|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 2.9850746268656714, |
|
"eval_steps": 500, |
|
"global_step": 800, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.018656716417910446, |
|
"grad_norm": 2.403158187866211, |
|
"learning_rate": 4.9998282347929784e-05, |
|
"loss": 3.3875, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.03731343283582089, |
|
"grad_norm": 2.301710367202759, |
|
"learning_rate": 4.99931296277454e-05, |
|
"loss": 2.9015, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.055970149253731345, |
|
"grad_norm": 1.271048665046692, |
|
"learning_rate": 4.998454254749331e-05, |
|
"loss": 2.6229, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.07462686567164178, |
|
"grad_norm": 1.069893717765808, |
|
"learning_rate": 4.997252228714279e-05, |
|
"loss": 2.3704, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.09328358208955224, |
|
"grad_norm": 0.9044906497001648, |
|
"learning_rate": 4.9957070498423854e-05, |
|
"loss": 2.3782, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.11194029850746269, |
|
"grad_norm": 0.9635376334190369, |
|
"learning_rate": 4.993818930460026e-05, |
|
"loss": 2.3576, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.13059701492537312, |
|
"grad_norm": 0.8513979315757751, |
|
"learning_rate": 4.9915881300177725e-05, |
|
"loss": 2.4603, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.14925373134328357, |
|
"grad_norm": 0.845267117023468, |
|
"learning_rate": 4.9890149550547454e-05, |
|
"loss": 2.2033, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.16791044776119404, |
|
"grad_norm": 0.6632418036460876, |
|
"learning_rate": 4.98609975915649e-05, |
|
"loss": 2.1851, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.1865671641791045, |
|
"grad_norm": 0.6857479810714722, |
|
"learning_rate": 4.982842942906386e-05, |
|
"loss": 2.3592, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.20522388059701493, |
|
"grad_norm": 0.7204287648200989, |
|
"learning_rate": 4.979244953830608e-05, |
|
"loss": 2.1323, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.22388059701492538, |
|
"grad_norm": 0.6864420175552368, |
|
"learning_rate": 4.9753062863366276e-05, |
|
"loss": 2.2138, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.24253731343283583, |
|
"grad_norm": 0.7536088228225708, |
|
"learning_rate": 4.971027481645274e-05, |
|
"loss": 2.2584, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.26119402985074625, |
|
"grad_norm": 0.9708526134490967, |
|
"learning_rate": 4.966409127716367e-05, |
|
"loss": 2.2669, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.2798507462686567, |
|
"grad_norm": 0.7516190409660339, |
|
"learning_rate": 4.96145185916792e-05, |
|
"loss": 2.2133, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.29850746268656714, |
|
"grad_norm": 0.7864778637886047, |
|
"learning_rate": 4.95615635718894e-05, |
|
"loss": 2.1683, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.31716417910447764, |
|
"grad_norm": 0.7846741080284119, |
|
"learning_rate": 4.950523349445824e-05, |
|
"loss": 2.1274, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 0.3358208955223881, |
|
"grad_norm": 0.816838800907135, |
|
"learning_rate": 4.944553609982363e-05, |
|
"loss": 2.2033, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.35447761194029853, |
|
"grad_norm": 0.7661916017532349, |
|
"learning_rate": 4.938247959113386e-05, |
|
"loss": 2.1492, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 0.373134328358209, |
|
"grad_norm": 0.8964986205101013, |
|
"learning_rate": 4.931607263312032e-05, |
|
"loss": 2.0862, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.3917910447761194, |
|
"grad_norm": 0.8603547215461731, |
|
"learning_rate": 4.924632435090696e-05, |
|
"loss": 2.1444, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 0.41044776119402987, |
|
"grad_norm": 0.8611045479774475, |
|
"learning_rate": 4.917324432875627e-05, |
|
"loss": 2.1202, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.4291044776119403, |
|
"grad_norm": 0.9499636888504028, |
|
"learning_rate": 4.909684260875235e-05, |
|
"loss": 2.1285, |
|
"step": 115 |
|
}, |
|
{ |
|
"epoch": 0.44776119402985076, |
|
"grad_norm": 0.8490393161773682, |
|
"learning_rate": 4.9017129689421e-05, |
|
"loss": 2.236, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.4664179104477612, |
|
"grad_norm": 0.9628555178642273, |
|
"learning_rate": 4.893411652428712e-05, |
|
"loss": 2.1219, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 0.48507462686567165, |
|
"grad_norm": 1.1119599342346191, |
|
"learning_rate": 4.8847814520369475e-05, |
|
"loss": 2.2537, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.503731343283582, |
|
"grad_norm": 0.9489665627479553, |
|
"learning_rate": 4.875823553661334e-05, |
|
"loss": 2.1018, |
|
"step": 135 |
|
}, |
|
{ |
|
"epoch": 0.5223880597014925, |
|
"grad_norm": 0.9434083700180054, |
|
"learning_rate": 4.8665391882260856e-05, |
|
"loss": 2.0809, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.5410447761194029, |
|
"grad_norm": 0.8856557607650757, |
|
"learning_rate": 4.856929631515964e-05, |
|
"loss": 2.0807, |
|
"step": 145 |
|
}, |
|
{ |
|
"epoch": 0.5597014925373134, |
|
"grad_norm": 0.8770031929016113, |
|
"learning_rate": 4.846996204000967e-05, |
|
"loss": 2.0843, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.5783582089552238, |
|
"grad_norm": 0.8374930620193481, |
|
"learning_rate": 4.8367402706548805e-05, |
|
"loss": 2.1869, |
|
"step": 155 |
|
}, |
|
{ |
|
"epoch": 0.5970149253731343, |
|
"grad_norm": 1.0829132795333862, |
|
"learning_rate": 4.8261632407677174e-05, |
|
"loss": 2.028, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.6156716417910447, |
|
"grad_norm": 0.9735206365585327, |
|
"learning_rate": 4.815266567752059e-05, |
|
"loss": 2.0966, |
|
"step": 165 |
|
}, |
|
{ |
|
"epoch": 0.6343283582089553, |
|
"grad_norm": 1.087944746017456, |
|
"learning_rate": 4.804051748943343e-05, |
|
"loss": 2.0863, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.6529850746268657, |
|
"grad_norm": 0.8176729083061218, |
|
"learning_rate": 4.792520325394111e-05, |
|
"loss": 2.1135, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 0.6716417910447762, |
|
"grad_norm": 0.9173070788383484, |
|
"learning_rate": 4.780673881662242e-05, |
|
"loss": 2.0564, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.6902985074626866, |
|
"grad_norm": 0.9463202953338623, |
|
"learning_rate": 4.7685140455932267e-05, |
|
"loss": 2.1579, |
|
"step": 185 |
|
}, |
|
{ |
|
"epoch": 0.7089552238805971, |
|
"grad_norm": 1.149950385093689, |
|
"learning_rate": 4.756042488096471e-05, |
|
"loss": 2.1447, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.7276119402985075, |
|
"grad_norm": 0.940965473651886, |
|
"learning_rate": 4.743260922915701e-05, |
|
"loss": 2.0823, |
|
"step": 195 |
|
}, |
|
{ |
|
"epoch": 0.746268656716418, |
|
"grad_norm": 0.9384671449661255, |
|
"learning_rate": 4.730171106393466e-05, |
|
"loss": 2.1445, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.7649253731343284, |
|
"grad_norm": 0.8937250971794128, |
|
"learning_rate": 4.716774837229804e-05, |
|
"loss": 2.014, |
|
"step": 205 |
|
}, |
|
{ |
|
"epoch": 0.7835820895522388, |
|
"grad_norm": 0.8928058743476868, |
|
"learning_rate": 4.7030739562350713e-05, |
|
"loss": 2.1882, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 0.8022388059701493, |
|
"grad_norm": 1.0239906311035156, |
|
"learning_rate": 4.6890703460769955e-05, |
|
"loss": 2.1042, |
|
"step": 215 |
|
}, |
|
{ |
|
"epoch": 0.8208955223880597, |
|
"grad_norm": 1.0555064678192139, |
|
"learning_rate": 4.674765931021976e-05, |
|
"loss": 2.015, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 0.8395522388059702, |
|
"grad_norm": 1.084709882736206, |
|
"learning_rate": 4.6601626766706626e-05, |
|
"loss": 2.0603, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 0.8582089552238806, |
|
"grad_norm": 0.9265861511230469, |
|
"learning_rate": 4.645262589687861e-05, |
|
"loss": 2.1006, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 0.8768656716417911, |
|
"grad_norm": 1.0058296918869019, |
|
"learning_rate": 4.6300677175267914e-05, |
|
"loss": 2.063, |
|
"step": 235 |
|
}, |
|
{ |
|
"epoch": 0.8955223880597015, |
|
"grad_norm": 1.0766576528549194, |
|
"learning_rate": 4.614580148147744e-05, |
|
"loss": 2.0781, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 0.914179104477612, |
|
"grad_norm": 1.0215730667114258, |
|
"learning_rate": 4.598802009731167e-05, |
|
"loss": 2.1774, |
|
"step": 245 |
|
}, |
|
{ |
|
"epoch": 0.9328358208955224, |
|
"grad_norm": 0.9870419502258301, |
|
"learning_rate": 4.582735470385229e-05, |
|
"loss": 1.9636, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.9514925373134329, |
|
"grad_norm": 1.1921675205230713, |
|
"learning_rate": 4.5663827378478975e-05, |
|
"loss": 2.0141, |
|
"step": 255 |
|
}, |
|
{ |
|
"epoch": 0.9701492537313433, |
|
"grad_norm": 1.0618964433670044, |
|
"learning_rate": 4.5497460591835615e-05, |
|
"loss": 2.0508, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 0.9888059701492538, |
|
"grad_norm": 0.9723111391067505, |
|
"learning_rate": 4.532827720474268e-05, |
|
"loss": 2.0312, |
|
"step": 265 |
|
}, |
|
{ |
|
"epoch": 1.007462686567164, |
|
"grad_norm": 0.9339023232460022, |
|
"learning_rate": 4.515630046505575e-05, |
|
"loss": 2.1107, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 1.0261194029850746, |
|
"grad_norm": 1.0588074922561646, |
|
"learning_rate": 4.498155400447107e-05, |
|
"loss": 2.0963, |
|
"step": 275 |
|
}, |
|
{ |
|
"epoch": 1.044776119402985, |
|
"grad_norm": 1.0709750652313232, |
|
"learning_rate": 4.480406183527823e-05, |
|
"loss": 2.0359, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 1.0634328358208955, |
|
"grad_norm": 1.2172249555587769, |
|
"learning_rate": 4.462384834706058e-05, |
|
"loss": 2.1083, |
|
"step": 285 |
|
}, |
|
{ |
|
"epoch": 1.0820895522388059, |
|
"grad_norm": 1.1719626188278198, |
|
"learning_rate": 4.4440938303343804e-05, |
|
"loss": 2.1259, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 1.1007462686567164, |
|
"grad_norm": 1.051269292831421, |
|
"learning_rate": 4.425535683819312e-05, |
|
"loss": 2.0901, |
|
"step": 295 |
|
}, |
|
{ |
|
"epoch": 1.1194029850746268, |
|
"grad_norm": 1.3167760372161865, |
|
"learning_rate": 4.406712945275955e-05, |
|
"loss": 2.0032, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 1.1380597014925373, |
|
"grad_norm": 1.2565367221832275, |
|
"learning_rate": 4.387628201177577e-05, |
|
"loss": 2.0148, |
|
"step": 305 |
|
}, |
|
{ |
|
"epoch": 1.1567164179104479, |
|
"grad_norm": 1.1141688823699951, |
|
"learning_rate": 4.368284074000193e-05, |
|
"loss": 2.0217, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 1.1753731343283582, |
|
"grad_norm": 1.1642612218856812, |
|
"learning_rate": 4.348683221862212e-05, |
|
"loss": 2.0194, |
|
"step": 315 |
|
}, |
|
{ |
|
"epoch": 1.1940298507462686, |
|
"grad_norm": 1.1613104343414307, |
|
"learning_rate": 4.328828338159173e-05, |
|
"loss": 1.9371, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 1.212686567164179, |
|
"grad_norm": 1.2319557666778564, |
|
"learning_rate": 4.3087221511936434e-05, |
|
"loss": 2.0227, |
|
"step": 325 |
|
}, |
|
{ |
|
"epoch": 1.2313432835820897, |
|
"grad_norm": 1.2520420551300049, |
|
"learning_rate": 4.288367423800319e-05, |
|
"loss": 1.9883, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"grad_norm": 1.0452089309692383, |
|
"learning_rate": 4.267766952966369e-05, |
|
"loss": 1.9912, |
|
"step": 335 |
|
}, |
|
{ |
|
"epoch": 1.2686567164179103, |
|
"grad_norm": 0.9965611100196838, |
|
"learning_rate": 4.2469235694471043e-05, |
|
"loss": 1.983, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 1.287313432835821, |
|
"grad_norm": 1.0808607339859009, |
|
"learning_rate": 4.225840137376993e-05, |
|
"loss": 1.9514, |
|
"step": 345 |
|
}, |
|
{ |
|
"epoch": 1.3059701492537314, |
|
"grad_norm": 1.102575659751892, |
|
"learning_rate": 4.204519553876095e-05, |
|
"loss": 2.0286, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 1.3246268656716418, |
|
"grad_norm": 1.0246608257293701, |
|
"learning_rate": 4.1829647486519596e-05, |
|
"loss": 2.0265, |
|
"step": 355 |
|
}, |
|
{ |
|
"epoch": 1.3432835820895521, |
|
"grad_norm": 1.0723367929458618, |
|
"learning_rate": 4.161178683597054e-05, |
|
"loss": 2.0077, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 1.3619402985074627, |
|
"grad_norm": 1.4298617839813232, |
|
"learning_rate": 4.139164352381758e-05, |
|
"loss": 2.0898, |
|
"step": 365 |
|
}, |
|
{ |
|
"epoch": 1.3805970149253732, |
|
"grad_norm": 1.1437115669250488, |
|
"learning_rate": 4.116924780042997e-05, |
|
"loss": 2.024, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 1.3992537313432836, |
|
"grad_norm": 1.326556921005249, |
|
"learning_rate": 4.094463022568569e-05, |
|
"loss": 2.2252, |
|
"step": 375 |
|
}, |
|
{ |
|
"epoch": 1.417910447761194, |
|
"grad_norm": 1.2549344301223755, |
|
"learning_rate": 4.071782166477213e-05, |
|
"loss": 1.9777, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 1.4365671641791045, |
|
"grad_norm": 1.1226497888565063, |
|
"learning_rate": 4.0488853283944806e-05, |
|
"loss": 2.0062, |
|
"step": 385 |
|
}, |
|
{ |
|
"epoch": 1.455223880597015, |
|
"grad_norm": 1.2250981330871582, |
|
"learning_rate": 4.0257756546244804e-05, |
|
"loss": 1.9147, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 1.4738805970149254, |
|
"grad_norm": 1.3552589416503906, |
|
"learning_rate": 4.0024563207175316e-05, |
|
"loss": 1.9709, |
|
"step": 395 |
|
}, |
|
{ |
|
"epoch": 1.4925373134328357, |
|
"grad_norm": 1.3661599159240723, |
|
"learning_rate": 3.978930531033807e-05, |
|
"loss": 1.9748, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 1.5111940298507462, |
|
"grad_norm": 1.1794605255126953, |
|
"learning_rate": 3.9552015183030136e-05, |
|
"loss": 2.0367, |
|
"step": 405 |
|
}, |
|
{ |
|
"epoch": 1.5298507462686568, |
|
"grad_norm": 1.19724440574646, |
|
"learning_rate": 3.93127254318018e-05, |
|
"loss": 1.9545, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 1.5485074626865671, |
|
"grad_norm": 1.310658574104309, |
|
"learning_rate": 3.907146893797599e-05, |
|
"loss": 1.9933, |
|
"step": 415 |
|
}, |
|
{ |
|
"epoch": 1.5671641791044775, |
|
"grad_norm": 1.2032736539840698, |
|
"learning_rate": 3.882827885312999e-05, |
|
"loss": 2.0442, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 1.585820895522388, |
|
"grad_norm": 1.2670124769210815, |
|
"learning_rate": 3.858318859454001e-05, |
|
"loss": 1.974, |
|
"step": 425 |
|
}, |
|
{ |
|
"epoch": 1.6044776119402986, |
|
"grad_norm": 1.5301685333251953, |
|
"learning_rate": 3.833623184058926e-05, |
|
"loss": 2.0865, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 1.623134328358209, |
|
"grad_norm": 1.3863707780838013, |
|
"learning_rate": 3.808744252614012e-05, |
|
"loss": 1.9614, |
|
"step": 435 |
|
}, |
|
{ |
|
"epoch": 1.6417910447761193, |
|
"grad_norm": 1.2591431140899658, |
|
"learning_rate": 3.783685483787105e-05, |
|
"loss": 1.949, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 1.6604477611940298, |
|
"grad_norm": 1.2093037366867065, |
|
"learning_rate": 3.758450320957899e-05, |
|
"loss": 1.9618, |
|
"step": 445 |
|
}, |
|
{ |
|
"epoch": 1.6791044776119404, |
|
"grad_norm": 1.1593824625015259, |
|
"learning_rate": 3.7330422317447685e-05, |
|
"loss": 2.0124, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 1.6977611940298507, |
|
"grad_norm": 1.7013437747955322, |
|
"learning_rate": 3.707464707528275e-05, |
|
"loss": 2.0613, |
|
"step": 455 |
|
}, |
|
{ |
|
"epoch": 1.716417910447761, |
|
"grad_norm": 1.2550350427627563, |
|
"learning_rate": 3.681721262971413e-05, |
|
"loss": 2.1354, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 1.7350746268656716, |
|
"grad_norm": 1.1735903024673462, |
|
"learning_rate": 3.6558154355366506e-05, |
|
"loss": 1.9618, |
|
"step": 465 |
|
}, |
|
{ |
|
"epoch": 1.7537313432835822, |
|
"grad_norm": 1.331148624420166, |
|
"learning_rate": 3.6297507849998344e-05, |
|
"loss": 1.9245, |
|
"step": 470 |
|
}, |
|
{ |
|
"epoch": 1.7723880597014925, |
|
"grad_norm": 1.3502494096755981, |
|
"learning_rate": 3.6035308929610446e-05, |
|
"loss": 1.9758, |
|
"step": 475 |
|
}, |
|
{ |
|
"epoch": 1.7910447761194028, |
|
"grad_norm": 1.2406198978424072, |
|
"learning_rate": 3.5771593623524265e-05, |
|
"loss": 1.9824, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 1.8097014925373134, |
|
"grad_norm": 1.224885106086731, |
|
"learning_rate": 3.550639816943111e-05, |
|
"loss": 2.069, |
|
"step": 485 |
|
}, |
|
{ |
|
"epoch": 1.828358208955224, |
|
"grad_norm": 1.4666011333465576, |
|
"learning_rate": 3.5239759008412666e-05, |
|
"loss": 2.0797, |
|
"step": 490 |
|
}, |
|
{ |
|
"epoch": 1.8470149253731343, |
|
"grad_norm": 1.2758076190948486, |
|
"learning_rate": 3.497171277993346e-05, |
|
"loss": 2.0195, |
|
"step": 495 |
|
}, |
|
{ |
|
"epoch": 1.8656716417910446, |
|
"grad_norm": 1.1991291046142578, |
|
"learning_rate": 3.4702296316806244e-05, |
|
"loss": 1.9558, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 1.8843283582089554, |
|
"grad_norm": 1.2548415660858154, |
|
"learning_rate": 3.443154664013067e-05, |
|
"loss": 1.9805, |
|
"step": 505 |
|
}, |
|
{ |
|
"epoch": 1.9029850746268657, |
|
"grad_norm": 1.5407222509384155, |
|
"learning_rate": 3.415950095420616e-05, |
|
"loss": 1.9152, |
|
"step": 510 |
|
}, |
|
{ |
|
"epoch": 1.921641791044776, |
|
"grad_norm": 1.285704493522644, |
|
"learning_rate": 3.3886196641419545e-05, |
|
"loss": 2.0442, |
|
"step": 515 |
|
}, |
|
{ |
|
"epoch": 1.9402985074626866, |
|
"grad_norm": 1.377465844154358, |
|
"learning_rate": 3.361167125710832e-05, |
|
"loss": 2.0537, |
|
"step": 520 |
|
}, |
|
{ |
|
"epoch": 1.9589552238805972, |
|
"grad_norm": 1.186889410018921, |
|
"learning_rate": 3.333596252440008e-05, |
|
"loss": 1.9798, |
|
"step": 525 |
|
}, |
|
{ |
|
"epoch": 1.9776119402985075, |
|
"grad_norm": 1.4855142831802368, |
|
"learning_rate": 3.305910832902884e-05, |
|
"loss": 2.0984, |
|
"step": 530 |
|
}, |
|
{ |
|
"epoch": 1.9962686567164178, |
|
"grad_norm": 1.47159743309021, |
|
"learning_rate": 3.278114671412917e-05, |
|
"loss": 1.9932, |
|
"step": 535 |
|
}, |
|
{ |
|
"epoch": 2.014925373134328, |
|
"grad_norm": 1.4078409671783447, |
|
"learning_rate": 3.2502115875008524e-05, |
|
"loss": 1.9457, |
|
"step": 540 |
|
}, |
|
{ |
|
"epoch": 2.033582089552239, |
|
"grad_norm": 1.1386340856552124, |
|
"learning_rate": 3.222205415389877e-05, |
|
"loss": 1.9334, |
|
"step": 545 |
|
}, |
|
{ |
|
"epoch": 2.0522388059701493, |
|
"grad_norm": 1.666084885597229, |
|
"learning_rate": 3.1941000034687515e-05, |
|
"loss": 1.9716, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 2.0708955223880596, |
|
"grad_norm": 1.3137987852096558, |
|
"learning_rate": 3.165899213762995e-05, |
|
"loss": 1.9189, |
|
"step": 555 |
|
}, |
|
{ |
|
"epoch": 2.08955223880597, |
|
"grad_norm": 1.2372797727584839, |
|
"learning_rate": 3.1376069214041913e-05, |
|
"loss": 2.0234, |
|
"step": 560 |
|
}, |
|
{ |
|
"epoch": 2.1082089552238807, |
|
"grad_norm": 1.3149720430374146, |
|
"learning_rate": 3.109227014097505e-05, |
|
"loss": 2.0271, |
|
"step": 565 |
|
}, |
|
{ |
|
"epoch": 2.126865671641791, |
|
"grad_norm": 1.4162675142288208, |
|
"learning_rate": 3.0807633915874584e-05, |
|
"loss": 1.8236, |
|
"step": 570 |
|
}, |
|
{ |
|
"epoch": 2.1455223880597014, |
|
"grad_norm": 1.4029136896133423, |
|
"learning_rate": 3.052219965122062e-05, |
|
"loss": 2.1821, |
|
"step": 575 |
|
}, |
|
{ |
|
"epoch": 2.1641791044776117, |
|
"grad_norm": 1.5424753427505493, |
|
"learning_rate": 3.0236006569153617e-05, |
|
"loss": 1.9496, |
|
"step": 580 |
|
}, |
|
{ |
|
"epoch": 2.1828358208955225, |
|
"grad_norm": 1.274217963218689, |
|
"learning_rate": 2.9949093996084747e-05, |
|
"loss": 2.0439, |
|
"step": 585 |
|
}, |
|
{ |
|
"epoch": 2.201492537313433, |
|
"grad_norm": 1.2068248987197876, |
|
"learning_rate": 2.9661501357292033e-05, |
|
"loss": 2.0805, |
|
"step": 590 |
|
}, |
|
{ |
|
"epoch": 2.220149253731343, |
|
"grad_norm": 1.2352491617202759, |
|
"learning_rate": 2.9373268171502777e-05, |
|
"loss": 1.975, |
|
"step": 595 |
|
}, |
|
{ |
|
"epoch": 2.2388059701492535, |
|
"grad_norm": 1.3039956092834473, |
|
"learning_rate": 2.9084434045463255e-05, |
|
"loss": 1.9834, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 2.2574626865671643, |
|
"grad_norm": 1.3400136232376099, |
|
"learning_rate": 2.8795038668496222e-05, |
|
"loss": 1.84, |
|
"step": 605 |
|
}, |
|
{ |
|
"epoch": 2.2761194029850746, |
|
"grad_norm": 1.458132028579712, |
|
"learning_rate": 2.850512180704715e-05, |
|
"loss": 1.9518, |
|
"step": 610 |
|
}, |
|
{ |
|
"epoch": 2.294776119402985, |
|
"grad_norm": 1.446595311164856, |
|
"learning_rate": 2.821472329921981e-05, |
|
"loss": 1.8977, |
|
"step": 615 |
|
}, |
|
{ |
|
"epoch": 2.3134328358208958, |
|
"grad_norm": 1.432244062423706, |
|
"learning_rate": 2.792388304930207e-05, |
|
"loss": 1.9742, |
|
"step": 620 |
|
}, |
|
{ |
|
"epoch": 2.332089552238806, |
|
"grad_norm": 1.499017596244812, |
|
"learning_rate": 2.7632641022282502e-05, |
|
"loss": 1.9379, |
|
"step": 625 |
|
}, |
|
{ |
|
"epoch": 2.3507462686567164, |
|
"grad_norm": 1.6504281759262085, |
|
"learning_rate": 2.7341037238358774e-05, |
|
"loss": 1.9175, |
|
"step": 630 |
|
}, |
|
{ |
|
"epoch": 2.3694029850746268, |
|
"grad_norm": 1.6585911512374878, |
|
"learning_rate": 2.704911176743833e-05, |
|
"loss": 2.0449, |
|
"step": 635 |
|
}, |
|
{ |
|
"epoch": 2.388059701492537, |
|
"grad_norm": 1.545623779296875, |
|
"learning_rate": 2.6756904723632324e-05, |
|
"loss": 2.0096, |
|
"step": 640 |
|
}, |
|
{ |
|
"epoch": 2.406716417910448, |
|
"grad_norm": 1.468853235244751, |
|
"learning_rate": 2.646445625974347e-05, |
|
"loss": 1.878, |
|
"step": 645 |
|
}, |
|
{ |
|
"epoch": 2.425373134328358, |
|
"grad_norm": 1.3598605394363403, |
|
"learning_rate": 2.6171806561748502e-05, |
|
"loss": 1.9625, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 2.4440298507462686, |
|
"grad_norm": 1.3197077512741089, |
|
"learning_rate": 2.5878995843276204e-05, |
|
"loss": 1.9375, |
|
"step": 655 |
|
}, |
|
{ |
|
"epoch": 2.4626865671641793, |
|
"grad_norm": 1.5469880104064941, |
|
"learning_rate": 2.5586064340081516e-05, |
|
"loss": 1.8402, |
|
"step": 660 |
|
}, |
|
{ |
|
"epoch": 2.4813432835820897, |
|
"grad_norm": 1.4435440301895142, |
|
"learning_rate": 2.529305230451666e-05, |
|
"loss": 1.8795, |
|
"step": 665 |
|
}, |
|
{ |
|
"epoch": 2.5, |
|
"grad_norm": 1.505194067955017, |
|
"learning_rate": 2.5e-05, |
|
"loss": 1.9938, |
|
"step": 670 |
|
}, |
|
{ |
|
"epoch": 2.5186567164179103, |
|
"grad_norm": 1.3251738548278809, |
|
"learning_rate": 2.4706947695483348e-05, |
|
"loss": 1.956, |
|
"step": 675 |
|
}, |
|
{ |
|
"epoch": 2.5373134328358207, |
|
"grad_norm": 1.4197183847427368, |
|
"learning_rate": 2.441393565991849e-05, |
|
"loss": 1.906, |
|
"step": 680 |
|
}, |
|
{ |
|
"epoch": 2.5559701492537314, |
|
"grad_norm": 1.4905989170074463, |
|
"learning_rate": 2.4121004156723802e-05, |
|
"loss": 1.9073, |
|
"step": 685 |
|
}, |
|
{ |
|
"epoch": 2.574626865671642, |
|
"grad_norm": 1.3891818523406982, |
|
"learning_rate": 2.3828193438251497e-05, |
|
"loss": 2.1399, |
|
"step": 690 |
|
}, |
|
{ |
|
"epoch": 2.593283582089552, |
|
"grad_norm": 1.6372982263565063, |
|
"learning_rate": 2.3535543740256536e-05, |
|
"loss": 1.873, |
|
"step": 695 |
|
}, |
|
{ |
|
"epoch": 2.611940298507463, |
|
"grad_norm": 1.5683703422546387, |
|
"learning_rate": 2.3243095276367685e-05, |
|
"loss": 1.8899, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 2.6305970149253732, |
|
"grad_norm": 1.585425615310669, |
|
"learning_rate": 2.2950888232561672e-05, |
|
"loss": 2.0511, |
|
"step": 705 |
|
}, |
|
{ |
|
"epoch": 2.6492537313432836, |
|
"grad_norm": 1.3682692050933838, |
|
"learning_rate": 2.2658962761641232e-05, |
|
"loss": 2.0364, |
|
"step": 710 |
|
}, |
|
{ |
|
"epoch": 2.667910447761194, |
|
"grad_norm": 1.7755306959152222, |
|
"learning_rate": 2.23673589777175e-05, |
|
"loss": 2.0033, |
|
"step": 715 |
|
}, |
|
{ |
|
"epoch": 2.6865671641791042, |
|
"grad_norm": 1.4118067026138306, |
|
"learning_rate": 2.207611695069794e-05, |
|
"loss": 2.102, |
|
"step": 720 |
|
}, |
|
{ |
|
"epoch": 2.705223880597015, |
|
"grad_norm": 1.5786772966384888, |
|
"learning_rate": 2.17852767007802e-05, |
|
"loss": 1.9894, |
|
"step": 725 |
|
}, |
|
{ |
|
"epoch": 2.7238805970149254, |
|
"grad_norm": 1.4233230352401733, |
|
"learning_rate": 2.1494878192952855e-05, |
|
"loss": 1.9355, |
|
"step": 730 |
|
}, |
|
{ |
|
"epoch": 2.7425373134328357, |
|
"grad_norm": 1.5830904245376587, |
|
"learning_rate": 2.1204961331503787e-05, |
|
"loss": 1.9399, |
|
"step": 735 |
|
}, |
|
{ |
|
"epoch": 2.7611940298507465, |
|
"grad_norm": 1.2974706888198853, |
|
"learning_rate": 2.0915565954536744e-05, |
|
"loss": 1.9814, |
|
"step": 740 |
|
}, |
|
{ |
|
"epoch": 2.779850746268657, |
|
"grad_norm": 1.2366008758544922, |
|
"learning_rate": 2.0626731828497225e-05, |
|
"loss": 1.9275, |
|
"step": 745 |
|
}, |
|
{ |
|
"epoch": 2.798507462686567, |
|
"grad_norm": 1.5165388584136963, |
|
"learning_rate": 2.0338498642707977e-05, |
|
"loss": 1.9444, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 2.8171641791044775, |
|
"grad_norm": 1.429136037826538, |
|
"learning_rate": 2.005090600391526e-05, |
|
"loss": 1.9831, |
|
"step": 755 |
|
}, |
|
{ |
|
"epoch": 2.835820895522388, |
|
"grad_norm": 1.4274283647537231, |
|
"learning_rate": 1.9763993430846395e-05, |
|
"loss": 2.0005, |
|
"step": 760 |
|
}, |
|
{ |
|
"epoch": 2.8544776119402986, |
|
"grad_norm": 1.502812147140503, |
|
"learning_rate": 1.947780034877938e-05, |
|
"loss": 2.0224, |
|
"step": 765 |
|
}, |
|
{ |
|
"epoch": 2.873134328358209, |
|
"grad_norm": 1.556489109992981, |
|
"learning_rate": 1.9192366084125425e-05, |
|
"loss": 1.9519, |
|
"step": 770 |
|
}, |
|
{ |
|
"epoch": 2.8917910447761193, |
|
"grad_norm": 1.467826008796692, |
|
"learning_rate": 1.890772985902496e-05, |
|
"loss": 1.9947, |
|
"step": 775 |
|
}, |
|
{ |
|
"epoch": 2.91044776119403, |
|
"grad_norm": 1.6837282180786133, |
|
"learning_rate": 1.8623930785958092e-05, |
|
"loss": 1.9335, |
|
"step": 780 |
|
}, |
|
{ |
|
"epoch": 2.9291044776119404, |
|
"grad_norm": 1.446560025215149, |
|
"learning_rate": 1.8341007862370056e-05, |
|
"loss": 1.9258, |
|
"step": 785 |
|
}, |
|
{ |
|
"epoch": 2.9477611940298507, |
|
"grad_norm": 1.453008770942688, |
|
"learning_rate": 1.8058999965312484e-05, |
|
"loss": 1.9039, |
|
"step": 790 |
|
}, |
|
{ |
|
"epoch": 2.966417910447761, |
|
"grad_norm": 1.3427950143814087, |
|
"learning_rate": 1.777794584610124e-05, |
|
"loss": 1.8156, |
|
"step": 795 |
|
}, |
|
{ |
|
"epoch": 2.9850746268656714, |
|
"grad_norm": 1.7210839986801147, |
|
"learning_rate": 1.749788412499149e-05, |
|
"loss": 2.0007, |
|
"step": 800 |
|
} |
|
], |
|
"logging_steps": 5, |
|
"max_steps": 1340, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 5, |
|
"save_steps": 100, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 8.332508541311386e+17, |
|
"train_batch_size": 4, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|