| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 312, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 1.317004218697548, |
| "epoch": 0.009685230024213076, |
| "grad_norm": 1.2896121740341187, |
| "learning_rate": 0.0, |
| "loss": 2.082634687423706, |
| "mean_token_accuracy": 0.5258517861366272, |
| "num_tokens": 97328.0, |
| "step": 1 |
| }, |
| { |
| "entropy": 1.306379646062851, |
| "epoch": 0.01937046004842615, |
| "grad_norm": 1.2239129543304443, |
| "learning_rate": 3.125e-06, |
| "loss": 2.047252655029297, |
| "mean_token_accuracy": 0.5331005752086639, |
| "num_tokens": 194259.0, |
| "step": 2 |
| }, |
| { |
| "entropy": 1.3193936496973038, |
| "epoch": 0.029055690072639227, |
| "grad_norm": 1.1433645486831665, |
| "learning_rate": 6.25e-06, |
| "loss": 2.0007200241088867, |
| "mean_token_accuracy": 0.5382249727845192, |
| "num_tokens": 291639.0, |
| "step": 3 |
| }, |
| { |
| "entropy": 1.421342894434929, |
| "epoch": 0.0387409200968523, |
| "grad_norm": 0.997297465801239, |
| "learning_rate": 9.375000000000001e-06, |
| "loss": 1.9897820949554443, |
| "mean_token_accuracy": 0.5354432910680771, |
| "num_tokens": 389132.0, |
| "step": 4 |
| }, |
| { |
| "entropy": 1.493358463048935, |
| "epoch": 0.048426150121065374, |
| "grad_norm": 0.7811200022697449, |
| "learning_rate": 1.25e-05, |
| "loss": 1.9146728515625, |
| "mean_token_accuracy": 0.5432016626000404, |
| "num_tokens": 487010.0, |
| "step": 5 |
| }, |
| { |
| "entropy": 1.6673749834299088, |
| "epoch": 0.05811138014527845, |
| "grad_norm": 0.5001599192619324, |
| "learning_rate": 1.5625e-05, |
| "loss": 1.8388503789901733, |
| "mean_token_accuracy": 0.5485250800848007, |
| "num_tokens": 584854.0, |
| "step": 6 |
| }, |
| { |
| "entropy": 1.8042271435260773, |
| "epoch": 0.06779661016949153, |
| "grad_norm": 0.4208337068557739, |
| "learning_rate": 1.8750000000000002e-05, |
| "loss": 1.825950026512146, |
| "mean_token_accuracy": 0.5503732189536095, |
| "num_tokens": 681659.0, |
| "step": 7 |
| }, |
| { |
| "entropy": 1.9454836398363113, |
| "epoch": 0.0774818401937046, |
| "grad_norm": 0.4707717001438141, |
| "learning_rate": 2.1875e-05, |
| "loss": 1.8017537593841553, |
| "mean_token_accuracy": 0.5541446879506111, |
| "num_tokens": 778901.0, |
| "step": 8 |
| }, |
| { |
| "entropy": 2.0539309233427048, |
| "epoch": 0.08716707021791767, |
| "grad_norm": 0.5857245922088623, |
| "learning_rate": 2.5e-05, |
| "loss": 1.800880789756775, |
| "mean_token_accuracy": 0.5496064275503159, |
| "num_tokens": 875325.0, |
| "step": 9 |
| }, |
| { |
| "entropy": 1.9075840711593628, |
| "epoch": 0.09685230024213075, |
| "grad_norm": 0.5037109851837158, |
| "learning_rate": 2.8125000000000003e-05, |
| "loss": 1.673196792602539, |
| "mean_token_accuracy": 0.5737576559185982, |
| "num_tokens": 972839.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 1.860039845108986, |
| "epoch": 0.10653753026634383, |
| "grad_norm": 0.45144304633140564, |
| "learning_rate": 3.125e-05, |
| "loss": 1.6727261543273926, |
| "mean_token_accuracy": 0.5697960630059242, |
| "num_tokens": 1069150.0, |
| "step": 11 |
| }, |
| { |
| "entropy": 1.6962992250919342, |
| "epoch": 0.1162227602905569, |
| "grad_norm": 0.33423277735710144, |
| "learning_rate": 3.4375e-05, |
| "loss": 1.6035898923873901, |
| "mean_token_accuracy": 0.5795940384268761, |
| "num_tokens": 1166507.0, |
| "step": 12 |
| }, |
| { |
| "entropy": 1.5210626274347305, |
| "epoch": 0.12590799031476999, |
| "grad_norm": 0.2858195900917053, |
| "learning_rate": 3.7500000000000003e-05, |
| "loss": 1.5204042196273804, |
| "mean_token_accuracy": 0.5941177308559418, |
| "num_tokens": 1264162.0, |
| "step": 13 |
| }, |
| { |
| "entropy": 1.5153919160366058, |
| "epoch": 0.13559322033898305, |
| "grad_norm": 0.30006346106529236, |
| "learning_rate": 4.0625000000000005e-05, |
| "loss": 1.565500259399414, |
| "mean_token_accuracy": 0.586014412343502, |
| "num_tokens": 1358318.0, |
| "step": 14 |
| }, |
| { |
| "entropy": 1.3367150872945786, |
| "epoch": 0.14527845036319612, |
| "grad_norm": 0.3114268481731415, |
| "learning_rate": 4.375e-05, |
| "loss": 1.430711030960083, |
| "mean_token_accuracy": 0.6141984984278679, |
| "num_tokens": 1455188.0, |
| "step": 15 |
| }, |
| { |
| "entropy": 1.3922923356294632, |
| "epoch": 0.1549636803874092, |
| "grad_norm": 0.264522522687912, |
| "learning_rate": 4.6875e-05, |
| "loss": 1.460913896560669, |
| "mean_token_accuracy": 0.6049858629703522, |
| "num_tokens": 1553207.0, |
| "step": 16 |
| }, |
| { |
| "entropy": 1.388969361782074, |
| "epoch": 0.16464891041162227, |
| "grad_norm": 0.24329984188079834, |
| "learning_rate": 5e-05, |
| "loss": 1.4352588653564453, |
| "mean_token_accuracy": 0.6117960214614868, |
| "num_tokens": 1650103.0, |
| "step": 17 |
| }, |
| { |
| "entropy": 1.4225876778364182, |
| "epoch": 0.17433414043583534, |
| "grad_norm": 0.2702501714229584, |
| "learning_rate": 4.999859193643945e-05, |
| "loss": 1.40070378780365, |
| "mean_token_accuracy": 0.6150684952735901, |
| "num_tokens": 1746941.0, |
| "step": 18 |
| }, |
| { |
| "entropy": 1.4131463915109634, |
| "epoch": 0.18401937046004843, |
| "grad_norm": 0.25621092319488525, |
| "learning_rate": 4.999436790436924e-05, |
| "loss": 1.3876947164535522, |
| "mean_token_accuracy": 0.6200384646654129, |
| "num_tokens": 1844188.0, |
| "step": 19 |
| }, |
| { |
| "entropy": 1.4005486369132996, |
| "epoch": 0.1937046004842615, |
| "grad_norm": 0.2253018468618393, |
| "learning_rate": 4.9987328379605816e-05, |
| "loss": 1.3485538959503174, |
| "mean_token_accuracy": 0.6284598782658577, |
| "num_tokens": 1941380.0, |
| "step": 20 |
| }, |
| { |
| "entropy": 1.4259228259325027, |
| "epoch": 0.2033898305084746, |
| "grad_norm": 0.21714746952056885, |
| "learning_rate": 4.9977474155117045e-05, |
| "loss": 1.3771286010742188, |
| "mean_token_accuracy": 0.621919259428978, |
| "num_tokens": 2039184.0, |
| "step": 21 |
| }, |
| { |
| "entropy": 1.3655668199062347, |
| "epoch": 0.21307506053268765, |
| "grad_norm": 0.24290618300437927, |
| "learning_rate": 4.9964806340932865e-05, |
| "loss": 1.3223435878753662, |
| "mean_token_accuracy": 0.631358377635479, |
| "num_tokens": 2136831.0, |
| "step": 22 |
| }, |
| { |
| "entropy": 1.337798997759819, |
| "epoch": 0.22276029055690072, |
| "grad_norm": 0.20359113812446594, |
| "learning_rate": 4.9949326364020314e-05, |
| "loss": 1.3159035444259644, |
| "mean_token_accuracy": 0.6321727335453033, |
| "num_tokens": 2233967.0, |
| "step": 23 |
| }, |
| { |
| "entropy": 1.2915576100349426, |
| "epoch": 0.2324455205811138, |
| "grad_norm": 0.18859286606311798, |
| "learning_rate": 4.993103596812268e-05, |
| "loss": 1.2781122922897339, |
| "mean_token_accuracy": 0.6395078897476196, |
| "num_tokens": 2331590.0, |
| "step": 24 |
| }, |
| { |
| "entropy": 1.3575056046247482, |
| "epoch": 0.24213075060532688, |
| "grad_norm": 0.17821626365184784, |
| "learning_rate": 4.9909937213563165e-05, |
| "loss": 1.3477147817611694, |
| "mean_token_accuracy": 0.6257509142160416, |
| "num_tokens": 2426793.0, |
| "step": 25 |
| }, |
| { |
| "entropy": 1.2926480323076248, |
| "epoch": 0.25181598062953997, |
| "grad_norm": 0.19382886588573456, |
| "learning_rate": 4.988603247701277e-05, |
| "loss": 1.2814431190490723, |
| "mean_token_accuracy": 0.6403299421072006, |
| "num_tokens": 2523683.0, |
| "step": 26 |
| }, |
| { |
| "entropy": 1.2796363830566406, |
| "epoch": 0.26150121065375304, |
| "grad_norm": 0.20317526161670685, |
| "learning_rate": 4.985932445122257e-05, |
| "loss": 1.2663755416870117, |
| "mean_token_accuracy": 0.6411352977156639, |
| "num_tokens": 2620933.0, |
| "step": 27 |
| }, |
| { |
| "entropy": 1.2351761311292648, |
| "epoch": 0.2711864406779661, |
| "grad_norm": 0.17594024538993835, |
| "learning_rate": 4.982981614472039e-05, |
| "loss": 1.2373441457748413, |
| "mean_token_accuracy": 0.6497108340263367, |
| "num_tokens": 2717551.0, |
| "step": 28 |
| }, |
| { |
| "entropy": 1.2417249828577042, |
| "epoch": 0.28087167070217917, |
| "grad_norm": 0.16841042041778564, |
| "learning_rate": 4.979751088147192e-05, |
| "loss": 1.246107816696167, |
| "mean_token_accuracy": 0.6476121693849564, |
| "num_tokens": 2814604.0, |
| "step": 29 |
| }, |
| { |
| "entropy": 1.2138695567846298, |
| "epoch": 0.29055690072639223, |
| "grad_norm": 0.17539004981517792, |
| "learning_rate": 4.97624123005063e-05, |
| "loss": 1.2159419059753418, |
| "mean_token_accuracy": 0.6527048200368881, |
| "num_tokens": 2907459.0, |
| "step": 30 |
| }, |
| { |
| "entropy": 1.2455604374408722, |
| "epoch": 0.30024213075060535, |
| "grad_norm": 0.1840510219335556, |
| "learning_rate": 4.972452435550614e-05, |
| "loss": 1.248232126235962, |
| "mean_token_accuracy": 0.6437666863203049, |
| "num_tokens": 3005431.0, |
| "step": 31 |
| }, |
| { |
| "entropy": 1.239659145474434, |
| "epoch": 0.3099273607748184, |
| "grad_norm": 0.1586979180574417, |
| "learning_rate": 4.968385131436222e-05, |
| "loss": 1.2250527143478394, |
| "mean_token_accuracy": 0.6520643010735512, |
| "num_tokens": 3102027.0, |
| "step": 32 |
| }, |
| { |
| "entropy": 1.235719233751297, |
| "epoch": 0.3196125907990315, |
| "grad_norm": 0.1657770574092865, |
| "learning_rate": 4.9640397758692715e-05, |
| "loss": 1.2115275859832764, |
| "mean_token_accuracy": 0.6527407914400101, |
| "num_tokens": 3199185.0, |
| "step": 33 |
| }, |
| { |
| "entropy": 1.2338766902685165, |
| "epoch": 0.32929782082324455, |
| "grad_norm": 0.1736833155155182, |
| "learning_rate": 4.9594168583327094e-05, |
| "loss": 1.1987342834472656, |
| "mean_token_accuracy": 0.6545186415314674, |
| "num_tokens": 3296154.0, |
| "step": 34 |
| }, |
| { |
| "entropy": 1.2545666545629501, |
| "epoch": 0.3389830508474576, |
| "grad_norm": 0.1628524214029312, |
| "learning_rate": 4.954516899575473e-05, |
| "loss": 1.229626178741455, |
| "mean_token_accuracy": 0.6491333171725273, |
| "num_tokens": 3393666.0, |
| "step": 35 |
| }, |
| { |
| "entropy": 1.2120293527841568, |
| "epoch": 0.3486682808716707, |
| "grad_norm": 0.1564643383026123, |
| "learning_rate": 4.949340451553833e-05, |
| "loss": 1.2005155086517334, |
| "mean_token_accuracy": 0.6557489335536957, |
| "num_tokens": 3490912.0, |
| "step": 36 |
| }, |
| { |
| "entropy": 1.1949793994426727, |
| "epoch": 0.3583535108958838, |
| "grad_norm": 0.1508495956659317, |
| "learning_rate": 4.943888097369216e-05, |
| "loss": 1.1847431659698486, |
| "mean_token_accuracy": 0.6587688028812408, |
| "num_tokens": 3588393.0, |
| "step": 37 |
| }, |
| { |
| "entropy": 1.181449294090271, |
| "epoch": 0.36803874092009686, |
| "grad_norm": 0.16626174747943878, |
| "learning_rate": 4.938160451202521e-05, |
| "loss": 1.1869372129440308, |
| "mean_token_accuracy": 0.6568842083215714, |
| "num_tokens": 3685968.0, |
| "step": 38 |
| }, |
| { |
| "entropy": 1.1504246890544891, |
| "epoch": 0.37772397094430993, |
| "grad_norm": 0.15905380249023438, |
| "learning_rate": 4.9321581582449365e-05, |
| "loss": 1.1604914665222168, |
| "mean_token_accuracy": 0.6636896058917046, |
| "num_tokens": 3783418.0, |
| "step": 39 |
| }, |
| { |
| "entropy": 1.1543444991111755, |
| "epoch": 0.387409200968523, |
| "grad_norm": 0.15155690908432007, |
| "learning_rate": 4.9258818946252624e-05, |
| "loss": 1.152838110923767, |
| "mean_token_accuracy": 0.6673597618937492, |
| "num_tokens": 3881389.0, |
| "step": 40 |
| }, |
| { |
| "entropy": 1.1898803561925888, |
| "epoch": 0.39709443099273606, |
| "grad_norm": 0.15378770232200623, |
| "learning_rate": 4.9193323673337476e-05, |
| "loss": 1.1838186979293823, |
| "mean_token_accuracy": 0.6584705263376236, |
| "num_tokens": 3978300.0, |
| "step": 41 |
| }, |
| { |
| "entropy": 1.178636059165001, |
| "epoch": 0.4067796610169492, |
| "grad_norm": 0.14911328256130219, |
| "learning_rate": 4.912510314142448e-05, |
| "loss": 1.1624752283096313, |
| "mean_token_accuracy": 0.6618187874555588, |
| "num_tokens": 4074320.0, |
| "step": 42 |
| }, |
| { |
| "entropy": 1.155859112739563, |
| "epoch": 0.41646489104116224, |
| "grad_norm": 0.14977990090847015, |
| "learning_rate": 4.9054165035221236e-05, |
| "loss": 1.1455484628677368, |
| "mean_token_accuracy": 0.6688502356410027, |
| "num_tokens": 4171931.0, |
| "step": 43 |
| }, |
| { |
| "entropy": 1.1802153587341309, |
| "epoch": 0.4261501210653753, |
| "grad_norm": 0.14762485027313232, |
| "learning_rate": 4.898051734555676e-05, |
| "loss": 1.1656816005706787, |
| "mean_token_accuracy": 0.6611011102795601, |
| "num_tokens": 4267550.0, |
| "step": 44 |
| }, |
| { |
| "entropy": 1.1514023691415787, |
| "epoch": 0.4358353510895884, |
| "grad_norm": 0.14387239515781403, |
| "learning_rate": 4.890416836848127e-05, |
| "loss": 1.1372427940368652, |
| "mean_token_accuracy": 0.6664102151989937, |
| "num_tokens": 4364712.0, |
| "step": 45 |
| }, |
| { |
| "entropy": 1.156693086028099, |
| "epoch": 0.44552058111380144, |
| "grad_norm": 0.1518811285495758, |
| "learning_rate": 4.88251267043318e-05, |
| "loss": 1.1605509519577026, |
| "mean_token_accuracy": 0.6634868234395981, |
| "num_tokens": 4461394.0, |
| "step": 46 |
| }, |
| { |
| "entropy": 1.1185480505228043, |
| "epoch": 0.4552058111380145, |
| "grad_norm": 0.16213111579418182, |
| "learning_rate": 4.87434012567633e-05, |
| "loss": 1.1149487495422363, |
| "mean_token_accuracy": 0.6748593971133232, |
| "num_tokens": 4558878.0, |
| "step": 47 |
| }, |
| { |
| "entropy": 1.1710628867149353, |
| "epoch": 0.4648910411622276, |
| "grad_norm": 0.14876942336559296, |
| "learning_rate": 4.865900123174574e-05, |
| "loss": 1.15852952003479, |
| "mean_token_accuracy": 0.6628599911928177, |
| "num_tokens": 4656033.0, |
| "step": 48 |
| }, |
| { |
| "entropy": 1.184880554676056, |
| "epoch": 0.4745762711864407, |
| "grad_norm": 0.14967085421085358, |
| "learning_rate": 4.857193613652711e-05, |
| "loss": 1.1690523624420166, |
| "mean_token_accuracy": 0.662392869591713, |
| "num_tokens": 4753610.0, |
| "step": 49 |
| }, |
| { |
| "entropy": 1.17043799161911, |
| "epoch": 0.48426150121065376, |
| "grad_norm": 0.156271830201149, |
| "learning_rate": 4.848221577856243e-05, |
| "loss": 1.1510560512542725, |
| "mean_token_accuracy": 0.6638557314872742, |
| "num_tokens": 4851486.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 1.1305849254131317, |
| "epoch": 0.4939467312348668, |
| "grad_norm": 0.14663065969944, |
| "learning_rate": 4.838985026440905e-05, |
| "loss": 1.112675428390503, |
| "mean_token_accuracy": 0.6735092177987099, |
| "num_tokens": 4948781.0, |
| "step": 51 |
| }, |
| { |
| "entropy": 1.1443408280611038, |
| "epoch": 0.5036319612590799, |
| "grad_norm": 0.14738105237483978, |
| "learning_rate": 4.829484999858815e-05, |
| "loss": 1.13261878490448, |
| "mean_token_accuracy": 0.6675093844532967, |
| "num_tokens": 5046085.0, |
| "step": 52 |
| }, |
| { |
| "entropy": 1.1511103957891464, |
| "epoch": 0.513317191283293, |
| "grad_norm": 0.15696625411510468, |
| "learning_rate": 4.819722568241274e-05, |
| "loss": 1.1610808372497559, |
| "mean_token_accuracy": 0.6629386246204376, |
| "num_tokens": 5142470.0, |
| "step": 53 |
| }, |
| { |
| "entropy": 1.13540880382061, |
| "epoch": 0.5230024213075061, |
| "grad_norm": 0.14982947707176208, |
| "learning_rate": 4.8096988312782174e-05, |
| "loss": 1.1378846168518066, |
| "mean_token_accuracy": 0.666424423456192, |
| "num_tokens": 5240348.0, |
| "step": 54 |
| }, |
| { |
| "entropy": 1.1485055983066559, |
| "epoch": 0.5326876513317191, |
| "grad_norm": 0.15001113712787628, |
| "learning_rate": 4.799414918094347e-05, |
| "loss": 1.1458028554916382, |
| "mean_token_accuracy": 0.6636912375688553, |
| "num_tokens": 5337856.0, |
| "step": 55 |
| }, |
| { |
| "entropy": 1.1504357308149338, |
| "epoch": 0.5423728813559322, |
| "grad_norm": 0.1556474268436432, |
| "learning_rate": 4.788871987121937e-05, |
| "loss": 1.135033369064331, |
| "mean_token_accuracy": 0.6674922555685043, |
| "num_tokens": 5435150.0, |
| "step": 56 |
| }, |
| { |
| "entropy": 1.1426950842142105, |
| "epoch": 0.5520581113801453, |
| "grad_norm": 0.147213876247406, |
| "learning_rate": 4.77807122597034e-05, |
| "loss": 1.1313400268554688, |
| "mean_token_accuracy": 0.6694349721074104, |
| "num_tokens": 5533227.0, |
| "step": 57 |
| }, |
| { |
| "entropy": 1.1269017159938812, |
| "epoch": 0.5617433414043583, |
| "grad_norm": 0.15351133048534393, |
| "learning_rate": 4.767013851292212e-05, |
| "loss": 1.1154887676239014, |
| "mean_token_accuracy": 0.6716312021017075, |
| "num_tokens": 5630374.0, |
| "step": 58 |
| }, |
| { |
| "entropy": 1.1352972239255905, |
| "epoch": 0.5714285714285714, |
| "grad_norm": 0.1449081301689148, |
| "learning_rate": 4.755701108646463e-05, |
| "loss": 1.115692377090454, |
| "mean_token_accuracy": 0.6710918322205544, |
| "num_tokens": 5727367.0, |
| "step": 59 |
| }, |
| { |
| "entropy": 1.134296178817749, |
| "epoch": 0.5811138014527845, |
| "grad_norm": 0.153062105178833, |
| "learning_rate": 4.744134272357948e-05, |
| "loss": 1.1301031112670898, |
| "mean_token_accuracy": 0.6712843775749207, |
| "num_tokens": 5824218.0, |
| "step": 60 |
| }, |
| { |
| "entropy": 1.1202774196863174, |
| "epoch": 0.5907990314769975, |
| "grad_norm": 0.14879855513572693, |
| "learning_rate": 4.732314645373921e-05, |
| "loss": 1.1113876104354858, |
| "mean_token_accuracy": 0.6735736131668091, |
| "num_tokens": 5921571.0, |
| "step": 61 |
| }, |
| { |
| "entropy": 1.102357640862465, |
| "epoch": 0.6004842615012107, |
| "grad_norm": 0.15212750434875488, |
| "learning_rate": 4.7202435591172676e-05, |
| "loss": 1.0985870361328125, |
| "mean_token_accuracy": 0.675997368991375, |
| "num_tokens": 6018773.0, |
| "step": 62 |
| }, |
| { |
| "entropy": 1.1048029512166977, |
| "epoch": 0.6101694915254238, |
| "grad_norm": 0.14792507886886597, |
| "learning_rate": 4.7079223733365237e-05, |
| "loss": 1.095569372177124, |
| "mean_token_accuracy": 0.675012968480587, |
| "num_tokens": 6115912.0, |
| "step": 63 |
| }, |
| { |
| "entropy": 1.1288667768239975, |
| "epoch": 0.6198547215496368, |
| "grad_norm": 0.14735190570354462, |
| "learning_rate": 4.6953524759527054e-05, |
| "loss": 1.11784827709198, |
| "mean_token_accuracy": 0.6701762154698372, |
| "num_tokens": 6212536.0, |
| "step": 64 |
| }, |
| { |
| "entropy": 1.114186018705368, |
| "epoch": 0.6295399515738499, |
| "grad_norm": 0.15394103527069092, |
| "learning_rate": 4.6825352829029705e-05, |
| "loss": 1.1040326356887817, |
| "mean_token_accuracy": 0.6742865368723869, |
| "num_tokens": 6310026.0, |
| "step": 65 |
| }, |
| { |
| "entropy": 1.0817014202475548, |
| "epoch": 0.639225181598063, |
| "grad_norm": 0.1501314491033554, |
| "learning_rate": 4.6694722379811185e-05, |
| "loss": 1.08419930934906, |
| "mean_token_accuracy": 0.6813223287463188, |
| "num_tokens": 6405142.0, |
| "step": 66 |
| }, |
| { |
| "entropy": 1.1135721951723099, |
| "epoch": 0.648910411622276, |
| "grad_norm": 0.16784843802452087, |
| "learning_rate": 4.656164812674951e-05, |
| "loss": 1.1132102012634277, |
| "mean_token_accuracy": 0.6742275431752205, |
| "num_tokens": 6502523.0, |
| "step": 67 |
| }, |
| { |
| "entropy": 1.1133443415164948, |
| "epoch": 0.6585956416464891, |
| "grad_norm": 0.15567201375961304, |
| "learning_rate": 4.642614506000523e-05, |
| "loss": 1.1113190650939941, |
| "mean_token_accuracy": 0.6731716245412827, |
| "num_tokens": 6599085.0, |
| "step": 68 |
| }, |
| { |
| "entropy": 1.091795675456524, |
| "epoch": 0.6682808716707022, |
| "grad_norm": 0.14981144666671753, |
| "learning_rate": 4.628822844333278e-05, |
| "loss": 1.0913615226745605, |
| "mean_token_accuracy": 0.6778776124119759, |
| "num_tokens": 6696224.0, |
| "step": 69 |
| }, |
| { |
| "entropy": 1.0920320302248, |
| "epoch": 0.6779661016949152, |
| "grad_norm": 0.15485303103923798, |
| "learning_rate": 4.614791381236115e-05, |
| "loss": 1.0870628356933594, |
| "mean_token_accuracy": 0.6780931428074837, |
| "num_tokens": 6792189.0, |
| "step": 70 |
| }, |
| { |
| "entropy": 1.1014160960912704, |
| "epoch": 0.6876513317191283, |
| "grad_norm": 0.1586335003376007, |
| "learning_rate": 4.6005216972843864e-05, |
| "loss": 1.1016792058944702, |
| "mean_token_accuracy": 0.6750583723187447, |
| "num_tokens": 6889269.0, |
| "step": 71 |
| }, |
| { |
| "entropy": 1.095201924443245, |
| "epoch": 0.6973365617433414, |
| "grad_norm": 0.15514244139194489, |
| "learning_rate": 4.5860153998878494e-05, |
| "loss": 1.089525580406189, |
| "mean_token_accuracy": 0.6761212572455406, |
| "num_tokens": 6987001.0, |
| "step": 72 |
| }, |
| { |
| "entropy": 1.110721379518509, |
| "epoch": 0.7070217917675545, |
| "grad_norm": 0.15483509004116058, |
| "learning_rate": 4.571274123109606e-05, |
| "loss": 1.1064794063568115, |
| "mean_token_accuracy": 0.6743339449167252, |
| "num_tokens": 7083766.0, |
| "step": 73 |
| }, |
| { |
| "entropy": 1.1040757596492767, |
| "epoch": 0.7167070217917676, |
| "grad_norm": 0.1559927612543106, |
| "learning_rate": 4.5562995274820284e-05, |
| "loss": 1.082243800163269, |
| "mean_token_accuracy": 0.6789897233247757, |
| "num_tokens": 7179679.0, |
| "step": 74 |
| }, |
| { |
| "entropy": 1.1098376661539078, |
| "epoch": 0.7263922518159807, |
| "grad_norm": 0.15505605936050415, |
| "learning_rate": 4.541093299819714e-05, |
| "loss": 1.0888028144836426, |
| "mean_token_accuracy": 0.6794665902853012, |
| "num_tokens": 7276243.0, |
| "step": 75 |
| }, |
| { |
| "entropy": 1.099312648177147, |
| "epoch": 0.7360774818401937, |
| "grad_norm": 0.14871232211589813, |
| "learning_rate": 4.5256571530294664e-05, |
| "loss": 1.0875135660171509, |
| "mean_token_accuracy": 0.6783665344119072, |
| "num_tokens": 7373015.0, |
| "step": 76 |
| }, |
| { |
| "entropy": 1.0749460384249687, |
| "epoch": 0.7457627118644068, |
| "grad_norm": 0.17334473133087158, |
| "learning_rate": 4.5099928259173516e-05, |
| "loss": 1.0605744123458862, |
| "mean_token_accuracy": 0.6834923177957535, |
| "num_tokens": 7469189.0, |
| "step": 77 |
| }, |
| { |
| "entropy": 1.0772480070590973, |
| "epoch": 0.7554479418886199, |
| "grad_norm": 0.15214787423610687, |
| "learning_rate": 4.4941020829928245e-05, |
| "loss": 1.076210856437683, |
| "mean_token_accuracy": 0.6795796528458595, |
| "num_tokens": 7565874.0, |
| "step": 78 |
| }, |
| { |
| "entropy": 1.0568204671144485, |
| "epoch": 0.7651331719128329, |
| "grad_norm": 0.15063218772411346, |
| "learning_rate": 4.477986714269972e-05, |
| "loss": 1.060287356376648, |
| "mean_token_accuracy": 0.6827899366617203, |
| "num_tokens": 7662843.0, |
| "step": 79 |
| }, |
| { |
| "entropy": 1.084660217165947, |
| "epoch": 0.774818401937046, |
| "grad_norm": 0.15119187533855438, |
| "learning_rate": 4.4616485350658685e-05, |
| "loss": 1.091611385345459, |
| "mean_token_accuracy": 0.6798556670546532, |
| "num_tokens": 7759463.0, |
| "step": 80 |
| }, |
| { |
| "entropy": 1.1101327538490295, |
| "epoch": 0.784503631961259, |
| "grad_norm": 0.15529696643352509, |
| "learning_rate": 4.445089385796099e-05, |
| "loss": 1.1128976345062256, |
| "mean_token_accuracy": 0.6707641705870628, |
| "num_tokens": 7857012.0, |
| "step": 81 |
| }, |
| { |
| "entropy": 1.091973900794983, |
| "epoch": 0.7941888619854721, |
| "grad_norm": 0.1531902551651001, |
| "learning_rate": 4.4283111317674374e-05, |
| "loss": 1.090956687927246, |
| "mean_token_accuracy": 0.6741223037242889, |
| "num_tokens": 7954176.0, |
| "step": 82 |
| }, |
| { |
| "entropy": 1.0863638073205948, |
| "epoch": 0.8038740920096852, |
| "grad_norm": 0.1566418707370758, |
| "learning_rate": 4.4113156629677316e-05, |
| "loss": 1.0832655429840088, |
| "mean_token_accuracy": 0.678005263209343, |
| "num_tokens": 8051738.0, |
| "step": 83 |
| }, |
| { |
| "entropy": 1.061260737478733, |
| "epoch": 0.8135593220338984, |
| "grad_norm": 0.15304933488368988, |
| "learning_rate": 4.394104893853007e-05, |
| "loss": 1.0538866519927979, |
| "mean_token_accuracy": 0.6874052137136459, |
| "num_tokens": 8148640.0, |
| "step": 84 |
| }, |
| { |
| "entropy": 1.0719867199659348, |
| "epoch": 0.8232445520581114, |
| "grad_norm": 0.1544543355703354, |
| "learning_rate": 4.3766807631318106e-05, |
| "loss": 1.0574662685394287, |
| "mean_token_accuracy": 0.6843332424759865, |
| "num_tokens": 8245229.0, |
| "step": 85 |
| }, |
| { |
| "entropy": 1.0613527670502663, |
| "epoch": 0.8329297820823245, |
| "grad_norm": 0.14801454544067383, |
| "learning_rate": 4.359045233546827e-05, |
| "loss": 1.0512840747833252, |
| "mean_token_accuracy": 0.6862121224403381, |
| "num_tokens": 8341261.0, |
| "step": 86 |
| }, |
| { |
| "entropy": 1.0908231735229492, |
| "epoch": 0.8426150121065376, |
| "grad_norm": 0.15294907987117767, |
| "learning_rate": 4.341200291653781e-05, |
| "loss": 1.0715211629867554, |
| "mean_token_accuracy": 0.6817414835095406, |
| "num_tokens": 8438977.0, |
| "step": 87 |
| }, |
| { |
| "entropy": 1.0881828963756561, |
| "epoch": 0.8523002421307506, |
| "grad_norm": 0.15974564850330353, |
| "learning_rate": 4.323147947597666e-05, |
| "loss": 1.0726957321166992, |
| "mean_token_accuracy": 0.6810331121087074, |
| "num_tokens": 8536075.0, |
| "step": 88 |
| }, |
| { |
| "entropy": 1.0424850583076477, |
| "epoch": 0.8619854721549637, |
| "grad_norm": 0.1496453583240509, |
| "learning_rate": 4.3048902348863116e-05, |
| "loss": 1.0368857383728027, |
| "mean_token_accuracy": 0.6897075176239014, |
| "num_tokens": 8633706.0, |
| "step": 89 |
| }, |
| { |
| "entropy": 1.0516717359423637, |
| "epoch": 0.8716707021791767, |
| "grad_norm": 0.15799377858638763, |
| "learning_rate": 4.2864292101613136e-05, |
| "loss": 1.0576695203781128, |
| "mean_token_accuracy": 0.6859739124774933, |
| "num_tokens": 8731736.0, |
| "step": 90 |
| }, |
| { |
| "entropy": 1.0575535222887993, |
| "epoch": 0.8813559322033898, |
| "grad_norm": 0.15401387214660645, |
| "learning_rate": 4.267766952966369e-05, |
| "loss": 1.0623745918273926, |
| "mean_token_accuracy": 0.6833577901124954, |
| "num_tokens": 8829732.0, |
| "step": 91 |
| }, |
| { |
| "entropy": 1.0572301000356674, |
| "epoch": 0.8910411622276029, |
| "grad_norm": 0.15554137527942657, |
| "learning_rate": 4.248905565513023e-05, |
| "loss": 1.0531975030899048, |
| "mean_token_accuracy": 0.6840359568595886, |
| "num_tokens": 8927532.0, |
| "step": 92 |
| }, |
| { |
| "entropy": 1.047728806734085, |
| "epoch": 0.9007263922518159, |
| "grad_norm": 0.15111669898033142, |
| "learning_rate": 4.229847172443866e-05, |
| "loss": 1.0404102802276611, |
| "mean_token_accuracy": 0.6903342977166176, |
| "num_tokens": 9023586.0, |
| "step": 93 |
| }, |
| { |
| "entropy": 1.0721349269151688, |
| "epoch": 0.910411622276029, |
| "grad_norm": 0.1501697152853012, |
| "learning_rate": 4.210593920593201e-05, |
| "loss": 1.0653115510940552, |
| "mean_token_accuracy": 0.6849683672189713, |
| "num_tokens": 9121309.0, |
| "step": 94 |
| }, |
| { |
| "entropy": 1.0481175184249878, |
| "epoch": 0.9200968523002422, |
| "grad_norm": 0.15556755661964417, |
| "learning_rate": 4.191147978745218e-05, |
| "loss": 1.0338795185089111, |
| "mean_token_accuracy": 0.6906152591109276, |
| "num_tokens": 9218589.0, |
| "step": 95 |
| }, |
| { |
| "entropy": 1.0750476568937302, |
| "epoch": 0.9297820823244553, |
| "grad_norm": 0.1613941788673401, |
| "learning_rate": 4.171511537389684e-05, |
| "loss": 1.067610502243042, |
| "mean_token_accuracy": 0.6825880706310272, |
| "num_tokens": 9315388.0, |
| "step": 96 |
| }, |
| { |
| "entropy": 1.0497909039258957, |
| "epoch": 0.9394673123486683, |
| "grad_norm": 0.15890054404735565, |
| "learning_rate": 4.151686808475204e-05, |
| "loss": 1.0334787368774414, |
| "mean_token_accuracy": 0.6903782784938812, |
| "num_tokens": 9412518.0, |
| "step": 97 |
| }, |
| { |
| "entropy": 1.062135674059391, |
| "epoch": 0.9491525423728814, |
| "grad_norm": 0.15434817969799042, |
| "learning_rate": 4.131676025160047e-05, |
| "loss": 1.0537683963775635, |
| "mean_token_accuracy": 0.6860457882285118, |
| "num_tokens": 9509730.0, |
| "step": 98 |
| }, |
| { |
| "entropy": 1.0554313883185387, |
| "epoch": 0.9588377723970944, |
| "grad_norm": 0.1582096815109253, |
| "learning_rate": 4.111481441560598e-05, |
| "loss": 1.050376296043396, |
| "mean_token_accuracy": 0.6866516023874283, |
| "num_tokens": 9607061.0, |
| "step": 99 |
| }, |
| { |
| "entropy": 1.0587477162480354, |
| "epoch": 0.9685230024213075, |
| "grad_norm": 0.15938952565193176, |
| "learning_rate": 4.091105332497439e-05, |
| "loss": 1.0483958721160889, |
| "mean_token_accuracy": 0.6882701963186264, |
| "num_tokens": 9703922.0, |
| "step": 100 |
| }, |
| { |
| "entropy": 1.0580755025148392, |
| "epoch": 0.9782082324455206, |
| "grad_norm": 0.15547914803028107, |
| "learning_rate": 4.070549993239106e-05, |
| "loss": 1.046097993850708, |
| "mean_token_accuracy": 0.6853689402341843, |
| "num_tokens": 9801726.0, |
| "step": 101 |
| }, |
| { |
| "entropy": 1.0280383378267288, |
| "epoch": 0.9878934624697336, |
| "grad_norm": 0.1550140529870987, |
| "learning_rate": 4.049817739243532e-05, |
| "loss": 1.0170772075653076, |
| "mean_token_accuracy": 0.6949135884642601, |
| "num_tokens": 9898921.0, |
| "step": 102 |
| }, |
| { |
| "entropy": 1.0521605014801025, |
| "epoch": 0.9975786924939467, |
| "grad_norm": 0.17861391603946686, |
| "learning_rate": 4.028910905897229e-05, |
| "loss": 1.0528624057769775, |
| "mean_token_accuracy": 0.6859815418720245, |
| "num_tokens": 9993769.0, |
| "step": 103 |
| }, |
| { |
| "entropy": 1.078683614730835, |
| "epoch": 1.0, |
| "grad_norm": 0.293241411447525, |
| "learning_rate": 4.007831848252211e-05, |
| "loss": 1.0659458637237549, |
| "mean_token_accuracy": 0.6819257438182831, |
| "num_tokens": 10018344.0, |
| "step": 104 |
| }, |
| { |
| "entropy": 1.0527139008045197, |
| "epoch": 1.0096852300242132, |
| "grad_norm": 0.15393514931201935, |
| "learning_rate": 3.986582940760717e-05, |
| "loss": 1.0312196016311646, |
| "mean_token_accuracy": 0.6884313523769379, |
| "num_tokens": 10115659.0, |
| "step": 105 |
| }, |
| { |
| "entropy": 1.0512973815202713, |
| "epoch": 1.0193704600484261, |
| "grad_norm": 0.16082046926021576, |
| "learning_rate": 3.965166577007733e-05, |
| "loss": 1.035767912864685, |
| "mean_token_accuracy": 0.6866201385855675, |
| "num_tokens": 10211527.0, |
| "step": 106 |
| }, |
| { |
| "entropy": 1.0013743713498116, |
| "epoch": 1.0290556900726393, |
| "grad_norm": 0.16090023517608643, |
| "learning_rate": 3.94358516944137e-05, |
| "loss": 0.9906958937644958, |
| "mean_token_accuracy": 0.6992318108677864, |
| "num_tokens": 10309417.0, |
| "step": 107 |
| }, |
| { |
| "entropy": 0.9876950681209564, |
| "epoch": 1.0387409200968523, |
| "grad_norm": 0.15504641830921173, |
| "learning_rate": 3.9218411491011176e-05, |
| "loss": 0.9848049879074097, |
| "mean_token_accuracy": 0.7014968618750572, |
| "num_tokens": 10406734.0, |
| "step": 108 |
| }, |
| { |
| "entropy": 0.9847687631845474, |
| "epoch": 1.0484261501210654, |
| "grad_norm": 0.15988144278526306, |
| "learning_rate": 3.899936965343989e-05, |
| "loss": 0.99200838804245, |
| "mean_token_accuracy": 0.6996799558401108, |
| "num_tokens": 10504216.0, |
| "step": 109 |
| }, |
| { |
| "entropy": 1.0373386070132256, |
| "epoch": 1.0581113801452784, |
| "grad_norm": 0.1665649116039276, |
| "learning_rate": 3.877875085568623e-05, |
| "loss": 1.0424879789352417, |
| "mean_token_accuracy": 0.6860214620828629, |
| "num_tokens": 10601221.0, |
| "step": 110 |
| }, |
| { |
| "entropy": 1.006909765303135, |
| "epoch": 1.0677966101694916, |
| "grad_norm": 0.17135179042816162, |
| "learning_rate": 3.8556579949373384e-05, |
| "loss": 1.0011496543884277, |
| "mean_token_accuracy": 0.697038896381855, |
| "num_tokens": 10698216.0, |
| "step": 111 |
| }, |
| { |
| "entropy": 1.0339294224977493, |
| "epoch": 1.0774818401937045, |
| "grad_norm": 0.3495365381240845, |
| "learning_rate": 3.833288196096194e-05, |
| "loss": 1.0213532447814941, |
| "mean_token_accuracy": 0.6919962093234062, |
| "num_tokens": 10794443.0, |
| "step": 112 |
| }, |
| { |
| "entropy": 1.014359325170517, |
| "epoch": 1.0871670702179177, |
| "grad_norm": 0.15867272019386292, |
| "learning_rate": 3.8107682088930794e-05, |
| "loss": 1.0012414455413818, |
| "mean_token_accuracy": 0.6972551345825195, |
| "num_tokens": 10891911.0, |
| "step": 113 |
| }, |
| { |
| "entropy": 1.0279297679662704, |
| "epoch": 1.0968523002421307, |
| "grad_norm": 0.1764051765203476, |
| "learning_rate": 3.7881005700938635e-05, |
| "loss": 1.0181093215942383, |
| "mean_token_accuracy": 0.6937251910567284, |
| "num_tokens": 10989116.0, |
| "step": 114 |
| }, |
| { |
| "entropy": 1.0274560377001762, |
| "epoch": 1.1065375302663438, |
| "grad_norm": 0.16643169522285461, |
| "learning_rate": 3.7652878330966415e-05, |
| "loss": 1.0174015760421753, |
| "mean_token_accuracy": 0.6908667907118797, |
| "num_tokens": 11084803.0, |
| "step": 115 |
| }, |
| { |
| "entropy": 1.0327078253030777, |
| "epoch": 1.116222760290557, |
| "grad_norm": 0.15448430180549622, |
| "learning_rate": 3.742332567644107e-05, |
| "loss": 1.0166220664978027, |
| "mean_token_accuracy": 0.6931489333510399, |
| "num_tokens": 11181973.0, |
| "step": 116 |
| }, |
| { |
| "entropy": 1.005529247224331, |
| "epoch": 1.12590799031477, |
| "grad_norm": 0.15470093488693237, |
| "learning_rate": 3.719237359534087e-05, |
| "loss": 0.9815049171447754, |
| "mean_token_accuracy": 0.7029531449079514, |
| "num_tokens": 11278229.0, |
| "step": 117 |
| }, |
| { |
| "entropy": 1.0355120077729225, |
| "epoch": 1.1355932203389831, |
| "grad_norm": 0.16246767342090607, |
| "learning_rate": 3.6960048103282566e-05, |
| "loss": 1.0237441062927246, |
| "mean_token_accuracy": 0.6898825466632843, |
| "num_tokens": 11376039.0, |
| "step": 118 |
| }, |
| { |
| "entropy": 0.9869595319032669, |
| "epoch": 1.145278450363196, |
| "grad_norm": 0.16088958084583282, |
| "learning_rate": 3.672637537059093e-05, |
| "loss": 0.9821566343307495, |
| "mean_token_accuracy": 0.7027229741215706, |
| "num_tokens": 11473015.0, |
| "step": 119 |
| }, |
| { |
| "entropy": 1.0389124602079391, |
| "epoch": 1.1549636803874093, |
| "grad_norm": 0.17190344631671906, |
| "learning_rate": 3.6491381719350756e-05, |
| "loss": 1.041792392730713, |
| "mean_token_accuracy": 0.6849705725908279, |
| "num_tokens": 11569127.0, |
| "step": 120 |
| }, |
| { |
| "entropy": 0.9944993853569031, |
| "epoch": 1.1646489104116222, |
| "grad_norm": 0.16722099483013153, |
| "learning_rate": 3.6255093620441834e-05, |
| "loss": 1.0041072368621826, |
| "mean_token_accuracy": 0.6962790638208389, |
| "num_tokens": 11666046.0, |
| "step": 121 |
| }, |
| { |
| "entropy": 1.0362465903162956, |
| "epoch": 1.1743341404358354, |
| "grad_norm": 0.1714034080505371, |
| "learning_rate": 3.6017537690557115e-05, |
| "loss": 1.0482139587402344, |
| "mean_token_accuracy": 0.6842761412262917, |
| "num_tokens": 11763038.0, |
| "step": 122 |
| }, |
| { |
| "entropy": 1.0122292712330818, |
| "epoch": 1.1840193704600483, |
| "grad_norm": 0.19055414199829102, |
| "learning_rate": 3.577874068920446e-05, |
| "loss": 0.9998619556427002, |
| "mean_token_accuracy": 0.6981455683708191, |
| "num_tokens": 11861046.0, |
| "step": 123 |
| }, |
| { |
| "entropy": 1.0271427854895592, |
| "epoch": 1.1937046004842615, |
| "grad_norm": 0.1609717458486557, |
| "learning_rate": 3.553872951569236e-05, |
| "loss": 1.0139104127883911, |
| "mean_token_accuracy": 0.6922897696495056, |
| "num_tokens": 11958159.0, |
| "step": 124 |
| }, |
| { |
| "entropy": 1.0043516531586647, |
| "epoch": 1.2033898305084745, |
| "grad_norm": 0.16940025985240936, |
| "learning_rate": 3.529753120609982e-05, |
| "loss": 0.9896243810653687, |
| "mean_token_accuracy": 0.6995930150151253, |
| "num_tokens": 12055985.0, |
| "step": 125 |
| }, |
| { |
| "entropy": 1.0002227425575256, |
| "epoch": 1.2130750605326877, |
| "grad_norm": 0.1827508509159088, |
| "learning_rate": 3.505517293023088e-05, |
| "loss": 0.9946459531784058, |
| "mean_token_accuracy": 0.6992078274488449, |
| "num_tokens": 12152563.0, |
| "step": 126 |
| }, |
| { |
| "entropy": 0.9895355477929115, |
| "epoch": 1.2227602905569008, |
| "grad_norm": 0.16334764659404755, |
| "learning_rate": 3.481168198855409e-05, |
| "loss": 0.9852023124694824, |
| "mean_token_accuracy": 0.7000364437699318, |
| "num_tokens": 12249284.0, |
| "step": 127 |
| }, |
| { |
| "entropy": 1.0013327971100807, |
| "epoch": 1.2324455205811138, |
| "grad_norm": 0.18240107595920563, |
| "learning_rate": 3.456708580912725e-05, |
| "loss": 0.9998993873596191, |
| "mean_token_accuracy": 0.6956321373581886, |
| "num_tokens": 12346625.0, |
| "step": 128 |
| }, |
| { |
| "entropy": 0.9897650331258774, |
| "epoch": 1.242130750605327, |
| "grad_norm": 0.16192273795604706, |
| "learning_rate": 3.432141194450772e-05, |
| "loss": 0.9910838007926941, |
| "mean_token_accuracy": 0.6981474161148071, |
| "num_tokens": 12443423.0, |
| "step": 129 |
| }, |
| { |
| "entropy": 1.0171176567673683, |
| "epoch": 1.25181598062954, |
| "grad_norm": 0.1593330055475235, |
| "learning_rate": 3.407468806864883e-05, |
| "loss": 1.003114104270935, |
| "mean_token_accuracy": 0.6951852440834045, |
| "num_tokens": 12541166.0, |
| "step": 130 |
| }, |
| { |
| "entropy": 1.0180558636784554, |
| "epoch": 1.261501210653753, |
| "grad_norm": 0.17485769093036652, |
| "learning_rate": 3.382694197378252e-05, |
| "loss": 1.0093272924423218, |
| "mean_token_accuracy": 0.6934061422944069, |
| "num_tokens": 12638845.0, |
| "step": 131 |
| }, |
| { |
| "entropy": 1.005481794476509, |
| "epoch": 1.271186440677966, |
| "grad_norm": 0.1836148053407669, |
| "learning_rate": 3.357820156728867e-05, |
| "loss": 0.9869861602783203, |
| "mean_token_accuracy": 0.6990575343370438, |
| "num_tokens": 12733623.0, |
| "step": 132 |
| }, |
| { |
| "entropy": 0.9898593574762344, |
| "epoch": 1.2808716707021792, |
| "grad_norm": 0.1664602905511856, |
| "learning_rate": 3.332849486855144e-05, |
| "loss": 0.9797360897064209, |
| "mean_token_accuracy": 0.7021661400794983, |
| "num_tokens": 12829825.0, |
| "step": 133 |
| }, |
| { |
| "entropy": 0.9863950312137604, |
| "epoch": 1.2905569007263922, |
| "grad_norm": 0.1690891683101654, |
| "learning_rate": 3.307785000580313e-05, |
| "loss": 0.980827808380127, |
| "mean_token_accuracy": 0.701657846570015, |
| "num_tokens": 12923633.0, |
| "step": 134 |
| }, |
| { |
| "entropy": 0.9906058982014656, |
| "epoch": 1.3002421307506054, |
| "grad_norm": 0.15890969336032867, |
| "learning_rate": 3.282629521295556e-05, |
| "loss": 0.9958356618881226, |
| "mean_token_accuracy": 0.6968998163938522, |
| "num_tokens": 13020411.0, |
| "step": 135 |
| }, |
| { |
| "entropy": 1.0109577104449272, |
| "epoch": 1.3099273607748185, |
| "grad_norm": 0.16917017102241516, |
| "learning_rate": 3.257385882641971e-05, |
| "loss": 1.0153030157089233, |
| "mean_token_accuracy": 0.6948636248707771, |
| "num_tokens": 13117045.0, |
| "step": 136 |
| }, |
| { |
| "entropy": 1.0368539690971375, |
| "epoch": 1.3196125907990315, |
| "grad_norm": 0.17096075415611267, |
| "learning_rate": 3.232056928191376e-05, |
| "loss": 1.0295624732971191, |
| "mean_token_accuracy": 0.6880865320563316, |
| "num_tokens": 13211963.0, |
| "step": 137 |
| }, |
| { |
| "entropy": 0.9937515407800674, |
| "epoch": 1.3292978208232444, |
| "grad_norm": 0.19687673449516296, |
| "learning_rate": 3.2066455111259945e-05, |
| "loss": 0.9872187376022339, |
| "mean_token_accuracy": 0.698190338909626, |
| "num_tokens": 13309094.0, |
| "step": 138 |
| }, |
| { |
| "entropy": 0.98258426040411, |
| "epoch": 1.3389830508474576, |
| "grad_norm": 0.165676087141037, |
| "learning_rate": 3.1811544939170575e-05, |
| "loss": 0.9701927900314331, |
| "mean_token_accuracy": 0.7041537314653397, |
| "num_tokens": 13406414.0, |
| "step": 139 |
| }, |
| { |
| "entropy": 0.9949894845485687, |
| "epoch": 1.3486682808716708, |
| "grad_norm": 0.15660059452056885, |
| "learning_rate": 3.155586748002362e-05, |
| "loss": 0.983566403388977, |
| "mean_token_accuracy": 0.7017008811235428, |
| "num_tokens": 13503735.0, |
| "step": 140 |
| }, |
| { |
| "entropy": 1.004142202436924, |
| "epoch": 1.3583535108958837, |
| "grad_norm": 0.16567955911159515, |
| "learning_rate": 3.1299451534628135e-05, |
| "loss": 1.0012168884277344, |
| "mean_token_accuracy": 0.6947325691580772, |
| "num_tokens": 13601694.0, |
| "step": 141 |
| }, |
| { |
| "entropy": 0.9967528283596039, |
| "epoch": 1.368038740920097, |
| "grad_norm": 0.17423281073570251, |
| "learning_rate": 3.1042325986980064e-05, |
| "loss": 0.9905361533164978, |
| "mean_token_accuracy": 0.6961910724639893, |
| "num_tokens": 13699699.0, |
| "step": 142 |
| }, |
| { |
| "entropy": 1.044846922159195, |
| "epoch": 1.3777239709443099, |
| "grad_norm": 0.1701992005109787, |
| "learning_rate": 3.0784519801008546e-05, |
| "loss": 1.0325303077697754, |
| "mean_token_accuracy": 0.6879749968647957, |
| "num_tokens": 13797230.0, |
| "step": 143 |
| }, |
| { |
| "entropy": 1.0034736841917038, |
| "epoch": 1.387409200968523, |
| "grad_norm": 0.16985328495502472, |
| "learning_rate": 3.0526062017313254e-05, |
| "loss": 0.9976470470428467, |
| "mean_token_accuracy": 0.6975297853350639, |
| "num_tokens": 13893851.0, |
| "step": 144 |
| }, |
| { |
| "entropy": 0.9837843105196953, |
| "epoch": 1.397094430992736, |
| "grad_norm": 0.1869051605463028, |
| "learning_rate": 3.0266981749893157e-05, |
| "loss": 0.9784363508224487, |
| "mean_token_accuracy": 0.7024175301194191, |
| "num_tokens": 13990839.0, |
| "step": 145 |
| }, |
| { |
| "entropy": 0.9944631829857826, |
| "epoch": 1.4067796610169492, |
| "grad_norm": 0.16853010654449463, |
| "learning_rate": 3.0007308182866985e-05, |
| "loss": 0.9833719730377197, |
| "mean_token_accuracy": 0.700514979660511, |
| "num_tokens": 14088620.0, |
| "step": 146 |
| }, |
| { |
| "entropy": 0.9787930250167847, |
| "epoch": 1.4164648910411621, |
| "grad_norm": 0.16168715059757233, |
| "learning_rate": 2.974707056718571e-05, |
| "loss": 0.9737643003463745, |
| "mean_token_accuracy": 0.7025149315595627, |
| "num_tokens": 14183918.0, |
| "step": 147 |
| }, |
| { |
| "entropy": 1.0163143053650856, |
| "epoch": 1.4261501210653753, |
| "grad_norm": 0.17619730532169342, |
| "learning_rate": 2.9486298217337637e-05, |
| "loss": 1.0215412378311157, |
| "mean_token_accuracy": 0.688766747713089, |
| "num_tokens": 14281302.0, |
| "step": 148 |
| }, |
| { |
| "entropy": 1.0120554715394974, |
| "epoch": 1.4358353510895885, |
| "grad_norm": 0.17382408678531647, |
| "learning_rate": 2.9225020508046232e-05, |
| "loss": 1.010115623474121, |
| "mean_token_accuracy": 0.6935223415493965, |
| "num_tokens": 14378796.0, |
| "step": 149 |
| }, |
| { |
| "entropy": 0.9807057455182076, |
| "epoch": 1.4455205811138014, |
| "grad_norm": 0.16812428832054138, |
| "learning_rate": 2.8963266870961226e-05, |
| "loss": 0.9738281965255737, |
| "mean_token_accuracy": 0.702357143163681, |
| "num_tokens": 14475849.0, |
| "step": 150 |
| }, |
| { |
| "entropy": 1.027015931904316, |
| "epoch": 1.4552058111380144, |
| "grad_norm": 0.16742290556430817, |
| "learning_rate": 2.8701066791343288e-05, |
| "loss": 1.0114233493804932, |
| "mean_token_accuracy": 0.6957972124218941, |
| "num_tokens": 14573306.0, |
| "step": 151 |
| }, |
| { |
| "entropy": 1.0127879902720451, |
| "epoch": 1.4648910411622276, |
| "grad_norm": 0.16959309577941895, |
| "learning_rate": 2.8438449804742628e-05, |
| "loss": 1.0022327899932861, |
| "mean_token_accuracy": 0.6963436901569366, |
| "num_tokens": 14670804.0, |
| "step": 152 |
| }, |
| { |
| "entropy": 1.0084099918603897, |
| "epoch": 1.4745762711864407, |
| "grad_norm": 0.1659703105688095, |
| "learning_rate": 2.8175445493671972e-05, |
| "loss": 0.9958415031433105, |
| "mean_token_accuracy": 0.6974244639277458, |
| "num_tokens": 14768628.0, |
| "step": 153 |
| }, |
| { |
| "entropy": 0.9794844463467598, |
| "epoch": 1.4842615012106537, |
| "grad_norm": 0.1611631065607071, |
| "learning_rate": 2.7912083484274266e-05, |
| "loss": 0.9711570143699646, |
| "mean_token_accuracy": 0.7039349600672722, |
| "num_tokens": 14865274.0, |
| "step": 154 |
| }, |
| { |
| "entropy": 0.9954876154661179, |
| "epoch": 1.4939467312348669, |
| "grad_norm": 0.16479367017745972, |
| "learning_rate": 2.7648393442985403e-05, |
| "loss": 0.9906888008117676, |
| "mean_token_accuracy": 0.6987522318959236, |
| "num_tokens": 14961344.0, |
| "step": 155 |
| }, |
| { |
| "entropy": 0.9944536164402962, |
| "epoch": 1.5036319612590798, |
| "grad_norm": 0.17284482717514038, |
| "learning_rate": 2.7384405073192454e-05, |
| "loss": 0.9951756000518799, |
| "mean_token_accuracy": 0.6990461647510529, |
| "num_tokens": 15058585.0, |
| "step": 156 |
| }, |
| { |
| "entropy": 1.0036951154470444, |
| "epoch": 1.513317191283293, |
| "grad_norm": 0.1650843620300293, |
| "learning_rate": 2.7120148111887732e-05, |
| "loss": 1.0069425106048584, |
| "mean_token_accuracy": 0.6929773390293121, |
| "num_tokens": 15154032.0, |
| "step": 157 |
| }, |
| { |
| "entropy": 1.0147020071744919, |
| "epoch": 1.5230024213075062, |
| "grad_norm": 0.16452395915985107, |
| "learning_rate": 2.6855652326319063e-05, |
| "loss": 1.011418104171753, |
| "mean_token_accuracy": 0.6934091821312904, |
| "num_tokens": 15251303.0, |
| "step": 158 |
| }, |
| { |
| "entropy": 0.9665024057030678, |
| "epoch": 1.5326876513317191, |
| "grad_norm": 0.16577263176441193, |
| "learning_rate": 2.659094751063666e-05, |
| "loss": 0.9683203101158142, |
| "mean_token_accuracy": 0.7044110149145126, |
| "num_tokens": 15349150.0, |
| "step": 159 |
| }, |
| { |
| "entropy": 0.9799178317189217, |
| "epoch": 1.542372881355932, |
| "grad_norm": 0.1703728437423706, |
| "learning_rate": 2.6326063482536934e-05, |
| "loss": 0.9746803045272827, |
| "mean_token_accuracy": 0.702017679810524, |
| "num_tokens": 15447053.0, |
| "step": 160 |
| }, |
| { |
| "entropy": 1.019065484404564, |
| "epoch": 1.5520581113801453, |
| "grad_norm": 0.1775662750005722, |
| "learning_rate": 2.606103007990371e-05, |
| "loss": 1.003313422203064, |
| "mean_token_accuracy": 0.6955779567360878, |
| "num_tokens": 15544017.0, |
| "step": 161 |
| }, |
| { |
| "entropy": 0.9930843040347099, |
| "epoch": 1.5617433414043584, |
| "grad_norm": 0.16264039278030396, |
| "learning_rate": 2.579587715744712e-05, |
| "loss": 0.9869210720062256, |
| "mean_token_accuracy": 0.6987086161971092, |
| "num_tokens": 15641272.0, |
| "step": 162 |
| }, |
| { |
| "entropy": 1.0073056146502495, |
| "epoch": 1.5714285714285714, |
| "grad_norm": 0.17356610298156738, |
| "learning_rate": 2.5530634583340592e-05, |
| "loss": 1.0044951438903809, |
| "mean_token_accuracy": 0.6942961737513542, |
| "num_tokens": 15738724.0, |
| "step": 163 |
| }, |
| { |
| "entropy": 0.9752182215452194, |
| "epoch": 1.5811138014527844, |
| "grad_norm": 0.16671140491962433, |
| "learning_rate": 2.526533223585641e-05, |
| "loss": 0.972718358039856, |
| "mean_token_accuracy": 0.7028070986270905, |
| "num_tokens": 15835590.0, |
| "step": 164 |
| }, |
| { |
| "entropy": 1.0182273015379906, |
| "epoch": 1.5907990314769975, |
| "grad_norm": 0.16183283925056458, |
| "learning_rate": 2.5e-05, |
| "loss": 1.0093859434127808, |
| "mean_token_accuracy": 0.6935742124915123, |
| "num_tokens": 15932676.0, |
| "step": 165 |
| }, |
| { |
| "entropy": 1.0086438283324242, |
| "epoch": 1.6004842615012107, |
| "grad_norm": 0.1724725067615509, |
| "learning_rate": 2.47346677641436e-05, |
| "loss": 0.9900722503662109, |
| "mean_token_accuracy": 0.6989754140377045, |
| "num_tokens": 16029299.0, |
| "step": 166 |
| }, |
| { |
| "entropy": 1.0013468265533447, |
| "epoch": 1.6101694915254239, |
| "grad_norm": 0.1769559532403946, |
| "learning_rate": 2.446936541665941e-05, |
| "loss": 0.9839099645614624, |
| "mean_token_accuracy": 0.7014129236340523, |
| "num_tokens": 16127099.0, |
| "step": 167 |
| }, |
| { |
| "entropy": 1.0107010528445244, |
| "epoch": 1.6198547215496368, |
| "grad_norm": 0.16785570979118347, |
| "learning_rate": 2.4204122842552896e-05, |
| "loss": 0.9957517385482788, |
| "mean_token_accuracy": 0.6972147971391678, |
| "num_tokens": 16224370.0, |
| "step": 168 |
| }, |
| { |
| "entropy": 1.0056702345609665, |
| "epoch": 1.6295399515738498, |
| "grad_norm": 0.16105356812477112, |
| "learning_rate": 2.39389699200963e-05, |
| "loss": 1.0083773136138916, |
| "mean_token_accuracy": 0.6938697770237923, |
| "num_tokens": 16322206.0, |
| "step": 169 |
| }, |
| { |
| "entropy": 0.9679917171597481, |
| "epoch": 1.639225181598063, |
| "grad_norm": 0.18555910885334015, |
| "learning_rate": 2.3673936517463075e-05, |
| "loss": 0.9662629961967468, |
| "mean_token_accuracy": 0.7058677673339844, |
| "num_tokens": 16420091.0, |
| "step": 170 |
| }, |
| { |
| "entropy": 0.9951441884040833, |
| "epoch": 1.6489104116222761, |
| "grad_norm": 0.16113026440143585, |
| "learning_rate": 2.3409052489363342e-05, |
| "loss": 0.9964888095855713, |
| "mean_token_accuracy": 0.6966480612754822, |
| "num_tokens": 16518151.0, |
| "step": 171 |
| }, |
| { |
| "entropy": 0.9950687289237976, |
| "epoch": 1.658595641646489, |
| "grad_norm": 0.1655929833650589, |
| "learning_rate": 2.3144347673680936e-05, |
| "loss": 0.9870741367340088, |
| "mean_token_accuracy": 0.6975122019648552, |
| "num_tokens": 16615773.0, |
| "step": 172 |
| }, |
| { |
| "entropy": 0.9828060492873192, |
| "epoch": 1.668280871670702, |
| "grad_norm": 0.15567153692245483, |
| "learning_rate": 2.287985188811228e-05, |
| "loss": 0.9722952246665955, |
| "mean_token_accuracy": 0.70285364985466, |
| "num_tokens": 16713397.0, |
| "step": 173 |
| }, |
| { |
| "entropy": 1.0082043036818504, |
| "epoch": 1.6779661016949152, |
| "grad_norm": 0.17026451230049133, |
| "learning_rate": 2.261559492680755e-05, |
| "loss": 0.9899446368217468, |
| "mean_token_accuracy": 0.6977179124951363, |
| "num_tokens": 16810390.0, |
| "step": 174 |
| }, |
| { |
| "entropy": 1.0040841177105904, |
| "epoch": 1.6876513317191284, |
| "grad_norm": 0.16849051415920258, |
| "learning_rate": 2.23516065570146e-05, |
| "loss": 0.9847683906555176, |
| "mean_token_accuracy": 0.7004509717226028, |
| "num_tokens": 16907393.0, |
| "step": 175 |
| }, |
| { |
| "entropy": 0.9779401943087578, |
| "epoch": 1.6973365617433414, |
| "grad_norm": 0.16106560826301575, |
| "learning_rate": 2.2087916515725737e-05, |
| "loss": 0.9651379585266113, |
| "mean_token_accuracy": 0.7060760706663132, |
| "num_tokens": 17004930.0, |
| "step": 176 |
| }, |
| { |
| "entropy": 0.9812775775790215, |
| "epoch": 1.7070217917675545, |
| "grad_norm": 0.16682280600070953, |
| "learning_rate": 2.182455450632803e-05, |
| "loss": 0.9719981551170349, |
| "mean_token_accuracy": 0.7013477832078934, |
| "num_tokens": 17101024.0, |
| "step": 177 |
| }, |
| { |
| "entropy": 0.9964217767119408, |
| "epoch": 1.7167070217917675, |
| "grad_norm": 0.16916021704673767, |
| "learning_rate": 2.1561550195257378e-05, |
| "loss": 0.9914392828941345, |
| "mean_token_accuracy": 0.6976988613605499, |
| "num_tokens": 17198565.0, |
| "step": 178 |
| }, |
| { |
| "entropy": 0.9807400777935982, |
| "epoch": 1.7263922518159807, |
| "grad_norm": 0.21374505758285522, |
| "learning_rate": 2.1298933208656718e-05, |
| "loss": 0.980735182762146, |
| "mean_token_accuracy": 0.7001545950770378, |
| "num_tokens": 17295612.0, |
| "step": 179 |
| }, |
| { |
| "entropy": 0.9822961390018463, |
| "epoch": 1.7360774818401938, |
| "grad_norm": 0.17142128944396973, |
| "learning_rate": 2.103673312903878e-05, |
| "loss": 0.9922733306884766, |
| "mean_token_accuracy": 0.6986024007201195, |
| "num_tokens": 17393410.0, |
| "step": 180 |
| }, |
| { |
| "entropy": 0.98645830899477, |
| "epoch": 1.7457627118644068, |
| "grad_norm": 0.16733792424201965, |
| "learning_rate": 2.0774979491953777e-05, |
| "loss": 0.9795247316360474, |
| "mean_token_accuracy": 0.701476626098156, |
| "num_tokens": 17490028.0, |
| "step": 181 |
| }, |
| { |
| "entropy": 0.989493116736412, |
| "epoch": 1.7554479418886197, |
| "grad_norm": 0.16438013315200806, |
| "learning_rate": 2.0513701782662366e-05, |
| "loss": 0.9933204054832458, |
| "mean_token_accuracy": 0.6978474259376526, |
| "num_tokens": 17587259.0, |
| "step": 182 |
| }, |
| { |
| "entropy": 0.9897148385643959, |
| "epoch": 1.765133171912833, |
| "grad_norm": 0.16726766526699066, |
| "learning_rate": 2.025292943281429e-05, |
| "loss": 0.9891308546066284, |
| "mean_token_accuracy": 0.6983208954334259, |
| "num_tokens": 17684414.0, |
| "step": 183 |
| }, |
| { |
| "entropy": 0.9797371402382851, |
| "epoch": 1.774818401937046, |
| "grad_norm": 0.16416160762310028, |
| "learning_rate": 1.9992691817133024e-05, |
| "loss": 0.969803512096405, |
| "mean_token_accuracy": 0.7029882669448853, |
| "num_tokens": 17781130.0, |
| "step": 184 |
| }, |
| { |
| "entropy": 1.004914864897728, |
| "epoch": 1.784503631961259, |
| "grad_norm": 0.1719769388437271, |
| "learning_rate": 1.973301825010685e-05, |
| "loss": 1.0040626525878906, |
| "mean_token_accuracy": 0.6956639438867569, |
| "num_tokens": 17878645.0, |
| "step": 185 |
| }, |
| { |
| "entropy": 0.9869519099593163, |
| "epoch": 1.794188861985472, |
| "grad_norm": 0.16303589940071106, |
| "learning_rate": 1.947393798268676e-05, |
| "loss": 0.9739397764205933, |
| "mean_token_accuracy": 0.7010327354073524, |
| "num_tokens": 17976579.0, |
| "step": 186 |
| }, |
| { |
| "entropy": 0.975304365158081, |
| "epoch": 1.8038740920096852, |
| "grad_norm": 0.1580132395029068, |
| "learning_rate": 1.9215480198991466e-05, |
| "loss": 0.9598423838615417, |
| "mean_token_accuracy": 0.7052361443638802, |
| "num_tokens": 18074189.0, |
| "step": 187 |
| }, |
| { |
| "entropy": 0.9971402436494827, |
| "epoch": 1.8135593220338984, |
| "grad_norm": 0.16983391344547272, |
| "learning_rate": 1.895767401301994e-05, |
| "loss": 0.9938044548034668, |
| "mean_token_accuracy": 0.6988947540521622, |
| "num_tokens": 18171237.0, |
| "step": 188 |
| }, |
| { |
| "entropy": 0.9822115898132324, |
| "epoch": 1.8232445520581115, |
| "grad_norm": 0.16956081986427307, |
| "learning_rate": 1.8700548465371874e-05, |
| "loss": 0.9686650633811951, |
| "mean_token_accuracy": 0.7034626305103302, |
| "num_tokens": 18268577.0, |
| "step": 189 |
| }, |
| { |
| "entropy": 1.002944439649582, |
| "epoch": 1.8329297820823245, |
| "grad_norm": 0.16677941381931305, |
| "learning_rate": 1.84441325199764e-05, |
| "loss": 0.9920344352722168, |
| "mean_token_accuracy": 0.6985628455877304, |
| "num_tokens": 18362794.0, |
| "step": 190 |
| }, |
| { |
| "entropy": 0.9808652997016907, |
| "epoch": 1.8426150121065374, |
| "grad_norm": 0.16181781888008118, |
| "learning_rate": 1.818845506082943e-05, |
| "loss": 0.972355842590332, |
| "mean_token_accuracy": 0.7030967250466347, |
| "num_tokens": 18460513.0, |
| "step": 191 |
| }, |
| { |
| "entropy": 0.9836144298315048, |
| "epoch": 1.8523002421307506, |
| "grad_norm": 0.16721659898757935, |
| "learning_rate": 1.793354488874006e-05, |
| "loss": 0.9754103422164917, |
| "mean_token_accuracy": 0.7023874595761299, |
| "num_tokens": 18556427.0, |
| "step": 192 |
| }, |
| { |
| "entropy": 0.9832232519984245, |
| "epoch": 1.8619854721549638, |
| "grad_norm": 0.1614263653755188, |
| "learning_rate": 1.7679430718086243e-05, |
| "loss": 0.969515323638916, |
| "mean_token_accuracy": 0.7037129253149033, |
| "num_tokens": 18654140.0, |
| "step": 193 |
| }, |
| { |
| "entropy": 0.9876326695084572, |
| "epoch": 1.8716707021791767, |
| "grad_norm": 0.173170268535614, |
| "learning_rate": 1.742614117358029e-05, |
| "loss": 0.9809838533401489, |
| "mean_token_accuracy": 0.7008324488997459, |
| "num_tokens": 18751703.0, |
| "step": 194 |
| }, |
| { |
| "entropy": 0.9655271023511887, |
| "epoch": 1.8813559322033897, |
| "grad_norm": 0.1669541597366333, |
| "learning_rate": 1.7173704787044446e-05, |
| "loss": 0.9667908549308777, |
| "mean_token_accuracy": 0.7037958055734634, |
| "num_tokens": 18849604.0, |
| "step": 195 |
| }, |
| { |
| "entropy": 0.9761006310582161, |
| "epoch": 1.8910411622276029, |
| "grad_norm": 0.16982783377170563, |
| "learning_rate": 1.6922149994196878e-05, |
| "loss": 0.9785382747650146, |
| "mean_token_accuracy": 0.7007183507084846, |
| "num_tokens": 18945573.0, |
| "step": 196 |
| }, |
| { |
| "entropy": 0.9784979596734047, |
| "epoch": 1.900726392251816, |
| "grad_norm": 0.1615481823682785, |
| "learning_rate": 1.667150513144856e-05, |
| "loss": 0.9882582426071167, |
| "mean_token_accuracy": 0.6977169886231422, |
| "num_tokens": 19043149.0, |
| "step": 197 |
| }, |
| { |
| "entropy": 0.9912172853946686, |
| "epoch": 1.910411622276029, |
| "grad_norm": 0.16227596998214722, |
| "learning_rate": 1.6421798432711345e-05, |
| "loss": 0.988640308380127, |
| "mean_token_accuracy": 0.696373961865902, |
| "num_tokens": 19140120.0, |
| "step": 198 |
| }, |
| { |
| "entropy": 0.9930980131030083, |
| "epoch": 1.9200968523002422, |
| "grad_norm": 0.16644878685474396, |
| "learning_rate": 1.617305802621748e-05, |
| "loss": 0.9825809001922607, |
| "mean_token_accuracy": 0.6994545757770538, |
| "num_tokens": 19238205.0, |
| "step": 199 |
| }, |
| { |
| "entropy": 0.9926598519086838, |
| "epoch": 1.9297820823244551, |
| "grad_norm": 0.1617429107427597, |
| "learning_rate": 1.5925311931351172e-05, |
| "loss": 0.9819120764732361, |
| "mean_token_accuracy": 0.7000753432512283, |
| "num_tokens": 19334020.0, |
| "step": 200 |
| }, |
| { |
| "entropy": 0.9761699810624123, |
| "epoch": 1.9394673123486683, |
| "grad_norm": 0.16152705252170563, |
| "learning_rate": 1.567858805549229e-05, |
| "loss": 0.964564323425293, |
| "mean_token_accuracy": 0.7047165408730507, |
| "num_tokens": 19431159.0, |
| "step": 201 |
| }, |
| { |
| "entropy": 0.9937325268983841, |
| "epoch": 1.9491525423728815, |
| "grad_norm": 0.16244447231292725, |
| "learning_rate": 1.5432914190872757e-05, |
| "loss": 0.9797715544700623, |
| "mean_token_accuracy": 0.7011676132678986, |
| "num_tokens": 19528580.0, |
| "step": 202 |
| }, |
| { |
| "entropy": 0.9928828999400139, |
| "epoch": 1.9588377723970944, |
| "grad_norm": 0.16242294013500214, |
| "learning_rate": 1.5188318011445906e-05, |
| "loss": 0.9902064800262451, |
| "mean_token_accuracy": 0.7003620937466621, |
| "num_tokens": 19624750.0, |
| "step": 203 |
| }, |
| { |
| "entropy": 0.9670996069908142, |
| "epoch": 1.9685230024213074, |
| "grad_norm": 0.16028518974781036, |
| "learning_rate": 1.4944827069769123e-05, |
| "loss": 0.95257967710495, |
| "mean_token_accuracy": 0.7070973888039589, |
| "num_tokens": 19720069.0, |
| "step": 204 |
| }, |
| { |
| "entropy": 0.9721826240420341, |
| "epoch": 1.9782082324455206, |
| "grad_norm": 0.16586320102214813, |
| "learning_rate": 1.4702468793900188e-05, |
| "loss": 0.9669836759567261, |
| "mean_token_accuracy": 0.7026080042123795, |
| "num_tokens": 19817446.0, |
| "step": 205 |
| }, |
| { |
| "entropy": 0.9796883463859558, |
| "epoch": 1.9878934624697338, |
| "grad_norm": 0.178948774933815, |
| "learning_rate": 1.4461270484307643e-05, |
| "loss": 0.9749795198440552, |
| "mean_token_accuracy": 0.7004246413707733, |
| "num_tokens": 19914879.0, |
| "step": 206 |
| }, |
| { |
| "entropy": 0.9879425168037415, |
| "epoch": 1.9975786924939467, |
| "grad_norm": 0.17937594652175903, |
| "learning_rate": 1.4221259310795543e-05, |
| "loss": 0.9886235594749451, |
| "mean_token_accuracy": 0.6989741027355194, |
| "num_tokens": 20012627.0, |
| "step": 207 |
| }, |
| { |
| "entropy": 0.9514671564102173, |
| "epoch": 2.0, |
| "grad_norm": 0.3125458061695099, |
| "learning_rate": 1.3982462309442889e-05, |
| "loss": 0.9488482475280762, |
| "mean_token_accuracy": 0.7110036909580231, |
| "num_tokens": 20036688.0, |
| "step": 208 |
| }, |
| { |
| "entropy": 0.935210257768631, |
| "epoch": 2.009685230024213, |
| "grad_norm": 0.16670554876327515, |
| "learning_rate": 1.3744906379558165e-05, |
| "loss": 0.9009658694267273, |
| "mean_token_accuracy": 0.7200484350323677, |
| "num_tokens": 20132151.0, |
| "step": 209 |
| }, |
| { |
| "entropy": 0.970642939209938, |
| "epoch": 2.0193704600484264, |
| "grad_norm": 0.1616680771112442, |
| "learning_rate": 1.3508618280649255e-05, |
| "loss": 0.9447044134140015, |
| "mean_token_accuracy": 0.7088503241539001, |
| "num_tokens": 20229560.0, |
| "step": 210 |
| }, |
| { |
| "entropy": 0.9589889943599701, |
| "epoch": 2.029055690072639, |
| "grad_norm": 0.16520114243030548, |
| "learning_rate": 1.3273624629409082e-05, |
| "loss": 0.9324673414230347, |
| "mean_token_accuracy": 0.7126134932041168, |
| "num_tokens": 20327500.0, |
| "step": 211 |
| }, |
| { |
| "entropy": 0.9479562044143677, |
| "epoch": 2.0387409200968523, |
| "grad_norm": 0.1709011346101761, |
| "learning_rate": 1.3039951896717445e-05, |
| "loss": 0.9266945719718933, |
| "mean_token_accuracy": 0.7146143615245819, |
| "num_tokens": 20424595.0, |
| "step": 212 |
| }, |
| { |
| "entropy": 0.954995684325695, |
| "epoch": 2.0484261501210654, |
| "grad_norm": 0.166041299700737, |
| "learning_rate": 1.2807626404659142e-05, |
| "loss": 0.9395579099655151, |
| "mean_token_accuracy": 0.7103377655148506, |
| "num_tokens": 20521809.0, |
| "step": 213 |
| }, |
| { |
| "entropy": 0.9718707501888275, |
| "epoch": 2.0581113801452786, |
| "grad_norm": 0.17487496137619019, |
| "learning_rate": 1.2576674323558929e-05, |
| "loss": 0.9646943807601929, |
| "mean_token_accuracy": 0.7033604010939598, |
| "num_tokens": 20619568.0, |
| "step": 214 |
| }, |
| { |
| "entropy": 0.9374101758003235, |
| "epoch": 2.0677966101694913, |
| "grad_norm": 0.1907682716846466, |
| "learning_rate": 1.234712166903359e-05, |
| "loss": 0.9350243806838989, |
| "mean_token_accuracy": 0.708103246986866, |
| "num_tokens": 20716223.0, |
| "step": 215 |
| }, |
| { |
| "entropy": 0.9411287754774094, |
| "epoch": 2.0774818401937045, |
| "grad_norm": 0.16793693602085114, |
| "learning_rate": 1.2118994299061376e-05, |
| "loss": 0.937713086605072, |
| "mean_token_accuracy": 0.7123425528407097, |
| "num_tokens": 20813542.0, |
| "step": 216 |
| }, |
| { |
| "entropy": 0.9248437285423279, |
| "epoch": 2.0871670702179177, |
| "grad_norm": 0.1725640445947647, |
| "learning_rate": 1.1892317911069212e-05, |
| "loss": 0.9310259819030762, |
| "mean_token_accuracy": 0.7092035114765167, |
| "num_tokens": 20911371.0, |
| "step": 217 |
| }, |
| { |
| "entropy": 0.9233638122677803, |
| "epoch": 2.096852300242131, |
| "grad_norm": 0.16743937134742737, |
| "learning_rate": 1.1667118039038064e-05, |
| "loss": 0.9297460913658142, |
| "mean_token_accuracy": 0.7147964909672737, |
| "num_tokens": 21008134.0, |
| "step": 218 |
| }, |
| { |
| "entropy": 0.9599243849515915, |
| "epoch": 2.106537530266344, |
| "grad_norm": 0.17014926671981812, |
| "learning_rate": 1.1443420050626625e-05, |
| "loss": 0.9641548991203308, |
| "mean_token_accuracy": 0.7034465074539185, |
| "num_tokens": 21105251.0, |
| "step": 219 |
| }, |
| { |
| "entropy": 0.9364227131009102, |
| "epoch": 2.116222760290557, |
| "grad_norm": 0.17084726691246033, |
| "learning_rate": 1.1221249144313778e-05, |
| "loss": 0.9421942234039307, |
| "mean_token_accuracy": 0.7104882076382637, |
| "num_tokens": 21201989.0, |
| "step": 220 |
| }, |
| { |
| "entropy": 0.9569654315710068, |
| "epoch": 2.12590799031477, |
| "grad_norm": 0.1694927215576172, |
| "learning_rate": 1.1000630346560117e-05, |
| "loss": 0.9526486396789551, |
| "mean_token_accuracy": 0.7051248848438263, |
| "num_tokens": 21299395.0, |
| "step": 221 |
| }, |
| { |
| "entropy": 0.9333659335970879, |
| "epoch": 2.135593220338983, |
| "grad_norm": 0.1715596616268158, |
| "learning_rate": 1.078158850898883e-05, |
| "loss": 0.9338709712028503, |
| "mean_token_accuracy": 0.7134337201714516, |
| "num_tokens": 21396912.0, |
| "step": 222 |
| }, |
| { |
| "entropy": 0.9515627101063728, |
| "epoch": 2.1452784503631963, |
| "grad_norm": 0.16776902973651886, |
| "learning_rate": 1.0564148305586296e-05, |
| "loss": 0.9470714330673218, |
| "mean_token_accuracy": 0.7065200731158257, |
| "num_tokens": 21494259.0, |
| "step": 223 |
| }, |
| { |
| "entropy": 0.9610101133584976, |
| "epoch": 2.154963680387409, |
| "grad_norm": 0.16883954405784607, |
| "learning_rate": 1.0348334229922677e-05, |
| "loss": 0.9485963582992554, |
| "mean_token_accuracy": 0.7087370902299881, |
| "num_tokens": 21591715.0, |
| "step": 224 |
| }, |
| { |
| "entropy": 0.9303972199559212, |
| "epoch": 2.164648910411622, |
| "grad_norm": 0.16886527836322784, |
| "learning_rate": 1.0134170592392836e-05, |
| "loss": 0.9146007299423218, |
| "mean_token_accuracy": 0.7167314291000366, |
| "num_tokens": 21689246.0, |
| "step": 225 |
| }, |
| { |
| "entropy": 0.9525900855660439, |
| "epoch": 2.1743341404358354, |
| "grad_norm": 0.16460201144218445, |
| "learning_rate": 9.9216815174779e-06, |
| "loss": 0.9324812293052673, |
| "mean_token_accuracy": 0.7116940021514893, |
| "num_tokens": 21787440.0, |
| "step": 226 |
| }, |
| { |
| "entropy": 0.9532545283436775, |
| "epoch": 2.1840193704600486, |
| "grad_norm": 0.16504663228988647, |
| "learning_rate": 9.710890941027722e-06, |
| "loss": 0.9364947080612183, |
| "mean_token_accuracy": 0.7101058140397072, |
| "num_tokens": 21884484.0, |
| "step": 227 |
| }, |
| { |
| "entropy": 0.9715408980846405, |
| "epoch": 2.1937046004842613, |
| "grad_norm": 0.17337989807128906, |
| "learning_rate": 9.501822607564678e-06, |
| "loss": 0.9469114542007446, |
| "mean_token_accuracy": 0.7051354795694351, |
| "num_tokens": 21981491.0, |
| "step": 228 |
| }, |
| { |
| "entropy": 0.9441230446100235, |
| "epoch": 2.2033898305084745, |
| "grad_norm": 0.16986575722694397, |
| "learning_rate": 9.29450006760894e-06, |
| "loss": 0.930769681930542, |
| "mean_token_accuracy": 0.7128172218799591, |
| "num_tokens": 22079121.0, |
| "step": 229 |
| }, |
| { |
| "entropy": 0.952056460082531, |
| "epoch": 2.2130750605326877, |
| "grad_norm": 0.16806066036224365, |
| "learning_rate": 9.088946675025605e-06, |
| "loss": 0.9320424795150757, |
| "mean_token_accuracy": 0.7113776057958603, |
| "num_tokens": 22177061.0, |
| "step": 230 |
| }, |
| { |
| "entropy": 0.9570830389857292, |
| "epoch": 2.222760290556901, |
| "grad_norm": 0.16914764046669006, |
| "learning_rate": 8.88518558439402e-06, |
| "loss": 0.9455908536911011, |
| "mean_token_accuracy": 0.7061085477471352, |
| "num_tokens": 22273105.0, |
| "step": 231 |
| }, |
| { |
| "entropy": 0.9495053663849831, |
| "epoch": 2.232445520581114, |
| "grad_norm": 0.16020551323890686, |
| "learning_rate": 8.683239748399539e-06, |
| "loss": 0.9452719688415527, |
| "mean_token_accuracy": 0.7079599052667618, |
| "num_tokens": 22370560.0, |
| "step": 232 |
| }, |
| { |
| "entropy": 0.9417334049940109, |
| "epoch": 2.2421307506053267, |
| "grad_norm": 0.17766158282756805, |
| "learning_rate": 8.483131915247968e-06, |
| "loss": 0.9379410147666931, |
| "mean_token_accuracy": 0.7104996889829636, |
| "num_tokens": 22467820.0, |
| "step": 233 |
| }, |
| { |
| "entropy": 0.9111597910523415, |
| "epoch": 2.25181598062954, |
| "grad_norm": 0.16672994196414948, |
| "learning_rate": 8.284884626103165e-06, |
| "loss": 0.910470187664032, |
| "mean_token_accuracy": 0.7176472991704941, |
| "num_tokens": 22564058.0, |
| "step": 234 |
| }, |
| { |
| "entropy": 0.9426783844828606, |
| "epoch": 2.261501210653753, |
| "grad_norm": 0.3562923073768616, |
| "learning_rate": 8.088520212547831e-06, |
| "loss": 0.9418071508407593, |
| "mean_token_accuracy": 0.709033690392971, |
| "num_tokens": 22660351.0, |
| "step": 235 |
| }, |
| { |
| "entropy": 0.9583405628800392, |
| "epoch": 2.2711864406779663, |
| "grad_norm": 0.1716354787349701, |
| "learning_rate": 7.894060794067987e-06, |
| "loss": 0.9610295295715332, |
| "mean_token_accuracy": 0.7040604129433632, |
| "num_tokens": 22756938.0, |
| "step": 236 |
| }, |
| { |
| "entropy": 0.9392780140042305, |
| "epoch": 2.280871670702179, |
| "grad_norm": 0.17350956797599792, |
| "learning_rate": 7.701528275561348e-06, |
| "loss": 0.9483029246330261, |
| "mean_token_accuracy": 0.7087198719382286, |
| "num_tokens": 22854716.0, |
| "step": 237 |
| }, |
| { |
| "entropy": 0.9282214939594269, |
| "epoch": 2.290556900726392, |
| "grad_norm": 0.16693778336048126, |
| "learning_rate": 7.510944344869774e-06, |
| "loss": 0.9324116110801697, |
| "mean_token_accuracy": 0.7124903500080109, |
| "num_tokens": 22951404.0, |
| "step": 238 |
| }, |
| { |
| "entropy": 0.9621627777814865, |
| "epoch": 2.3002421307506054, |
| "grad_norm": 0.17030690610408783, |
| "learning_rate": 7.3223304703363135e-06, |
| "loss": 0.9539659023284912, |
| "mean_token_accuracy": 0.7052002549171448, |
| "num_tokens": 23049106.0, |
| "step": 239 |
| }, |
| { |
| "entropy": 0.9691312462091446, |
| "epoch": 2.3099273607748185, |
| "grad_norm": 0.19137652218341827, |
| "learning_rate": 7.13570789838687e-06, |
| "loss": 0.9654158353805542, |
| "mean_token_accuracy": 0.7027337849140167, |
| "num_tokens": 23145981.0, |
| "step": 240 |
| }, |
| { |
| "entropy": 0.9534872993826866, |
| "epoch": 2.3196125907990313, |
| "grad_norm": 0.20619812607765198, |
| "learning_rate": 6.951097651136889e-06, |
| "loss": 0.9388442039489746, |
| "mean_token_accuracy": 0.7103362306952477, |
| "num_tokens": 23243247.0, |
| "step": 241 |
| }, |
| { |
| "entropy": 0.9576206207275391, |
| "epoch": 2.3292978208232444, |
| "grad_norm": 0.17732170224189758, |
| "learning_rate": 6.768520524023348e-06, |
| "loss": 0.9409503936767578, |
| "mean_token_accuracy": 0.7121771350502968, |
| "num_tokens": 23340536.0, |
| "step": 242 |
| }, |
| { |
| "entropy": 0.9551548361778259, |
| "epoch": 2.3389830508474576, |
| "grad_norm": 0.16700609028339386, |
| "learning_rate": 6.587997083462197e-06, |
| "loss": 0.9494003057479858, |
| "mean_token_accuracy": 0.7064109221100807, |
| "num_tokens": 23438030.0, |
| "step": 243 |
| }, |
| { |
| "entropy": 0.9394743740558624, |
| "epoch": 2.348668280871671, |
| "grad_norm": 0.16255992650985718, |
| "learning_rate": 6.4095476645317346e-06, |
| "loss": 0.9245573878288269, |
| "mean_token_accuracy": 0.7135687842965126, |
| "num_tokens": 23534316.0, |
| "step": 244 |
| }, |
| { |
| "entropy": 0.9393111318349838, |
| "epoch": 2.358353510895884, |
| "grad_norm": 0.16755938529968262, |
| "learning_rate": 6.23319236868189e-06, |
| "loss": 0.9254769682884216, |
| "mean_token_accuracy": 0.7146429866552353, |
| "num_tokens": 23631649.0, |
| "step": 245 |
| }, |
| { |
| "entropy": 0.9549592733383179, |
| "epoch": 2.3680387409200967, |
| "grad_norm": 0.16677358746528625, |
| "learning_rate": 6.058951061469931e-06, |
| "loss": 0.9551336169242859, |
| "mean_token_accuracy": 0.7040988355875015, |
| "num_tokens": 23728328.0, |
| "step": 246 |
| }, |
| { |
| "entropy": 0.9785780981183052, |
| "epoch": 2.37772397094431, |
| "grad_norm": 0.1658286154270172, |
| "learning_rate": 5.886843370322692e-06, |
| "loss": 0.968536376953125, |
| "mean_token_accuracy": 0.703674927353859, |
| "num_tokens": 23826551.0, |
| "step": 247 |
| }, |
| { |
| "entropy": 0.9652357175946236, |
| "epoch": 2.387409200968523, |
| "grad_norm": 0.17107026278972626, |
| "learning_rate": 5.7168886823256355e-06, |
| "loss": 0.9558674693107605, |
| "mean_token_accuracy": 0.704446978867054, |
| "num_tokens": 23923602.0, |
| "step": 248 |
| }, |
| { |
| "entropy": 0.92726169526577, |
| "epoch": 2.3970944309927362, |
| "grad_norm": 0.16148178279399872, |
| "learning_rate": 5.549106142039018e-06, |
| "loss": 0.9140968322753906, |
| "mean_token_accuracy": 0.7169576361775398, |
| "num_tokens": 24021318.0, |
| "step": 249 |
| }, |
| { |
| "entropy": 0.9580587595701218, |
| "epoch": 2.406779661016949, |
| "grad_norm": 0.16659744083881378, |
| "learning_rate": 5.38351464934132e-06, |
| "loss": 0.9415776133537292, |
| "mean_token_accuracy": 0.7071748673915863, |
| "num_tokens": 24118718.0, |
| "step": 250 |
| }, |
| { |
| "entropy": 0.9650172963738441, |
| "epoch": 2.416464891041162, |
| "grad_norm": 0.1726813018321991, |
| "learning_rate": 5.220132857300286e-06, |
| "loss": 0.9537863731384277, |
| "mean_token_accuracy": 0.7061520591378212, |
| "num_tokens": 24215182.0, |
| "step": 251 |
| }, |
| { |
| "entropy": 0.9325862675905228, |
| "epoch": 2.4261501210653753, |
| "grad_norm": 0.17481137812137604, |
| "learning_rate": 5.058979170071754e-06, |
| "loss": 0.9204489588737488, |
| "mean_token_accuracy": 0.7168339118361473, |
| "num_tokens": 24312294.0, |
| "step": 252 |
| }, |
| { |
| "entropy": 0.9335382729768753, |
| "epoch": 2.4358353510895885, |
| "grad_norm": 0.16730333864688873, |
| "learning_rate": 4.900071740826489e-06, |
| "loss": 0.9185258150100708, |
| "mean_token_accuracy": 0.7174666225910187, |
| "num_tokens": 24410090.0, |
| "step": 253 |
| }, |
| { |
| "entropy": 0.948505662381649, |
| "epoch": 2.4455205811138017, |
| "grad_norm": 0.1664707213640213, |
| "learning_rate": 4.743428469705335e-06, |
| "loss": 0.9372999668121338, |
| "mean_token_accuracy": 0.7105081677436829, |
| "num_tokens": 24507254.0, |
| "step": 254 |
| }, |
| { |
| "entropy": 0.930232472717762, |
| "epoch": 2.4552058111380144, |
| "grad_norm": 0.17097648978233337, |
| "learning_rate": 4.58906700180286e-06, |
| "loss": 0.9181429743766785, |
| "mean_token_accuracy": 0.7164758443832397, |
| "num_tokens": 24604324.0, |
| "step": 255 |
| }, |
| { |
| "entropy": 0.9333597794175148, |
| "epoch": 2.4648910411622276, |
| "grad_norm": 0.1771240234375, |
| "learning_rate": 4.437004725179713e-06, |
| "loss": 0.9287640452384949, |
| "mean_token_accuracy": 0.7118443995714188, |
| "num_tokens": 24701080.0, |
| "step": 256 |
| }, |
| { |
| "entropy": 0.938852846622467, |
| "epoch": 2.4745762711864407, |
| "grad_norm": 0.1651614010334015, |
| "learning_rate": 4.2872587689039484e-06, |
| "loss": 0.9305993914604187, |
| "mean_token_accuracy": 0.7106853127479553, |
| "num_tokens": 24797772.0, |
| "step": 257 |
| }, |
| { |
| "entropy": 0.9542669057846069, |
| "epoch": 2.484261501210654, |
| "grad_norm": 0.1661830097436905, |
| "learning_rate": 4.139846001121514e-06, |
| "loss": 0.9489066004753113, |
| "mean_token_accuracy": 0.7092757672071457, |
| "num_tokens": 24894828.0, |
| "step": 258 |
| }, |
| { |
| "entropy": 0.9796763882040977, |
| "epoch": 2.4939467312348667, |
| "grad_norm": 0.17312757670879364, |
| "learning_rate": 3.9947830271561435e-06, |
| "loss": 0.9775505065917969, |
| "mean_token_accuracy": 0.6989206299185753, |
| "num_tokens": 24990844.0, |
| "step": 259 |
| }, |
| { |
| "entropy": 0.9374477416276932, |
| "epoch": 2.50363196125908, |
| "grad_norm": 0.16772004961967468, |
| "learning_rate": 3.852086187638846e-06, |
| "loss": 0.9270609617233276, |
| "mean_token_accuracy": 0.7119311392307281, |
| "num_tokens": 25087148.0, |
| "step": 260 |
| }, |
| { |
| "entropy": 0.9339680001139641, |
| "epoch": 2.513317191283293, |
| "grad_norm": 0.16526588797569275, |
| "learning_rate": 3.711771556667218e-06, |
| "loss": 0.9333970546722412, |
| "mean_token_accuracy": 0.7097160294651985, |
| "num_tokens": 25182598.0, |
| "step": 261 |
| }, |
| { |
| "entropy": 0.9129763543605804, |
| "epoch": 2.523002421307506, |
| "grad_norm": 0.1655433177947998, |
| "learning_rate": 3.57385493999477e-06, |
| "loss": 0.9104778170585632, |
| "mean_token_accuracy": 0.715905599296093, |
| "num_tokens": 25279832.0, |
| "step": 262 |
| }, |
| { |
| "entropy": 0.9448607638478279, |
| "epoch": 2.5326876513317194, |
| "grad_norm": 0.17114008963108063, |
| "learning_rate": 3.438351873250492e-06, |
| "loss": 0.9437493085861206, |
| "mean_token_accuracy": 0.7074448689818382, |
| "num_tokens": 25377665.0, |
| "step": 263 |
| }, |
| { |
| "entropy": 0.9569372236728668, |
| "epoch": 2.542372881355932, |
| "grad_norm": 0.17035846412181854, |
| "learning_rate": 3.305277620188826e-06, |
| "loss": 0.9598438739776611, |
| "mean_token_accuracy": 0.7023394778370857, |
| "num_tokens": 25474106.0, |
| "step": 264 |
| }, |
| { |
| "entropy": 0.9569888487458229, |
| "epoch": 2.5520581113801453, |
| "grad_norm": 0.17136558890342712, |
| "learning_rate": 3.1746471709702964e-06, |
| "loss": 0.94973224401474, |
| "mean_token_accuracy": 0.7059400156140327, |
| "num_tokens": 25569849.0, |
| "step": 265 |
| }, |
| { |
| "entropy": 0.9513968750834465, |
| "epoch": 2.5617433414043584, |
| "grad_norm": 0.1710221916437149, |
| "learning_rate": 3.0464752404729484e-06, |
| "loss": 0.9531828761100769, |
| "mean_token_accuracy": 0.7063041105866432, |
| "num_tokens": 25664248.0, |
| "step": 266 |
| }, |
| { |
| "entropy": 0.9446399211883545, |
| "epoch": 2.571428571428571, |
| "grad_norm": 0.1684202253818512, |
| "learning_rate": 2.920776266634767e-06, |
| "loss": 0.9451112151145935, |
| "mean_token_accuracy": 0.7093753665685654, |
| "num_tokens": 25759529.0, |
| "step": 267 |
| }, |
| { |
| "entropy": 0.9532052129507065, |
| "epoch": 2.5811138014527844, |
| "grad_norm": 0.1699952483177185, |
| "learning_rate": 2.797564408827319e-06, |
| "loss": 0.9383787512779236, |
| "mean_token_accuracy": 0.7081884369254112, |
| "num_tokens": 25855803.0, |
| "step": 268 |
| }, |
| { |
| "entropy": 0.960293136537075, |
| "epoch": 2.5907990314769975, |
| "grad_norm": 0.1699799746274948, |
| "learning_rate": 2.676853546260791e-06, |
| "loss": 0.9511731863021851, |
| "mean_token_accuracy": 0.704736977815628, |
| "num_tokens": 25953105.0, |
| "step": 269 |
| }, |
| { |
| "entropy": 0.9205162972211838, |
| "epoch": 2.6004842615012107, |
| "grad_norm": 0.16682550311088562, |
| "learning_rate": 2.558657276420526e-06, |
| "loss": 0.9143545627593994, |
| "mean_token_accuracy": 0.7158432006835938, |
| "num_tokens": 26050650.0, |
| "step": 270 |
| }, |
| { |
| "entropy": 0.9444830790162086, |
| "epoch": 2.610169491525424, |
| "grad_norm": 0.16638049483299255, |
| "learning_rate": 2.442988913535374e-06, |
| "loss": 0.938468337059021, |
| "mean_token_accuracy": 0.7088308557868004, |
| "num_tokens": 26148036.0, |
| "step": 271 |
| }, |
| { |
| "entropy": 0.9229314625263214, |
| "epoch": 2.619854721549637, |
| "grad_norm": 0.16461524367332458, |
| "learning_rate": 2.3298614870778835e-06, |
| "loss": 0.9185367822647095, |
| "mean_token_accuracy": 0.7175709903240204, |
| "num_tokens": 26245786.0, |
| "step": 272 |
| }, |
| { |
| "entropy": 0.9480500891804695, |
| "epoch": 2.62953995157385, |
| "grad_norm": 0.16297025978565216, |
| "learning_rate": 2.219287740296605e-06, |
| "loss": 0.9371967315673828, |
| "mean_token_accuracy": 0.7089260220527649, |
| "num_tokens": 26343335.0, |
| "step": 273 |
| }, |
| { |
| "entropy": 0.9384135827422142, |
| "epoch": 2.639225181598063, |
| "grad_norm": 0.16432765126228333, |
| "learning_rate": 2.1112801287806378e-06, |
| "loss": 0.9259079694747925, |
| "mean_token_accuracy": 0.7134666740894318, |
| "num_tokens": 26440936.0, |
| "step": 274 |
| }, |
| { |
| "entropy": 0.9579407349228859, |
| "epoch": 2.648910411622276, |
| "grad_norm": 0.1699051409959793, |
| "learning_rate": 2.0058508190565315e-06, |
| "loss": 0.9492658972740173, |
| "mean_token_accuracy": 0.7082375735044479, |
| "num_tokens": 26537470.0, |
| "step": 275 |
| }, |
| { |
| "entropy": 0.9152144119143486, |
| "epoch": 2.658595641646489, |
| "grad_norm": 0.16096487641334534, |
| "learning_rate": 1.9030116872178316e-06, |
| "loss": 0.899905800819397, |
| "mean_token_accuracy": 0.7211910039186478, |
| "num_tokens": 26634682.0, |
| "step": 276 |
| }, |
| { |
| "entropy": 0.93470898270607, |
| "epoch": 2.668280871670702, |
| "grad_norm": 0.1644560694694519, |
| "learning_rate": 1.8027743175872664e-06, |
| "loss": 0.9234951734542847, |
| "mean_token_accuracy": 0.7130272164940834, |
| "num_tokens": 26730832.0, |
| "step": 277 |
| }, |
| { |
| "entropy": 0.9358469098806381, |
| "epoch": 2.6779661016949152, |
| "grad_norm": 0.16249701380729675, |
| "learning_rate": 1.7051500014118454e-06, |
| "loss": 0.9318698644638062, |
| "mean_token_accuracy": 0.7116388902068138, |
| "num_tokens": 26827964.0, |
| "step": 278 |
| }, |
| { |
| "entropy": 0.9300618097186089, |
| "epoch": 2.6876513317191284, |
| "grad_norm": 0.16613486409187317, |
| "learning_rate": 1.610149735590949e-06, |
| "loss": 0.923961341381073, |
| "mean_token_accuracy": 0.714269369840622, |
| "num_tokens": 26925220.0, |
| "step": 279 |
| }, |
| { |
| "entropy": 0.9225321561098099, |
| "epoch": 2.6973365617433416, |
| "grad_norm": 0.1646852195262909, |
| "learning_rate": 1.517784221437568e-06, |
| "loss": 0.915350615978241, |
| "mean_token_accuracy": 0.7171403914690018, |
| "num_tokens": 27022314.0, |
| "step": 280 |
| }, |
| { |
| "entropy": 0.9450459405779839, |
| "epoch": 2.7070217917675548, |
| "grad_norm": 0.16406670212745667, |
| "learning_rate": 1.428063863472895e-06, |
| "loss": 0.9351706504821777, |
| "mean_token_accuracy": 0.7092677056789398, |
| "num_tokens": 27119653.0, |
| "step": 281 |
| }, |
| { |
| "entropy": 0.9531601071357727, |
| "epoch": 2.7167070217917675, |
| "grad_norm": 0.16610991954803467, |
| "learning_rate": 1.3409987682542619e-06, |
| "loss": 0.9477585554122925, |
| "mean_token_accuracy": 0.705516405403614, |
| "num_tokens": 27216443.0, |
| "step": 282 |
| }, |
| { |
| "entropy": 0.9612323269248009, |
| "epoch": 2.7263922518159807, |
| "grad_norm": 0.18620504438877106, |
| "learning_rate": 1.2565987432367033e-06, |
| "loss": 0.9591161012649536, |
| "mean_token_accuracy": 0.7057809606194496, |
| "num_tokens": 27314010.0, |
| "step": 283 |
| }, |
| { |
| "entropy": 0.9213037863373756, |
| "epoch": 2.736077481840194, |
| "grad_norm": 0.1644224375486374, |
| "learning_rate": 1.1748732956682025e-06, |
| "loss": 0.9110376834869385, |
| "mean_token_accuracy": 0.7162144333124161, |
| "num_tokens": 27411167.0, |
| "step": 284 |
| }, |
| { |
| "entropy": 0.9464965313673019, |
| "epoch": 2.7457627118644066, |
| "grad_norm": 0.1668902486562729, |
| "learning_rate": 1.095831631518729e-06, |
| "loss": 0.9322018027305603, |
| "mean_token_accuracy": 0.7100046798586845, |
| "num_tokens": 27508031.0, |
| "step": 285 |
| }, |
| { |
| "entropy": 0.9544007554650307, |
| "epoch": 2.7554479418886197, |
| "grad_norm": 0.18488800525665283, |
| "learning_rate": 1.0194826544432518e-06, |
| "loss": 0.9435421824455261, |
| "mean_token_accuracy": 0.7083205059170723, |
| "num_tokens": 27605285.0, |
| "step": 286 |
| }, |
| { |
| "entropy": 0.8945954814553261, |
| "epoch": 2.765133171912833, |
| "grad_norm": 0.16488690674304962, |
| "learning_rate": 9.458349647787662e-07, |
| "loss": 0.8838295340538025, |
| "mean_token_accuracy": 0.7242212444543839, |
| "num_tokens": 27702427.0, |
| "step": 287 |
| }, |
| { |
| "entropy": 0.9702121391892433, |
| "epoch": 2.774818401937046, |
| "grad_norm": 0.16656972467899323, |
| "learning_rate": 8.748968585755274e-07, |
| "loss": 0.9568536281585693, |
| "mean_token_accuracy": 0.7047922909259796, |
| "num_tokens": 27799147.0, |
| "step": 288 |
| }, |
| { |
| "entropy": 0.9478838741779327, |
| "epoch": 2.7845036319612593, |
| "grad_norm": 0.17403890192508698, |
| "learning_rate": 8.066763266625282e-07, |
| "loss": 0.9389169216156006, |
| "mean_token_accuracy": 0.7113012373447418, |
| "num_tokens": 27896050.0, |
| "step": 289 |
| }, |
| { |
| "entropy": 0.9535737633705139, |
| "epoch": 2.794188861985472, |
| "grad_norm": 0.166892409324646, |
| "learning_rate": 7.411810537473752e-07, |
| "loss": 0.9484093189239502, |
| "mean_token_accuracy": 0.7070039212703705, |
| "num_tokens": 27992970.0, |
| "step": 290 |
| }, |
| { |
| "entropy": 0.958631694316864, |
| "epoch": 2.803874092009685, |
| "grad_norm": 0.16444478929042816, |
| "learning_rate": 6.784184175506358e-07, |
| "loss": 0.9509057998657227, |
| "mean_token_accuracy": 0.7056354582309723, |
| "num_tokens": 28090059.0, |
| "step": 291 |
| }, |
| { |
| "entropy": 0.9479002580046654, |
| "epoch": 2.8135593220338984, |
| "grad_norm": 0.1822536736726761, |
| "learning_rate": 6.18395487974796e-07, |
| "loss": 0.9432950019836426, |
| "mean_token_accuracy": 0.7077231630682945, |
| "num_tokens": 28186811.0, |
| "step": 292 |
| }, |
| { |
| "entropy": 0.9351063743233681, |
| "epoch": 2.8232445520581115, |
| "grad_norm": 0.16567029058933258, |
| "learning_rate": 5.611190263078464e-07, |
| "loss": 0.9310054183006287, |
| "mean_token_accuracy": 0.7107162848114967, |
| "num_tokens": 28284018.0, |
| "step": 293 |
| }, |
| { |
| "entropy": 0.9591771215200424, |
| "epoch": 2.8329297820823243, |
| "grad_norm": 0.16885747015476227, |
| "learning_rate": 5.065954844616721e-07, |
| "loss": 0.9529502391815186, |
| "mean_token_accuracy": 0.7055745720863342, |
| "num_tokens": 28381345.0, |
| "step": 294 |
| }, |
| { |
| "entropy": 0.9498507678508759, |
| "epoch": 2.8426150121065374, |
| "grad_norm": 0.16632238030433655, |
| "learning_rate": 4.548310042452736e-07, |
| "loss": 0.9452009201049805, |
| "mean_token_accuracy": 0.7089792340993881, |
| "num_tokens": 28478621.0, |
| "step": 295 |
| }, |
| { |
| "entropy": 0.9331349283456802, |
| "epoch": 2.8523002421307506, |
| "grad_norm": 0.16203045845031738, |
| "learning_rate": 4.05831416672911e-07, |
| "loss": 0.9260942339897156, |
| "mean_token_accuracy": 0.7138590812683105, |
| "num_tokens": 28576142.0, |
| "step": 296 |
| }, |
| { |
| "entropy": 0.9537334218621254, |
| "epoch": 2.861985472154964, |
| "grad_norm": 0.16420294344425201, |
| "learning_rate": 3.5960224130728857e-07, |
| "loss": 0.9425039291381836, |
| "mean_token_accuracy": 0.7078607529401779, |
| "num_tokens": 28673385.0, |
| "step": 297 |
| }, |
| { |
| "entropy": 0.9406188875436783, |
| "epoch": 2.871670702179177, |
| "grad_norm": 0.17383691668510437, |
| "learning_rate": 3.1614868563778487e-07, |
| "loss": 0.9344635009765625, |
| "mean_token_accuracy": 0.7101663425564766, |
| "num_tokens": 28770610.0, |
| "step": 298 |
| }, |
| { |
| "entropy": 0.9869333431124687, |
| "epoch": 2.8813559322033897, |
| "grad_norm": 0.16637319326400757, |
| "learning_rate": 2.7547564449386664e-07, |
| "loss": 0.9826959371566772, |
| "mean_token_accuracy": 0.6976040154695511, |
| "num_tokens": 28868471.0, |
| "step": 299 |
| }, |
| { |
| "entropy": 0.9270701333880424, |
| "epoch": 2.891041162227603, |
| "grad_norm": 0.16629470884799957, |
| "learning_rate": 2.3758769949370762e-07, |
| "loss": 0.9205951690673828, |
| "mean_token_accuracy": 0.7137936651706696, |
| "num_tokens": 28966310.0, |
| "step": 300 |
| }, |
| { |
| "entropy": 0.9618567153811455, |
| "epoch": 2.900726392251816, |
| "grad_norm": 0.16480699181556702, |
| "learning_rate": 2.0248911852807916e-07, |
| "loss": 0.9476888179779053, |
| "mean_token_accuracy": 0.7057019248604774, |
| "num_tokens": 29061489.0, |
| "step": 301 |
| }, |
| { |
| "entropy": 0.9283742234110832, |
| "epoch": 2.910411622276029, |
| "grad_norm": 0.16359148919582367, |
| "learning_rate": 1.7018385527961533e-07, |
| "loss": 0.9214900732040405, |
| "mean_token_accuracy": 0.714975893497467, |
| "num_tokens": 29159147.0, |
| "step": 302 |
| }, |
| { |
| "entropy": 0.9527766108512878, |
| "epoch": 2.920096852300242, |
| "grad_norm": 0.20369553565979004, |
| "learning_rate": 1.406755487774386e-07, |
| "loss": 0.9437915682792664, |
| "mean_token_accuracy": 0.7090083435177803, |
| "num_tokens": 29255680.0, |
| "step": 303 |
| }, |
| { |
| "entropy": 0.9490475505590439, |
| "epoch": 2.929782082324455, |
| "grad_norm": 0.16631481051445007, |
| "learning_rate": 1.1396752298723501e-07, |
| "loss": 0.930048406124115, |
| "mean_token_accuracy": 0.7110621780157089, |
| "num_tokens": 29352014.0, |
| "step": 304 |
| }, |
| { |
| "entropy": 0.9295504689216614, |
| "epoch": 2.9394673123486683, |
| "grad_norm": 0.16186374425888062, |
| "learning_rate": 9.006278643683696e-08, |
| "loss": 0.9188652038574219, |
| "mean_token_accuracy": 0.7166802957653999, |
| "num_tokens": 29449604.0, |
| "step": 305 |
| }, |
| { |
| "entropy": 0.9896544814109802, |
| "epoch": 2.9491525423728815, |
| "grad_norm": 0.17655886709690094, |
| "learning_rate": 6.896403187732215e-08, |
| "loss": 0.9824331998825073, |
| "mean_token_accuracy": 0.6990053206682205, |
| "num_tokens": 29546482.0, |
| "step": 306 |
| }, |
| { |
| "entropy": 0.9492818415164948, |
| "epoch": 2.9588377723970947, |
| "grad_norm": 0.16435672342777252, |
| "learning_rate": 5.0673635979686665e-08, |
| "loss": 0.9428920745849609, |
| "mean_token_accuracy": 0.7084559351205826, |
| "num_tokens": 29644144.0, |
| "step": 307 |
| }, |
| { |
| "entropy": 0.9456490948796272, |
| "epoch": 2.9685230024213074, |
| "grad_norm": 0.16370128095149994, |
| "learning_rate": 3.5193659067131455e-08, |
| "loss": 0.9404333829879761, |
| "mean_token_accuracy": 0.7083645612001419, |
| "num_tokens": 29741422.0, |
| "step": 308 |
| }, |
| { |
| "entropy": 0.9275098890066147, |
| "epoch": 2.9782082324455206, |
| "grad_norm": 0.16650019586086273, |
| "learning_rate": 2.2525844882964607e-08, |
| "loss": 0.9310476183891296, |
| "mean_token_accuracy": 0.7136205583810806, |
| "num_tokens": 29836098.0, |
| "step": 309 |
| }, |
| { |
| "entropy": 0.9617797136306763, |
| "epoch": 2.9878934624697338, |
| "grad_norm": 0.16825121641159058, |
| "learning_rate": 1.267162039418901e-08, |
| "loss": 0.9549292325973511, |
| "mean_token_accuracy": 0.704559862613678, |
| "num_tokens": 29933445.0, |
| "step": 310 |
| }, |
| { |
| "entropy": 0.9481191709637642, |
| "epoch": 2.9975786924939465, |
| "grad_norm": 0.16763824224472046, |
| "learning_rate": 5.632095630764278e-09, |
| "loss": 0.9431383013725281, |
| "mean_token_accuracy": 0.7091331407427788, |
| "num_tokens": 30030604.0, |
| "step": 311 |
| }, |
| { |
| "entropy": 0.9415148198604584, |
| "epoch": 3.0, |
| "grad_norm": 0.3272308111190796, |
| "learning_rate": 1.4080635605512316e-09, |
| "loss": 0.9364659786224365, |
| "mean_token_accuracy": 0.7106925845146179, |
| "num_tokens": 30055032.0, |
| "step": 312 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 312, |
| "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": 4.227645643482464e+18, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
