| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 49.57446808510638, | |
| "eval_steps": 500, | |
| "global_step": 675, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.999990671457219e-06, | |
| "loss": 2.0607, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.9997667899113055e-06, | |
| "loss": 2.0852, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.999067203154777e-06, | |
| "loss": 2.0685, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 2.0233097076416016, | |
| "eval_runtime": 4.0604, | |
| "eval_samples_per_second": 20.441, | |
| "eval_steps_per_second": 1.478, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 4.997901370250966e-06, | |
| "loss": 2.0386, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 4.99626950870707e-06, | |
| "loss": 2.0152, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 4.994171922976349e-06, | |
| "loss": 1.9972, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "eval_loss": 1.9437636137008667, | |
| "eval_runtime": 3.9692, | |
| "eval_samples_per_second": 20.911, | |
| "eval_steps_per_second": 1.512, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 4.991609004401324e-06, | |
| "loss": 1.956, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 4.988581231140772e-06, | |
| "loss": 1.9288, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 4.985089168080509e-06, | |
| "loss": 1.9109, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "eval_loss": 1.8719902038574219, | |
| "eval_runtime": 3.9854, | |
| "eval_samples_per_second": 20.826, | |
| "eval_steps_per_second": 1.505, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 4.981133466728004e-06, | |
| "loss": 1.8712, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 4.976714865090827e-06, | |
| "loss": 1.8583, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "eval_loss": 1.809607744216919, | |
| "eval_runtime": 3.9774, | |
| "eval_samples_per_second": 20.868, | |
| "eval_steps_per_second": 1.509, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 4.971834187538963e-06, | |
| "loss": 1.843, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 4.966492344651006e-06, | |
| "loss": 1.8171, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 4.960690333044279e-06, | |
| "loss": 1.7903, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "eval_loss": 1.7595775127410889, | |
| "eval_runtime": 3.9935, | |
| "eval_samples_per_second": 20.784, | |
| "eval_steps_per_second": 1.502, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 4.954429235188897e-06, | |
| "loss": 1.7816, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "learning_rate": 4.947710219205808e-06, | |
| "loss": 1.765, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "learning_rate": 4.940534538648862e-06, | |
| "loss": 1.7454, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "eval_loss": 1.7169337272644043, | |
| "eval_runtime": 3.9846, | |
| "eval_samples_per_second": 20.83, | |
| "eval_steps_per_second": 1.506, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 6.17, | |
| "learning_rate": 4.932903532270939e-06, | |
| "loss": 1.7242, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 6.38, | |
| "learning_rate": 4.924818623774178e-06, | |
| "loss": 1.7146, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "eval_loss": 1.6789494752883911, | |
| "eval_runtime": 3.9897, | |
| "eval_samples_per_second": 20.803, | |
| "eval_steps_per_second": 1.504, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 4.916281321544362e-06, | |
| "loss": 1.7114, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 7.23, | |
| "learning_rate": 4.907293218369499e-06, | |
| "loss": 1.6893, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 7.45, | |
| "learning_rate": 4.897855991142658e-06, | |
| "loss": 1.6737, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 7.57, | |
| "eval_loss": 1.6394565105438232, | |
| "eval_runtime": 3.9863, | |
| "eval_samples_per_second": 20.821, | |
| "eval_steps_per_second": 1.505, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 8.09, | |
| "learning_rate": 4.8879714005491205e-06, | |
| "loss": 1.6691, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "learning_rate": 4.8776412907378845e-06, | |
| "loss": 1.6507, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 8.51, | |
| "learning_rate": 4.8668675889776095e-06, | |
| "loss": 1.6289, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "eval_loss": 1.605614185333252, | |
| "eval_runtime": 4.0005, | |
| "eval_samples_per_second": 20.748, | |
| "eval_steps_per_second": 1.5, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 9.15, | |
| "learning_rate": 4.855652305297052e-06, | |
| "loss": 1.6312, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "learning_rate": 4.843997532110051e-06, | |
| "loss": 1.5965, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 9.57, | |
| "learning_rate": 4.83190544382516e-06, | |
| "loss": 1.5934, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 9.57, | |
| "eval_loss": 1.5665417909622192, | |
| "eval_runtime": 3.9832, | |
| "eval_samples_per_second": 20.838, | |
| "eval_steps_per_second": 1.506, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 10.21, | |
| "learning_rate": 4.819378296439962e-06, | |
| "loss": 1.5634, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 10.43, | |
| "learning_rate": 4.80641842712018e-06, | |
| "loss": 1.565, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 10.55, | |
| "eval_loss": 1.5258013010025024, | |
| "eval_runtime": 3.9933, | |
| "eval_samples_per_second": 20.785, | |
| "eval_steps_per_second": 1.503, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 11.06, | |
| "learning_rate": 4.793028253763633e-06, | |
| "loss": 1.5491, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 11.28, | |
| "learning_rate": 4.7792102745491345e-06, | |
| "loss": 1.5353, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 11.49, | |
| "learning_rate": 4.764967067470409e-06, | |
| "loss": 1.519, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 11.57, | |
| "eval_loss": 1.4776073694229126, | |
| "eval_runtime": 3.9813, | |
| "eval_samples_per_second": 20.847, | |
| "eval_steps_per_second": 1.507, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 12.13, | |
| "learning_rate": 4.750301289855128e-06, | |
| "loss": 1.4823, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 12.34, | |
| "learning_rate": 4.735215677869129e-06, | |
| "loss": 1.4795, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 12.55, | |
| "learning_rate": 4.7197130460059385e-06, | |
| "loss": 1.4593, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 12.55, | |
| "eval_loss": 1.4280617237091064, | |
| "eval_runtime": 3.9852, | |
| "eval_samples_per_second": 20.827, | |
| "eval_steps_per_second": 1.506, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 13.19, | |
| "learning_rate": 4.7037962865616795e-06, | |
| "loss": 1.4393, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 13.4, | |
| "learning_rate": 4.687468369095457e-06, | |
| "loss": 1.4156, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 13.57, | |
| "eval_loss": 1.3676358461380005, | |
| "eval_runtime": 3.9729, | |
| "eval_samples_per_second": 20.892, | |
| "eval_steps_per_second": 1.51, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 14.04, | |
| "learning_rate": 4.6707323398753346e-06, | |
| "loss": 1.3898, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 14.26, | |
| "learning_rate": 4.6535913213100005e-06, | |
| "loss": 1.3671, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 14.47, | |
| "learning_rate": 4.636048511366222e-06, | |
| "loss": 1.3512, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 14.55, | |
| "eval_loss": 1.3222225904464722, | |
| "eval_runtime": 4.0174, | |
| "eval_samples_per_second": 20.66, | |
| "eval_steps_per_second": 1.494, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 15.11, | |
| "learning_rate": 4.618107182972209e-06, | |
| "loss": 1.3308, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 15.32, | |
| "learning_rate": 4.599770683406992e-06, | |
| "loss": 1.3194, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 15.53, | |
| "learning_rate": 4.58104243367592e-06, | |
| "loss": 1.3146, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 15.57, | |
| "eval_loss": 1.2824859619140625, | |
| "eval_runtime": 3.9833, | |
| "eval_samples_per_second": 20.837, | |
| "eval_steps_per_second": 1.506, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 16.17, | |
| "learning_rate": 4.561925927872421e-06, | |
| "loss": 1.3001, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 16.38, | |
| "learning_rate": 4.542424732526105e-06, | |
| "loss": 1.2798, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 16.55, | |
| "eval_loss": 1.2492066621780396, | |
| "eval_runtime": 3.9849, | |
| "eval_samples_per_second": 20.829, | |
| "eval_steps_per_second": 1.506, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 17.02, | |
| "learning_rate": 4.522542485937369e-06, | |
| "loss": 1.259, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 17.23, | |
| "learning_rate": 4.5022828974986044e-06, | |
| "loss": 1.2516, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 17.45, | |
| "learning_rate": 4.481649747002146e-06, | |
| "loss": 1.2532, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 17.57, | |
| "eval_loss": 1.22245192527771, | |
| "eval_runtime": 3.9686, | |
| "eval_samples_per_second": 20.914, | |
| "eval_steps_per_second": 1.512, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 18.09, | |
| "learning_rate": 4.460646883935079e-06, | |
| "loss": 1.2491, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 18.3, | |
| "learning_rate": 4.43927822676105e-06, | |
| "loss": 1.2058, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 18.51, | |
| "learning_rate": 4.417547762189207e-06, | |
| "loss": 1.2277, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 18.55, | |
| "eval_loss": 1.2032711505889893, | |
| "eval_runtime": 3.9983, | |
| "eval_samples_per_second": 20.759, | |
| "eval_steps_per_second": 1.501, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 19.15, | |
| "learning_rate": 4.395459544430407e-06, | |
| "loss": 1.2244, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 19.36, | |
| "learning_rate": 4.373017694440828e-06, | |
| "loss": 1.1986, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 19.57, | |
| "learning_rate": 4.35022639915313e-06, | |
| "loss": 1.208, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 19.57, | |
| "eval_loss": 1.18324875831604, | |
| "eval_runtime": 3.9861, | |
| "eval_samples_per_second": 20.822, | |
| "eval_steps_per_second": 1.505, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 20.21, | |
| "learning_rate": 4.32708991069531e-06, | |
| "loss": 1.1919, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 20.43, | |
| "learning_rate": 4.30361254559739e-06, | |
| "loss": 1.1944, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 20.55, | |
| "eval_loss": 1.1732494831085205, | |
| "eval_runtime": 3.9909, | |
| "eval_samples_per_second": 20.797, | |
| "eval_steps_per_second": 1.503, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 21.06, | |
| "learning_rate": 4.279798683986084e-06, | |
| "loss": 1.18, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 21.28, | |
| "learning_rate": 4.255652768767619e-06, | |
| "loss": 1.1806, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 21.49, | |
| "learning_rate": 4.2311793047988145e-06, | |
| "loss": 1.1799, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 21.57, | |
| "eval_loss": 1.158596158027649, | |
| "eval_runtime": 3.993, | |
| "eval_samples_per_second": 20.787, | |
| "eval_steps_per_second": 1.503, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 22.13, | |
| "learning_rate": 4.206382858046636e-06, | |
| "loss": 1.1803, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 22.34, | |
| "learning_rate": 4.181268054736319e-06, | |
| "loss": 1.1532, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 22.55, | |
| "learning_rate": 4.15583958048827e-06, | |
| "loss": 1.1621, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 22.55, | |
| "eval_loss": 1.1493983268737793, | |
| "eval_runtime": 3.9997, | |
| "eval_samples_per_second": 20.752, | |
| "eval_steps_per_second": 1.5, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 23.19, | |
| "learning_rate": 4.130102179443877e-06, | |
| "loss": 1.1681, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 23.4, | |
| "learning_rate": 4.104060653380403e-06, | |
| "loss": 1.1448, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 23.57, | |
| "eval_loss": 1.1393245458602905, | |
| "eval_runtime": 3.9913, | |
| "eval_samples_per_second": 20.795, | |
| "eval_steps_per_second": 1.503, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 24.04, | |
| "learning_rate": 4.077719860815132e-06, | |
| "loss": 1.1513, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 24.26, | |
| "learning_rate": 4.051084716098921e-06, | |
| "loss": 1.1441, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 24.47, | |
| "learning_rate": 4.024160188499337e-06, | |
| "loss": 1.1564, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 24.55, | |
| "eval_loss": 1.1301108598709106, | |
| "eval_runtime": 3.9936, | |
| "eval_samples_per_second": 20.783, | |
| "eval_steps_per_second": 1.502, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 25.11, | |
| "learning_rate": 3.996951301273556e-06, | |
| "loss": 1.1396, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 25.32, | |
| "learning_rate": 3.969463130731183e-06, | |
| "loss": 1.1346, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 25.53, | |
| "learning_rate": 3.941700805287169e-06, | |
| "loss": 1.1293, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 25.57, | |
| "eval_loss": 1.1233478784561157, | |
| "eval_runtime": 3.9814, | |
| "eval_samples_per_second": 20.847, | |
| "eval_steps_per_second": 1.507, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 26.17, | |
| "learning_rate": 3.913669504505015e-06, | |
| "loss": 1.1483, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 26.38, | |
| "learning_rate": 3.8853744581304376e-06, | |
| "loss": 1.1228, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 26.55, | |
| "eval_loss": 1.1160305738449097, | |
| "eval_runtime": 3.9869, | |
| "eval_samples_per_second": 20.818, | |
| "eval_steps_per_second": 1.505, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 27.02, | |
| "learning_rate": 3.856820945115655e-06, | |
| "loss": 1.1261, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 27.23, | |
| "learning_rate": 3.828014292634508e-06, | |
| "loss": 1.1307, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 27.45, | |
| "learning_rate": 3.798959875088584e-06, | |
| "loss": 1.1266, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 27.57, | |
| "eval_loss": 1.1105799674987793, | |
| "eval_runtime": 3.9806, | |
| "eval_samples_per_second": 20.851, | |
| "eval_steps_per_second": 1.507, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 28.09, | |
| "learning_rate": 3.769663113104516e-06, | |
| "loss": 1.1051, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 28.3, | |
| "learning_rate": 3.7401294725226707e-06, | |
| "loss": 1.1152, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 28.51, | |
| "learning_rate": 3.7103644633774015e-06, | |
| "loss": 1.1159, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 28.55, | |
| "eval_loss": 1.1047321557998657, | |
| "eval_runtime": 3.9941, | |
| "eval_samples_per_second": 20.781, | |
| "eval_steps_per_second": 1.502, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 29.15, | |
| "learning_rate": 3.680373638869047e-06, | |
| "loss": 1.1149, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 29.36, | |
| "learning_rate": 3.650162594327881e-06, | |
| "loss": 1.0942, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 29.57, | |
| "learning_rate": 3.6197369661702052e-06, | |
| "loss": 1.125, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 29.57, | |
| "eval_loss": 1.098873496055603, | |
| "eval_runtime": 3.9772, | |
| "eval_samples_per_second": 20.869, | |
| "eval_steps_per_second": 1.509, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 30.21, | |
| "learning_rate": 3.589102430846773e-06, | |
| "loss": 1.1067, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 30.43, | |
| "learning_rate": 3.5582647037837446e-06, | |
| "loss": 1.094, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 30.55, | |
| "eval_loss": 1.0941215753555298, | |
| "eval_runtime": 3.9808, | |
| "eval_samples_per_second": 20.85, | |
| "eval_steps_per_second": 1.507, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 31.06, | |
| "learning_rate": 3.527229538316371e-06, | |
| "loss": 1.1033, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 31.28, | |
| "learning_rate": 3.4960027246156043e-06, | |
| "loss": 1.0886, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 31.49, | |
| "learning_rate": 3.4645900886078388e-06, | |
| "loss": 1.1077, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 31.57, | |
| "eval_loss": 1.0902585983276367, | |
| "eval_runtime": 3.9794, | |
| "eval_samples_per_second": 20.857, | |
| "eval_steps_per_second": 1.508, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 32.13, | |
| "learning_rate": 3.432997490887979e-06, | |
| "loss": 1.1054, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 32.34, | |
| "learning_rate": 3.4012308256260366e-06, | |
| "loss": 1.0936, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 32.55, | |
| "learning_rate": 3.369296019467473e-06, | |
| "loss": 1.0874, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 32.55, | |
| "eval_loss": 1.0833797454833984, | |
| "eval_runtime": 3.9868, | |
| "eval_samples_per_second": 20.819, | |
| "eval_steps_per_second": 1.505, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 33.19, | |
| "learning_rate": 3.3371990304274654e-06, | |
| "loss": 1.0687, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 33.4, | |
| "learning_rate": 3.304945846779346e-06, | |
| "loss": 1.0957, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 33.57, | |
| "eval_loss": 1.0769224166870117, | |
| "eval_runtime": 3.9835, | |
| "eval_samples_per_second": 20.836, | |
| "eval_steps_per_second": 1.506, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 34.04, | |
| "learning_rate": 3.272542485937369e-06, | |
| "loss": 1.0894, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 34.26, | |
| "learning_rate": 3.239994993334059e-06, | |
| "loss": 1.0906, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 34.47, | |
| "learning_rate": 3.207309441292325e-06, | |
| "loss": 1.0755, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 34.55, | |
| "eval_loss": 1.0749725103378296, | |
| "eval_runtime": 3.9797, | |
| "eval_samples_per_second": 20.856, | |
| "eval_steps_per_second": 1.508, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 35.11, | |
| "learning_rate": 3.174491927892561e-06, | |
| "loss": 1.0862, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 35.32, | |
| "learning_rate": 3.1415485758349344e-06, | |
| "loss": 1.0767, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 35.53, | |
| "learning_rate": 3.1084855312970897e-06, | |
| "loss": 1.0705, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 35.57, | |
| "eval_loss": 1.0719436407089233, | |
| "eval_runtime": 3.9776, | |
| "eval_samples_per_second": 20.867, | |
| "eval_steps_per_second": 1.508, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 36.17, | |
| "learning_rate": 3.0753089627874668e-06, | |
| "loss": 1.0786, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 36.38, | |
| "learning_rate": 3.0420250599944525e-06, | |
| "loss": 1.0749, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 36.55, | |
| "eval_loss": 1.0687665939331055, | |
| "eval_runtime": 3.9811, | |
| "eval_samples_per_second": 20.848, | |
| "eval_steps_per_second": 1.507, | |
| "step": 499 | |
| }, | |
| { | |
| "epoch": 37.02, | |
| "learning_rate": 3.0086400326315853e-06, | |
| "loss": 1.0646, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 37.23, | |
| "learning_rate": 2.9751601092790185e-06, | |
| "loss": 1.0734, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 37.45, | |
| "learning_rate": 2.941591536221469e-06, | |
| "loss": 1.0742, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 37.57, | |
| "eval_loss": 1.064079761505127, | |
| "eval_runtime": 3.9781, | |
| "eval_samples_per_second": 20.864, | |
| "eval_steps_per_second": 1.508, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 38.09, | |
| "learning_rate": 2.907940576282856e-06, | |
| "loss": 1.0547, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 38.3, | |
| "learning_rate": 2.8742135076578608e-06, | |
| "loss": 1.0686, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 38.51, | |
| "learning_rate": 2.840416622740617e-06, | |
| "loss": 1.064, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 38.55, | |
| "eval_loss": 1.0626107454299927, | |
| "eval_runtime": 3.9847, | |
| "eval_samples_per_second": 20.829, | |
| "eval_steps_per_second": 1.506, | |
| "step": 526 | |
| }, | |
| { | |
| "epoch": 39.15, | |
| "learning_rate": 2.8065562269507464e-06, | |
| "loss": 1.0739, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 39.36, | |
| "learning_rate": 2.7726386375569748e-06, | |
| "loss": 1.0569, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 39.57, | |
| "learning_rate": 2.7386701824985257e-06, | |
| "loss": 1.0569, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 39.57, | |
| "eval_loss": 1.0592881441116333, | |
| "eval_runtime": 3.9656, | |
| "eval_samples_per_second": 20.93, | |
| "eval_steps_per_second": 1.513, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 40.21, | |
| "learning_rate": 2.7046571992045334e-06, | |
| "loss": 1.0466, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 40.43, | |
| "learning_rate": 2.670606033411678e-06, | |
| "loss": 1.0686, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 40.55, | |
| "eval_loss": 1.0553538799285889, | |
| "eval_runtime": 3.9786, | |
| "eval_samples_per_second": 20.862, | |
| "eval_steps_per_second": 1.508, | |
| "step": 553 | |
| }, | |
| { | |
| "epoch": 41.06, | |
| "learning_rate": 2.636523037980275e-06, | |
| "loss": 1.0564, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 41.28, | |
| "learning_rate": 2.602414571709036e-06, | |
| "loss": 1.0523, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 41.49, | |
| "learning_rate": 2.5682869981487154e-06, | |
| "loss": 1.059, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 41.57, | |
| "eval_loss": 1.0516701936721802, | |
| "eval_runtime": 3.9778, | |
| "eval_samples_per_second": 20.866, | |
| "eval_steps_per_second": 1.508, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 42.13, | |
| "learning_rate": 2.5341466844148775e-06, | |
| "loss": 1.0414, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 42.34, | |
| "learning_rate": 2.5e-06, | |
| "loss": 1.0394, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 42.55, | |
| "learning_rate": 2.465853315585123e-06, | |
| "loss": 1.0588, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 42.55, | |
| "eval_loss": 1.0469306707382202, | |
| "eval_runtime": 4.0006, | |
| "eval_samples_per_second": 20.747, | |
| "eval_steps_per_second": 1.5, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 43.19, | |
| "learning_rate": 2.431713001851286e-06, | |
| "loss": 1.0442, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 43.4, | |
| "learning_rate": 2.3975854282909645e-06, | |
| "loss": 1.0447, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 43.57, | |
| "eval_loss": 1.0471419095993042, | |
| "eval_runtime": 3.9796, | |
| "eval_samples_per_second": 20.856, | |
| "eval_steps_per_second": 1.508, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 44.04, | |
| "learning_rate": 2.3634769620197253e-06, | |
| "loss": 1.0573, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 44.26, | |
| "learning_rate": 2.3293939665883233e-06, | |
| "loss": 1.0478, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 44.47, | |
| "learning_rate": 2.2953428007954682e-06, | |
| "loss": 1.0356, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 44.55, | |
| "eval_loss": 1.0420819520950317, | |
| "eval_runtime": 3.9978, | |
| "eval_samples_per_second": 20.762, | |
| "eval_steps_per_second": 1.501, | |
| "step": 607 | |
| }, | |
| { | |
| "epoch": 45.11, | |
| "learning_rate": 2.261329817501475e-06, | |
| "loss": 1.0465, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 45.32, | |
| "learning_rate": 2.2273613624430256e-06, | |
| "loss": 1.0389, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 45.53, | |
| "learning_rate": 2.1934437730492544e-06, | |
| "loss": 1.0431, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 45.57, | |
| "eval_loss": 1.0415891408920288, | |
| "eval_runtime": 3.9789, | |
| "eval_samples_per_second": 20.86, | |
| "eval_steps_per_second": 1.508, | |
| "step": 621 | |
| }, | |
| { | |
| "epoch": 46.17, | |
| "learning_rate": 2.159583377259384e-06, | |
| "loss": 1.045, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 46.38, | |
| "learning_rate": 2.1257864923421405e-06, | |
| "loss": 1.0195, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 46.55, | |
| "eval_loss": 1.038739562034607, | |
| "eval_runtime": 3.9849, | |
| "eval_samples_per_second": 20.829, | |
| "eval_steps_per_second": 1.506, | |
| "step": 634 | |
| }, | |
| { | |
| "epoch": 47.02, | |
| "learning_rate": 2.092059423717145e-06, | |
| "loss": 1.0458, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 47.23, | |
| "learning_rate": 2.0584084637785316e-06, | |
| "loss": 1.0347, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 47.45, | |
| "learning_rate": 2.0248398907209827e-06, | |
| "loss": 1.0326, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 47.57, | |
| "eval_loss": 1.0356136560440063, | |
| "eval_runtime": 3.9756, | |
| "eval_samples_per_second": 20.877, | |
| "eval_steps_per_second": 1.509, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 48.09, | |
| "learning_rate": 1.991359967368416e-06, | |
| "loss": 1.0351, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 48.3, | |
| "learning_rate": 1.957974940005548e-06, | |
| "loss": 1.0422, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 48.51, | |
| "learning_rate": 1.9246910372125345e-06, | |
| "loss": 1.0227, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 48.55, | |
| "eval_loss": 1.0340739488601685, | |
| "eval_runtime": 3.9883, | |
| "eval_samples_per_second": 20.811, | |
| "eval_steps_per_second": 1.504, | |
| "step": 661 | |
| }, | |
| { | |
| "epoch": 49.15, | |
| "learning_rate": 1.8915144687029107e-06, | |
| "loss": 1.0192, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 49.36, | |
| "learning_rate": 1.8584514241650667e-06, | |
| "loss": 1.0328, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 49.57, | |
| "learning_rate": 1.8255080721074391e-06, | |
| "loss": 1.0403, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 49.57, | |
| "eval_loss": 1.0316752195358276, | |
| "eval_runtime": 3.9751, | |
| "eval_samples_per_second": 20.88, | |
| "eval_steps_per_second": 1.509, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 49.57, | |
| "step": 675, | |
| "total_flos": 6306831714484224.0, | |
| "train_loss": 1.2869272242652046, | |
| "train_runtime": 6519.8949, | |
| "train_samples_per_second": 5.721, | |
| "train_steps_per_second": 0.176 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 1150, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "total_flos": 6306831714484224.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |