| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.6157872455066774, | |
| "eval_steps": 200, | |
| "global_step": 2000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003078936227533387, | |
| "grad_norm": 0.567386619418904, | |
| "learning_rate": 6.153846153846154e-07, | |
| "loss": 1.3715, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015394681137666935, | |
| "grad_norm": 0.5288856739094128, | |
| "learning_rate": 3.0769230769230774e-06, | |
| "loss": 1.3257, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003078936227533387, | |
| "grad_norm": 0.514193298068005, | |
| "learning_rate": 6.153846153846155e-06, | |
| "loss": 1.3509, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004618404341300081, | |
| "grad_norm": 0.5439189819234317, | |
| "learning_rate": 9.230769230769232e-06, | |
| "loss": 1.3301, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006157872455066774, | |
| "grad_norm": 0.40780463269778033, | |
| "learning_rate": 1.230769230769231e-05, | |
| "loss": 1.3432, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007697340568833468, | |
| "grad_norm": 0.21241926749939638, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 1.2848, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.009236808682600161, | |
| "grad_norm": 0.22229732202041577, | |
| "learning_rate": 1.8461538461538465e-05, | |
| "loss": 1.2157, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.010776276796366856, | |
| "grad_norm": 0.22180484192931016, | |
| "learning_rate": 2.1538461538461542e-05, | |
| "loss": 1.2437, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.012315744910133548, | |
| "grad_norm": 0.26148958772269565, | |
| "learning_rate": 2.461538461538462e-05, | |
| "loss": 1.1774, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.013855213023900243, | |
| "grad_norm": 0.1381120764969843, | |
| "learning_rate": 2.7692307692307694e-05, | |
| "loss": 1.202, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.015394681137666935, | |
| "grad_norm": 0.11244566836575712, | |
| "learning_rate": 3.0769230769230774e-05, | |
| "loss": 1.147, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01693414925143363, | |
| "grad_norm": 0.11021185664583819, | |
| "learning_rate": 3.384615384615385e-05, | |
| "loss": 1.1643, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.018473617365200323, | |
| "grad_norm": 0.09699197885691936, | |
| "learning_rate": 3.692307692307693e-05, | |
| "loss": 1.1375, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.020013085478967015, | |
| "grad_norm": 0.08432503700919332, | |
| "learning_rate": 4e-05, | |
| "loss": 1.157, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.02155255359273371, | |
| "grad_norm": 0.08841813904259435, | |
| "learning_rate": 4.3076923076923084e-05, | |
| "loss": 1.1193, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.023092021706500404, | |
| "grad_norm": 0.09260059592301743, | |
| "learning_rate": 4.615384615384616e-05, | |
| "loss": 1.1143, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.024631489820267097, | |
| "grad_norm": 0.11247544113589666, | |
| "learning_rate": 4.923076923076924e-05, | |
| "loss": 1.1422, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.026170957934033793, | |
| "grad_norm": 0.10305516893175011, | |
| "learning_rate": 5.230769230769231e-05, | |
| "loss": 1.1301, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.027710426047800486, | |
| "grad_norm": 0.10094078438604197, | |
| "learning_rate": 5.538461538461539e-05, | |
| "loss": 1.07, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.02924989416156718, | |
| "grad_norm": 0.09878535861697932, | |
| "learning_rate": 5.846153846153847e-05, | |
| "loss": 1.1062, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.03078936227533387, | |
| "grad_norm": 0.0880914200143609, | |
| "learning_rate": 6.153846153846155e-05, | |
| "loss": 1.0792, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03232883038910057, | |
| "grad_norm": 0.09739295977826301, | |
| "learning_rate": 6.461538461538462e-05, | |
| "loss": 1.0886, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.03386829850286726, | |
| "grad_norm": 0.12352134648547326, | |
| "learning_rate": 6.76923076923077e-05, | |
| "loss": 1.0846, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.03540776661663395, | |
| "grad_norm": 0.09422623480770391, | |
| "learning_rate": 7.076923076923078e-05, | |
| "loss": 1.0892, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.036947234730400645, | |
| "grad_norm": 0.11191294618136459, | |
| "learning_rate": 7.384615384615386e-05, | |
| "loss": 1.0709, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.03848670284416734, | |
| "grad_norm": 0.10765812088608237, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 1.084, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.04002617095793403, | |
| "grad_norm": 0.0922143630736113, | |
| "learning_rate": 8e-05, | |
| "loss": 1.1205, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.04156563907170073, | |
| "grad_norm": 0.12839655709773654, | |
| "learning_rate": 8.307692307692309e-05, | |
| "loss": 1.0738, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.04310510718546742, | |
| "grad_norm": 0.11121867345439279, | |
| "learning_rate": 8.615384615384617e-05, | |
| "loss": 1.0821, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.044644575299234115, | |
| "grad_norm": 0.0928933843755614, | |
| "learning_rate": 8.923076923076924e-05, | |
| "loss": 1.0604, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.04618404341300081, | |
| "grad_norm": 0.09586858247024442, | |
| "learning_rate": 9.230769230769232e-05, | |
| "loss": 1.0644, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0477235115267675, | |
| "grad_norm": 0.10507553798424621, | |
| "learning_rate": 9.53846153846154e-05, | |
| "loss": 1.0617, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.049262979640534194, | |
| "grad_norm": 0.11036562639685599, | |
| "learning_rate": 9.846153846153848e-05, | |
| "loss": 1.0732, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.050802447754300886, | |
| "grad_norm": 0.11309124416557308, | |
| "learning_rate": 0.00010153846153846153, | |
| "loss": 1.0557, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.052341915868067586, | |
| "grad_norm": 0.15677878221994676, | |
| "learning_rate": 0.00010461538461538463, | |
| "loss": 1.0706, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.05388138398183428, | |
| "grad_norm": 0.11661519431178777, | |
| "learning_rate": 0.0001076923076923077, | |
| "loss": 1.098, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.05542085209560097, | |
| "grad_norm": 0.12109397309650635, | |
| "learning_rate": 0.00011076923076923077, | |
| "loss": 1.0311, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.056960320209367664, | |
| "grad_norm": 0.11093871974267784, | |
| "learning_rate": 0.00011384615384615384, | |
| "loss": 1.0707, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.05849978832313436, | |
| "grad_norm": 0.11357908911113367, | |
| "learning_rate": 0.00011692307692307694, | |
| "loss": 1.0845, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.06003925643690105, | |
| "grad_norm": 0.12394460027791813, | |
| "learning_rate": 0.00012, | |
| "loss": 1.0495, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.06157872455066774, | |
| "grad_norm": 0.11194042323004598, | |
| "learning_rate": 0.0001230769230769231, | |
| "loss": 1.0614, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.06157872455066774, | |
| "eval_loss": 1.0632128715515137, | |
| "eval_runtime": 3818.978, | |
| "eval_samples_per_second": 6.051, | |
| "eval_steps_per_second": 0.378, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.06311819266443444, | |
| "grad_norm": 0.1033181877601895, | |
| "learning_rate": 0.00012615384615384615, | |
| "loss": 1.0433, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.06465766077820113, | |
| "grad_norm": 0.12063646484450094, | |
| "learning_rate": 0.00012923076923076923, | |
| "loss": 1.0714, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.06619712889196783, | |
| "grad_norm": 0.11588361936604014, | |
| "learning_rate": 0.0001323076923076923, | |
| "loss": 1.057, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.06773659700573452, | |
| "grad_norm": 0.11616868785038624, | |
| "learning_rate": 0.0001353846153846154, | |
| "loss": 1.0553, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.06927606511950121, | |
| "grad_norm": 0.09562740234655313, | |
| "learning_rate": 0.00013846153846153847, | |
| "loss": 1.0257, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.0708155332332679, | |
| "grad_norm": 0.09393900612118493, | |
| "learning_rate": 0.00014153846153846156, | |
| "loss": 1.0445, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.0723550013470346, | |
| "grad_norm": 0.10841095433316549, | |
| "learning_rate": 0.0001446153846153846, | |
| "loss": 1.0103, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.07389446946080129, | |
| "grad_norm": 0.10223643461806235, | |
| "learning_rate": 0.00014769230769230772, | |
| "loss": 1.0717, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.07543393757456798, | |
| "grad_norm": 0.11204179743813408, | |
| "learning_rate": 0.00015076923076923077, | |
| "loss": 1.0724, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.07697340568833468, | |
| "grad_norm": 0.09200458344532117, | |
| "learning_rate": 0.00015384615384615385, | |
| "loss": 1.0636, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.07851287380210137, | |
| "grad_norm": 0.11400449644867688, | |
| "learning_rate": 0.00015692307692307693, | |
| "loss": 0.9971, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.08005234191586806, | |
| "grad_norm": 0.11612263416102313, | |
| "learning_rate": 0.00016, | |
| "loss": 1.0694, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.08159181002963477, | |
| "grad_norm": 0.09082765987050115, | |
| "learning_rate": 0.0001630769230769231, | |
| "loss": 1.0467, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.08313127814340146, | |
| "grad_norm": 0.091051842252486, | |
| "learning_rate": 0.00016615384615384617, | |
| "loss": 1.0909, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.08467074625716815, | |
| "grad_norm": 0.09996524510558816, | |
| "learning_rate": 0.00016923076923076923, | |
| "loss": 1.038, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.08621021437093485, | |
| "grad_norm": 0.08559129966794987, | |
| "learning_rate": 0.00017230769230769234, | |
| "loss": 1.055, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.08774968248470154, | |
| "grad_norm": 0.09417658234399054, | |
| "learning_rate": 0.0001753846153846154, | |
| "loss": 1.0628, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.08928915059846823, | |
| "grad_norm": 0.09367818742833312, | |
| "learning_rate": 0.00017846153846153847, | |
| "loss": 1.0698, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.09082861871223492, | |
| "grad_norm": 0.091480252033389, | |
| "learning_rate": 0.00018153846153846155, | |
| "loss": 1.065, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.09236808682600162, | |
| "grad_norm": 0.0938796736597296, | |
| "learning_rate": 0.00018461538461538463, | |
| "loss": 1.0532, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.09390755493976831, | |
| "grad_norm": 0.09576286670666531, | |
| "learning_rate": 0.0001876923076923077, | |
| "loss": 1.0496, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.095447023053535, | |
| "grad_norm": 0.09248254454681183, | |
| "learning_rate": 0.0001907692307692308, | |
| "loss": 1.0636, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.0969864911673017, | |
| "grad_norm": 0.08693274686688061, | |
| "learning_rate": 0.00019384615384615385, | |
| "loss": 1.0838, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.09852595928106839, | |
| "grad_norm": 0.07975001335214404, | |
| "learning_rate": 0.00019692307692307696, | |
| "loss": 1.037, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.10006542739483508, | |
| "grad_norm": 0.09900399369206245, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0476, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.10160489550860177, | |
| "grad_norm": 0.0883635278339313, | |
| "learning_rate": 0.00019999855506507185, | |
| "loss": 1.0765, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.10314436362236847, | |
| "grad_norm": 0.08877039836306448, | |
| "learning_rate": 0.00019999422030204418, | |
| "loss": 1.059, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.10468383173613517, | |
| "grad_norm": 0.07996176059015918, | |
| "learning_rate": 0.00019998699583618593, | |
| "loss": 1.0418, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.10622329984990186, | |
| "grad_norm": 0.0870003860102271, | |
| "learning_rate": 0.00019997688187627482, | |
| "loss": 1.0557, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.10776276796366856, | |
| "grad_norm": 0.09383600372135154, | |
| "learning_rate": 0.0001999638787145911, | |
| "loss": 1.0735, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.10930223607743525, | |
| "grad_norm": 0.09891188283344632, | |
| "learning_rate": 0.0001999479867269092, | |
| "loss": 1.0584, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.11084170419120194, | |
| "grad_norm": 0.12102740620306172, | |
| "learning_rate": 0.00019992920637248697, | |
| "loss": 1.0489, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.11238117230496864, | |
| "grad_norm": 0.08137547822372986, | |
| "learning_rate": 0.00019990753819405213, | |
| "loss": 1.0277, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.11392064041873533, | |
| "grad_norm": 0.08421354630258387, | |
| "learning_rate": 0.00019988298281778684, | |
| "loss": 1.062, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.11546010853250202, | |
| "grad_norm": 0.08071712029036497, | |
| "learning_rate": 0.00019985554095330955, | |
| "loss": 1.0215, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.11699957664626871, | |
| "grad_norm": 0.0928078752872806, | |
| "learning_rate": 0.0001998252133936544, | |
| "loss": 1.053, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.1185390447600354, | |
| "grad_norm": 0.08562676553948985, | |
| "learning_rate": 0.00019979200101524845, | |
| "loss": 1.0701, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.1200785128738021, | |
| "grad_norm": 0.08403649770517699, | |
| "learning_rate": 0.00019975590477788613, | |
| "loss": 1.0514, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.12161798098756879, | |
| "grad_norm": 0.08183724425629081, | |
| "learning_rate": 0.0001997169257247018, | |
| "loss": 1.0095, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.12315744910133548, | |
| "grad_norm": 0.08039658119705519, | |
| "learning_rate": 0.00019967506498213931, | |
| "loss": 1.0689, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.12315744910133548, | |
| "eval_loss": 1.0475565195083618, | |
| "eval_runtime": 3802.3739, | |
| "eval_samples_per_second": 6.078, | |
| "eval_steps_per_second": 0.38, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.12469691721510218, | |
| "grad_norm": 0.08379276105126061, | |
| "learning_rate": 0.00019963032375991966, | |
| "loss": 1.0782, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.12623638532886888, | |
| "grad_norm": 0.07908083743105887, | |
| "learning_rate": 0.00019958270335100595, | |
| "loss": 1.0235, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.12777585344263556, | |
| "grad_norm": 0.08493671539476158, | |
| "learning_rate": 0.00019953220513156602, | |
| "loss": 1.0907, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.12931532155640227, | |
| "grad_norm": 0.08337456151040325, | |
| "learning_rate": 0.0001994788305609327, | |
| "loss": 1.0326, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.13085478967016895, | |
| "grad_norm": 0.08547228164895211, | |
| "learning_rate": 0.00019942258118156163, | |
| "loss": 1.0442, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.13239425778393565, | |
| "grad_norm": 0.0750158452168834, | |
| "learning_rate": 0.00019936345861898663, | |
| "loss": 1.0684, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.13393372589770233, | |
| "grad_norm": 0.07579154319260911, | |
| "learning_rate": 0.0001993014645817728, | |
| "loss": 1.0547, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.13547319401146904, | |
| "grad_norm": 0.07323307416728322, | |
| "learning_rate": 0.00019923660086146723, | |
| "loss": 1.0491, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.13701266212523572, | |
| "grad_norm": 0.08937561723880813, | |
| "learning_rate": 0.0001991688693325469, | |
| "loss": 1.0484, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.13855213023900242, | |
| "grad_norm": 0.08089791643667314, | |
| "learning_rate": 0.00019909827195236493, | |
| "loss": 1.0422, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.14009159835276913, | |
| "grad_norm": 0.07004371269562998, | |
| "learning_rate": 0.00019902481076109372, | |
| "loss": 1.0779, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.1416310664665358, | |
| "grad_norm": 0.07219709532645062, | |
| "learning_rate": 0.00019894848788166604, | |
| "loss": 1.0578, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.14317053458030252, | |
| "grad_norm": 0.08319824295039546, | |
| "learning_rate": 0.00019886930551971387, | |
| "loss": 1.0776, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.1447100026940692, | |
| "grad_norm": 0.08461977605731112, | |
| "learning_rate": 0.0001987872659635043, | |
| "loss": 1.0398, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.1462494708078359, | |
| "grad_norm": 0.07913296391073374, | |
| "learning_rate": 0.00019870237158387384, | |
| "loss": 1.0496, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.14778893892160258, | |
| "grad_norm": 0.07884194841699313, | |
| "learning_rate": 0.00019861462483415952, | |
| "loss": 1.0401, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.1493284070353693, | |
| "grad_norm": 0.08715608209779739, | |
| "learning_rate": 0.0001985240282501282, | |
| "loss": 1.0458, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.15086787514913597, | |
| "grad_norm": 0.07255994722623947, | |
| "learning_rate": 0.0001984305844499033, | |
| "loss": 1.023, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.15240734326290267, | |
| "grad_norm": 0.0769318406138446, | |
| "learning_rate": 0.00019833429613388902, | |
| "loss": 1.0476, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.15394681137666935, | |
| "grad_norm": 0.07401383185768683, | |
| "learning_rate": 0.0001982351660846924, | |
| "loss": 1.0415, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.15548627949043606, | |
| "grad_norm": 0.07649017525208568, | |
| "learning_rate": 0.00019813319716704278, | |
| "loss": 1.0427, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.15702574760420274, | |
| "grad_norm": 0.07708900519770054, | |
| "learning_rate": 0.00019802839232770921, | |
| "loss": 1.0855, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.15856521571796944, | |
| "grad_norm": 0.07439539455159229, | |
| "learning_rate": 0.00019792075459541518, | |
| "loss": 1.0224, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.16010468383173612, | |
| "grad_norm": 0.08182572188820655, | |
| "learning_rate": 0.00019781028708075102, | |
| "loss": 1.0302, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.16164415194550283, | |
| "grad_norm": 0.08161041915734439, | |
| "learning_rate": 0.00019769699297608417, | |
| "loss": 1.0245, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.16318362005926954, | |
| "grad_norm": 0.08888339173595923, | |
| "learning_rate": 0.00019758087555546682, | |
| "loss": 1.0747, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.16472308817303621, | |
| "grad_norm": 0.07764918511303621, | |
| "learning_rate": 0.0001974619381745413, | |
| "loss": 1.0696, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.16626255628680292, | |
| "grad_norm": 0.07999928337629646, | |
| "learning_rate": 0.00019734018427044307, | |
| "loss": 1.0351, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.1678020244005696, | |
| "grad_norm": 0.07656288262788609, | |
| "learning_rate": 0.0001972156173617016, | |
| "loss": 1.0399, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.1693414925143363, | |
| "grad_norm": 0.07902096762825829, | |
| "learning_rate": 0.00019708824104813837, | |
| "loss": 1.0397, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.17088096062810298, | |
| "grad_norm": 0.08100109284928467, | |
| "learning_rate": 0.00019695805901076308, | |
| "loss": 1.0661, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.1724204287418697, | |
| "grad_norm": 0.07617725821540045, | |
| "learning_rate": 0.00019682507501166718, | |
| "loss": 1.088, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.17395989685563637, | |
| "grad_norm": 0.0781772918354948, | |
| "learning_rate": 0.00019668929289391523, | |
| "loss": 1.0325, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.17549936496940308, | |
| "grad_norm": 0.07602400296386462, | |
| "learning_rate": 0.00019655071658143366, | |
| "loss": 1.0493, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.17703883308316976, | |
| "grad_norm": 0.07965301834511823, | |
| "learning_rate": 0.00019640935007889755, | |
| "loss": 1.0759, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.17857830119693646, | |
| "grad_norm": 0.07753220082647658, | |
| "learning_rate": 0.0001962651974716149, | |
| "loss": 1.0601, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.18011776931070314, | |
| "grad_norm": 0.07648415793765183, | |
| "learning_rate": 0.0001961182629254084, | |
| "loss": 1.0151, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.18165723742446985, | |
| "grad_norm": 0.08029992977054808, | |
| "learning_rate": 0.00019596855068649522, | |
| "loss": 1.0499, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.18319670553823653, | |
| "grad_norm": 0.08092320232434004, | |
| "learning_rate": 0.00019581606508136426, | |
| "loss": 1.0631, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.18473617365200323, | |
| "grad_norm": 0.0748434186581261, | |
| "learning_rate": 0.00019566081051665098, | |
| "loss": 1.0053, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.18473617365200323, | |
| "eval_loss": 1.0412589311599731, | |
| "eval_runtime": 3798.478, | |
| "eval_samples_per_second": 6.084, | |
| "eval_steps_per_second": 0.38, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.18627564176576994, | |
| "grad_norm": 0.07474772922675897, | |
| "learning_rate": 0.00019550279147901036, | |
| "loss": 1.0811, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.18781510987953662, | |
| "grad_norm": 0.0773035541962382, | |
| "learning_rate": 0.00019534201253498682, | |
| "loss": 1.0359, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.18935457799330332, | |
| "grad_norm": 0.08385957791440671, | |
| "learning_rate": 0.0001951784783308827, | |
| "loss": 0.9995, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.19089404610707, | |
| "grad_norm": 0.07841850327107855, | |
| "learning_rate": 0.0001950121935926236, | |
| "loss": 1.0417, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.1924335142208367, | |
| "grad_norm": 0.11766060709484247, | |
| "learning_rate": 0.00019484316312562205, | |
| "loss": 1.0227, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.1939729823346034, | |
| "grad_norm": 0.07110694761741441, | |
| "learning_rate": 0.00019467139181463862, | |
| "loss": 1.0652, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.1955124504483701, | |
| "grad_norm": 0.07470835721419704, | |
| "learning_rate": 0.00019449688462364056, | |
| "loss": 1.0299, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.19705191856213677, | |
| "grad_norm": 0.08102828325973369, | |
| "learning_rate": 0.00019431964659565867, | |
| "loss": 1.0488, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.19859138667590348, | |
| "grad_norm": 0.07603967351010721, | |
| "learning_rate": 0.0001941396828526412, | |
| "loss": 1.0459, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.20013085478967016, | |
| "grad_norm": 0.08273841396400562, | |
| "learning_rate": 0.00019395699859530623, | |
| "loss": 1.0194, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.20167032290343687, | |
| "grad_norm": 0.08236332870987446, | |
| "learning_rate": 0.00019377159910299093, | |
| "loss": 1.0307, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.20320979101720354, | |
| "grad_norm": 0.06867994321607887, | |
| "learning_rate": 0.00019358348973349943, | |
| "loss": 1.0098, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.20474925913097025, | |
| "grad_norm": 0.08144032256455716, | |
| "learning_rate": 0.00019339267592294763, | |
| "loss": 1.048, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.20628872724473693, | |
| "grad_norm": 0.07918355281230142, | |
| "learning_rate": 0.00019319916318560635, | |
| "loss": 1.0227, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.20782819535850364, | |
| "grad_norm": 0.07792694280227995, | |
| "learning_rate": 0.00019300295711374187, | |
| "loss": 1.039, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.20936766347227034, | |
| "grad_norm": 0.07841373321559497, | |
| "learning_rate": 0.00019280406337745428, | |
| "loss": 1.0185, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.21090713158603702, | |
| "grad_norm": 0.12957233088012476, | |
| "learning_rate": 0.00019260248772451377, | |
| "loss": 1.0496, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.21244659969980373, | |
| "grad_norm": 0.07758713390528212, | |
| "learning_rate": 0.0001923982359801943, | |
| "loss": 1.0425, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.2139860678135704, | |
| "grad_norm": 0.08451147321948667, | |
| "learning_rate": 0.00019219131404710552, | |
| "loss": 1.0749, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.21552553592733711, | |
| "grad_norm": 0.08218923027527074, | |
| "learning_rate": 0.00019198172790502196, | |
| "loss": 1.0244, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.2170650040411038, | |
| "grad_norm": 0.07475377041516394, | |
| "learning_rate": 0.0001917694836107104, | |
| "loss": 1.0367, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 0.2186044721548705, | |
| "grad_norm": 0.06989397102142611, | |
| "learning_rate": 0.00019155458729775467, | |
| "loss": 1.049, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.22014394026863718, | |
| "grad_norm": 0.07403450910939992, | |
| "learning_rate": 0.0001913370451763786, | |
| "loss": 1.0135, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 0.22168340838240388, | |
| "grad_norm": 0.06736867483748331, | |
| "learning_rate": 0.00019111686353326631, | |
| "loss": 1.0213, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.22322287649617056, | |
| "grad_norm": 0.07406189263799307, | |
| "learning_rate": 0.00019089404873138082, | |
| "loss": 1.0521, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.22476234460993727, | |
| "grad_norm": 0.07355438357203191, | |
| "learning_rate": 0.00019066860720977986, | |
| "loss": 1.0483, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.22630181272370395, | |
| "grad_norm": 0.07568463711454308, | |
| "learning_rate": 0.00019044054548343002, | |
| "loss": 1.0289, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.22784128083747066, | |
| "grad_norm": 0.07229067305689793, | |
| "learning_rate": 0.0001902098701430184, | |
| "loss": 1.0694, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.22938074895123733, | |
| "grad_norm": 0.07530804590739208, | |
| "learning_rate": 0.00018997658785476214, | |
| "loss": 1.0651, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 0.23092021706500404, | |
| "grad_norm": 0.07259570093477205, | |
| "learning_rate": 0.00018974070536021572, | |
| "loss": 1.0685, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.23245968517877075, | |
| "grad_norm": 0.06991198063848746, | |
| "learning_rate": 0.00018950222947607625, | |
| "loss": 1.0524, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 0.23399915329253743, | |
| "grad_norm": 0.07071964916232602, | |
| "learning_rate": 0.0001892611670939865, | |
| "loss": 0.9967, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.23553862140630413, | |
| "grad_norm": 0.08069984398117862, | |
| "learning_rate": 0.00018901752518033548, | |
| "loss": 1.0503, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 0.2370780895200708, | |
| "grad_norm": 0.0719126875966159, | |
| "learning_rate": 0.0001887713107760575, | |
| "loss": 1.0497, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.23861755763383752, | |
| "grad_norm": 0.07933165083127114, | |
| "learning_rate": 0.00018852253099642833, | |
| "loss": 1.0163, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.2401570257476042, | |
| "grad_norm": 0.07529876789807866, | |
| "learning_rate": 0.0001882711930308599, | |
| "loss": 1.0503, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.2416964938613709, | |
| "grad_norm": 0.074705285570636, | |
| "learning_rate": 0.00018801730414269225, | |
| "loss": 1.0424, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 0.24323596197513758, | |
| "grad_norm": 0.07414239254048278, | |
| "learning_rate": 0.0001877608716689839, | |
| "loss": 1.0655, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.2447754300889043, | |
| "grad_norm": 0.07941506265986978, | |
| "learning_rate": 0.00018750190302029956, | |
| "loss": 1.0193, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 0.24631489820267097, | |
| "grad_norm": 0.08230667165269098, | |
| "learning_rate": 0.00018724040568049612, | |
| "loss": 1.0446, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.24631489820267097, | |
| "eval_loss": 1.0366028547286987, | |
| "eval_runtime": 3798.2715, | |
| "eval_samples_per_second": 6.084, | |
| "eval_steps_per_second": 0.38, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.24785436631643767, | |
| "grad_norm": 0.08052061406166201, | |
| "learning_rate": 0.00018697638720650646, | |
| "loss": 1.0329, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.24939383443020435, | |
| "grad_norm": 0.07060612206330524, | |
| "learning_rate": 0.00018670985522812084, | |
| "loss": 1.0123, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.25093330254397106, | |
| "grad_norm": 0.07261155032686553, | |
| "learning_rate": 0.0001864408174477665, | |
| "loss": 1.0394, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 0.25247277065773777, | |
| "grad_norm": 0.07296759582556935, | |
| "learning_rate": 0.00018616928164028523, | |
| "loss": 1.0021, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.2540122387715045, | |
| "grad_norm": 0.06646733390910516, | |
| "learning_rate": 0.00018589525565270844, | |
| "loss": 1.0286, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.2555517068852711, | |
| "grad_norm": 0.07496596424661404, | |
| "learning_rate": 0.0001856187474040306, | |
| "loss": 1.0502, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.25709117499903783, | |
| "grad_norm": 0.08500360217319118, | |
| "learning_rate": 0.00018533976488498016, | |
| "loss": 1.0256, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 0.25863064311280454, | |
| "grad_norm": 0.07817756873072405, | |
| "learning_rate": 0.0001850583161577889, | |
| "loss": 1.0609, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.26017011122657124, | |
| "grad_norm": 0.07136612848707545, | |
| "learning_rate": 0.00018477440935595873, | |
| "loss": 1.0775, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 0.2617095793403379, | |
| "grad_norm": 0.07292608365481835, | |
| "learning_rate": 0.00018448805268402672, | |
| "loss": 1.058, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.2632490474541046, | |
| "grad_norm": 0.07716711803643432, | |
| "learning_rate": 0.00018419925441732804, | |
| "loss": 1.0294, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 0.2647885155678713, | |
| "grad_norm": 0.07526261921660161, | |
| "learning_rate": 0.00018390802290175673, | |
| "loss": 1.0467, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.266327983681638, | |
| "grad_norm": 0.0735157839737638, | |
| "learning_rate": 0.00018361436655352456, | |
| "loss": 1.0278, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 0.26786745179540467, | |
| "grad_norm": 0.07101822956411033, | |
| "learning_rate": 0.00018331829385891783, | |
| "loss": 1.0188, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.26940691990917137, | |
| "grad_norm": 0.07406443039738211, | |
| "learning_rate": 0.00018301981337405212, | |
| "loss": 1.0476, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.2709463880229381, | |
| "grad_norm": 0.07470379094242477, | |
| "learning_rate": 0.00018271893372462497, | |
| "loss": 1.0468, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.2724858561367048, | |
| "grad_norm": 0.07458412123750419, | |
| "learning_rate": 0.00018241566360566665, | |
| "loss": 1.0279, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 0.27402532425047144, | |
| "grad_norm": 0.08164107594170099, | |
| "learning_rate": 0.00018211001178128892, | |
| "loss": 1.0472, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.27556479236423814, | |
| "grad_norm": 0.07748097167228449, | |
| "learning_rate": 0.00018180198708443173, | |
| "loss": 1.0534, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 0.27710426047800485, | |
| "grad_norm": 0.07485972229218758, | |
| "learning_rate": 0.00018149159841660795, | |
| "loss": 1.0419, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.27864372859177156, | |
| "grad_norm": 0.07553124022662376, | |
| "learning_rate": 0.00018117885474764613, | |
| "loss": 1.0836, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 0.28018319670553826, | |
| "grad_norm": 0.07966215645919128, | |
| "learning_rate": 0.00018086376511543126, | |
| "loss": 1.0642, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.2817226648193049, | |
| "grad_norm": 0.08376456009997757, | |
| "learning_rate": 0.00018054633862564368, | |
| "loss": 1.0398, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 0.2832621329330716, | |
| "grad_norm": 0.075508959246266, | |
| "learning_rate": 0.0001802265844514958, | |
| "loss": 0.9996, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.2848016010468383, | |
| "grad_norm": 0.07358158800850821, | |
| "learning_rate": 0.0001799045118334671, | |
| "loss": 1.0542, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.28634106916060503, | |
| "grad_norm": 0.08094264187967125, | |
| "learning_rate": 0.00017958013007903713, | |
| "loss": 1.0563, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.2878805372743717, | |
| "grad_norm": 0.07424176124118159, | |
| "learning_rate": 0.0001792534485624164, | |
| "loss": 1.0405, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 0.2894200053881384, | |
| "grad_norm": 0.07418414794842867, | |
| "learning_rate": 0.00017892447672427563, | |
| "loss": 1.0391, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.2909594735019051, | |
| "grad_norm": 0.0704593007549167, | |
| "learning_rate": 0.00017859322407147272, | |
| "loss": 1.0543, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 0.2924989416156718, | |
| "grad_norm": 0.07058098730245323, | |
| "learning_rate": 0.00017825970017677832, | |
| "loss": 1.0693, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.29403840972943845, | |
| "grad_norm": 0.07100077379863531, | |
| "learning_rate": 0.00017792391467859886, | |
| "loss": 1.0157, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 0.29557787784320516, | |
| "grad_norm": 0.07264965656385536, | |
| "learning_rate": 0.0001775858772806983, | |
| "loss": 1.0669, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.29711734595697187, | |
| "grad_norm": 0.06945646756969821, | |
| "learning_rate": 0.00017724559775191744, | |
| "loss": 1.0282, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 0.2986568140707386, | |
| "grad_norm": 0.0800750187488917, | |
| "learning_rate": 0.00017690308592589182, | |
| "loss": 1.0424, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.3001962821845053, | |
| "grad_norm": 0.07826578070698212, | |
| "learning_rate": 0.0001765583517007675, | |
| "loss": 0.994, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.30173575029827193, | |
| "grad_norm": 0.07185624380063993, | |
| "learning_rate": 0.00017621140503891488, | |
| "loss": 1.0117, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.30327521841203864, | |
| "grad_norm": 0.07770724836361542, | |
| "learning_rate": 0.00017586225596664102, | |
| "loss": 1.0282, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 0.30481468652580535, | |
| "grad_norm": 0.07425549788358596, | |
| "learning_rate": 0.00017551091457389966, | |
| "loss": 1.0332, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.30635415463957205, | |
| "grad_norm": 0.07157671192234144, | |
| "learning_rate": 0.00017515739101399983, | |
| "loss": 1.0202, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 0.3078936227533387, | |
| "grad_norm": 0.07195148099166214, | |
| "learning_rate": 0.00017480169550331231, | |
| "loss": 1.0091, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.3078936227533387, | |
| "eval_loss": 1.033624291419983, | |
| "eval_runtime": 3799.3073, | |
| "eval_samples_per_second": 6.082, | |
| "eval_steps_per_second": 0.38, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.3094330908671054, | |
| "grad_norm": 0.0709967222808181, | |
| "learning_rate": 0.00017444383832097442, | |
| "loss": 1.0306, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 0.3109725589808721, | |
| "grad_norm": 0.08017250953363526, | |
| "learning_rate": 0.00017408382980859305, | |
| "loss": 1.0335, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.3125120270946388, | |
| "grad_norm": 0.0763005407159528, | |
| "learning_rate": 0.00017372168036994566, | |
| "loss": 1.0155, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 0.3140514952084055, | |
| "grad_norm": 0.068090767981409, | |
| "learning_rate": 0.00017335740047067972, | |
| "loss": 1.0226, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.3155909633221722, | |
| "grad_norm": 0.07053765308848822, | |
| "learning_rate": 0.0001729910006380102, | |
| "loss": 1.0455, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.3171304314359389, | |
| "grad_norm": 0.07639366775520491, | |
| "learning_rate": 0.00017262249146041546, | |
| "loss": 1.0737, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.3186698995497056, | |
| "grad_norm": 0.07414091472835294, | |
| "learning_rate": 0.00017225188358733107, | |
| "loss": 1.0159, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 0.32020936766347224, | |
| "grad_norm": 0.07840200264036183, | |
| "learning_rate": 0.00017187918772884232, | |
| "loss": 1.0605, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.32174883577723895, | |
| "grad_norm": 0.06946548404139283, | |
| "learning_rate": 0.00017150441465537447, | |
| "loss": 1.0549, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 0.32328830389100566, | |
| "grad_norm": 0.0726329779508538, | |
| "learning_rate": 0.00017112757519738154, | |
| "loss": 1.0294, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.32482777200477236, | |
| "grad_norm": 0.07366641465053547, | |
| "learning_rate": 0.0001707486802450335, | |
| "loss": 1.0439, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 0.32636724011853907, | |
| "grad_norm": 0.07461023494546891, | |
| "learning_rate": 0.00017036774074790132, | |
| "loss": 1.0036, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.3279067082323057, | |
| "grad_norm": 0.07745841056330656, | |
| "learning_rate": 0.00016998476771464072, | |
| "loss": 1.039, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 0.32944617634607243, | |
| "grad_norm": 0.07562279638819498, | |
| "learning_rate": 0.00016959977221267392, | |
| "loss": 1.0136, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.33098564445983913, | |
| "grad_norm": 0.07269409212200949, | |
| "learning_rate": 0.0001692127653678699, | |
| "loss": 1.0447, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.33252511257360584, | |
| "grad_norm": 0.07863977410900856, | |
| "learning_rate": 0.00016882375836422284, | |
| "loss": 1.032, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.3340645806873725, | |
| "grad_norm": 0.08154682576838618, | |
| "learning_rate": 0.00016843276244352885, | |
| "loss": 1.0576, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 0.3356040488011392, | |
| "grad_norm": 0.07324914224304953, | |
| "learning_rate": 0.00016803978890506113, | |
| "loss": 1.0677, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.3371435169149059, | |
| "grad_norm": 0.08330706239189462, | |
| "learning_rate": 0.00016764484910524358, | |
| "loss": 1.0244, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 0.3386829850286726, | |
| "grad_norm": 0.07527643648007623, | |
| "learning_rate": 0.00016724795445732243, | |
| "loss": 0.9977, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.34022245314243926, | |
| "grad_norm": 0.07895912028160554, | |
| "learning_rate": 0.00016684911643103642, | |
| "loss": 1.0575, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 0.34176192125620597, | |
| "grad_norm": 0.073939133015858, | |
| "learning_rate": 0.0001664483465522855, | |
| "loss": 1.0337, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.3433013893699727, | |
| "grad_norm": 0.07648599682491888, | |
| "learning_rate": 0.00016604565640279754, | |
| "loss": 1.0462, | |
| "step": 1115 | |
| }, | |
| { | |
| "epoch": 0.3448408574837394, | |
| "grad_norm": 0.07375239907970622, | |
| "learning_rate": 0.0001656410576197938, | |
| "loss": 1.0537, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.3463803255975061, | |
| "grad_norm": 0.07218952828382294, | |
| "learning_rate": 0.0001652345618956526, | |
| "loss": 1.0702, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 0.34791979371127274, | |
| "grad_norm": 0.07501734343767677, | |
| "learning_rate": 0.00016482618097757122, | |
| "loss": 1.045, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.34945926182503945, | |
| "grad_norm": 0.07478505250167114, | |
| "learning_rate": 0.00016441592666722684, | |
| "loss": 1.0356, | |
| "step": 1135 | |
| }, | |
| { | |
| "epoch": 0.35099872993880615, | |
| "grad_norm": 0.07035501241737965, | |
| "learning_rate": 0.00016400381082043507, | |
| "loss": 1.0819, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.35253819805257286, | |
| "grad_norm": 0.07713003380587562, | |
| "learning_rate": 0.00016358984534680748, | |
| "loss": 1.0494, | |
| "step": 1145 | |
| }, | |
| { | |
| "epoch": 0.3540776661663395, | |
| "grad_norm": 0.07012091124270008, | |
| "learning_rate": 0.00016317404220940758, | |
| "loss": 1.022, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.3556171342801062, | |
| "grad_norm": 0.06697708347109951, | |
| "learning_rate": 0.00016275641342440483, | |
| "loss": 1.0589, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 0.3571566023938729, | |
| "grad_norm": 0.07573896521834783, | |
| "learning_rate": 0.0001623369710607277, | |
| "loss": 1.0044, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.35869607050763963, | |
| "grad_norm": 0.06946529088193742, | |
| "learning_rate": 0.00016191572723971455, | |
| "loss": 1.0652, | |
| "step": 1165 | |
| }, | |
| { | |
| "epoch": 0.3602355386214063, | |
| "grad_norm": 0.0727340465476027, | |
| "learning_rate": 0.00016149269413476353, | |
| "loss": 1.0057, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.361775006735173, | |
| "grad_norm": 0.08017843239666048, | |
| "learning_rate": 0.00016106788397098095, | |
| "loss": 0.9942, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 0.3633144748489397, | |
| "grad_norm": 0.06899110462149576, | |
| "learning_rate": 0.0001606413090248276, | |
| "loss": 0.9958, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.3648539429627064, | |
| "grad_norm": 0.07737025459856088, | |
| "learning_rate": 0.00016021298162376428, | |
| "loss": 1.0211, | |
| "step": 1185 | |
| }, | |
| { | |
| "epoch": 0.36639341107647305, | |
| "grad_norm": 0.07807131065906221, | |
| "learning_rate": 0.00015978291414589542, | |
| "loss": 1.039, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.36793287919023976, | |
| "grad_norm": 0.07059155235596021, | |
| "learning_rate": 0.0001593511190196115, | |
| "loss": 1.0513, | |
| "step": 1195 | |
| }, | |
| { | |
| "epoch": 0.36947234730400647, | |
| "grad_norm": 0.07422722970665956, | |
| "learning_rate": 0.00015891760872322963, | |
| "loss": 1.0093, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.36947234730400647, | |
| "eval_loss": 1.0309594869613647, | |
| "eval_runtime": 3796.5579, | |
| "eval_samples_per_second": 6.087, | |
| "eval_steps_per_second": 0.381, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.37101181541777317, | |
| "grad_norm": 0.06806084338199529, | |
| "learning_rate": 0.00015848239578463325, | |
| "loss": 1.0504, | |
| "step": 1205 | |
| }, | |
| { | |
| "epoch": 0.3725512835315399, | |
| "grad_norm": 0.07638211255486586, | |
| "learning_rate": 0.00015804549278090982, | |
| "loss": 1.0145, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.37409075164530653, | |
| "grad_norm": 0.07232165039483601, | |
| "learning_rate": 0.00015760691233798757, | |
| "loss": 1.011, | |
| "step": 1215 | |
| }, | |
| { | |
| "epoch": 0.37563021975907324, | |
| "grad_norm": 0.0725477342684882, | |
| "learning_rate": 0.00015716666713027055, | |
| "loss": 1.0338, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.37716968787283994, | |
| "grad_norm": 0.08448404468374969, | |
| "learning_rate": 0.00015672476988027228, | |
| "loss": 1.0388, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 0.37870915598660665, | |
| "grad_norm": 0.08451055602238913, | |
| "learning_rate": 0.0001562812333582482, | |
| "loss": 1.0041, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.3802486241003733, | |
| "grad_norm": 0.07357435195090126, | |
| "learning_rate": 0.00015583607038182655, | |
| "loss": 1.0286, | |
| "step": 1235 | |
| }, | |
| { | |
| "epoch": 0.38178809221414, | |
| "grad_norm": 0.07981414373807207, | |
| "learning_rate": 0.000155389293815638, | |
| "loss": 1.0293, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.3833275603279067, | |
| "grad_norm": 0.074241776686085, | |
| "learning_rate": 0.00015494091657094385, | |
| "loss": 1.033, | |
| "step": 1245 | |
| }, | |
| { | |
| "epoch": 0.3848670284416734, | |
| "grad_norm": 0.07517760872068341, | |
| "learning_rate": 0.00015449095160526292, | |
| "loss": 1.0559, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.38640649655544007, | |
| "grad_norm": 0.07476423646372729, | |
| "learning_rate": 0.00015403941192199718, | |
| "loss": 1.0343, | |
| "step": 1255 | |
| }, | |
| { | |
| "epoch": 0.3879459646692068, | |
| "grad_norm": 0.07214431115898451, | |
| "learning_rate": 0.0001535863105700558, | |
| "loss": 1.0467, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.3894854327829735, | |
| "grad_norm": 0.07644175139453621, | |
| "learning_rate": 0.00015313166064347814, | |
| "loss": 1.0188, | |
| "step": 1265 | |
| }, | |
| { | |
| "epoch": 0.3910249008967402, | |
| "grad_norm": 0.06984113294468933, | |
| "learning_rate": 0.00015267547528105538, | |
| "loss": 1.0341, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.3925643690105069, | |
| "grad_norm": 0.06690863213166448, | |
| "learning_rate": 0.0001522177676659508, | |
| "loss": 1.0625, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 0.39410383712427355, | |
| "grad_norm": 0.06950059946334636, | |
| "learning_rate": 0.00015175855102531887, | |
| "loss": 1.0123, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.39564330523804025, | |
| "grad_norm": 0.06964516306819979, | |
| "learning_rate": 0.00015129783862992283, | |
| "loss": 1.0201, | |
| "step": 1285 | |
| }, | |
| { | |
| "epoch": 0.39718277335180696, | |
| "grad_norm": 0.080130428292661, | |
| "learning_rate": 0.0001508356437937512, | |
| "loss": 1.0448, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.39872224146557367, | |
| "grad_norm": 0.07373600496196321, | |
| "learning_rate": 0.00015037197987363338, | |
| "loss": 1.0272, | |
| "step": 1295 | |
| }, | |
| { | |
| "epoch": 0.4002617095793403, | |
| "grad_norm": 0.07444079143838864, | |
| "learning_rate": 0.0001499068602688532, | |
| "loss": 1.0625, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.401801177693107, | |
| "grad_norm": 0.07495218470810172, | |
| "learning_rate": 0.00014944029842076185, | |
| "loss": 1.0277, | |
| "step": 1305 | |
| }, | |
| { | |
| "epoch": 0.40334064580687373, | |
| "grad_norm": 0.07148138370454796, | |
| "learning_rate": 0.0001489723078123896, | |
| "loss": 1.0393, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.40488011392064044, | |
| "grad_norm": 0.07184439296288066, | |
| "learning_rate": 0.00014850290196805594, | |
| "loss": 1.0413, | |
| "step": 1315 | |
| }, | |
| { | |
| "epoch": 0.4064195820344071, | |
| "grad_norm": 0.07052670997188848, | |
| "learning_rate": 0.00014803209445297887, | |
| "loss": 1.0056, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.4079590501481738, | |
| "grad_norm": 0.07344695167875763, | |
| "learning_rate": 0.00014755989887288285, | |
| "loss": 1.0411, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 0.4094985182619405, | |
| "grad_norm": 0.0769706853052285, | |
| "learning_rate": 0.00014708632887360564, | |
| "loss": 1.0387, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.4110379863757072, | |
| "grad_norm": 0.0739404718972198, | |
| "learning_rate": 0.0001466113981407039, | |
| "loss": 1.0452, | |
| "step": 1335 | |
| }, | |
| { | |
| "epoch": 0.41257745448947386, | |
| "grad_norm": 0.08213823024505344, | |
| "learning_rate": 0.00014613512039905765, | |
| "loss": 1.0339, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.41411692260324057, | |
| "grad_norm": 0.07328616522330499, | |
| "learning_rate": 0.00014565750941247386, | |
| "loss": 1.0133, | |
| "step": 1345 | |
| }, | |
| { | |
| "epoch": 0.4156563907170073, | |
| "grad_norm": 0.07420350570178859, | |
| "learning_rate": 0.0001451785789832884, | |
| "loss": 1.0186, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.417195858830774, | |
| "grad_norm": 0.07745166588825841, | |
| "learning_rate": 0.00014469834295196743, | |
| "loss": 1.0498, | |
| "step": 1355 | |
| }, | |
| { | |
| "epoch": 0.4187353269445407, | |
| "grad_norm": 0.07355335272924506, | |
| "learning_rate": 0.00014421681519670722, | |
| "loss": 1.0435, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.42027479505830734, | |
| "grad_norm": 0.07280563497532423, | |
| "learning_rate": 0.0001437340096330332, | |
| "loss": 1.0503, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 0.42181426317207404, | |
| "grad_norm": 0.08984865578017236, | |
| "learning_rate": 0.0001432499402133979, | |
| "loss": 1.0373, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.42335373128584075, | |
| "grad_norm": 0.07403634652711334, | |
| "learning_rate": 0.0001427646209267775, | |
| "loss": 1.0296, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 0.42489319939960746, | |
| "grad_norm": 0.06941364422871579, | |
| "learning_rate": 0.00014227806579826774, | |
| "loss": 1.0097, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.4264326675133741, | |
| "grad_norm": 0.07802992325990128, | |
| "learning_rate": 0.00014179028888867867, | |
| "loss": 1.0745, | |
| "step": 1385 | |
| }, | |
| { | |
| "epoch": 0.4279721356271408, | |
| "grad_norm": 0.08282848213775869, | |
| "learning_rate": 0.00014130130429412815, | |
| "loss": 1.0273, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.4295116037409075, | |
| "grad_norm": 0.08153105885218227, | |
| "learning_rate": 0.0001408111261456346, | |
| "loss": 1.0099, | |
| "step": 1395 | |
| }, | |
| { | |
| "epoch": 0.43105107185467423, | |
| "grad_norm": 0.0676196363646441, | |
| "learning_rate": 0.00014031976860870855, | |
| "loss": 1.0086, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.43105107185467423, | |
| "eval_loss": 1.0290647745132446, | |
| "eval_runtime": 3812.7057, | |
| "eval_samples_per_second": 6.061, | |
| "eval_steps_per_second": 0.379, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.4325905399684409, | |
| "grad_norm": 0.07464451118448104, | |
| "learning_rate": 0.00013982724588294335, | |
| "loss": 1.0198, | |
| "step": 1405 | |
| }, | |
| { | |
| "epoch": 0.4341300080822076, | |
| "grad_norm": 0.07512676303409935, | |
| "learning_rate": 0.00013933357220160476, | |
| "loss": 1.0591, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.4356694761959743, | |
| "grad_norm": 0.06938767156943278, | |
| "learning_rate": 0.00013883876183121973, | |
| "loss": 1.0523, | |
| "step": 1415 | |
| }, | |
| { | |
| "epoch": 0.437208944309741, | |
| "grad_norm": 0.0777955845768148, | |
| "learning_rate": 0.000138342829071164, | |
| "loss": 1.0436, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.4387484124235077, | |
| "grad_norm": 0.076768877519892, | |
| "learning_rate": 0.00013784578825324885, | |
| "loss": 1.0098, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 0.44028788053727436, | |
| "grad_norm": 0.07138945295655025, | |
| "learning_rate": 0.00013734765374130717, | |
| "loss": 1.0262, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.44182734865104106, | |
| "grad_norm": 0.07543031342117723, | |
| "learning_rate": 0.00013684843993077788, | |
| "loss": 1.0124, | |
| "step": 1435 | |
| }, | |
| { | |
| "epoch": 0.44336681676480777, | |
| "grad_norm": 0.07202890380872994, | |
| "learning_rate": 0.00013634816124829063, | |
| "loss": 1.0183, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.4449062848785745, | |
| "grad_norm": 0.06782846978809214, | |
| "learning_rate": 0.0001358468321512481, | |
| "loss": 1.0552, | |
| "step": 1445 | |
| }, | |
| { | |
| "epoch": 0.4464457529923411, | |
| "grad_norm": 0.07176237407539487, | |
| "learning_rate": 0.00013534446712740877, | |
| "loss": 1.025, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.44798522110610783, | |
| "grad_norm": 0.07601715009456655, | |
| "learning_rate": 0.0001348410806944681, | |
| "loss": 1.0153, | |
| "step": 1455 | |
| }, | |
| { | |
| "epoch": 0.44952468921987454, | |
| "grad_norm": 0.0761359028970367, | |
| "learning_rate": 0.00013433668739963882, | |
| "loss": 1.0244, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.45106415733364125, | |
| "grad_norm": 0.07165181931814346, | |
| "learning_rate": 0.00013383130181923071, | |
| "loss": 1.0237, | |
| "step": 1465 | |
| }, | |
| { | |
| "epoch": 0.4526036254474079, | |
| "grad_norm": 0.07219427827224394, | |
| "learning_rate": 0.00013332493855822936, | |
| "loss": 1.0064, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.4541430935611746, | |
| "grad_norm": 0.07315240256522645, | |
| "learning_rate": 0.00013281761224987398, | |
| "loss": 1.0049, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 0.4556825616749413, | |
| "grad_norm": 0.07283831171004836, | |
| "learning_rate": 0.00013230933755523466, | |
| "loss": 1.028, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.457222029788708, | |
| "grad_norm": 0.08277958377037488, | |
| "learning_rate": 0.00013180012916278854, | |
| "loss": 1.0402, | |
| "step": 1485 | |
| }, | |
| { | |
| "epoch": 0.45876149790247467, | |
| "grad_norm": 0.0732834274712129, | |
| "learning_rate": 0.00013129000178799548, | |
| "loss": 1.0366, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.4603009660162414, | |
| "grad_norm": 0.07270925231246442, | |
| "learning_rate": 0.00013077897017287272, | |
| "loss": 1.0006, | |
| "step": 1495 | |
| }, | |
| { | |
| "epoch": 0.4618404341300081, | |
| "grad_norm": 0.07601545515982518, | |
| "learning_rate": 0.00013026704908556888, | |
| "loss": 1.0555, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.4633799022437748, | |
| "grad_norm": 0.0775749000511019, | |
| "learning_rate": 0.0001297542533199371, | |
| "loss": 1.0409, | |
| "step": 1505 | |
| }, | |
| { | |
| "epoch": 0.4649193703575415, | |
| "grad_norm": 0.07378648062711159, | |
| "learning_rate": 0.00012924059769510768, | |
| "loss": 1.0314, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.46645883847130815, | |
| "grad_norm": 0.07321573368492998, | |
| "learning_rate": 0.00012872609705505964, | |
| "loss": 1.0502, | |
| "step": 1515 | |
| }, | |
| { | |
| "epoch": 0.46799830658507485, | |
| "grad_norm": 0.07930733821420928, | |
| "learning_rate": 0.00012821076626819196, | |
| "loss": 1.0414, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.46953777469884156, | |
| "grad_norm": 0.07511260278964532, | |
| "learning_rate": 0.00012769462022689363, | |
| "loss": 1.0205, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 0.47107724281260827, | |
| "grad_norm": 0.06779778370699593, | |
| "learning_rate": 0.0001271776738471136, | |
| "loss": 1.0274, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.4726167109263749, | |
| "grad_norm": 0.07717323700425802, | |
| "learning_rate": 0.00012665994206792938, | |
| "loss": 1.0589, | |
| "step": 1535 | |
| }, | |
| { | |
| "epoch": 0.4741561790401416, | |
| "grad_norm": 0.06842508429114769, | |
| "learning_rate": 0.00012614143985111565, | |
| "loss": 1.0987, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.47569564715390833, | |
| "grad_norm": 0.07643849238067586, | |
| "learning_rate": 0.00012562218218071164, | |
| "loss": 1.0218, | |
| "step": 1545 | |
| }, | |
| { | |
| "epoch": 0.47723511526767504, | |
| "grad_norm": 0.07406016562514833, | |
| "learning_rate": 0.0001251021840625883, | |
| "loss": 1.0182, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.4787745833814417, | |
| "grad_norm": 0.07954321360596633, | |
| "learning_rate": 0.00012458146052401442, | |
| "loss": 1.0283, | |
| "step": 1555 | |
| }, | |
| { | |
| "epoch": 0.4803140514952084, | |
| "grad_norm": 0.07374926807557698, | |
| "learning_rate": 0.00012406002661322264, | |
| "loss": 1.0165, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.4818535196089751, | |
| "grad_norm": 0.07376676091481264, | |
| "learning_rate": 0.00012353789739897437, | |
| "loss": 1.0503, | |
| "step": 1565 | |
| }, | |
| { | |
| "epoch": 0.4833929877227418, | |
| "grad_norm": 0.07439474348790363, | |
| "learning_rate": 0.00012301508797012432, | |
| "loss": 1.0292, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.4849324558365085, | |
| "grad_norm": 0.07661999249880341, | |
| "learning_rate": 0.00012249161343518466, | |
| "loss": 1.0111, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 0.48647192395027516, | |
| "grad_norm": 0.07208564187421422, | |
| "learning_rate": 0.00012196748892188816, | |
| "loss": 1.0441, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.48801139206404187, | |
| "grad_norm": 0.07849547483606649, | |
| "learning_rate": 0.00012144272957675108, | |
| "loss": 1.0235, | |
| "step": 1585 | |
| }, | |
| { | |
| "epoch": 0.4895508601778086, | |
| "grad_norm": 0.07505211623162304, | |
| "learning_rate": 0.00012091735056463562, | |
| "loss": 1.0032, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.4910903282915753, | |
| "grad_norm": 0.08312558481401704, | |
| "learning_rate": 0.00012039136706831145, | |
| "loss": 1.059, | |
| "step": 1595 | |
| }, | |
| { | |
| "epoch": 0.49262979640534194, | |
| "grad_norm": 0.07454335234650318, | |
| "learning_rate": 0.00011986479428801709, | |
| "loss": 1.0362, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.49262979640534194, | |
| "eval_loss": 1.0269535779953003, | |
| "eval_runtime": 3800.036, | |
| "eval_samples_per_second": 6.081, | |
| "eval_steps_per_second": 0.38, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.49416926451910864, | |
| "grad_norm": 0.07456362557265384, | |
| "learning_rate": 0.00011933764744102058, | |
| "loss": 1.016, | |
| "step": 1605 | |
| }, | |
| { | |
| "epoch": 0.49570873263287535, | |
| "grad_norm": 0.08008662438079932, | |
| "learning_rate": 0.00011880994176117976, | |
| "loss": 1.0392, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.49724820074664206, | |
| "grad_norm": 0.07176749751196013, | |
| "learning_rate": 0.00011828169249850201, | |
| "loss": 1.0392, | |
| "step": 1615 | |
| }, | |
| { | |
| "epoch": 0.4987876688604087, | |
| "grad_norm": 0.07655608798136061, | |
| "learning_rate": 0.00011775291491870351, | |
| "loss": 1.0212, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.5003271369741754, | |
| "grad_norm": 0.07786227626103659, | |
| "learning_rate": 0.00011722362430276816, | |
| "loss": 1.03, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 0.5018666050879421, | |
| "grad_norm": 0.07799113973393568, | |
| "learning_rate": 0.00011669383594650593, | |
| "loss": 1.0589, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.5034060732017088, | |
| "grad_norm": 0.06547994125184468, | |
| "learning_rate": 0.00011616356516011083, | |
| "loss": 1.0084, | |
| "step": 1635 | |
| }, | |
| { | |
| "epoch": 0.5049455413154755, | |
| "grad_norm": 0.07784862670275924, | |
| "learning_rate": 0.00011563282726771847, | |
| "loss": 1.0449, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.5064850094292422, | |
| "grad_norm": 0.0771399540024009, | |
| "learning_rate": 0.0001151016376069632, | |
| "loss": 1.0634, | |
| "step": 1645 | |
| }, | |
| { | |
| "epoch": 0.508024477543009, | |
| "grad_norm": 0.07334720494239291, | |
| "learning_rate": 0.00011457001152853493, | |
| "loss": 1.0142, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.5095639456567755, | |
| "grad_norm": 0.07439128068501075, | |
| "learning_rate": 0.00011403796439573544, | |
| "loss": 1.0309, | |
| "step": 1655 | |
| }, | |
| { | |
| "epoch": 0.5111034137705422, | |
| "grad_norm": 0.0708288260968639, | |
| "learning_rate": 0.00011350551158403442, | |
| "loss": 1.0531, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.512642881884309, | |
| "grad_norm": 0.06763171945470464, | |
| "learning_rate": 0.0001129726684806252, | |
| "loss": 1.0086, | |
| "step": 1665 | |
| }, | |
| { | |
| "epoch": 0.5141823499980757, | |
| "grad_norm": 0.07768921401375369, | |
| "learning_rate": 0.00011243945048398003, | |
| "loss": 1.0148, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.5157218181118424, | |
| "grad_norm": 0.06896327791840266, | |
| "learning_rate": 0.000111905873003405, | |
| "loss": 1.0261, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 0.5172612862256091, | |
| "grad_norm": 0.07842199537412599, | |
| "learning_rate": 0.00011137195145859494, | |
| "loss": 0.999, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.5188007543393758, | |
| "grad_norm": 0.06865343546929636, | |
| "learning_rate": 0.00011083770127918762, | |
| "loss": 0.9982, | |
| "step": 1685 | |
| }, | |
| { | |
| "epoch": 0.5203402224531425, | |
| "grad_norm": 0.08103281697737574, | |
| "learning_rate": 0.00011030313790431788, | |
| "loss": 1.042, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.5218796905669091, | |
| "grad_norm": 0.07974961051333619, | |
| "learning_rate": 0.00010976827678217161, | |
| "loss": 1.0039, | |
| "step": 1695 | |
| }, | |
| { | |
| "epoch": 0.5234191586806758, | |
| "grad_norm": 0.06625737159764002, | |
| "learning_rate": 0.00010923313336953913, | |
| "loss": 1.0115, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.5249586267944425, | |
| "grad_norm": 0.07000163587644152, | |
| "learning_rate": 0.00010869772313136861, | |
| "loss": 1.0223, | |
| "step": 1705 | |
| }, | |
| { | |
| "epoch": 0.5264980949082092, | |
| "grad_norm": 0.06839426065828255, | |
| "learning_rate": 0.00010816206154031916, | |
| "loss": 1.0088, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.5280375630219759, | |
| "grad_norm": 0.07949491269796151, | |
| "learning_rate": 0.00010762616407631356, | |
| "loss": 1.071, | |
| "step": 1715 | |
| }, | |
| { | |
| "epoch": 0.5295770311357426, | |
| "grad_norm": 0.07557511886462906, | |
| "learning_rate": 0.00010709004622609116, | |
| "loss": 1.0676, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.5311164992495093, | |
| "grad_norm": 0.08195884945191133, | |
| "learning_rate": 0.00010655372348276006, | |
| "loss": 1.0198, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 0.532655967363276, | |
| "grad_norm": 0.0781242359342465, | |
| "learning_rate": 0.00010601721134534959, | |
| "loss": 1.0314, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.5341954354770427, | |
| "grad_norm": 0.07628144377233338, | |
| "learning_rate": 0.00010548052531836223, | |
| "loss": 1.0299, | |
| "step": 1735 | |
| }, | |
| { | |
| "epoch": 0.5357349035908093, | |
| "grad_norm": 0.07983920659956817, | |
| "learning_rate": 0.00010494368091132576, | |
| "loss": 1.0317, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.537274371704576, | |
| "grad_norm": 0.07418551402340584, | |
| "learning_rate": 0.00010440669363834483, | |
| "loss": 1.0129, | |
| "step": 1745 | |
| }, | |
| { | |
| "epoch": 0.5388138398183427, | |
| "grad_norm": 0.07002417164492032, | |
| "learning_rate": 0.00010386957901765277, | |
| "loss": 1.0278, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.5403533079321095, | |
| "grad_norm": 0.0707377171946109, | |
| "learning_rate": 0.00010333235257116313, | |
| "loss": 0.9727, | |
| "step": 1755 | |
| }, | |
| { | |
| "epoch": 0.5418927760458762, | |
| "grad_norm": 0.0737915692626489, | |
| "learning_rate": 0.00010279502982402103, | |
| "loss": 1.0433, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.5434322441596429, | |
| "grad_norm": 0.07512990163556856, | |
| "learning_rate": 0.00010225762630415457, | |
| "loss": 1.0111, | |
| "step": 1765 | |
| }, | |
| { | |
| "epoch": 0.5449717122734096, | |
| "grad_norm": 0.0753662165245646, | |
| "learning_rate": 0.00010172015754182607, | |
| "loss": 1.037, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.5465111803871763, | |
| "grad_norm": 0.1349186814580228, | |
| "learning_rate": 0.00010118263906918331, | |
| "loss": 1.0381, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 0.5480506485009429, | |
| "grad_norm": 0.07557478098317172, | |
| "learning_rate": 0.00010064508641981054, | |
| "loss": 0.9955, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.5495901166147096, | |
| "grad_norm": 0.07668998832423247, | |
| "learning_rate": 0.0001001075151282798, | |
| "loss": 1.051, | |
| "step": 1785 | |
| }, | |
| { | |
| "epoch": 0.5511295847284763, | |
| "grad_norm": 0.07585620860956059, | |
| "learning_rate": 9.956994072970179e-05, | |
| "loss": 1.0272, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.552669052842243, | |
| "grad_norm": 0.07008056728318604, | |
| "learning_rate": 9.903237875927698e-05, | |
| "loss": 1.0653, | |
| "step": 1795 | |
| }, | |
| { | |
| "epoch": 0.5542085209560097, | |
| "grad_norm": 0.07151388140558161, | |
| "learning_rate": 9.849484475184672e-05, | |
| "loss": 1.0155, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.5542085209560097, | |
| "eval_loss": 1.0255825519561768, | |
| "eval_runtime": 3798.3842, | |
| "eval_samples_per_second": 6.084, | |
| "eval_steps_per_second": 0.38, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.5557479890697764, | |
| "grad_norm": 0.08081651371496165, | |
| "learning_rate": 9.795735424144428e-05, | |
| "loss": 1.0102, | |
| "step": 1805 | |
| }, | |
| { | |
| "epoch": 0.5572874571835431, | |
| "grad_norm": 0.11914760104172627, | |
| "learning_rate": 9.74199227608459e-05, | |
| "loss": 1.0316, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.5588269252973098, | |
| "grad_norm": 0.07607697309485299, | |
| "learning_rate": 9.688256584112192e-05, | |
| "loss": 1.0158, | |
| "step": 1815 | |
| }, | |
| { | |
| "epoch": 0.5603663934110765, | |
| "grad_norm": 0.07962971403841683, | |
| "learning_rate": 9.634529901118799e-05, | |
| "loss": 1.0243, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.5619058615248431, | |
| "grad_norm": 0.0715309251551143, | |
| "learning_rate": 9.580813779735624e-05, | |
| "loss": 1.0354, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 0.5634453296386098, | |
| "grad_norm": 0.0752110141233035, | |
| "learning_rate": 9.52710977228867e-05, | |
| "loss": 1.0291, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.5649847977523765, | |
| "grad_norm": 0.07768363081585787, | |
| "learning_rate": 9.473419430753864e-05, | |
| "loss": 0.9735, | |
| "step": 1835 | |
| }, | |
| { | |
| "epoch": 0.5665242658661432, | |
| "grad_norm": 0.07642437297948991, | |
| "learning_rate": 9.419744306712197e-05, | |
| "loss": 1.0035, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.56806373397991, | |
| "grad_norm": 0.0725535618760288, | |
| "learning_rate": 9.3660859513049e-05, | |
| "loss": 1.0624, | |
| "step": 1845 | |
| }, | |
| { | |
| "epoch": 0.5696032020936767, | |
| "grad_norm": 0.075838714661654, | |
| "learning_rate": 9.312445915188609e-05, | |
| "loss": 1.0273, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.5711426702074434, | |
| "grad_norm": 0.07494133610203221, | |
| "learning_rate": 9.258825748490558e-05, | |
| "loss": 1.043, | |
| "step": 1855 | |
| }, | |
| { | |
| "epoch": 0.5726821383212101, | |
| "grad_norm": 0.0774699889487116, | |
| "learning_rate": 9.205227000763788e-05, | |
| "loss": 1.0386, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.5742216064349767, | |
| "grad_norm": 0.0767041878914581, | |
| "learning_rate": 9.151651220942349e-05, | |
| "loss": 1.0475, | |
| "step": 1865 | |
| }, | |
| { | |
| "epoch": 0.5757610745487434, | |
| "grad_norm": 0.07367320031783889, | |
| "learning_rate": 9.098099957296552e-05, | |
| "loss": 1.0356, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.5773005426625101, | |
| "grad_norm": 0.07237560796588688, | |
| "learning_rate": 9.044574757388224e-05, | |
| "loss": 1.0291, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 0.5788400107762768, | |
| "grad_norm": 0.0733597412062657, | |
| "learning_rate": 8.991077168025976e-05, | |
| "loss": 1.0289, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.5803794788900435, | |
| "grad_norm": 0.0781082222836356, | |
| "learning_rate": 8.937608735220527e-05, | |
| "loss": 1.0411, | |
| "step": 1885 | |
| }, | |
| { | |
| "epoch": 0.5819189470038102, | |
| "grad_norm": 0.0787222190348577, | |
| "learning_rate": 8.884171004139996e-05, | |
| "loss": 1.0176, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.5834584151175769, | |
| "grad_norm": 0.07114468470409495, | |
| "learning_rate": 8.830765519065262e-05, | |
| "loss": 0.9838, | |
| "step": 1895 | |
| }, | |
| { | |
| "epoch": 0.5849978832313436, | |
| "grad_norm": 0.08086984212119945, | |
| "learning_rate": 8.777393823345343e-05, | |
| "loss": 1.0438, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.5865373513451103, | |
| "grad_norm": 0.0703832911854875, | |
| "learning_rate": 8.724057459352784e-05, | |
| "loss": 0.9889, | |
| "step": 1905 | |
| }, | |
| { | |
| "epoch": 0.5880768194588769, | |
| "grad_norm": 0.06956832590218136, | |
| "learning_rate": 8.670757968439086e-05, | |
| "loss": 1.0573, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 0.5896162875726436, | |
| "grad_norm": 0.07709995404199901, | |
| "learning_rate": 8.617496890890179e-05, | |
| "loss": 1.0277, | |
| "step": 1915 | |
| }, | |
| { | |
| "epoch": 0.5911557556864103, | |
| "grad_norm": 0.07724046895867277, | |
| "learning_rate": 8.564275765881887e-05, | |
| "loss": 1.0349, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.592695223800177, | |
| "grad_norm": 0.0743764979962109, | |
| "learning_rate": 8.511096131435454e-05, | |
| "loss": 1.0117, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 0.5942346919139437, | |
| "grad_norm": 0.07389820884013973, | |
| "learning_rate": 8.457959524373109e-05, | |
| "loss": 1.025, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 0.5957741600277104, | |
| "grad_norm": 0.07448602446253362, | |
| "learning_rate": 8.404867480273636e-05, | |
| "loss": 1.0524, | |
| "step": 1935 | |
| }, | |
| { | |
| "epoch": 0.5973136281414771, | |
| "grad_norm": 0.07016834564183058, | |
| "learning_rate": 8.351821533428023e-05, | |
| "loss": 1.0253, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.5988530962552439, | |
| "grad_norm": 0.07324470240300807, | |
| "learning_rate": 8.298823216795093e-05, | |
| "loss": 1.0454, | |
| "step": 1945 | |
| }, | |
| { | |
| "epoch": 0.6003925643690106, | |
| "grad_norm": 0.07179143590884257, | |
| "learning_rate": 8.245874061957224e-05, | |
| "loss": 1.0349, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.6019320324827772, | |
| "grad_norm": 0.07332238543813964, | |
| "learning_rate": 8.192975599076078e-05, | |
| "loss": 1.0112, | |
| "step": 1955 | |
| }, | |
| { | |
| "epoch": 0.6034715005965439, | |
| "grad_norm": 0.06832929405392676, | |
| "learning_rate": 8.140129356848387e-05, | |
| "loss": 1.0159, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.6050109687103106, | |
| "grad_norm": 0.07163605823180465, | |
| "learning_rate": 8.087336862461783e-05, | |
| "loss": 1.0064, | |
| "step": 1965 | |
| }, | |
| { | |
| "epoch": 0.6065504368240773, | |
| "grad_norm": 0.07827638868021947, | |
| "learning_rate": 8.034599641550642e-05, | |
| "loss": 1.0431, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 0.608089904937844, | |
| "grad_norm": 0.07793183715870357, | |
| "learning_rate": 7.981919218152016e-05, | |
| "loss": 0.9968, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 0.6096293730516107, | |
| "grad_norm": 0.07306876363104758, | |
| "learning_rate": 7.929297114661581e-05, | |
| "loss": 1.0114, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.6111688411653774, | |
| "grad_norm": 0.07438965485093788, | |
| "learning_rate": 7.876734851789643e-05, | |
| "loss": 1.042, | |
| "step": 1985 | |
| }, | |
| { | |
| "epoch": 0.6127083092791441, | |
| "grad_norm": 0.07813162760393345, | |
| "learning_rate": 7.824233948517185e-05, | |
| "loss": 1.0437, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.6142477773929107, | |
| "grad_norm": 0.07126718370690863, | |
| "learning_rate": 7.771795922051999e-05, | |
| "loss": 1.0444, | |
| "step": 1995 | |
| }, | |
| { | |
| "epoch": 0.6157872455066774, | |
| "grad_norm": 0.0756263745043903, | |
| "learning_rate": 7.719422287784798e-05, | |
| "loss": 1.0138, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.6157872455066774, | |
| "eval_loss": 1.02396821975708, | |
| "eval_runtime": 3800.6654, | |
| "eval_samples_per_second": 6.08, | |
| "eval_steps_per_second": 0.38, | |
| "step": 2000 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 3247, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 2.3416021014544384e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |