| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "global_step": 2233188, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.977610483309063e-05, | |
| "loss": 0.0854, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.955220966618126e-05, | |
| "loss": 0.0801, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.9328314499271894e-05, | |
| "loss": 0.082, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.910441933236253e-05, | |
| "loss": 0.0851, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.8880524165453154e-05, | |
| "loss": 0.0858, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.865662899854379e-05, | |
| "loss": 0.0777, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.843273383163442e-05, | |
| "loss": 0.0853, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.8208838664725045e-05, | |
| "loss": 0.0838, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.798494349781568e-05, | |
| "loss": 0.084, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.776104833090631e-05, | |
| "loss": 0.0794, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.753715316399694e-05, | |
| "loss": 0.0805, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.7313257997087574e-05, | |
| "loss": 0.0876, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.708936283017821e-05, | |
| "loss": 0.0773, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.6865467663268834e-05, | |
| "loss": 0.0846, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.6641572496359465e-05, | |
| "loss": 0.0867, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 0.07421331852674484, | |
| "eval_runtime": 1684.9579, | |
| "eval_samples_per_second": 36.816, | |
| "eval_steps_per_second": 36.816, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.64176773294501e-05, | |
| "loss": 0.0779, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.6193782162540726e-05, | |
| "loss": 0.0795, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.596988699563136e-05, | |
| "loss": 0.082, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.574599182872199e-05, | |
| "loss": 0.0821, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.5522096661812623e-05, | |
| "loss": 0.0787, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.5298201494903254e-05, | |
| "loss": 0.0803, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.5074306327993884e-05, | |
| "loss": 0.0788, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.4850411161084515e-05, | |
| "loss": 0.0822, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.4626515994175145e-05, | |
| "loss": 0.0782, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.4402620827265775e-05, | |
| "loss": 0.0804, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.4178725660356406e-05, | |
| "loss": 0.0778, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.3954830493447036e-05, | |
| "loss": 0.0772, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.3730935326537667e-05, | |
| "loss": 0.0819, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.35070401596283e-05, | |
| "loss": 0.0741, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.3283144992718934e-05, | |
| "loss": 0.0783, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 0.06954144686460495, | |
| "eval_runtime": 1688.3337, | |
| "eval_samples_per_second": 36.742, | |
| "eval_steps_per_second": 36.742, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.3059249825809564e-05, | |
| "loss": 0.072, | |
| "step": 155000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.2835354658900195e-05, | |
| "loss": 0.0824, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.2611459491990825e-05, | |
| "loss": 0.0779, | |
| "step": 165000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.2387564325081456e-05, | |
| "loss": 0.0733, | |
| "step": 170000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.2163669158172086e-05, | |
| "loss": 0.0784, | |
| "step": 175000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.1939773991262716e-05, | |
| "loss": 0.0745, | |
| "step": 180000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.171587882435335e-05, | |
| "loss": 0.0778, | |
| "step": 185000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.149198365744398e-05, | |
| "loss": 0.0753, | |
| "step": 190000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.1268088490534614e-05, | |
| "loss": 0.0735, | |
| "step": 195000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.104419332362524e-05, | |
| "loss": 0.072, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.082029815671587e-05, | |
| "loss": 0.0752, | |
| "step": 205000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.0596402989806505e-05, | |
| "loss": 0.0759, | |
| "step": 210000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.037250782289713e-05, | |
| "loss": 0.0715, | |
| "step": 215000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.0148612655987766e-05, | |
| "loss": 0.0734, | |
| "step": 220000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3.9924717489078396e-05, | |
| "loss": 0.0719, | |
| "step": 225000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 0.07320380210876465, | |
| "eval_runtime": 1689.2398, | |
| "eval_samples_per_second": 36.722, | |
| "eval_steps_per_second": 36.722, | |
| "step": 225000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.970082232216903e-05, | |
| "loss": 0.0782, | |
| "step": 230000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.947692715525966e-05, | |
| "loss": 0.0689, | |
| "step": 235000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.925303198835029e-05, | |
| "loss": 0.0721, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.902913682144092e-05, | |
| "loss": 0.0717, | |
| "step": 245000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.880524165453155e-05, | |
| "loss": 0.0751, | |
| "step": 250000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.8581346487622186e-05, | |
| "loss": 0.075, | |
| "step": 255000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.835745132071281e-05, | |
| "loss": 0.0774, | |
| "step": 260000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.8133556153803446e-05, | |
| "loss": 0.0729, | |
| "step": 265000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.790966098689408e-05, | |
| "loss": 0.0666, | |
| "step": 270000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 3.76857658199847e-05, | |
| "loss": 0.0668, | |
| "step": 275000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 3.746187065307534e-05, | |
| "loss": 0.0688, | |
| "step": 280000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.723797548616597e-05, | |
| "loss": 0.0732, | |
| "step": 285000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.70140803192566e-05, | |
| "loss": 0.0729, | |
| "step": 290000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.679018515234723e-05, | |
| "loss": 0.0746, | |
| "step": 295000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.6566289985437866e-05, | |
| "loss": 0.0743, | |
| "step": 300000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 0.06632131338119507, | |
| "eval_runtime": 1749.4291, | |
| "eval_samples_per_second": 35.459, | |
| "eval_steps_per_second": 35.459, | |
| "step": 300000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.634239481852849e-05, | |
| "loss": 0.0689, | |
| "step": 305000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.611849965161912e-05, | |
| "loss": 0.0705, | |
| "step": 310000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.589460448470976e-05, | |
| "loss": 0.0691, | |
| "step": 315000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 3.567070931780038e-05, | |
| "loss": 0.0673, | |
| "step": 320000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 3.544681415089102e-05, | |
| "loss": 0.0713, | |
| "step": 325000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3.522291898398165e-05, | |
| "loss": 0.0704, | |
| "step": 330000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3.499902381707228e-05, | |
| "loss": 0.0734, | |
| "step": 335000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3.477512865016291e-05, | |
| "loss": 0.0731, | |
| "step": 340000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 3.455123348325354e-05, | |
| "loss": 0.0682, | |
| "step": 345000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 3.432733831634417e-05, | |
| "loss": 0.0719, | |
| "step": 350000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.41034431494348e-05, | |
| "loss": 0.0724, | |
| "step": 355000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.387954798252544e-05, | |
| "loss": 0.0677, | |
| "step": 360000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 3.365565281561606e-05, | |
| "loss": 0.0697, | |
| "step": 365000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 3.343175764870669e-05, | |
| "loss": 0.0759, | |
| "step": 370000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.320786248179733e-05, | |
| "loss": 0.0659, | |
| "step": 375000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 0.06863044947385788, | |
| "eval_runtime": 1687.8956, | |
| "eval_samples_per_second": 36.752, | |
| "eval_steps_per_second": 36.752, | |
| "step": 375000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.298396731488795e-05, | |
| "loss": 0.0704, | |
| "step": 380000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.276007214797859e-05, | |
| "loss": 0.0711, | |
| "step": 385000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 3.253617698106922e-05, | |
| "loss": 0.0689, | |
| "step": 390000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 3.231228181415985e-05, | |
| "loss": 0.0689, | |
| "step": 395000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.208838664725048e-05, | |
| "loss": 0.0657, | |
| "step": 400000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.186449148034111e-05, | |
| "loss": 0.0695, | |
| "step": 405000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 3.164059631343174e-05, | |
| "loss": 0.07, | |
| "step": 410000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 3.141670114652237e-05, | |
| "loss": 0.0654, | |
| "step": 415000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 3.1192805979613e-05, | |
| "loss": 0.0668, | |
| "step": 420000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 3.096891081270363e-05, | |
| "loss": 0.0692, | |
| "step": 425000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 3.074501564579427e-05, | |
| "loss": 0.0692, | |
| "step": 430000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 3.052112047888489e-05, | |
| "loss": 0.0707, | |
| "step": 435000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 3.0297225311975523e-05, | |
| "loss": 0.0677, | |
| "step": 440000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 3.007333014506616e-05, | |
| "loss": 0.0721, | |
| "step": 445000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2.9849434978156787e-05, | |
| "loss": 0.0664, | |
| "step": 450000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 0.06826464831829071, | |
| "eval_runtime": 1692.5106, | |
| "eval_samples_per_second": 36.651, | |
| "eval_steps_per_second": 36.651, | |
| "step": 450000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 2.962553981124742e-05, | |
| "loss": 0.0647, | |
| "step": 455000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 2.940164464433805e-05, | |
| "loss": 0.0683, | |
| "step": 460000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 2.9177749477428685e-05, | |
| "loss": 0.0693, | |
| "step": 465000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 2.8953854310519312e-05, | |
| "loss": 0.0677, | |
| "step": 470000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 2.8729959143609942e-05, | |
| "loss": 0.0674, | |
| "step": 475000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 2.8506063976700576e-05, | |
| "loss": 0.0675, | |
| "step": 480000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 2.8282168809791203e-05, | |
| "loss": 0.0676, | |
| "step": 485000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 2.8058273642881837e-05, | |
| "loss": 0.066, | |
| "step": 490000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 2.7834378475972467e-05, | |
| "loss": 0.0692, | |
| "step": 495000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2.76104833090631e-05, | |
| "loss": 0.0709, | |
| "step": 500000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2.7386588142153728e-05, | |
| "loss": 0.0651, | |
| "step": 505000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2.716269297524436e-05, | |
| "loss": 0.0684, | |
| "step": 510000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2.6938797808334992e-05, | |
| "loss": 0.067, | |
| "step": 515000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.6714902641425623e-05, | |
| "loss": 0.0631, | |
| "step": 520000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.6491007474516256e-05, | |
| "loss": 0.0637, | |
| "step": 525000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 0.06799625605344772, | |
| "eval_runtime": 1690.2201, | |
| "eval_samples_per_second": 36.701, | |
| "eval_steps_per_second": 36.701, | |
| "step": 525000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.6267112307606883e-05, | |
| "loss": 0.0691, | |
| "step": 530000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.6043217140697517e-05, | |
| "loss": 0.0707, | |
| "step": 535000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.5819321973788147e-05, | |
| "loss": 0.0692, | |
| "step": 540000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.5595426806878774e-05, | |
| "loss": 0.067, | |
| "step": 545000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.5371531639969408e-05, | |
| "loss": 0.067, | |
| "step": 550000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.514763647306004e-05, | |
| "loss": 0.0734, | |
| "step": 555000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.492374130615067e-05, | |
| "loss": 0.0663, | |
| "step": 560000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 2.46998461392413e-05, | |
| "loss": 0.0689, | |
| "step": 565000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 2.4475950972331933e-05, | |
| "loss": 0.0642, | |
| "step": 570000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 2.4252055805422564e-05, | |
| "loss": 0.0684, | |
| "step": 575000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.4028160638513194e-05, | |
| "loss": 0.0696, | |
| "step": 580000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.3804265471603828e-05, | |
| "loss": 0.0693, | |
| "step": 585000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.3580370304694455e-05, | |
| "loss": 0.069, | |
| "step": 590000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.3356475137785085e-05, | |
| "loss": 0.066, | |
| "step": 595000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.313257997087572e-05, | |
| "loss": 0.0655, | |
| "step": 600000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 0.0641070306301117, | |
| "eval_runtime": 1688.8537, | |
| "eval_samples_per_second": 36.731, | |
| "eval_steps_per_second": 36.731, | |
| "step": 600000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.290868480396635e-05, | |
| "loss": 0.0659, | |
| "step": 605000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.268478963705698e-05, | |
| "loss": 0.0662, | |
| "step": 610000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.246089447014761e-05, | |
| "loss": 0.0689, | |
| "step": 615000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.2236999303238244e-05, | |
| "loss": 0.0676, | |
| "step": 620000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.201310413632887e-05, | |
| "loss": 0.0615, | |
| "step": 625000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.1789208969419504e-05, | |
| "loss": 0.0706, | |
| "step": 630000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 2.1565313802510135e-05, | |
| "loss": 0.064, | |
| "step": 635000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 2.1341418635600765e-05, | |
| "loss": 0.0711, | |
| "step": 640000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2.1117523468691396e-05, | |
| "loss": 0.0647, | |
| "step": 645000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2.089362830178203e-05, | |
| "loss": 0.0691, | |
| "step": 650000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 2.066973313487266e-05, | |
| "loss": 0.0652, | |
| "step": 655000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 2.0445837967963287e-05, | |
| "loss": 0.0631, | |
| "step": 660000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 2.022194280105392e-05, | |
| "loss": 0.063, | |
| "step": 665000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1.999804763414455e-05, | |
| "loss": 0.0683, | |
| "step": 670000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1.977415246723518e-05, | |
| "loss": 0.0676, | |
| "step": 675000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 0.0644209161400795, | |
| "eval_runtime": 1688.2291, | |
| "eval_samples_per_second": 36.744, | |
| "eval_steps_per_second": 36.744, | |
| "step": 675000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 1.9550257300325815e-05, | |
| "loss": 0.067, | |
| "step": 680000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 1.9326362133416445e-05, | |
| "loss": 0.0633, | |
| "step": 685000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.9102466966507072e-05, | |
| "loss": 0.067, | |
| "step": 690000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.8878571799597706e-05, | |
| "loss": 0.0642, | |
| "step": 695000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.8654676632688336e-05, | |
| "loss": 0.0647, | |
| "step": 700000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.8430781465778967e-05, | |
| "loss": 0.0683, | |
| "step": 705000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.82068862988696e-05, | |
| "loss": 0.0636, | |
| "step": 710000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.798299113196023e-05, | |
| "loss": 0.0682, | |
| "step": 715000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.775909596505086e-05, | |
| "loss": 0.0669, | |
| "step": 720000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.7535200798141492e-05, | |
| "loss": 0.0641, | |
| "step": 725000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.7311305631232122e-05, | |
| "loss": 0.0656, | |
| "step": 730000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.7087410464322753e-05, | |
| "loss": 0.0676, | |
| "step": 735000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.6863515297413386e-05, | |
| "loss": 0.0679, | |
| "step": 740000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.6639620130504017e-05, | |
| "loss": 0.0649, | |
| "step": 745000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.6415724963594647e-05, | |
| "loss": 0.0704, | |
| "step": 750000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 0.06448209285736084, | |
| "eval_runtime": 1685.6964, | |
| "eval_samples_per_second": 36.8, | |
| "eval_steps_per_second": 36.8, | |
| "step": 750000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.6191829796685277e-05, | |
| "loss": 0.0633, | |
| "step": 755000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.5967934629775908e-05, | |
| "loss": 0.0663, | |
| "step": 760000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.5744039462866538e-05, | |
| "loss": 0.065, | |
| "step": 765000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.5520144295957172e-05, | |
| "loss": 0.0668, | |
| "step": 770000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.5296249129047802e-05, | |
| "loss": 0.0651, | |
| "step": 775000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.5072353962138433e-05, | |
| "loss": 0.0671, | |
| "step": 780000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.4848458795229065e-05, | |
| "loss": 0.0666, | |
| "step": 785000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.4624563628319693e-05, | |
| "loss": 0.0715, | |
| "step": 790000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.4400668461410324e-05, | |
| "loss": 0.0665, | |
| "step": 795000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.4176773294500956e-05, | |
| "loss": 0.0635, | |
| "step": 800000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.3952878127591586e-05, | |
| "loss": 0.0674, | |
| "step": 805000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.3728982960682218e-05, | |
| "loss": 0.0645, | |
| "step": 810000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.350508779377285e-05, | |
| "loss": 0.0658, | |
| "step": 815000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.328119262686348e-05, | |
| "loss": 0.0676, | |
| "step": 820000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.305729745995411e-05, | |
| "loss": 0.0687, | |
| "step": 825000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 0.061014574021101, | |
| "eval_runtime": 1687.4471, | |
| "eval_samples_per_second": 36.761, | |
| "eval_steps_per_second": 36.761, | |
| "step": 825000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.2833402293044742e-05, | |
| "loss": 0.0679, | |
| "step": 830000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.2609507126135372e-05, | |
| "loss": 0.0683, | |
| "step": 835000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.2385611959226004e-05, | |
| "loss": 0.0702, | |
| "step": 840000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.2161716792316636e-05, | |
| "loss": 0.0652, | |
| "step": 845000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.1937821625407265e-05, | |
| "loss": 0.0636, | |
| "step": 850000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.1713926458497897e-05, | |
| "loss": 0.0637, | |
| "step": 855000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.1490031291588529e-05, | |
| "loss": 0.0628, | |
| "step": 860000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.126613612467916e-05, | |
| "loss": 0.0701, | |
| "step": 865000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.104224095776979e-05, | |
| "loss": 0.0663, | |
| "step": 870000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.081834579086042e-05, | |
| "loss": 0.0686, | |
| "step": 875000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.0594450623951052e-05, | |
| "loss": 0.0655, | |
| "step": 880000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.0370555457041682e-05, | |
| "loss": 0.0622, | |
| "step": 885000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.0146660290132313e-05, | |
| "loss": 0.0585, | |
| "step": 890000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 9.922765123222945e-06, | |
| "loss": 0.0658, | |
| "step": 895000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 9.698869956313575e-06, | |
| "loss": 0.059, | |
| "step": 900000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 0.06522925943136215, | |
| "eval_runtime": 1686.0104, | |
| "eval_samples_per_second": 36.793, | |
| "eval_steps_per_second": 36.793, | |
| "step": 900000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 9.474974789404206e-06, | |
| "loss": 0.0624, | |
| "step": 905000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 9.251079622494838e-06, | |
| "loss": 0.0722, | |
| "step": 910000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9.02718445558547e-06, | |
| "loss": 0.0599, | |
| "step": 915000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 8.803289288676098e-06, | |
| "loss": 0.0699, | |
| "step": 920000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.57939412176673e-06, | |
| "loss": 0.0606, | |
| "step": 925000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.355498954857361e-06, | |
| "loss": 0.0696, | |
| "step": 930000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.131603787947991e-06, | |
| "loss": 0.0626, | |
| "step": 935000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 7.907708621038623e-06, | |
| "loss": 0.0658, | |
| "step": 940000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 7.683813454129254e-06, | |
| "loss": 0.0641, | |
| "step": 945000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 7.459918287219884e-06, | |
| "loss": 0.0659, | |
| "step": 950000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 7.236023120310516e-06, | |
| "loss": 0.062, | |
| "step": 955000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 7.012127953401147e-06, | |
| "loss": 0.0658, | |
| "step": 960000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 6.788232786491779e-06, | |
| "loss": 0.0624, | |
| "step": 965000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 6.564337619582408e-06, | |
| "loss": 0.0619, | |
| "step": 970000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 6.34044245267304e-06, | |
| "loss": 0.0666, | |
| "step": 975000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_loss": 0.061893004924058914, | |
| "eval_runtime": 1682.9916, | |
| "eval_samples_per_second": 36.859, | |
| "eval_steps_per_second": 36.859, | |
| "step": 975000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 6.116547285763671e-06, | |
| "loss": 0.0665, | |
| "step": 980000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 5.892652118854302e-06, | |
| "loss": 0.0687, | |
| "step": 985000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 5.668756951944933e-06, | |
| "loss": 0.0656, | |
| "step": 990000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 5.444861785035564e-06, | |
| "loss": 0.0678, | |
| "step": 995000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 5.220966618126195e-06, | |
| "loss": 0.0645, | |
| "step": 1000000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 4.997071451216825e-06, | |
| "loss": 0.0661, | |
| "step": 1005000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 4.773176284307457e-06, | |
| "loss": 0.0672, | |
| "step": 1010000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 4.5492811173980875e-06, | |
| "loss": 0.0618, | |
| "step": 1015000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 4.325385950488719e-06, | |
| "loss": 0.064, | |
| "step": 1020000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 4.101490783579349e-06, | |
| "loss": 0.0622, | |
| "step": 1025000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.87759561666998e-06, | |
| "loss": 0.0673, | |
| "step": 1030000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.6537004497606115e-06, | |
| "loss": 0.0643, | |
| "step": 1035000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.4298052828512423e-06, | |
| "loss": 0.0688, | |
| "step": 1040000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.2059101159418736e-06, | |
| "loss": 0.0642, | |
| "step": 1045000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 2.9820149490325044e-06, | |
| "loss": 0.0624, | |
| "step": 1050000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": 0.061922721564769745, | |
| "eval_runtime": 1682.5086, | |
| "eval_samples_per_second": 36.869, | |
| "eval_steps_per_second": 36.869, | |
| "step": 1050000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 2.758119782123135e-06, | |
| "loss": 0.0636, | |
| "step": 1055000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 2.5342246152137664e-06, | |
| "loss": 0.0636, | |
| "step": 1060000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 2.310329448304397e-06, | |
| "loss": 0.0669, | |
| "step": 1065000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 2.086434281395028e-06, | |
| "loss": 0.0608, | |
| "step": 1070000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.862539114485659e-06, | |
| "loss": 0.0604, | |
| "step": 1075000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.63864394757629e-06, | |
| "loss": 0.0656, | |
| "step": 1080000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.4147487806669212e-06, | |
| "loss": 0.0693, | |
| "step": 1085000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.190853613757552e-06, | |
| "loss": 0.0604, | |
| "step": 1090000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 9.66958446848183e-07, | |
| "loss": 0.0665, | |
| "step": 1095000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 7.43063279938814e-07, | |
| "loss": 0.0642, | |
| "step": 1100000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 5.191681130294449e-07, | |
| "loss": 0.067, | |
| "step": 1105000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 2.952729461200759e-07, | |
| "loss": 0.0638, | |
| "step": 1110000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 7.137777921070686e-08, | |
| "loss": 0.0596, | |
| "step": 1115000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 2.492374130615067e-05, | |
| "loss": 0.0633, | |
| "step": 1120000 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 2.4811793722695988e-05, | |
| "loss": 0.0625, | |
| "step": 1125000 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 0.06666136533021927, | |
| "eval_runtime": 1682.1519, | |
| "eval_samples_per_second": 36.877, | |
| "eval_steps_per_second": 36.877, | |
| "step": 1125000 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 2.46998461392413e-05, | |
| "loss": 0.0645, | |
| "step": 1130000 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 2.4587898555786618e-05, | |
| "loss": 0.058, | |
| "step": 1135000 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 2.4475950972331933e-05, | |
| "loss": 0.0644, | |
| "step": 1140000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 2.4364003388877245e-05, | |
| "loss": 0.0599, | |
| "step": 1145000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 2.4252055805422564e-05, | |
| "loss": 0.0614, | |
| "step": 1150000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_loss": 0.06576403230428696, | |
| "eval_runtime": 1686.8754, | |
| "eval_samples_per_second": 36.774, | |
| "eval_steps_per_second": 36.774, | |
| "step": 1150000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 2.414010822196788e-05, | |
| "loss": 0.0637, | |
| "step": 1155000 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 2.4028160638513194e-05, | |
| "loss": 0.058, | |
| "step": 1160000 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 2.391621305505851e-05, | |
| "loss": 0.0623, | |
| "step": 1165000 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 2.3804265471603828e-05, | |
| "loss": 0.0628, | |
| "step": 1170000 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 2.369231788814914e-05, | |
| "loss": 0.0597, | |
| "step": 1175000 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "eval_loss": 0.06830067932605743, | |
| "eval_runtime": 1683.3372, | |
| "eval_samples_per_second": 36.851, | |
| "eval_steps_per_second": 36.851, | |
| "step": 1175000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 2.3580370304694455e-05, | |
| "loss": 0.0622, | |
| "step": 1180000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 2.3468422721239773e-05, | |
| "loss": 0.0579, | |
| "step": 1185000 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 2.3356475137785085e-05, | |
| "loss": 0.0644, | |
| "step": 1190000 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 2.3244527554330404e-05, | |
| "loss": 0.063, | |
| "step": 1195000 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 2.313257997087572e-05, | |
| "loss": 0.0629, | |
| "step": 1200000 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 0.0691303089261055, | |
| "eval_runtime": 1683.681, | |
| "eval_samples_per_second": 36.844, | |
| "eval_steps_per_second": 36.844, | |
| "step": 1200000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 2.3020632387421034e-05, | |
| "loss": 0.0647, | |
| "step": 1205000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 2.290868480396635e-05, | |
| "loss": 0.0645, | |
| "step": 1210000 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 2.2796737220511664e-05, | |
| "loss": 0.063, | |
| "step": 1215000 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 2.268478963705698e-05, | |
| "loss": 0.0638, | |
| "step": 1220000 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 2.2572842053602295e-05, | |
| "loss": 0.0603, | |
| "step": 1225000 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_loss": 0.06777703762054443, | |
| "eval_runtime": 1680.6968, | |
| "eval_samples_per_second": 36.909, | |
| "eval_steps_per_second": 36.909, | |
| "step": 1225000 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 2.246089447014761e-05, | |
| "loss": 0.0612, | |
| "step": 1230000 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 2.2348946886692925e-05, | |
| "loss": 0.0586, | |
| "step": 1235000 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 2.2236999303238244e-05, | |
| "loss": 0.0607, | |
| "step": 1240000 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 2.212505171978356e-05, | |
| "loss": 0.0653, | |
| "step": 1245000 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 2.201310413632887e-05, | |
| "loss": 0.0601, | |
| "step": 1250000 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_loss": 0.07459407299757004, | |
| "eval_runtime": 1683.3206, | |
| "eval_samples_per_second": 36.852, | |
| "eval_steps_per_second": 36.852, | |
| "step": 1250000 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 2.190115655287419e-05, | |
| "loss": 0.0638, | |
| "step": 1255000 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 2.1789208969419504e-05, | |
| "loss": 0.0634, | |
| "step": 1260000 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 2.167726138596482e-05, | |
| "loss": 0.0622, | |
| "step": 1265000 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 2.1565313802510135e-05, | |
| "loss": 0.0593, | |
| "step": 1270000 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 2.145336621905545e-05, | |
| "loss": 0.0606, | |
| "step": 1275000 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "eval_loss": 0.06908420473337173, | |
| "eval_runtime": 1680.5541, | |
| "eval_samples_per_second": 36.912, | |
| "eval_steps_per_second": 36.912, | |
| "step": 1275000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 2.1341418635600765e-05, | |
| "loss": 0.0612, | |
| "step": 1280000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 2.122947105214608e-05, | |
| "loss": 0.066, | |
| "step": 1285000 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 2.1117523468691396e-05, | |
| "loss": 0.0562, | |
| "step": 1290000 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 2.100557588523671e-05, | |
| "loss": 0.0617, | |
| "step": 1295000 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 2.089362830178203e-05, | |
| "loss": 0.0671, | |
| "step": 1300000 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_loss": 0.07024173438549042, | |
| "eval_runtime": 1683.3132, | |
| "eval_samples_per_second": 36.852, | |
| "eval_steps_per_second": 36.852, | |
| "step": 1300000 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 2.078168071832734e-05, | |
| "loss": 0.0578, | |
| "step": 1305000 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 2.066973313487266e-05, | |
| "loss": 0.0592, | |
| "step": 1310000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 2.0557785551417975e-05, | |
| "loss": 0.0607, | |
| "step": 1315000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 2.0445837967963287e-05, | |
| "loss": 0.0645, | |
| "step": 1320000 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 2.0333890384508605e-05, | |
| "loss": 0.0625, | |
| "step": 1325000 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "eval_loss": 0.06607282906770706, | |
| "eval_runtime": 1680.5346, | |
| "eval_samples_per_second": 36.913, | |
| "eval_steps_per_second": 36.913, | |
| "step": 1325000 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 2.022194280105392e-05, | |
| "loss": 0.0625, | |
| "step": 1330000 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 2.0109995217599236e-05, | |
| "loss": 0.0605, | |
| "step": 1335000 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 1.999804763414455e-05, | |
| "loss": 0.0592, | |
| "step": 1340000 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 1.9886100050689866e-05, | |
| "loss": 0.0652, | |
| "step": 1345000 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 1.977415246723518e-05, | |
| "loss": 0.0617, | |
| "step": 1350000 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "eval_loss": 0.0687505304813385, | |
| "eval_runtime": 1680.1242, | |
| "eval_samples_per_second": 36.922, | |
| "eval_steps_per_second": 36.922, | |
| "step": 1350000 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 1.9662204883780496e-05, | |
| "loss": 0.0607, | |
| "step": 1355000 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 1.9550257300325815e-05, | |
| "loss": 0.0619, | |
| "step": 1360000 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 1.9438309716871127e-05, | |
| "loss": 0.0629, | |
| "step": 1365000 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 1.9326362133416445e-05, | |
| "loss": 0.0637, | |
| "step": 1370000 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 1.921441454996176e-05, | |
| "loss": 0.0579, | |
| "step": 1375000 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "eval_loss": 0.06793049722909927, | |
| "eval_runtime": 1680.8053, | |
| "eval_samples_per_second": 36.907, | |
| "eval_steps_per_second": 36.907, | |
| "step": 1375000 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 1.9102466966507072e-05, | |
| "loss": 0.0632, | |
| "step": 1380000 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 1.899051938305239e-05, | |
| "loss": 0.0593, | |
| "step": 1385000 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 1.8878571799597706e-05, | |
| "loss": 0.0622, | |
| "step": 1390000 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 1.876662421614302e-05, | |
| "loss": 0.064, | |
| "step": 1395000 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 1.8654676632688336e-05, | |
| "loss": 0.0663, | |
| "step": 1400000 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_loss": 0.0633900910615921, | |
| "eval_runtime": 1680.7989, | |
| "eval_samples_per_second": 36.907, | |
| "eval_steps_per_second": 36.907, | |
| "step": 1400000 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 1.8542729049233655e-05, | |
| "loss": 0.0606, | |
| "step": 1405000 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 1.8430781465778967e-05, | |
| "loss": 0.0633, | |
| "step": 1410000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 1.8318833882324282e-05, | |
| "loss": 0.064, | |
| "step": 1415000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 1.82068862988696e-05, | |
| "loss": 0.0573, | |
| "step": 1420000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 1.8094938715414912e-05, | |
| "loss": 0.0583, | |
| "step": 1425000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_loss": 0.063847616314888, | |
| "eval_runtime": 1680.6703, | |
| "eval_samples_per_second": 36.91, | |
| "eval_steps_per_second": 36.91, | |
| "step": 1425000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 1.798299113196023e-05, | |
| "loss": 0.0669, | |
| "step": 1430000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 1.7871043548505546e-05, | |
| "loss": 0.0576, | |
| "step": 1435000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 1.775909596505086e-05, | |
| "loss": 0.0603, | |
| "step": 1440000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 1.7647148381596177e-05, | |
| "loss": 0.0628, | |
| "step": 1445000 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 1.7535200798141492e-05, | |
| "loss": 0.0623, | |
| "step": 1450000 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "eval_loss": 0.06811905652284622, | |
| "eval_runtime": 1680.0308, | |
| "eval_samples_per_second": 36.924, | |
| "eval_steps_per_second": 36.924, | |
| "step": 1450000 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 1.7423253214686807e-05, | |
| "loss": 0.066, | |
| "step": 1455000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 1.7311305631232122e-05, | |
| "loss": 0.0645, | |
| "step": 1460000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 1.719935804777744e-05, | |
| "loss": 0.0673, | |
| "step": 1465000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 1.7087410464322753e-05, | |
| "loss": 0.0601, | |
| "step": 1470000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 1.697546288086807e-05, | |
| "loss": 0.0615, | |
| "step": 1475000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "eval_loss": 0.06700597703456879, | |
| "eval_runtime": 1680.6996, | |
| "eval_samples_per_second": 36.909, | |
| "eval_steps_per_second": 36.909, | |
| "step": 1475000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 1.6863515297413386e-05, | |
| "loss": 0.0651, | |
| "step": 1480000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 1.6751567713958698e-05, | |
| "loss": 0.0596, | |
| "step": 1485000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 1.6639620130504017e-05, | |
| "loss": 0.0616, | |
| "step": 1490000 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 1.6527672547049332e-05, | |
| "loss": 0.0609, | |
| "step": 1495000 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 1.6415724963594647e-05, | |
| "loss": 0.0592, | |
| "step": 1500000 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "eval_loss": 0.06664443016052246, | |
| "eval_runtime": 1681.9546, | |
| "eval_samples_per_second": 36.881, | |
| "eval_steps_per_second": 36.881, | |
| "step": 1500000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 1.6303777380139962e-05, | |
| "loss": 0.0618, | |
| "step": 1505000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 1.6191829796685277e-05, | |
| "loss": 0.0586, | |
| "step": 1510000 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 1.6079882213230593e-05, | |
| "loss": 0.0611, | |
| "step": 1515000 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 1.5967934629775908e-05, | |
| "loss": 0.0635, | |
| "step": 1520000 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 1.5855987046321223e-05, | |
| "loss": 0.0626, | |
| "step": 1525000 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "eval_loss": 0.06663180142641068, | |
| "eval_runtime": 1679.9392, | |
| "eval_samples_per_second": 36.926, | |
| "eval_steps_per_second": 36.926, | |
| "step": 1525000 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 1.5744039462866538e-05, | |
| "loss": 0.0637, | |
| "step": 1530000 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 1.5632091879411857e-05, | |
| "loss": 0.0582, | |
| "step": 1535000 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 1.5520144295957172e-05, | |
| "loss": 0.0618, | |
| "step": 1540000 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 1.5408196712502487e-05, | |
| "loss": 0.0594, | |
| "step": 1545000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 1.5296249129047802e-05, | |
| "loss": 0.063, | |
| "step": 1550000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_loss": 0.06467917561531067, | |
| "eval_runtime": 1681.2275, | |
| "eval_samples_per_second": 36.897, | |
| "eval_steps_per_second": 36.897, | |
| "step": 1550000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 1.5184301545593116e-05, | |
| "loss": 0.0637, | |
| "step": 1555000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.5072353962138433e-05, | |
| "loss": 0.0641, | |
| "step": 1560000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.4960406378683748e-05, | |
| "loss": 0.0615, | |
| "step": 1565000 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 1.4848458795229065e-05, | |
| "loss": 0.061, | |
| "step": 1570000 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 1.4736511211774378e-05, | |
| "loss": 0.0648, | |
| "step": 1575000 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "eval_loss": 0.06533137708902359, | |
| "eval_runtime": 1677.1597, | |
| "eval_samples_per_second": 36.987, | |
| "eval_steps_per_second": 36.987, | |
| "step": 1575000 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 1.4624563628319693e-05, | |
| "loss": 0.0623, | |
| "step": 1580000 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 1.451261604486501e-05, | |
| "loss": 0.0631, | |
| "step": 1585000 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 1.4400668461410324e-05, | |
| "loss": 0.0613, | |
| "step": 1590000 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 1.428872087795564e-05, | |
| "loss": 0.0611, | |
| "step": 1595000 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 1.4176773294500956e-05, | |
| "loss": 0.0611, | |
| "step": 1600000 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "eval_loss": 0.06996028870344162, | |
| "eval_runtime": 1678.7591, | |
| "eval_samples_per_second": 36.952, | |
| "eval_steps_per_second": 36.952, | |
| "step": 1600000 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 1.4064825711046273e-05, | |
| "loss": 0.0629, | |
| "step": 1605000 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 1.3952878127591586e-05, | |
| "loss": 0.0607, | |
| "step": 1610000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 1.3840930544136901e-05, | |
| "loss": 0.0653, | |
| "step": 1615000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 1.3728982960682218e-05, | |
| "loss": 0.0608, | |
| "step": 1620000 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 1.3617035377227534e-05, | |
| "loss": 0.0622, | |
| "step": 1625000 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "eval_loss": 0.0634424015879631, | |
| "eval_runtime": 1677.9992, | |
| "eval_samples_per_second": 36.968, | |
| "eval_steps_per_second": 36.968, | |
| "step": 1625000 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 1.350508779377285e-05, | |
| "loss": 0.0622, | |
| "step": 1630000 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 1.3393140210318164e-05, | |
| "loss": 0.0634, | |
| "step": 1635000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 1.328119262686348e-05, | |
| "loss": 0.059, | |
| "step": 1640000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 1.3169245043408796e-05, | |
| "loss": 0.0608, | |
| "step": 1645000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 1.305729745995411e-05, | |
| "loss": 0.0617, | |
| "step": 1650000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_loss": 0.06513845920562744, | |
| "eval_runtime": 1682.3756, | |
| "eval_samples_per_second": 36.872, | |
| "eval_steps_per_second": 36.872, | |
| "step": 1650000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 1.2945349876499426e-05, | |
| "loss": 0.0622, | |
| "step": 1655000 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 1.2833402293044742e-05, | |
| "loss": 0.0603, | |
| "step": 1660000 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 1.2721454709590058e-05, | |
| "loss": 0.0647, | |
| "step": 1665000 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 1.2609507126135372e-05, | |
| "loss": 0.0579, | |
| "step": 1670000 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 1.2497559542680689e-05, | |
| "loss": 0.0613, | |
| "step": 1675000 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_loss": 0.0634496882557869, | |
| "eval_runtime": 1679.6133, | |
| "eval_samples_per_second": 36.933, | |
| "eval_steps_per_second": 36.933, | |
| "step": 1675000 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 1.2385611959226004e-05, | |
| "loss": 0.0574, | |
| "step": 1680000 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 1.227366437577132e-05, | |
| "loss": 0.0574, | |
| "step": 1685000 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 1.2161716792316636e-05, | |
| "loss": 0.0616, | |
| "step": 1690000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 1.2049769208861951e-05, | |
| "loss": 0.06, | |
| "step": 1695000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 1.1937821625407265e-05, | |
| "loss": 0.0639, | |
| "step": 1700000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_loss": 0.0661427304148674, | |
| "eval_runtime": 1685.0546, | |
| "eval_samples_per_second": 36.814, | |
| "eval_steps_per_second": 36.814, | |
| "step": 1700000 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 1.1825874041952582e-05, | |
| "loss": 0.0638, | |
| "step": 1705000 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 1.1713926458497897e-05, | |
| "loss": 0.0618, | |
| "step": 1710000 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 1.1601978875043212e-05, | |
| "loss": 0.0616, | |
| "step": 1715000 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 1.1490031291588529e-05, | |
| "loss": 0.0597, | |
| "step": 1720000 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 1.1378083708133844e-05, | |
| "loss": 0.0615, | |
| "step": 1725000 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "eval_loss": 0.06442756205797195, | |
| "eval_runtime": 1688.2768, | |
| "eval_samples_per_second": 36.743, | |
| "eval_steps_per_second": 36.743, | |
| "step": 1725000 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 1.126613612467916e-05, | |
| "loss": 0.0627, | |
| "step": 1730000 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 1.1154188541224474e-05, | |
| "loss": 0.0599, | |
| "step": 1735000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 1.104224095776979e-05, | |
| "loss": 0.0609, | |
| "step": 1740000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 1.0930293374315105e-05, | |
| "loss": 0.067, | |
| "step": 1745000 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 1.081834579086042e-05, | |
| "loss": 0.0605, | |
| "step": 1750000 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "eval_loss": 0.06615401804447174, | |
| "eval_runtime": 1682.0319, | |
| "eval_samples_per_second": 36.88, | |
| "eval_steps_per_second": 36.88, | |
| "step": 1750000 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 1.0706398207405737e-05, | |
| "loss": 0.0603, | |
| "step": 1755000 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 1.0594450623951052e-05, | |
| "loss": 0.0578, | |
| "step": 1760000 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 1.0482503040496367e-05, | |
| "loss": 0.0658, | |
| "step": 1765000 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 1.0370555457041682e-05, | |
| "loss": 0.0594, | |
| "step": 1770000 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 1.0258607873586998e-05, | |
| "loss": 0.0622, | |
| "step": 1775000 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "eval_loss": 0.06558772176504135, | |
| "eval_runtime": 1679.2015, | |
| "eval_samples_per_second": 36.942, | |
| "eval_steps_per_second": 36.942, | |
| "step": 1775000 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 1.0146660290132313e-05, | |
| "loss": 0.0654, | |
| "step": 1780000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 1.003471270667763e-05, | |
| "loss": 0.0629, | |
| "step": 1785000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 9.922765123222945e-06, | |
| "loss": 0.0541, | |
| "step": 1790000 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 9.81081753976826e-06, | |
| "loss": 0.0605, | |
| "step": 1795000 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 9.698869956313575e-06, | |
| "loss": 0.0585, | |
| "step": 1800000 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "eval_loss": 0.0633106529712677, | |
| "eval_runtime": 1681.6891, | |
| "eval_samples_per_second": 36.887, | |
| "eval_steps_per_second": 36.887, | |
| "step": 1800000 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 9.58692237285889e-06, | |
| "loss": 0.0654, | |
| "step": 1805000 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 9.474974789404206e-06, | |
| "loss": 0.0622, | |
| "step": 1810000 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 9.363027205949523e-06, | |
| "loss": 0.0612, | |
| "step": 1815000 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 9.251079622494838e-06, | |
| "loss": 0.056, | |
| "step": 1820000 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 9.139132039040153e-06, | |
| "loss": 0.0628, | |
| "step": 1825000 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "eval_loss": 0.06252375990152359, | |
| "eval_runtime": 1681.1292, | |
| "eval_samples_per_second": 36.9, | |
| "eval_steps_per_second": 36.9, | |
| "step": 1825000 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 9.02718445558547e-06, | |
| "loss": 0.0619, | |
| "step": 1830000 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 8.915236872130783e-06, | |
| "loss": 0.063, | |
| "step": 1835000 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 8.803289288676098e-06, | |
| "loss": 0.0607, | |
| "step": 1840000 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 8.691341705221415e-06, | |
| "loss": 0.0633, | |
| "step": 1845000 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 8.57939412176673e-06, | |
| "loss": 0.0638, | |
| "step": 1850000 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "eval_loss": 0.06624045222997665, | |
| "eval_runtime": 1680.5873, | |
| "eval_samples_per_second": 36.912, | |
| "eval_steps_per_second": 36.912, | |
| "step": 1850000 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 8.467446538312046e-06, | |
| "loss": 0.0601, | |
| "step": 1855000 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 8.355498954857361e-06, | |
| "loss": 0.065, | |
| "step": 1860000 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 8.243551371402678e-06, | |
| "loss": 0.059, | |
| "step": 1865000 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 8.131603787947991e-06, | |
| "loss": 0.064, | |
| "step": 1870000 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 8.019656204493308e-06, | |
| "loss": 0.0599, | |
| "step": 1875000 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "eval_loss": 0.06644026190042496, | |
| "eval_runtime": 1678.6507, | |
| "eval_samples_per_second": 36.954, | |
| "eval_steps_per_second": 36.954, | |
| "step": 1875000 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 7.907708621038623e-06, | |
| "loss": 0.0639, | |
| "step": 1880000 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 7.795761037583939e-06, | |
| "loss": 0.0631, | |
| "step": 1885000 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 7.683813454129254e-06, | |
| "loss": 0.064, | |
| "step": 1890000 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 7.57186587067457e-06, | |
| "loss": 0.062, | |
| "step": 1895000 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 7.459918287219884e-06, | |
| "loss": 0.0583, | |
| "step": 1900000 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "eval_loss": 0.0668446272611618, | |
| "eval_runtime": 1681.2378, | |
| "eval_samples_per_second": 36.897, | |
| "eval_steps_per_second": 36.897, | |
| "step": 1900000 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 7.3479707037652e-06, | |
| "loss": 0.0599, | |
| "step": 1905000 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 7.236023120310516e-06, | |
| "loss": 0.0611, | |
| "step": 1910000 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 7.124075536855831e-06, | |
| "loss": 0.0627, | |
| "step": 1915000 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 7.012127953401147e-06, | |
| "loss": 0.0591, | |
| "step": 1920000 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 6.900180369946463e-06, | |
| "loss": 0.0543, | |
| "step": 1925000 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "eval_loss": 0.06305810809135437, | |
| "eval_runtime": 1683.6555, | |
| "eval_samples_per_second": 36.844, | |
| "eval_steps_per_second": 36.844, | |
| "step": 1925000 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 6.788232786491779e-06, | |
| "loss": 0.0622, | |
| "step": 1930000 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 6.676285203037093e-06, | |
| "loss": 0.0605, | |
| "step": 1935000 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 6.564337619582408e-06, | |
| "loss": 0.0622, | |
| "step": 1940000 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 6.452390036127724e-06, | |
| "loss": 0.0596, | |
| "step": 1945000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 6.34044245267304e-06, | |
| "loss": 0.06, | |
| "step": 1950000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_loss": 0.06286083161830902, | |
| "eval_runtime": 1684.2136, | |
| "eval_samples_per_second": 36.832, | |
| "eval_steps_per_second": 36.832, | |
| "step": 1950000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 6.2284948692183554e-06, | |
| "loss": 0.058, | |
| "step": 1955000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 6.116547285763671e-06, | |
| "loss": 0.0594, | |
| "step": 1960000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 6.004599702308987e-06, | |
| "loss": 0.0679, | |
| "step": 1965000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 5.892652118854302e-06, | |
| "loss": 0.0621, | |
| "step": 1970000 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 5.780704535399617e-06, | |
| "loss": 0.0615, | |
| "step": 1975000 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "eval_loss": 0.06435712426900864, | |
| "eval_runtime": 1684.3427, | |
| "eval_samples_per_second": 36.829, | |
| "eval_steps_per_second": 36.829, | |
| "step": 1975000 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 5.668756951944933e-06, | |
| "loss": 0.0602, | |
| "step": 1980000 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 5.556809368490248e-06, | |
| "loss": 0.0589, | |
| "step": 1985000 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 5.444861785035564e-06, | |
| "loss": 0.0578, | |
| "step": 1990000 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 5.332914201580879e-06, | |
| "loss": 0.0626, | |
| "step": 1995000 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 5.220966618126195e-06, | |
| "loss": 0.0587, | |
| "step": 2000000 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "eval_loss": 0.06628864258527756, | |
| "eval_runtime": 1682.6389, | |
| "eval_samples_per_second": 36.866, | |
| "eval_steps_per_second": 36.866, | |
| "step": 2000000 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 5.109019034671511e-06, | |
| "loss": 0.0595, | |
| "step": 2005000 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 4.997071451216825e-06, | |
| "loss": 0.0584, | |
| "step": 2010000 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 4.885123867762141e-06, | |
| "loss": 0.0562, | |
| "step": 2015000 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 4.773176284307457e-06, | |
| "loss": 0.0694, | |
| "step": 2020000 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 4.661228700852772e-06, | |
| "loss": 0.0647, | |
| "step": 2025000 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "eval_loss": 0.06544966250658035, | |
| "eval_runtime": 1682.8498, | |
| "eval_samples_per_second": 36.862, | |
| "eval_steps_per_second": 36.862, | |
| "step": 2025000 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 4.5492811173980875e-06, | |
| "loss": 0.0596, | |
| "step": 2030000 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 4.4373335339434035e-06, | |
| "loss": 0.062, | |
| "step": 2035000 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 4.325385950488719e-06, | |
| "loss": 0.0656, | |
| "step": 2040000 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 4.213438367034034e-06, | |
| "loss": 0.0632, | |
| "step": 2045000 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 4.101490783579349e-06, | |
| "loss": 0.0604, | |
| "step": 2050000 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "eval_loss": 0.06386958807706833, | |
| "eval_runtime": 1684.8253, | |
| "eval_samples_per_second": 36.819, | |
| "eval_steps_per_second": 36.819, | |
| "step": 2050000 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 3.989543200124665e-06, | |
| "loss": 0.0586, | |
| "step": 2055000 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 3.87759561666998e-06, | |
| "loss": 0.0595, | |
| "step": 2060000 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 3.765648033215296e-06, | |
| "loss": 0.0628, | |
| "step": 2065000 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 3.6537004497606115e-06, | |
| "loss": 0.0614, | |
| "step": 2070000 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 3.541752866305927e-06, | |
| "loss": 0.0641, | |
| "step": 2075000 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_loss": 0.06358933448791504, | |
| "eval_runtime": 1682.4468, | |
| "eval_samples_per_second": 36.871, | |
| "eval_steps_per_second": 36.871, | |
| "step": 2075000 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 3.4298052828512423e-06, | |
| "loss": 0.0612, | |
| "step": 2080000 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 3.317857699396558e-06, | |
| "loss": 0.0675, | |
| "step": 2085000 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 3.2059101159418736e-06, | |
| "loss": 0.0657, | |
| "step": 2090000 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 3.0939625324871888e-06, | |
| "loss": 0.0628, | |
| "step": 2095000 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 2.9820149490325044e-06, | |
| "loss": 0.0604, | |
| "step": 2100000 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "eval_loss": 0.0636412724852562, | |
| "eval_runtime": 1687.8932, | |
| "eval_samples_per_second": 36.752, | |
| "eval_steps_per_second": 36.752, | |
| "step": 2100000 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 2.87006736557782e-06, | |
| "loss": 0.0592, | |
| "step": 2105000 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 2.758119782123135e-06, | |
| "loss": 0.0619, | |
| "step": 2110000 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 2.6461721986684508e-06, | |
| "loss": 0.0623, | |
| "step": 2115000 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 2.5342246152137664e-06, | |
| "loss": 0.0568, | |
| "step": 2120000 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 2.4222770317590816e-06, | |
| "loss": 0.0654, | |
| "step": 2125000 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "eval_loss": 0.06523974984884262, | |
| "eval_runtime": 1681.6119, | |
| "eval_samples_per_second": 36.889, | |
| "eval_steps_per_second": 36.889, | |
| "step": 2125000 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 2.310329448304397e-06, | |
| "loss": 0.0597, | |
| "step": 2130000 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 2.198381864849713e-06, | |
| "loss": 0.0614, | |
| "step": 2135000 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 2.086434281395028e-06, | |
| "loss": 0.0576, | |
| "step": 2140000 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 1.9744866979403436e-06, | |
| "loss": 0.0625, | |
| "step": 2145000 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.862539114485659e-06, | |
| "loss": 0.0588, | |
| "step": 2150000 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "eval_loss": 0.06383997201919556, | |
| "eval_runtime": 1685.504, | |
| "eval_samples_per_second": 36.804, | |
| "eval_steps_per_second": 36.804, | |
| "step": 2150000 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.7505915310309748e-06, | |
| "loss": 0.0525, | |
| "step": 2155000 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.63864394757629e-06, | |
| "loss": 0.0573, | |
| "step": 2160000 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 1.5266963641216056e-06, | |
| "loss": 0.0612, | |
| "step": 2165000 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 1.4147487806669212e-06, | |
| "loss": 0.0625, | |
| "step": 2170000 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 1.3028011972122364e-06, | |
| "loss": 0.0616, | |
| "step": 2175000 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "eval_loss": 0.06566296517848969, | |
| "eval_runtime": 1686.3029, | |
| "eval_samples_per_second": 36.786, | |
| "eval_steps_per_second": 36.786, | |
| "step": 2175000 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 1.190853613757552e-06, | |
| "loss": 0.0629, | |
| "step": 2180000 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 1.0789060303028674e-06, | |
| "loss": 0.0543, | |
| "step": 2185000 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 9.66958446848183e-07, | |
| "loss": 0.0584, | |
| "step": 2190000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 8.550108633934986e-07, | |
| "loss": 0.0595, | |
| "step": 2195000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 7.43063279938814e-07, | |
| "loss": 0.0598, | |
| "step": 2200000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_loss": 0.06455818563699722, | |
| "eval_runtime": 1682.3023, | |
| "eval_samples_per_second": 36.874, | |
| "eval_steps_per_second": 36.874, | |
| "step": 2200000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 6.311156964841294e-07, | |
| "loss": 0.0595, | |
| "step": 2205000 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 5.191681130294449e-07, | |
| "loss": 0.0602, | |
| "step": 2210000 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 4.0722052957476043e-07, | |
| "loss": 0.0601, | |
| "step": 2215000 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 2.952729461200759e-07, | |
| "loss": 0.0595, | |
| "step": 2220000 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 1.8332536266539136e-07, | |
| "loss": 0.0633, | |
| "step": 2225000 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_loss": 0.06449371576309204, | |
| "eval_runtime": 1682.7954, | |
| "eval_samples_per_second": 36.863, | |
| "eval_steps_per_second": 36.863, | |
| "step": 2225000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 7.137777921070686e-08, | |
| "loss": 0.0603, | |
| "step": 2230000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 2233188, | |
| "total_flos": 6.706494317713766e+17, | |
| "train_loss": 0.030777697094727392, | |
| "train_runtime": 228453.6417, | |
| "train_samples_per_second": 9.775, | |
| "train_steps_per_second": 9.775 | |
| } | |
| ], | |
| "max_steps": 2233188, | |
| "num_train_epochs": 2, | |
| "total_flos": 6.706494317713766e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |