
| "entropy": 1.0513081327080727, |
| "epoch": 1.6451612903225805, |
| "grad_norm": 0.10655758529901505, |
| "learning_rate": 2.358562377040519e-05, |
| "loss": 1.04603111743927, |
| "mean_token_accuracy": 0.6915493980050087, |
| "num_tokens": 16468262.0, |
| "step": 128 |
| }, |
| { |
| "entropy": 1.0846867859363556, |
| "epoch": 1.6580645161290324, |
| "grad_norm": 0.10952936857938766, |
| "learning_rate": 2.3232560858700137e-05, |
| "loss": 1.0864813327789307, |
| "mean_token_accuracy": 0.6824182942509651, |
| "num_tokens": 16597219.0, |
| "step": 129 |
| }, |
| { |
| "entropy": 1.0925589501857758, |
| "epoch": 1.6709677419354838, |
| "grad_norm": 0.10761820524930954, |
| "learning_rate": 2.287985188811228e-05, |
| "loss": 1.0888445377349854, |
| "mean_token_accuracy": 0.680370032787323, |
| "num_tokens": 16725933.0, |
| "step": 130 |
| }, |
| { |
| "entropy": 1.0831595808267593, |
| "epoch": 1.6838709677419355, |
| "grad_norm": 0.11058152467012405, |
| "learning_rate": 2.2527567490893758e-05, |
| "loss": 1.0811421871185303, |
| "mean_token_accuracy": 0.681232288479805, |
| "num_tokens": 16854221.0, |
| "step": 131 |
| }, |
| { |
| "entropy": 1.0961327701807022, |
| "epoch": 1.696774193548387, |
| "grad_norm": 0.10876961052417755, |
| "learning_rate": 2.2175778214273185e-05, |
| "loss": 1.0899490118026733, |
| "mean_token_accuracy": 0.6814906597137451, |
| "num_tokens": 16984319.0, |
| "step": 132 |
| }, |
| { |
| "entropy": 1.0888055264949799, |
| "epoch": 1.7096774193548387, |
| "grad_norm": 0.1107635572552681, |
| "learning_rate": 2.182455450632803e-05, |
| "loss": 1.088341236114502, |
| "mean_token_accuracy": 0.6830911487340927, |
| "num_tokens": 17112766.0, |
| "step": 133 |
| }, |
| { |
| "entropy": 1.0918050706386566, |
| "epoch": 1.7225806451612904, |
| "grad_norm": 0.10795822739601135, |
| "learning_rate": 2.1473966701877025e-05, |
| "loss": 1.0982195138931274, |
| "mean_token_accuracy": 0.6785562857985497, |
| "num_tokens": 17241888.0, |
| "step": 134 |
| }, |
| { |
| "entropy": 1.0576870888471603, |
| "epoch": 1.7354838709677418, |
| "grad_norm": 0.10716155916452408, |
| "learning_rate": 2.1124085008395054e-05, |
| "loss": 1.056051254272461, |
| "mean_token_accuracy": 0.6887547969818115, |
| "num_tokens": 17371518.0, |
| "step": 135 |
| }, |
| { |
| "entropy": 1.080827847123146, |
| "epoch": 1.7483870967741937, |
| "grad_norm": 0.10587362200021744, |
| "learning_rate": 2.0774979491953777e-05, |
| "loss": 1.0835041999816895, |
| "mean_token_accuracy": 0.6818873062729836, |
| "num_tokens": 17501856.0, |
| "step": 136 |
| }, |
| { |
| "entropy": 1.0682593137025833, |
| "epoch": 1.761290322580645, |
| "grad_norm": 0.10766828060150146, |
| "learning_rate": 2.0426720063190335e-05, |
| "loss": 1.0668219327926636, |
| "mean_token_accuracy": 0.6868961676955223, |
| "num_tokens": 17630077.0, |
| "step": 137 |
| }, |
| { |
| "entropy": 1.0730333402752876, |
| "epoch": 1.7741935483870968, |
| "grad_norm": 0.11129513382911682, |
| "learning_rate": 2.0079376463307368e-05, |
| "loss": 1.0753192901611328, |
| "mean_token_accuracy": 0.6843588948249817, |
| "num_tokens": 17757628.0, |
| "step": 138 |
| }, |
| { |
| "entropy": 1.0627059638500214, |
| "epoch": 1.7870967741935484, |
| "grad_norm": 0.1097295805811882, |
| "learning_rate": 1.973301825010685e-05, |
| "loss": 1.0669927597045898, |
| "mean_token_accuracy": 0.6858029961585999, |
| "num_tokens": 17887287.0, |
| "step": 139 |
| }, |
| { |
| "entropy": 1.1067379415035248, |
| "epoch": 1.8, |
| "grad_norm": 0.10846037417650223, |
| "learning_rate": 1.9387714784060685e-05, |
| "loss": 1.1105893850326538, |
| "mean_token_accuracy": 0.6761542558670044, |
| "num_tokens": 18016015.0, |
| "step": 140 |
| }, |
| { |
| "entropy": 1.0782186388969421, |
| "epoch": 1.8129032258064517, |
| "grad_norm": 0.10785773396492004, |
| "learning_rate": 1.904353521442088e-05, |
| "loss": 1.0804530382156372, |
| "mean_token_accuracy": 0.6803460195660591, |
| "num_tokens": 18145940.0, |
| "step": 141 |
| }, |
| { |
| "entropy": 1.0552142038941383, |
| "epoch": 1.8258064516129031, |
| "grad_norm": 0.11273064464330673, |
| "learning_rate": 1.8700548465371874e-05, |
| "loss": 1.0440943241119385, |
| "mean_token_accuracy": 0.6903438195586205, |
| "num_tokens": 18276039.0, |
| "step": 142 |
| }, |
| { |
| "entropy": 1.0844019800424576, |
| "epoch": 1.838709677419355, |
| "grad_norm": 0.10984650254249573, |
| "learning_rate": 1.8358823222228097e-05, |
| "loss": 1.0856590270996094, |
| "mean_token_accuracy": 0.6822653189301491, |
| "num_tokens": 18401790.0, |
| "step": 143 |
| }, |
| { |
| "entropy": 1.0662296265363693, |
| "epoch": 1.8516129032258064, |
| "grad_norm": 0.10815320163965225, |
| "learning_rate": 1.801842791767925e-05, |
| "loss": 1.0641754865646362, |
| "mean_token_accuracy": 0.6871967539191246, |
| "num_tokens": 18530808.0, |
| "step": 144 |
| }, |
| { |
| "entropy": 1.0416738837957382, |
| "epoch": 1.864516129032258, |
| "grad_norm": 0.10722067207098007, |
| "learning_rate": 1.7679430718086243e-05, |
| "loss": 1.043981909751892, |
| "mean_token_accuracy": 0.6929837614297867, |
| "num_tokens": 18659766.0, |
| "step": 145 |
| }, |
| { |
| "entropy": 1.0620247423648834, |
| "epoch": 1.8774193548387097, |
| "grad_norm": 0.10642781108617783, |
| "learning_rate": 1.7341899509830416e-05, |
| "loss": 1.0664876699447632, |
| "mean_token_accuracy": 0.6869184374809265, |
| "num_tokens": 18789014.0, |
| "step": 146 |
| }, |
| { |
| "entropy": 1.083692416548729, |
| "epoch": 1.8903225806451613, |
| "grad_norm": 0.10695701092481613, |
| "learning_rate": 1.700590188571887e-05, |
| "loss": 1.0759789943695068, |
| "mean_token_accuracy": 0.6821576431393623, |
| "num_tokens": 18918025.0, |
| "step": 147 |
| }, |
| { |
| "entropy": 1.0451694130897522, |
| "epoch": 1.903225806451613, |
| "grad_norm": 0.11168710142374039, |
| "learning_rate": 1.667150513144856e-05, |
| "loss": 1.04537832736969, |
| "mean_token_accuracy": 0.6932294592261314, |
| "num_tokens": 19048295.0, |
| "step": 148 |
| }, |
| { |
| "entropy": 1.0767835974693298, |
| "epoch": 1.9161290322580644, |
| "grad_norm": 0.10878083854913712, |
| "learning_rate": 1.633877621213192e-05, |
| "loss": 1.0719680786132812, |
| "mean_token_accuracy": 0.6834145188331604, |
| "num_tokens": 19173607.0, |
| "step": 149 |
| }, |
| { |
| "entropy": 1.054766684770584, |
| "epoch": 1.9290322580645163, |
| "grad_norm": 0.10753705352544785, |
| "learning_rate": 1.6007781758886607e-05, |
| "loss": 1.0576591491699219, |
| "mean_token_accuracy": 0.6865810304880142, |
| "num_tokens": 19303083.0, |
| "step": 150 |
| }, |
| { |
| "entropy": 1.1032528281211853, |
| "epoch": 1.9419354838709677, |
| "grad_norm": 0.11035779863595963, |
| "learning_rate": 1.567858805549229e-05, |
| "loss": 1.100153923034668, |
| "mean_token_accuracy": 0.6790175065398216, |
| "num_tokens": 19431668.0, |
| "step": 151 |
| }, |
| { |
| "entropy": 1.095763847231865, |
| "epoch": 1.9548387096774194, |
| "grad_norm": 0.10870419442653656, |
| "learning_rate": 1.535126102511678e-05, |
| "loss": 1.0910307168960571, |
| "mean_token_accuracy": 0.6778731271624565, |
| "num_tokens": 19560373.0, |
| "step": 152 |
| }, |
| { |
| "entropy": 1.0872143507003784, |
| "epoch": 1.967741935483871, |
| "grad_norm": 0.11192327737808228, |
| "learning_rate": 1.5025866217114592e-05, |
| "loss": 1.0831270217895508, |
| "mean_token_accuracy": 0.6787481904029846, |
| "num_tokens": 19688747.0, |
| "step": 153 |
| }, |
| { |
| "entropy": 1.090033859014511, |
| "epoch": 1.9806451612903224, |
| "grad_norm": 0.11166636645793915, |
| "learning_rate": 1.4702468793900188e-05, |
| "loss": 1.0931189060211182, |
| "mean_token_accuracy": 0.6795905977487564, |
| "num_tokens": 19816935.0, |
| "step": 154 |
| }, |
| { |
| "entropy": 1.0729367583990097, |
| "epoch": 1.9935483870967743, |
| "grad_norm": 0.10527553409337997, |
| "learning_rate": 1.4381133517898804e-05, |
| "loss": 1.0672760009765625, |
| "mean_token_accuracy": 0.686238594353199, |
| "num_tokens": 19946010.0, |
| "step": 155 |
| }, |
| { |
| "entropy": 1.0717603862285614, |
| "epoch": 2.0, |
| "grad_norm": 0.14860950410366058, |
| "learning_rate": 1.4061924738577403e-05, |
| "loss": 1.0576205253601074, |
| "mean_token_accuracy": 0.6823940128087997, |
| "num_tokens": 19994005.0, |
| "step": 156 |
| }, |
| { |
| "entropy": 1.0596345961093903, |
| "epoch": 2.0129032258064514, |
| "grad_norm": 0.10707081109285355, |
| "learning_rate": 1.3744906379558165e-05, |
| "loss": 1.0458970069885254, |
| "mean_token_accuracy": 0.6898052915930748, |
| "num_tokens": 20123770.0, |
| "step": 157 |
| }, |
| { |
| "entropy": 1.0868264734745026, |
| "epoch": 2.0258064516129033, |
| "grad_norm": 0.11118680983781815, |
| "learning_rate": 1.3430141925817532e-05, |
| "loss": 1.0691285133361816, |
| "mean_token_accuracy": 0.6845634579658508, |
| "num_tokens": 20253618.0, |
| "step": 158 |
| }, |
| { |
| "entropy": 1.0599489361047745, |
| "epoch": 2.0387096774193547, |
| "grad_norm": 0.10883183032274246, |
| "learning_rate": 1.3117694410972748e-05, |
| "loss": 1.0526676177978516, |
| "mean_token_accuracy": 0.6902280747890472, |
| "num_tokens": 20382498.0, |
| "step": 159 |
| }, |
| { |
| "entropy": 1.0741997808218002, |
| "epoch": 2.0516129032258066, |
| "grad_norm": 0.10998189449310303, |
| "learning_rate": 1.2807626404659142e-05, |
| "loss": 1.0633370876312256, |
| "mean_token_accuracy": 0.6858223527669907, |
| "num_tokens": 20511465.0, |
| "step": 160 |
| }, |
| { |
| "entropy": 1.0478936806321144, |
| "epoch": 2.064516129032258, |
| "grad_norm": 0.10860773175954819, |
| "learning_rate": 1.2500000000000006e-05, |
| "loss": 1.0446070432662964, |
| "mean_token_accuracy": 0.6915075108408928, |
| "num_tokens": 20640276.0, |
| "step": 161 |
| }, |
| { |
| "entropy": 1.0602229833602905, |
| "epoch": 2.07741935483871, |
| "grad_norm": 0.10706065595149994, |
| "learning_rate": 1.2194876801172148e-05, |
| "loss": 1.0545692443847656, |
| "mean_token_accuracy": 0.6886847466230392, |
| "num_tokens": 20770635.0, |
| "step": 162 |
| }, |
| { |
| "entropy": 1.0668027848005295, |
| "epoch": 2.0903225806451613, |
| "grad_norm": 0.10802215337753296, |
| "learning_rate": 1.1892317911069212e-05, |
| "loss": 1.0540719032287598, |
| "mean_token_accuracy": 0.6878442168235779, |
| "num_tokens": 20900634.0, |
| "step": 163 |
| }, |
| { |
| "entropy": 1.0489486157894135, |
| "epoch": 2.1032258064516127, |
| "grad_norm": 0.10800980031490326, |
| "learning_rate": 1.1592383919065442e-05, |
| "loss": 1.0526444911956787, |
| "mean_token_accuracy": 0.6882949322462082, |
| "num_tokens": 21030337.0, |
| "step": 164 |
| }, |
| { |
| "entropy": 1.0250826254487038, |
| "epoch": 2.1161290322580646, |
| "grad_norm": 0.10843278467655182, |
| "learning_rate": 1.1295134888882258e-05, |
| "loss": 1.0237047672271729, |
| "mean_token_accuracy": 0.697336807847023, |
| "num_tokens": 21160459.0, |
| "step": 165 |
| }, |
| { |
| "entropy": 1.057710163295269, |
| "epoch": 2.129032258064516, |
| "grad_norm": 0.11167071014642715, |
| "learning_rate": 1.1000630346560117e-05, |
| "loss": 1.065138578414917, |
| "mean_token_accuracy": 0.6859450489282608, |
| "num_tokens": 21289979.0, |
| "step": 166 |
| }, |
| { |
| "entropy": 1.0299690663814545, |
| "epoch": 2.141935483870968, |
| "grad_norm": 0.1100035309791565, |
| "learning_rate": 1.0708929268538034e-05, |
| "loss": 1.0371811389923096, |
| "mean_token_accuracy": 0.6927487999200821, |
| "num_tokens": 21417697.0, |
| "step": 167 |
| }, |
| { |
| "entropy": 1.0722354650497437, |
| "epoch": 2.1548387096774193, |
| "grad_norm": 0.10992293059825897, |
| "learning_rate": 1.0420090069843167e-05, |
| "loss": 1.073203206062317, |
| "mean_token_accuracy": 0.6821405664086342, |
| "num_tokens": 21547900.0, |
| "step": 168 |
| }, |
| { |
| "entropy": 1.0406329035758972, |
| "epoch": 2.167741935483871, |
| "grad_norm": 0.11027650535106659, |
| "learning_rate": 1.0134170592392836e-05, |
| "loss": 1.0443116426467896, |
| "mean_token_accuracy": 0.6919047608971596, |
| "num_tokens": 21677940.0, |
| "step": 169 |
| }, |
| { |
| "entropy": 1.0213668644428253, |
| "epoch": 2.1806451612903226, |
| "grad_norm": 0.10933554172515869, |
| "learning_rate": 9.851228093411296e-06, |
| "loss": 1.0201184749603271, |
| "mean_token_accuracy": 0.6964388787746429, |
| "num_tokens": 21807629.0, |
| "step": 170 |
| }, |
| { |
| "entropy": 1.0638275891542435, |
| "epoch": 2.193548387096774, |
| "grad_norm": 0.11138866096735, |
| "learning_rate": 9.571319233963627e-06, |
| "loss": 1.0656756162643433, |
| "mean_token_accuracy": 0.685239166021347, |
| "num_tokens": 21937842.0, |
| "step": 171 |
| }, |
| { |
| "entropy": 1.0584878250956535, |
| "epoch": 2.206451612903226, |
| "grad_norm": 0.11099617183208466, |
| "learning_rate": 9.29450006760894e-06, |
| "loss": 1.0568838119506836, |
| "mean_token_accuracy": 0.6879113540053368, |
| "num_tokens": 22067033.0, |
| "step": 172 |
| }, |
| { |
| "entropy": 1.0079772621393204, |
| "epoch": 2.2193548387096773, |
| "grad_norm": 0.10624755918979645, |
| "learning_rate": 9.020826029175384e-06, |
| "loss": 1.0130298137664795, |
| "mean_token_accuracy": 0.6985160782933235, |
| "num_tokens": 22196381.0, |
| "step": 173 |
| }, |
| { |
| "entropy": 1.0430931448936462, |
| "epoch": 2.232258064516129, |
| "grad_norm": 0.11061278730630875, |
| "learning_rate": 8.750351923658832e-06, |
| "loss": 1.0414340496063232, |
| "mean_token_accuracy": 0.6911179795861244, |
| "num_tokens": 22325575.0, |
| "step": 174 |
| }, |
| { |
| "entropy": 1.0494736358523369, |
| "epoch": 2.2451612903225806, |
| "grad_norm": 0.10799900442361832, |
| "learning_rate": 8.483131915247968e-06, |
| "loss": 1.0516412258148193, |
| "mean_token_accuracy": 0.6891112700104713, |
| "num_tokens": 22454987.0, |
| "step": 175 |
| }, |
| { |
| "entropy": 1.0281440168619156, |
| "epoch": 2.258064516129032, |
| "grad_norm": 0.10775752365589142, |
| "learning_rate": 8.219219516477428e-06, |
| "loss": 1.0262537002563477, |
| "mean_token_accuracy": 0.6939218863844872, |
| "num_tokens": 22584324.0, |
| "step": 176 |
| }, |
| { |
| "entropy": 1.050694078207016, |
| "epoch": 2.270967741935484, |
| "grad_norm": 0.10874587297439575, |
| "learning_rate": 7.958667577511683e-06, |
| "loss": 1.0525567531585693, |
| "mean_token_accuracy": 0.6875178813934326, |
| "num_tokens": 22713028.0, |
| "step": 177 |
| }, |
| { |
| "entropy": 1.055702917277813, |
| "epoch": 2.2838709677419353, |
| "grad_norm": 0.10784310102462769, |
| "learning_rate": 7.701528275561348e-06, |
| "loss": 1.048429012298584, |
| "mean_token_accuracy": 0.6900188326835632, |
| "num_tokens": 22841542.0, |
| "step": 178 |
| }, |
| { |
| "entropy": 1.0563756823539734, |
| "epoch": 2.296774193548387, |
| "grad_norm": 0.11210503429174423, |
| "learning_rate": 7.447853104434438e-06, |
| "loss": 1.0528168678283691, |
| "mean_token_accuracy": 0.6885445043444633, |
| "num_tokens": 22969323.0, |
| "step": 179 |
| }, |
| { |
| "entropy": 1.0545407757163048, |
| "epoch": 2.3096774193548386, |
| "grad_norm": 0.10958606004714966, |
| "learning_rate": 7.197692864224365e-06, |
| "loss": 1.0522735118865967, |
| "mean_token_accuracy": 0.687314435839653, |
| "num_tokens": 23098695.0, |
| "step": 180 |
| }, |
| { |
| "entropy": 1.0319481864571571, |
| "epoch": 2.3225806451612905, |
| "grad_norm": 0.10795482993125916, |
| "learning_rate": 6.951097651136889e-06, |
| "loss": 1.0273221731185913, |
| "mean_token_accuracy": 0.6960562095046043, |
| "num_tokens": 23228396.0, |
| "step": 181 |
| }, |
| { |
| "entropy": 1.0450568944215775, |
| "epoch": 2.335483870967742, |
| "grad_norm": 0.10884442180395126, |
| "learning_rate": 6.708116847458043e-06, |
| "loss": 1.0443098545074463, |
| "mean_token_accuracy": 0.6926383003592491, |
| "num_tokens": 23358823.0, |
| "step": 182 |
| }, |
| { |
| "entropy": 1.0453576296567917, |
| "epoch": 2.3483870967741938, |
| "grad_norm": 0.10940878838300705, |
| "learning_rate": 6.468799111665003e-06, |
| "loss": 1.0371437072753906, |
| "mean_token_accuracy": 0.6917492002248764, |
| "num_tokens": 23488354.0, |
| "step": 183 |
| }, |
| { |
| "entropy": 1.0119262486696243, |
| "epoch": 2.361290322580645, |
| "grad_norm": 0.10757909715175629, |
| "learning_rate": 6.23319236868189e-06, |
| "loss": 1.0083694458007812, |
| "mean_token_accuracy": 0.7006818130612373, |
| "num_tokens": 23618360.0, |
| "step": 184 |
| }, |
| { |
| "entropy": 1.0501391366124153, |
| "epoch": 2.3741935483870966, |
| "grad_norm": 0.11320532858371735, |
| "learning_rate": 6.001343800282569e-06, |
| "loss": 1.0464301109313965, |
| "mean_token_accuracy": 0.6907839700579643, |
| "num_tokens": 23748436.0, |
| "step": 185 |
| }, |
| { |
| "entropy": 1.0813187807798386, |
| "epoch": 2.3870967741935485, |
| "grad_norm": 0.11211083829402924, |
| "learning_rate": 5.7732998356420796e-06, |
| "loss": 1.0763766765594482, |
| "mean_token_accuracy": 0.6818836182355881, |
| "num_tokens": 23874993.0, |
| "step": 186 |
| }, |
| { |
| "entropy": 1.0404710844159126, |
| "epoch": 2.4, |
| "grad_norm": 0.10749558359384537, |
| "learning_rate": 5.549106142039018e-06, |
| "loss": 1.0386872291564941, |
| "mean_token_accuracy": 0.6925826296210289, |
| "num_tokens": 24003568.0, |
| "step": 187 |
| }, |
| { |
| "entropy": 1.0303776264190674, |
| "epoch": 2.412903225806452, |
| "grad_norm": 0.10823489725589752, |
| "learning_rate": 5.328807615710246e-06, |
| "loss": 1.0304882526397705, |
| "mean_token_accuracy": 0.6956811174750328, |
| "num_tokens": 24133856.0, |
| "step": 188 |
| }, |
| { |
| "entropy": 1.0453997105360031, |
| "epoch": 2.425806451612903, |
| "grad_norm": 0.10833070427179337, |
| "learning_rate": 5.112448372860257e-06, |
| "loss": 1.0392625331878662, |
| "mean_token_accuracy": 0.6904457956552505, |
| "num_tokens": 24264174.0, |
| "step": 189 |
| }, |
| { |
| "entropy": 1.028484746813774, |
| "epoch": 2.4387096774193546, |
| "grad_norm": 0.11039452254772186, |
| "learning_rate": 4.900071740826489e-06, |
| "loss": 1.0227563381195068, |
| "mean_token_accuracy": 0.6968299075961113, |
| "num_tokens": 24391008.0, |
| "step": 190 |
| }, |
| { |
| "entropy": 1.0460204929113388, |
| "epoch": 2.4516129032258065, |
| "grad_norm": 0.10934290289878845, |
| "learning_rate": 4.691720249402856e-06, |
| "loss": 1.052173137664795, |
| "mean_token_accuracy": 0.6907312348484993, |
| "num_tokens": 24518432.0, |
| "step": 191 |
| }, |
| { |
| "entropy": 1.0388439744710922, |
| "epoch": 2.464516129032258, |
| "grad_norm": 0.10959555208683014, |
| "learning_rate": 4.487435622322814e-06, |
| "loss": 1.037489414215088, |
| "mean_token_accuracy": 0.6960867270827293, |
| "num_tokens": 24647693.0, |
| "step": 192 |
| }, |
| { |
| "entropy": 1.041866846382618, |
| "epoch": 2.47741935483871, |
| "grad_norm": 0.10859796404838562, |
| "learning_rate": 4.2872587689039484e-06, |
| "loss": 1.039006233215332, |
| "mean_token_accuracy": 0.6929642558097839, |
| "num_tokens": 24776864.0, |
| "step": 193 |
| }, |
| { |
| "entropy": 1.0423323065042496, |
| "epoch": 2.490322580645161, |
| "grad_norm": 0.1073613241314888, |
| "learning_rate": 4.091229775855598e-06, |
| "loss": 1.0422580242156982, |
| "mean_token_accuracy": 0.6903884261846542, |
| "num_tokens": 24905902.0, |
| "step": 194 |
| }, |
| { |
| "entropy": 1.0294964462518692, |
| "epoch": 2.5032258064516126, |
| "grad_norm": 0.11159957200288773, |
| "learning_rate": 3.8993878992512415e-06, |
| "loss": 1.0288416147232056, |
| "mean_token_accuracy": 0.6945132687687874, |
| "num_tokens": 25034657.0, |
| "step": 195 |
| }, |
| { |
| "entropy": 1.033381126821041, |
| "epoch": 2.5161290322580645, |
| "grad_norm": 0.10906282067298889, |
| "learning_rate": 3.711771556667218e-06, |
| "loss": 1.0272278785705566, |
| "mean_token_accuracy": 0.6954454779624939, |
| "num_tokens": 25164329.0, |
| "step": 196 |
| }, |
| { |
| "entropy": 1.0441596508026123, |
| "epoch": 2.5290322580645164, |
| "grad_norm": 0.10644666105508804, |
| "learning_rate": 3.5284183194893488e-06, |
| "loss": 1.0416760444641113, |
| "mean_token_accuracy": 0.6897891834378242, |
| "num_tokens": 25293811.0, |
| "step": 197 |
| }, |
| { |
| "entropy": 1.0637371689081192, |
| "epoch": 2.541935483870968, |
| "grad_norm": 0.11722967773675919, |
| "learning_rate": 3.3493649053890326e-06, |
| "loss": 1.0671195983886719, |
| "mean_token_accuracy": 0.6864657178521156, |
| "num_tokens": 25423153.0, |
| "step": 198 |
| }, |
| { |
| "entropy": 1.0501241013407707, |
| "epoch": 2.554838709677419, |
| "grad_norm": 0.11004006117582321, |
| "learning_rate": 3.1746471709702964e-06, |
| "loss": 1.0558295249938965, |
| "mean_token_accuracy": 0.6875061243772507, |
| "num_tokens": 25551382.0, |
| "step": 199 |
| }, |
| { |
| "entropy": 1.0354173332452774, |
| "epoch": 2.567741935483871, |
| "grad_norm": 0.10754505544900894, |
| "learning_rate": 3.0043001045892695e-06, |
| "loss": 1.0345330238342285, |
| "mean_token_accuracy": 0.6924821436405182, |
| "num_tokens": 25681542.0, |
| "step": 200 |
| }, |
| { |
| "entropy": 1.060821533203125, |
| "epoch": 2.5806451612903225, |
| "grad_norm": 0.11222092062234879, |
| "learning_rate": 2.8383578193475315e-06, |
| "loss": 1.0553414821624756, |
| "mean_token_accuracy": 0.6884602159261703, |
| "num_tokens": 25811593.0, |
| "step": 201 |
| }, |
| { |
| "entropy": 1.0455363541841507, |
| "epoch": 2.5935483870967744, |
| "grad_norm": 0.10915622115135193, |
| "learning_rate": 2.676853546260791e-06, |
| "loss": 1.0400724411010742, |
| "mean_token_accuracy": 0.6905817687511444, |
| "num_tokens": 25940206.0, |
| "step": 202 |
| }, |
| { |
| "entropy": 1.0424106270074844, |
| "epoch": 2.606451612903226, |
| "grad_norm": 0.1086404025554657, |
| "learning_rate": 2.5198196276040782e-06, |
| "loss": 1.0467170476913452, |
| "mean_token_accuracy": 0.6901760175824165, |
| "num_tokens": 26068569.0, |
| "step": 203 |
| }, |
| { |
| "entropy": 1.0670628994703293, |
| "epoch": 2.6193548387096772, |
| "grad_norm": 0.10955141484737396, |
| "learning_rate": 2.3672875104350844e-06, |
| "loss": 1.068419098854065, |
| "mean_token_accuracy": 0.6845669150352478, |
| "num_tokens": 26198474.0, |
| "step": 204 |
| }, |
| { |
| "entropy": 1.0173008292913437, |
| "epoch": 2.632258064516129, |
| "grad_norm": 0.10962691158056259, |
| "learning_rate": 2.219287740296605e-06, |
| "loss": 1.017364263534546, |
| "mean_token_accuracy": 0.6959098726511002, |
| "num_tokens": 26326152.0, |
| "step": 205 |
| }, |
| { |
| "entropy": 1.017060548067093, |
| "epoch": 2.6451612903225805, |
| "grad_norm": 0.108258917927742, |
| "learning_rate": 2.075849955099668e-06, |
| "loss": 1.0192623138427734, |
| "mean_token_accuracy": 0.6978500708937645, |
| "num_tokens": 26455939.0, |
| "step": 206 |
| }, |
| { |
| "entropy": 1.031680092215538, |
| "epoch": 2.6580645161290324, |
| "grad_norm": 0.10703052580356598, |
| "learning_rate": 1.937002879188285e-06, |
| "loss": 1.0324689149856567, |
| "mean_token_accuracy": 0.6944908797740936, |
| "num_tokens": 26585781.0, |
| "step": 207 |
| }, |
| { |
| "entropy": 1.0165016651153564, |
| "epoch": 2.670967741935484, |
| "grad_norm": 0.10673050582408905, |
| "learning_rate": 1.8027743175872664e-06, |
| "loss": 1.0239442586898804, |
| "mean_token_accuracy": 0.6977909207344055, |
| "num_tokens": 26711858.0, |
| "step": 208 |
| }, |
| { |
| "entropy": 1.0468274727463722, |
| "epoch": 2.6838709677419352, |
| "grad_norm": 0.1072036623954773, |
| "learning_rate": 1.673191150434067e-06, |
| "loss": 1.0476675033569336, |
| "mean_token_accuracy": 0.6896422803401947, |
| "num_tokens": 26840657.0, |
| "step": 209 |
| }, |
| { |
| "entropy": 1.0346852168440819, |
| "epoch": 2.696774193548387, |
| "grad_norm": 0.10651984065771103, |
| "learning_rate": 1.5482793275958529e-06, |
| "loss": 1.0319528579711914, |
| "mean_token_accuracy": 0.6947586163878441, |
| "num_tokens": 26970561.0, |
| "step": 210 |
| }, |
| { |
| "entropy": 1.0479450896382332, |
| "epoch": 2.709677419354839, |
| "grad_norm": 0.10804249346256256, |
| "learning_rate": 1.428063863472895e-06, |
| "loss": 1.0493197441101074, |
| "mean_token_accuracy": 0.6889068260788918, |
| "num_tokens": 27099808.0, |
| "step": 211 |
| }, |
| { |
| "entropy": 1.0522058978676796, |
| "epoch": 2.7225806451612904, |
| "grad_norm": 0.10875978320837021, |
| "learning_rate": 1.312568831989258e-06, |
| "loss": 1.0467654466629028, |
| "mean_token_accuracy": 0.6907722055912018, |
| "num_tokens": 27227187.0, |
| "step": 212 |
| }, |
| { |
| "entropy": 1.031970702111721, |
| "epoch": 2.735483870967742, |
| "grad_norm": 0.1061997190117836, |
| "learning_rate": 1.201817361771837e-06, |
| "loss": 1.0309909582138062, |
| "mean_token_accuracy": 0.6966234892606735, |
| "num_tokens": 27356425.0, |
| "step": 213 |
| }, |
| { |
| "entropy": 1.0382237881422043, |
| "epoch": 2.7483870967741937, |
| "grad_norm": 0.1096247136592865, |
| "learning_rate": 1.095831631518729e-06, |
| "loss": 1.0349082946777344, |
| "mean_token_accuracy": 0.6920067444443703, |
| "num_tokens": 27485158.0, |
| "step": 214 |
| }, |
| { |
| "entropy": 1.0544036328792572, |
| "epoch": 2.761290322580645, |
| "grad_norm": 0.11023124307394028, |
| "learning_rate": 9.946328655577624e-07, |
| "loss": 1.0543882846832275, |
| "mean_token_accuracy": 0.688176341354847, |
| "num_tokens": 27613898.0, |
| "step": 215 |
| }, |
| { |
| "entropy": 1.0303477346897125, |
| "epoch": 2.774193548387097, |
| "grad_norm": 0.10916352272033691, |
| "learning_rate": 8.98241329596236e-07, |
| "loss": 1.0285627841949463, |
| "mean_token_accuracy": 0.6944142505526543, |
| "num_tokens": 27742345.0, |
| "step": 216 |
| }, |
| { |
| "entropy": 1.0519348457455635, |
| "epoch": 2.7870967741935484, |
| "grad_norm": 0.107175812125206, |
| "learning_rate": 8.066763266625282e-07, |
| "loss": 1.0508193969726562, |
| "mean_token_accuracy": 0.6894998773932457, |
| "num_tokens": 27871525.0, |
| "step": 217 |
| }, |
| { |
| "entropy": 1.0263159945607185, |
| "epoch": 2.8, |
| "grad_norm": 0.10735797882080078, |
| "learning_rate": 7.199561932405952e-07, |
| "loss": 1.0223097801208496, |
| "mean_token_accuracy": 0.6967111676931381, |
| "num_tokens": 28000658.0, |
| "step": 218 |
| }, |
| { |
| "entropy": 1.0704012513160706, |
| "epoch": 2.8129032258064517, |
| "grad_norm": 0.10850393772125244, |
| "learning_rate": 6.380982955979192e-07, |
| "loss": 1.063401222229004, |
| "mean_token_accuracy": 0.6871140673756599, |
| "num_tokens": 28129810.0, |
| "step": 219 |
| }, |
| { |
| "entropy": 0.9961521849036217, |
| "epoch": 2.825806451612903, |
| "grad_norm": 0.10615446418523788, |
| "learning_rate": 5.611190263078464e-07, |
| "loss": 0.9923411011695862, |
| "mean_token_accuracy": 0.7040284797549248, |
| "num_tokens": 28259343.0, |
| "step": 220 |
| }, |
| { |
| "entropy": 1.0457279533147812, |
| "epoch": 2.838709677419355, |
| "grad_norm": 0.10723281651735306, |
| "learning_rate": 4.890338009668316e-07, |
| "loss": 1.0384149551391602, |
| "mean_token_accuracy": 0.6930935382843018, |
| "num_tokens": 28389274.0, |
| "step": 221 |
| }, |
| { |
| "entropy": 1.0505697131156921, |
| "epoch": 2.8516129032258064, |
| "grad_norm": 0.10903427004814148, |
| "learning_rate": 4.2185705510739415e-07, |
| "loss": 1.048717975616455, |
| "mean_token_accuracy": 0.6905554085969925, |
| "num_tokens": 28518414.0, |
| "step": 222 |
| }, |
| { |
| "entropy": 1.0408155992627144, |
| "epoch": 2.864516129032258, |
| "grad_norm": 0.10706758499145508, |
| "learning_rate": 3.5960224130728857e-07, |
| "loss": 1.0356512069702148, |
| "mean_token_accuracy": 0.6926485896110535, |
| "num_tokens": 28648178.0, |
| "step": 223 |
| }, |
| { |
| "entropy": 1.0356387048959732, |
| "epoch": 2.8774193548387097, |
| "grad_norm": 0.10854515433311462, |
| "learning_rate": 3.0228182649555126e-07, |
| "loss": 1.030407190322876, |
| "mean_token_accuracy": 0.6930520460009575, |
| "num_tokens": 28777130.0, |
| "step": 224 |
| }, |
| { |
| "entropy": 1.0356003567576408, |
| "epoch": 2.8903225806451616, |
| "grad_norm": 0.10882875323295593, |
| "learning_rate": 2.499072894559057e-07, |
| "loss": 1.039480209350586, |
| "mean_token_accuracy": 0.6941024139523506, |
| "num_tokens": 28906037.0, |
| "step": 225 |
| }, |
| { |
| "entropy": 1.0353758111596107, |
| "epoch": 2.903225806451613, |
| "grad_norm": 0.10648636519908905, |
| "learning_rate": 2.0248911852807916e-07, |
| "loss": 1.0339810848236084, |
| "mean_token_accuracy": 0.6936473175883293, |
| "num_tokens": 29036308.0, |
| "step": 226 |
| }, |
| { |
| "entropy": 1.040413811802864, |
| "epoch": 2.9161290322580644, |
| "grad_norm": 0.11142022907733917, |
| "learning_rate": 1.6003680950742728e-07, |
| "loss": 1.0437448024749756, |
| "mean_token_accuracy": 0.6905373185873032, |
| "num_tokens": 29165368.0, |
| "step": 227 |
| }, |
| { |
| "entropy": 1.0560034364461899, |
| "epoch": 2.9290322580645163, |
| "grad_norm": 0.10875936597585678, |
| "learning_rate": 1.2255886374334946e-07, |
| "loss": 1.0542490482330322, |
| "mean_token_accuracy": 0.6896227449178696, |
| "num_tokens": 29295274.0, |
| "step": 228 |
| }, |
| { |
| "entropy": 1.0223482325673103, |
| "epoch": 2.9419354838709677, |
| "grad_norm": 0.10559869557619095, |
| "learning_rate": 9.006278643683696e-08, |
| "loss": 1.0181331634521484, |
| "mean_token_accuracy": 0.6966415643692017, |
| "num_tokens": 29424540.0, |
| "step": 229 |
| }, |
| { |
| "entropy": 1.0373627617955208, |
| "epoch": 2.9548387096774196, |
| "grad_norm": 0.10600678622722626, |
| "learning_rate": 6.255508513750841e-08, |
| "loss": 1.0333645343780518, |
| "mean_token_accuracy": 0.6949755847454071, |
| "num_tokens": 29553990.0, |
| "step": 230 |
| }, |
| { |
| "entropy": 1.047977827489376, |
| "epoch": 2.967741935483871, |
| "grad_norm": 0.10843431204557419, |
| "learning_rate": 4.004126844042444e-08, |
| "loss": 1.0439516305923462, |
| "mean_token_accuracy": 0.6914435401558876, |
| "num_tokens": 29683419.0, |
| "step": 231 |
| }, |
| { |
| "entropy": 1.0630123317241669, |
| "epoch": 2.9806451612903224, |
| "grad_norm": 0.10723218321800232, |
| "learning_rate": 2.2525844882964607e-08, |
| "loss": 1.0580321550369263, |
| "mean_token_accuracy": 0.6877385601401329, |
| "num_tokens": 29813015.0, |
| "step": 232 |
| }, |
| { |
| "entropy": 1.0483429431915283, |
| "epoch": 2.9935483870967743, |
| "grad_norm": 0.10975757986307144, |
| "learning_rate": 1.0012322041960676e-08, |
| "loss": 1.0429267883300781, |
| "mean_token_accuracy": 0.6912823766469955, |
| "num_tokens": 29942783.0, |
| "step": 233 |
| }, |
| { |
| "entropy": 1.032555729150772, |
| "epoch": 3.0, |
| "grad_norm": 0.1499345600605011, |
| "learning_rate": 2.503205831277944e-09, |
| "loss": 1.0281625986099243, |
| "mean_token_accuracy": 0.6969237774610519, |
| "num_tokens": 29991313.0, |
| "step": 234 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 234, |
| "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": 1.4654462242188165e+18, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
