| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 20, | |
| "global_step": 3801, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 9.999984629559935e-07, | |
| "loss": 2.5917, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 9.99993851833424e-07, | |
| "loss": 2.5954, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.999861666606418e-07, | |
| "loss": 2.4758, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.999754074848963e-07, | |
| "loss": 2.4339, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.999615743723372e-07, | |
| "loss": 2.4302, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.999446674080123e-07, | |
| "loss": 2.4127, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.4218649864196777, | |
| "eval_runtime": 422.4825, | |
| "eval_samples_per_second": 20.204, | |
| "eval_steps_per_second": 0.632, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.999246866958693e-07, | |
| "loss": 2.4245, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.999016323587525e-07, | |
| "loss": 2.4331, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.998755045384044e-07, | |
| "loss": 2.408, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.998463033954637e-07, | |
| "loss": 2.4111, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.998140291094635e-07, | |
| "loss": 2.3888, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.997786818788323e-07, | |
| "loss": 2.3767, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.997402619208908e-07, | |
| "loss": 2.4407, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.4008724689483643, | |
| "eval_runtime": 422.6497, | |
| "eval_samples_per_second": 20.196, | |
| "eval_steps_per_second": 0.632, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.996987694718518e-07, | |
| "loss": 2.4586, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.996542047868183e-07, | |
| "loss": 2.3972, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.996065681397816e-07, | |
| "loss": 2.439, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.995558598236203e-07, | |
| "loss": 2.3865, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.995020801500979e-07, | |
| "loss": 2.385, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.994452294498617e-07, | |
| "loss": 2.361, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.993853080724395e-07, | |
| "loss": 2.3373, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.3903119564056396, | |
| "eval_runtime": 422.8009, | |
| "eval_samples_per_second": 20.189, | |
| "eval_steps_per_second": 0.632, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.993223163862385e-07, | |
| "loss": 2.4323, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.992562547785425e-07, | |
| "loss": 2.3833, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.991871236555104e-07, | |
| "loss": 2.4518, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.99114923442172e-07, | |
| "loss": 2.3919, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.990396545824274e-07, | |
| "loss": 2.3552, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.989613175390423e-07, | |
| "loss": 2.4349, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.3834221363067627, | |
| "eval_runtime": 422.8964, | |
| "eval_samples_per_second": 20.185, | |
| "eval_steps_per_second": 0.631, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.988799127936468e-07, | |
| "loss": 2.3704, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.987954408467319e-07, | |
| "loss": 2.3947, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.987079022176455e-07, | |
| "loss": 2.3535, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.98617297444591e-07, | |
| "loss": 2.3119, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.98523627084622e-07, | |
| "loss": 2.4012, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.98426891713641e-07, | |
| "loss": 2.3829, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.983270919263933e-07, | |
| "loss": 2.405, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.3782522678375244, | |
| "eval_runtime": 422.9999, | |
| "eval_samples_per_second": 20.18, | |
| "eval_steps_per_second": 0.631, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.982242283364663e-07, | |
| "loss": 2.3665, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.981183015762831e-07, | |
| "loss": 2.3767, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.980093122971e-07, | |
| "loss": 2.4046, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.978972611690023e-07, | |
| "loss": 2.4044, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.977821488809001e-07, | |
| "loss": 2.3571, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.97663976140524e-07, | |
| "loss": 2.3326, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.97542743674421e-07, | |
| "loss": 2.4464, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.3740499019622803, | |
| "eval_runtime": 423.0066, | |
| "eval_samples_per_second": 20.179, | |
| "eval_steps_per_second": 0.631, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.974184522279497e-07, | |
| "loss": 2.3707, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.972911025652754e-07, | |
| "loss": 2.3392, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.971606954693662e-07, | |
| "loss": 2.3824, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.970272317419883e-07, | |
| "loss": 2.4347, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.968907122037001e-07, | |
| "loss": 2.3334, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.967511376938473e-07, | |
| "loss": 2.3781, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 2.3706772327423096, | |
| "eval_runtime": 423.1326, | |
| "eval_samples_per_second": 20.173, | |
| "eval_steps_per_second": 0.631, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.96608509070559e-07, | |
| "loss": 2.3542, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.964628272107412e-07, | |
| "loss": 2.3856, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.963140930100713e-07, | |
| "loss": 2.4, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.961623073829934e-07, | |
| "loss": 2.3335, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.960074712627125e-07, | |
| "loss": 2.3617, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.95849585601188e-07, | |
| "loss": 2.2984, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.956886513691288e-07, | |
| "loss": 2.3507, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 2.367818832397461, | |
| "eval_runtime": 423.1446, | |
| "eval_samples_per_second": 20.173, | |
| "eval_steps_per_second": 0.631, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.95524669555987e-07, | |
| "loss": 2.3621, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.953576411699514e-07, | |
| "loss": 2.4055, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.951875672379423e-07, | |
| "loss": 2.3237, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.95014448805604e-07, | |
| "loss": 2.3707, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.94838286937299e-07, | |
| "loss": 2.4194, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.946590827161018e-07, | |
| "loss": 2.3874, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.94476837243791e-07, | |
| "loss": 2.3603, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 2.365144729614258, | |
| "eval_runtime": 423.0504, | |
| "eval_samples_per_second": 20.177, | |
| "eval_steps_per_second": 0.631, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.94291551640844e-07, | |
| "loss": 2.3569, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.941032270464298e-07, | |
| "loss": 2.3908, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.939118646184005e-07, | |
| "loss": 2.3899, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.937174655332863e-07, | |
| "loss": 2.2911, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.93520030986287e-07, | |
| "loss": 2.3508, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.933195621912648e-07, | |
| "loss": 2.4146, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 2.362793445587158, | |
| "eval_runtime": 423.1986, | |
| "eval_samples_per_second": 20.17, | |
| "eval_steps_per_second": 0.631, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.931160603807374e-07, | |
| "loss": 2.2788, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.929095268058694e-07, | |
| "loss": 2.3609, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.926999627364658e-07, | |
| "loss": 2.3661, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.924873694609634e-07, | |
| "loss": 2.3941, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.922717482864232e-07, | |
| "loss": 2.3673, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.920531005385216e-07, | |
| "loss": 2.3008, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.91831427561544e-07, | |
| "loss": 2.3091, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 2.360593557357788, | |
| "eval_runtime": 423.1159, | |
| "eval_samples_per_second": 20.174, | |
| "eval_steps_per_second": 0.631, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.916067307183748e-07, | |
| "loss": 2.4117, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.913790113904893e-07, | |
| "loss": 2.3798, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.911482709779467e-07, | |
| "loss": 2.3493, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.909145108993792e-07, | |
| "loss": 2.259, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.90677732591985e-07, | |
| "loss": 2.338, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.90437937511519e-07, | |
| "loss": 2.3372, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.901951271322831e-07, | |
| "loss": 2.3506, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 2.358410596847534, | |
| "eval_runtime": 423.1811, | |
| "eval_samples_per_second": 20.171, | |
| "eval_steps_per_second": 0.631, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.899493029471187e-07, | |
| "loss": 2.3795, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.897004664673962e-07, | |
| "loss": 2.3647, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.894486192230056e-07, | |
| "loss": 2.3606, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.891937627623485e-07, | |
| "loss": 2.313, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.889358986523273e-07, | |
| "loss": 2.3567, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.886750284783358e-07, | |
| "loss": 2.4321, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 2.356544017791748, | |
| "eval_runtime": 423.3087, | |
| "eval_samples_per_second": 20.165, | |
| "eval_steps_per_second": 0.631, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.884111538442496e-07, | |
| "loss": 2.4032, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.881442763724167e-07, | |
| "loss": 2.3998, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.878743977036467e-07, | |
| "loss": 2.3175, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.87601519497201e-07, | |
| "loss": 2.3615, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.873256434307828e-07, | |
| "loss": 2.3314, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.870467712005268e-07, | |
| "loss": 2.3243, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.86764904520989e-07, | |
| "loss": 2.3704, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 2.354780912399292, | |
| "eval_runtime": 423.2181, | |
| "eval_samples_per_second": 20.169, | |
| "eval_steps_per_second": 0.631, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.864800451251346e-07, | |
| "loss": 2.3973, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.8619219476433e-07, | |
| "loss": 2.2891, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.859013552083293e-07, | |
| "loss": 2.3691, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.856075282452657e-07, | |
| "loss": 2.3868, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.85310715681639e-07, | |
| "loss": 2.3333, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.85010919342305e-07, | |
| "loss": 2.3556, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.847081410704645e-07, | |
| "loss": 2.3586, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 2.3531601428985596, | |
| "eval_runtime": 423.3067, | |
| "eval_samples_per_second": 20.165, | |
| "eval_steps_per_second": 0.631, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.844023827276515e-07, | |
| "loss": 2.3413, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.84093646193722e-07, | |
| "loss": 2.3982, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.837819333668428e-07, | |
| "loss": 2.3644, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.83467246163479e-07, | |
| "loss": 2.3705, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.831495865183832e-07, | |
| "loss": 2.3576, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.828289563845823e-07, | |
| "loss": 2.3258, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 2.3516056537628174, | |
| "eval_runtime": 423.25, | |
| "eval_samples_per_second": 20.168, | |
| "eval_steps_per_second": 0.631, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.825053577333674e-07, | |
| "loss": 2.358, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.8217879255428e-07, | |
| "loss": 2.344, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.818492628550997e-07, | |
| "loss": 2.3398, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.815167706618335e-07, | |
| "loss": 2.4292, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.811813180187019e-07, | |
| "loss": 2.3581, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.808429069881266e-07, | |
| "loss": 2.2791, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.805015396507184e-07, | |
| "loss": 2.3342, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 2.3501791954040527, | |
| "eval_runtime": 423.3402, | |
| "eval_samples_per_second": 20.163, | |
| "eval_steps_per_second": 0.631, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.801572181052637e-07, | |
| "loss": 2.3974, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.798099444687122e-07, | |
| "loss": 2.3568, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.79459720876163e-07, | |
| "loss": 2.3222, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.791065494808526e-07, | |
| "loss": 2.3403, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.787504324541408e-07, | |
| "loss": 2.3505, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.783913719854976e-07, | |
| "loss": 2.3776, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.780293702824904e-07, | |
| "loss": 2.373, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 2.348997116088867, | |
| "eval_runtime": 423.3678, | |
| "eval_samples_per_second": 20.162, | |
| "eval_steps_per_second": 0.631, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 9.77664429570769e-07, | |
| "loss": 2.3458, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 9.772965520940534e-07, | |
| "loss": 2.3343, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 9.76925740114119e-07, | |
| "loss": 2.3392, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 9.765519959107831e-07, | |
| "loss": 2.3095, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 9.761753217818906e-07, | |
| "loss": 2.3243, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 9.75795720043301e-07, | |
| "loss": 2.4109, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 2.3476743698120117, | |
| "eval_runtime": 423.3185, | |
| "eval_samples_per_second": 20.164, | |
| "eval_steps_per_second": 0.631, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 9.75413193028872e-07, | |
| "loss": 2.3704, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 9.750277430904472e-07, | |
| "loss": 2.337, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 9.746393725978408e-07, | |
| "loss": 2.3453, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 9.74248083938823e-07, | |
| "loss": 2.3184, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 9.73853879519105e-07, | |
| "loss": 2.3148, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 9.73456761762325e-07, | |
| "loss": 2.3685, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 9.730567331100333e-07, | |
| "loss": 2.3615, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 2.346473455429077, | |
| "eval_runtime": 423.3308, | |
| "eval_samples_per_second": 20.164, | |
| "eval_steps_per_second": 0.631, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 9.726537960216761e-07, | |
| "loss": 2.3704, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 9.722479529745818e-07, | |
| "loss": 2.4062, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 9.718392064639446e-07, | |
| "loss": 2.281, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 9.7142755900281e-07, | |
| "loss": 2.3275, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 9.710130131220595e-07, | |
| "loss": 2.3032, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 9.705955713703937e-07, | |
| "loss": 2.3293, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 9.701752363143183e-07, | |
| "loss": 2.3226, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 2.345350742340088, | |
| "eval_runtime": 423.3234, | |
| "eval_samples_per_second": 20.164, | |
| "eval_steps_per_second": 0.631, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 9.697520105381268e-07, | |
| "loss": 2.369, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 9.693258966438862e-07, | |
| "loss": 2.337, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 9.688968972514193e-07, | |
| "loss": 2.3456, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 9.684650149982902e-07, | |
| "loss": 2.3434, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 9.68030252539787e-07, | |
| "loss": 2.2863, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 9.675926125489055e-07, | |
| "loss": 2.2545, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 2.3442280292510986, | |
| "eval_runtime": 423.3552, | |
| "eval_samples_per_second": 20.163, | |
| "eval_steps_per_second": 0.631, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 9.671520977163339e-07, | |
| "loss": 2.3126, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 9.667087107504346e-07, | |
| "loss": 2.2938, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 9.662624543772288e-07, | |
| "loss": 2.3645, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 9.658133313403792e-07, | |
| "loss": 2.3402, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 9.653613444011735e-07, | |
| "loss": 2.3062, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 9.649064963385065e-07, | |
| "loss": 2.3401, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 9.644487899488646e-07, | |
| "loss": 2.3225, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 2.343186616897583, | |
| "eval_runtime": 423.247, | |
| "eval_samples_per_second": 20.168, | |
| "eval_steps_per_second": 0.631, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 9.63988228046307e-07, | |
| "loss": 2.3865, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 9.635248134624494e-07, | |
| "loss": 2.304, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 9.630585490464464e-07, | |
| "loss": 2.3999, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 9.625894376649734e-07, | |
| "loss": 2.3153, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 9.6211748220221e-07, | |
| "loss": 2.3494, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 9.616426855598216e-07, | |
| "loss": 2.3437, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 9.61165050656941e-07, | |
| "loss": 2.2526, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 2.342107057571411, | |
| "eval_runtime": 423.3423, | |
| "eval_samples_per_second": 20.163, | |
| "eval_steps_per_second": 0.631, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 9.606845804301523e-07, | |
| "loss": 2.3333, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 9.602012778334705e-07, | |
| "loss": 2.3749, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 9.597151458383251e-07, | |
| "loss": 2.2808, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 9.592261874335416e-07, | |
| "loss": 2.3618, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 9.587344056253219e-07, | |
| "loss": 2.2409, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 9.582398034372272e-07, | |
| "loss": 2.4525, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 2.3411149978637695, | |
| "eval_runtime": 423.3183, | |
| "eval_samples_per_second": 20.164, | |
| "eval_steps_per_second": 0.631, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 9.57742383910159e-07, | |
| "loss": 2.3754, | |
| "step": 501 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 9.572421501023401e-07, | |
| "loss": 2.3668, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 9.567391050892959e-07, | |
| "loss": 2.3598, | |
| "step": 507 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 9.562332519638357e-07, | |
| "loss": 2.3844, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 9.557245938360333e-07, | |
| "loss": 2.2853, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 9.55213133833209e-07, | |
| "loss": 2.371, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 9.546988750999086e-07, | |
| "loss": 2.2973, | |
| "step": 519 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 2.340139627456665, | |
| "eval_runtime": 423.3666, | |
| "eval_samples_per_second": 20.162, | |
| "eval_steps_per_second": 0.631, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 9.541818207978852e-07, | |
| "loss": 2.3004, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 9.536619741060799e-07, | |
| "loss": 2.315, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 9.531393382206014e-07, | |
| "loss": 2.2997, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 9.526139163547072e-07, | |
| "loss": 2.2578, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 9.520857117387836e-07, | |
| "loss": 2.2945, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 9.515547276203255e-07, | |
| "loss": 2.3291, | |
| "step": 537 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 9.510209672639164e-07, | |
| "loss": 2.3566, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 2.339249610900879, | |
| "eval_runtime": 423.2809, | |
| "eval_samples_per_second": 20.166, | |
| "eval_steps_per_second": 0.631, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 9.504844339512094e-07, | |
| "loss": 2.3153, | |
| "step": 543 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 9.499451309809057e-07, | |
| "loss": 2.3686, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 9.494030616687345e-07, | |
| "loss": 2.2894, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 9.488582293474337e-07, | |
| "loss": 2.4301, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 9.483106373667282e-07, | |
| "loss": 2.3472, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 9.477602890933099e-07, | |
| "loss": 2.3336, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 2.3383405208587646, | |
| "eval_runtime": 423.3766, | |
| "eval_samples_per_second": 20.162, | |
| "eval_steps_per_second": 0.631, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 9.472071879108168e-07, | |
| "loss": 2.296, | |
| "step": 561 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 9.466513372198124e-07, | |
| "loss": 2.2938, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 9.460927404377646e-07, | |
| "loss": 2.3346, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 9.455314009990247e-07, | |
| "loss": 2.3366, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 9.449673223548063e-07, | |
| "loss": 2.3299, | |
| "step": 573 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 9.444005079731645e-07, | |
| "loss": 2.3808, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 9.438309613389736e-07, | |
| "loss": 2.3591, | |
| "step": 579 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 2.33746075630188, | |
| "eval_runtime": 423.3304, | |
| "eval_samples_per_second": 20.164, | |
| "eval_steps_per_second": 0.631, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 9.432586859539067e-07, | |
| "loss": 2.4369, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 9.426836853364134e-07, | |
| "loss": 2.3023, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 9.42105963021699e-07, | |
| "loss": 2.3798, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 9.415255225617018e-07, | |
| "loss": 2.3748, | |
| "step": 591 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 9.409423675250719e-07, | |
| "loss": 2.3385, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 9.403565014971493e-07, | |
| "loss": 2.3596, | |
| "step": 597 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 9.397679280799413e-07, | |
| "loss": 2.3233, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 2.3365979194641113, | |
| "eval_runtime": 423.3209, | |
| "eval_samples_per_second": 20.164, | |
| "eval_steps_per_second": 0.631, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 9.39176650892101e-07, | |
| "loss": 2.3402, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 9.385826735689044e-07, | |
| "loss": 2.299, | |
| "step": 606 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 9.37985999762229e-07, | |
| "loss": 2.297, | |
| "step": 609 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 9.3738663314053e-07, | |
| "loss": 2.457, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 9.367845773888192e-07, | |
| "loss": 2.3527, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 9.361798362086412e-07, | |
| "loss": 2.2866, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 2.335691452026367, | |
| "eval_runtime": 423.1955, | |
| "eval_samples_per_second": 20.17, | |
| "eval_steps_per_second": 0.631, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 9.355724133180511e-07, | |
| "loss": 2.3485, | |
| "step": 621 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 9.349623124515921e-07, | |
| "loss": 2.3777, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 9.343495373602714e-07, | |
| "loss": 2.2958, | |
| "step": 627 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 9.337340918115384e-07, | |
| "loss": 2.3733, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 9.331159795892604e-07, | |
| "loss": 2.3486, | |
| "step": 633 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 9.324952044937003e-07, | |
| "loss": 2.2597, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 9.318717703414927e-07, | |
| "loss": 2.3699, | |
| "step": 639 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 2.3348851203918457, | |
| "eval_runtime": 423.3298, | |
| "eval_samples_per_second": 20.164, | |
| "eval_steps_per_second": 0.631, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 9.312456809656203e-07, | |
| "loss": 2.3104, | |
| "step": 642 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 9.306169402153909e-07, | |
| "loss": 2.38, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 9.299855519564135e-07, | |
| "loss": 2.3243, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 9.293515200705739e-07, | |
| "loss": 2.3186, | |
| "step": 651 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.287148484560119e-07, | |
| "loss": 2.3206, | |
| "step": 654 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.280755410270969e-07, | |
| "loss": 2.3302, | |
| "step": 657 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.274336017144031e-07, | |
| "loss": 2.3104, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 2.334101915359497, | |
| "eval_runtime": 423.3459, | |
| "eval_samples_per_second": 20.163, | |
| "eval_steps_per_second": 0.631, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.267890344646867e-07, | |
| "loss": 2.3382, | |
| "step": 663 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.261418432408605e-07, | |
| "loss": 2.2546, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.254920320219699e-07, | |
| "loss": 2.3398, | |
| "step": 669 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.248396048031689e-07, | |
| "loss": 2.259, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.241845655956948e-07, | |
| "loss": 2.3811, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.235269184268441e-07, | |
| "loss": 2.3023, | |
| "step": 678 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 2.333385467529297, | |
| "eval_runtime": 423.3544, | |
| "eval_samples_per_second": 20.163, | |
| "eval_steps_per_second": 0.631, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.22866667339947e-07, | |
| "loss": 2.3402, | |
| "step": 681 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.222038163943437e-07, | |
| "loss": 2.3985, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.215383696653585e-07, | |
| "loss": 2.3785, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.208703312442747e-07, | |
| "loss": 2.3002, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.201997052383106e-07, | |
| "loss": 2.2807, | |
| "step": 693 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.195264957705925e-07, | |
| "loss": 2.3218, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.18850706980131e-07, | |
| "loss": 2.3797, | |
| "step": 699 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 2.332702159881592, | |
| "eval_runtime": 423.4023, | |
| "eval_samples_per_second": 20.16, | |
| "eval_steps_per_second": 0.631, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.181723430217943e-07, | |
| "loss": 2.3441, | |
| "step": 702 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.174914080662837e-07, | |
| "loss": 2.4208, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.168079063001069e-07, | |
| "loss": 2.3724, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.161218419255531e-07, | |
| "loss": 2.3602, | |
| "step": 711 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.154332191606671e-07, | |
| "loss": 2.3921, | |
| "step": 714 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 9.147420422392226e-07, | |
| "loss": 2.3401, | |
| "step": 717 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 9.14048315410697e-07, | |
| "loss": 2.378, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 2.3319976329803467, | |
| "eval_runtime": 423.2623, | |
| "eval_samples_per_second": 20.167, | |
| "eval_steps_per_second": 0.631, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 9.133520429402452e-07, | |
| "loss": 2.2433, | |
| "step": 723 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 9.126532291086727e-07, | |
| "loss": 2.2643, | |
| "step": 726 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 9.119518782124101e-07, | |
| "loss": 2.2668, | |
| "step": 729 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 9.112479945634858e-07, | |
| "loss": 2.3394, | |
| "step": 732 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 9.105415824895007e-07, | |
| "loss": 2.3177, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 9.098326463336005e-07, | |
| "loss": 2.3163, | |
| "step": 738 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 2.331338882446289, | |
| "eval_runtime": 423.2629, | |
| "eval_samples_per_second": 20.167, | |
| "eval_steps_per_second": 0.631, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 9.091211904544497e-07, | |
| "loss": 2.3085, | |
| "step": 741 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 9.084072192262038e-07, | |
| "loss": 2.3119, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 9.076907370384841e-07, | |
| "loss": 2.3025, | |
| "step": 747 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 9.069717482963488e-07, | |
| "loss": 2.3669, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 9.062502574202676e-07, | |
| "loss": 2.3758, | |
| "step": 753 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 9.05526268846093e-07, | |
| "loss": 2.2763, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 9.047997870250346e-07, | |
| "loss": 2.2827, | |
| "step": 759 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 2.3305909633636475, | |
| "eval_runtime": 423.267, | |
| "eval_samples_per_second": 20.167, | |
| "eval_steps_per_second": 0.631, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 9.040708164236302e-07, | |
| "loss": 2.3013, | |
| "step": 762 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 9.033393615237195e-07, | |
| "loss": 2.3456, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 9.026054268224159e-07, | |
| "loss": 2.3182, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 9.018690168320794e-07, | |
| "loss": 2.3545, | |
| "step": 771 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 9.01130136080288e-07, | |
| "loss": 2.3051, | |
| "step": 774 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 9.003887891098106e-07, | |
| "loss": 2.3245, | |
| "step": 777 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 8.996449804785791e-07, | |
| "loss": 2.3258, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 2.3299028873443604, | |
| "eval_runtime": 423.3796, | |
| "eval_samples_per_second": 20.162, | |
| "eval_steps_per_second": 0.631, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 8.988987147596597e-07, | |
| "loss": 2.3031, | |
| "step": 783 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 8.981499965412255e-07, | |
| "loss": 2.2865, | |
| "step": 786 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 8.973988304265279e-07, | |
| "loss": 2.3572, | |
| "step": 789 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 8.966452210338682e-07, | |
| "loss": 2.3531, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 8.958891729965698e-07, | |
| "loss": 2.3163, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 8.951306909629492e-07, | |
| "loss": 2.3084, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 2.329281806945801, | |
| "eval_runtime": 423.286, | |
| "eval_samples_per_second": 20.166, | |
| "eval_steps_per_second": 0.631, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 8.943697795962872e-07, | |
| "loss": 2.3127, | |
| "step": 801 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 8.93606443574801e-07, | |
| "loss": 2.2973, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 8.928406875916148e-07, | |
| "loss": 2.3217, | |
| "step": 807 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 8.920725163547311e-07, | |
| "loss": 2.3282, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 8.91301934587002e-07, | |
| "loss": 2.2591, | |
| "step": 813 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 8.905289470260997e-07, | |
| "loss": 2.35, | |
| "step": 816 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 8.897535584244879e-07, | |
| "loss": 2.335, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 2.3287057876586914, | |
| "eval_runtime": 423.3273, | |
| "eval_samples_per_second": 20.164, | |
| "eval_steps_per_second": 0.631, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 8.889757735493923e-07, | |
| "loss": 2.3729, | |
| "step": 822 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 8.88195597182771e-07, | |
| "loss": 2.3513, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 8.874130341212858e-07, | |
| "loss": 2.3196, | |
| "step": 828 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 8.866280891762722e-07, | |
| "loss": 2.3505, | |
| "step": 831 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 8.858407671737098e-07, | |
| "loss": 2.3756, | |
| "step": 834 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 8.850510729541926e-07, | |
| "loss": 2.3981, | |
| "step": 837 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 8.842590113729e-07, | |
| "loss": 2.395, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 2.328066825866699, | |
| "eval_runtime": 423.2871, | |
| "eval_samples_per_second": 20.166, | |
| "eval_steps_per_second": 0.631, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 8.834645872995661e-07, | |
| "loss": 2.3557, | |
| "step": 843 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 8.826678056184498e-07, | |
| "loss": 2.3604, | |
| "step": 846 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 8.81868671228305e-07, | |
| "loss": 2.3875, | |
| "step": 849 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 8.810671890423507e-07, | |
| "loss": 2.282, | |
| "step": 852 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 8.802633639882405e-07, | |
| "loss": 2.3101, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 8.794572010080324e-07, | |
| "loss": 2.3383, | |
| "step": 858 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 2.327450752258301, | |
| "eval_runtime": 423.3291, | |
| "eval_samples_per_second": 20.164, | |
| "eval_steps_per_second": 0.631, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 8.786487050581581e-07, | |
| "loss": 2.3591, | |
| "step": 861 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 8.778378811093932e-07, | |
| "loss": 2.347, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 8.770247341468258e-07, | |
| "loss": 2.2565, | |
| "step": 867 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 8.762092691698271e-07, | |
| "loss": 2.3666, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 8.753914911920187e-07, | |
| "loss": 2.3629, | |
| "step": 873 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 8.74571405241244e-07, | |
| "loss": 2.3472, | |
| "step": 876 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 8.737490163595354e-07, | |
| "loss": 2.3475, | |
| "step": 879 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 2.3268442153930664, | |
| "eval_runtime": 423.3258, | |
| "eval_samples_per_second": 20.164, | |
| "eval_steps_per_second": 0.631, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 8.72924329603085e-07, | |
| "loss": 2.3445, | |
| "step": 882 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 8.720973500422118e-07, | |
| "loss": 2.3023, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 8.712680827613316e-07, | |
| "loss": 2.2698, | |
| "step": 888 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 8.704365328589258e-07, | |
| "loss": 2.3663, | |
| "step": 891 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 8.696027054475097e-07, | |
| "loss": 2.3187, | |
| "step": 894 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 8.687666056536008e-07, | |
| "loss": 2.3517, | |
| "step": 897 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 8.679282386176878e-07, | |
| "loss": 2.2548, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 2.32629132270813, | |
| "eval_runtime": 423.3296, | |
| "eval_samples_per_second": 20.164, | |
| "eval_steps_per_second": 0.631, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 8.67087609494199e-07, | |
| "loss": 2.2959, | |
| "step": 903 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 8.662447234514701e-07, | |
| "loss": 2.3644, | |
| "step": 906 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 8.653995856717129e-07, | |
| "loss": 2.3586, | |
| "step": 909 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 8.645522013509831e-07, | |
| "loss": 2.3266, | |
| "step": 912 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 8.637025756991489e-07, | |
| "loss": 2.3161, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 8.628507139398582e-07, | |
| "loss": 2.3037, | |
| "step": 918 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 2.3255677223205566, | |
| "eval_runtime": 423.3411, | |
| "eval_samples_per_second": 20.163, | |
| "eval_steps_per_second": 0.631, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 8.61996621310507e-07, | |
| "loss": 2.2742, | |
| "step": 921 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 8.611403030622074e-07, | |
| "loss": 2.2825, | |
| "step": 924 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 8.602817644597542e-07, | |
| "loss": 2.2959, | |
| "step": 927 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 8.594210107815944e-07, | |
| "loss": 2.3072, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 8.585580473197928e-07, | |
| "loss": 2.2897, | |
| "step": 933 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 8.576928793800009e-07, | |
| "loss": 2.3138, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 8.568255122814234e-07, | |
| "loss": 2.302, | |
| "step": 939 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 2.3249897956848145, | |
| "eval_runtime": 423.2819, | |
| "eval_samples_per_second": 20.166, | |
| "eval_steps_per_second": 0.631, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 8.559559513567858e-07, | |
| "loss": 2.3026, | |
| "step": 942 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 8.550842019523018e-07, | |
| "loss": 2.3182, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 8.5421026942764e-07, | |
| "loss": 2.2286, | |
| "step": 948 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 8.53334159155892e-07, | |
| "loss": 2.2955, | |
| "step": 951 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 8.524558765235372e-07, | |
| "loss": 2.2946, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 8.515754269304123e-07, | |
| "loss": 2.3708, | |
| "step": 957 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 8.506928157896763e-07, | |
| "loss": 2.333, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 2.3244550228118896, | |
| "eval_runtime": 423.4402, | |
| "eval_samples_per_second": 20.159, | |
| "eval_steps_per_second": 0.631, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 8.498080485277777e-07, | |
| "loss": 2.3298, | |
| "step": 963 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 8.489211305844215e-07, | |
| "loss": 2.3625, | |
| "step": 966 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 8.480320674125354e-07, | |
| "loss": 2.3087, | |
| "step": 969 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 8.471408644782362e-07, | |
| "loss": 2.2796, | |
| "step": 972 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 8.462475272607964e-07, | |
| "loss": 2.317, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 8.453520612526104e-07, | |
| "loss": 2.3447, | |
| "step": 978 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 2.323906421661377, | |
| "eval_runtime": 423.4069, | |
| "eval_samples_per_second": 20.16, | |
| "eval_steps_per_second": 0.631, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 8.44454471959161e-07, | |
| "loss": 2.3125, | |
| "step": 981 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 8.435547648989851e-07, | |
| "loss": 2.299, | |
| "step": 984 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 8.4265294560364e-07, | |
| "loss": 2.3087, | |
| "step": 987 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 8.417490196176695e-07, | |
| "loss": 2.271, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 8.408429924985697e-07, | |
| "loss": 2.3086, | |
| "step": 993 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 8.39934869816755e-07, | |
| "loss": 2.3539, | |
| "step": 996 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 8.390246571555232e-07, | |
| "loss": 2.2637, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 2.3233530521392822, | |
| "eval_runtime": 423.4804, | |
| "eval_samples_per_second": 20.157, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 8.38112360111022e-07, | |
| "loss": 2.2723, | |
| "step": 1002 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 8.371979842922145e-07, | |
| "loss": 2.2917, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 8.36281535320844e-07, | |
| "loss": 2.2947, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 8.353630188314001e-07, | |
| "loss": 2.3794, | |
| "step": 1011 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 8.344424404710837e-07, | |
| "loss": 2.2467, | |
| "step": 1014 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 8.335198058997728e-07, | |
| "loss": 2.3408, | |
| "step": 1017 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 8.325951207899871e-07, | |
| "loss": 2.4003, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 2.322751045227051, | |
| "eval_runtime": 423.3682, | |
| "eval_samples_per_second": 20.162, | |
| "eval_steps_per_second": 0.631, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 8.316683908268536e-07, | |
| "loss": 2.3281, | |
| "step": 1023 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 8.307396217080709e-07, | |
| "loss": 2.3577, | |
| "step": 1026 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 8.298088191438752e-07, | |
| "loss": 2.3012, | |
| "step": 1029 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 8.288759888570046e-07, | |
| "loss": 2.366, | |
| "step": 1032 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 8.279411365826639e-07, | |
| "loss": 2.4175, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 8.270042680684892e-07, | |
| "loss": 2.3281, | |
| "step": 1038 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 2.322261095046997, | |
| "eval_runtime": 423.4505, | |
| "eval_samples_per_second": 20.158, | |
| "eval_steps_per_second": 0.631, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 8.260653890745133e-07, | |
| "loss": 2.2987, | |
| "step": 1041 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 8.251245053731292e-07, | |
| "loss": 2.3284, | |
| "step": 1044 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.241816227490561e-07, | |
| "loss": 2.3436, | |
| "step": 1047 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.232367469993017e-07, | |
| "loss": 2.2726, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.22289883933129e-07, | |
| "loss": 2.3239, | |
| "step": 1053 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.213410393720181e-07, | |
| "loss": 2.3221, | |
| "step": 1056 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.20390219149633e-07, | |
| "loss": 2.2965, | |
| "step": 1059 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 2.321779251098633, | |
| "eval_runtime": 423.38, | |
| "eval_samples_per_second": 20.162, | |
| "eval_steps_per_second": 0.631, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.194374291117835e-07, | |
| "loss": 2.2872, | |
| "step": 1062 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.184826751163909e-07, | |
| "loss": 2.2789, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.175259630334503e-07, | |
| "loss": 2.2781, | |
| "step": 1068 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 8.165672987449961e-07, | |
| "loss": 2.2374, | |
| "step": 1071 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 8.156066881450653e-07, | |
| "loss": 2.2523, | |
| "step": 1074 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 8.146441371396607e-07, | |
| "loss": 2.2907, | |
| "step": 1077 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 8.136796516467156e-07, | |
| "loss": 2.3227, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 2.3212733268737793, | |
| "eval_runtime": 423.4264, | |
| "eval_samples_per_second": 20.159, | |
| "eval_steps_per_second": 0.631, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 8.127132375960564e-07, | |
| "loss": 2.2747, | |
| "step": 1083 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 8.117449009293668e-07, | |
| "loss": 2.3263, | |
| "step": 1086 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 8.107746476001511e-07, | |
| "loss": 2.3275, | |
| "step": 1089 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 8.098024835736976e-07, | |
| "loss": 2.311, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 8.088284148270416e-07, | |
| "loss": 2.4011, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 8.078524473489298e-07, | |
| "loss": 2.2933, | |
| "step": 1098 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_loss": 2.3207974433898926, | |
| "eval_runtime": 423.4678, | |
| "eval_samples_per_second": 20.157, | |
| "eval_steps_per_second": 0.631, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 8.068745871397815e-07, | |
| "loss": 2.3474, | |
| "step": 1101 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 8.058948402116537e-07, | |
| "loss": 2.3132, | |
| "step": 1104 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 8.049132125882027e-07, | |
| "loss": 2.377, | |
| "step": 1107 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 8.039297103046483e-07, | |
| "loss": 2.2774, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 8.029443394077355e-07, | |
| "loss": 2.3629, | |
| "step": 1113 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 8.019571059556978e-07, | |
| "loss": 2.3565, | |
| "step": 1116 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 8.009680160182205e-07, | |
| "loss": 2.2868, | |
| "step": 1119 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 2.320247173309326, | |
| "eval_runtime": 423.4681, | |
| "eval_samples_per_second": 20.157, | |
| "eval_steps_per_second": 0.631, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 7.999770756764026e-07, | |
| "loss": 2.3414, | |
| "step": 1122 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 7.989842910227196e-07, | |
| "loss": 2.3327, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 7.979896681609864e-07, | |
| "loss": 2.3244, | |
| "step": 1128 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 7.969932132063195e-07, | |
| "loss": 2.3004, | |
| "step": 1131 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 7.959949322850993e-07, | |
| "loss": 2.3689, | |
| "step": 1134 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 7.949948315349328e-07, | |
| "loss": 2.3043, | |
| "step": 1137 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 7.93992917104615e-07, | |
| "loss": 2.3528, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 2.319669723510742, | |
| "eval_runtime": 423.3384, | |
| "eval_samples_per_second": 20.164, | |
| "eval_steps_per_second": 0.631, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 7.929891951540928e-07, | |
| "loss": 2.2625, | |
| "step": 1143 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 7.919836718544248e-07, | |
| "loss": 2.321, | |
| "step": 1146 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 7.909763533877459e-07, | |
| "loss": 2.3248, | |
| "step": 1149 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 7.899672459472266e-07, | |
| "loss": 2.3621, | |
| "step": 1152 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 7.889563557370377e-07, | |
| "loss": 2.3353, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 7.879436889723101e-07, | |
| "loss": 2.2961, | |
| "step": 1158 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": 2.3192245960235596, | |
| "eval_runtime": 423.3625, | |
| "eval_samples_per_second": 20.162, | |
| "eval_steps_per_second": 0.631, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 7.869292518790969e-07, | |
| "loss": 2.3059, | |
| "step": 1161 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 7.859130506943361e-07, | |
| "loss": 2.2811, | |
| "step": 1164 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 7.848950916658117e-07, | |
| "loss": 2.2763, | |
| "step": 1167 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 7.838753810521148e-07, | |
| "loss": 2.2624, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 7.828539251226058e-07, | |
| "loss": 2.3175, | |
| "step": 1173 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 7.818307301573755e-07, | |
| "loss": 2.2654, | |
| "step": 1176 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 7.808058024472066e-07, | |
| "loss": 2.3594, | |
| "step": 1179 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 2.318722724914551, | |
| "eval_runtime": 423.4852, | |
| "eval_samples_per_second": 20.157, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 7.797791482935354e-07, | |
| "loss": 2.332, | |
| "step": 1182 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 7.787507740084119e-07, | |
| "loss": 2.3029, | |
| "step": 1185 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 7.777206859144626e-07, | |
| "loss": 2.3374, | |
| "step": 1188 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 7.7668889034485e-07, | |
| "loss": 2.2754, | |
| "step": 1191 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 7.756553936432355e-07, | |
| "loss": 2.3292, | |
| "step": 1194 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 7.746202021637383e-07, | |
| "loss": 2.333, | |
| "step": 1197 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 7.735833222708978e-07, | |
| "loss": 2.3139, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": 2.3182308673858643, | |
| "eval_runtime": 423.5569, | |
| "eval_samples_per_second": 20.153, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 7.725447603396344e-07, | |
| "loss": 2.3044, | |
| "step": 1203 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 7.715045227552095e-07, | |
| "loss": 2.2979, | |
| "step": 1206 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 7.704626159131866e-07, | |
| "loss": 2.286, | |
| "step": 1209 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 7.694190462193929e-07, | |
| "loss": 2.3523, | |
| "step": 1212 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 7.683738200898783e-07, | |
| "loss": 2.3239, | |
| "step": 1215 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 7.673269439508769e-07, | |
| "loss": 2.3573, | |
| "step": 1218 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 2.317840337753296, | |
| "eval_runtime": 423.5223, | |
| "eval_samples_per_second": 20.155, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 7.662784242387678e-07, | |
| "loss": 2.3076, | |
| "step": 1221 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 7.652282674000345e-07, | |
| "loss": 2.2982, | |
| "step": 1224 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 7.641764798912262e-07, | |
| "loss": 2.3276, | |
| "step": 1227 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 7.631230681789176e-07, | |
| "loss": 2.307, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 7.620680387396695e-07, | |
| "loss": 2.3529, | |
| "step": 1233 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 7.610113980599883e-07, | |
| "loss": 2.282, | |
| "step": 1236 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 7.599531526362873e-07, | |
| "loss": 2.3404, | |
| "step": 1239 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 2.3173727989196777, | |
| "eval_runtime": 423.4318, | |
| "eval_samples_per_second": 20.159, | |
| "eval_steps_per_second": 0.631, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 7.588933089748451e-07, | |
| "loss": 2.3277, | |
| "step": 1242 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 7.578318735917675e-07, | |
| "loss": 2.2916, | |
| "step": 1245 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 7.56768853012946e-07, | |
| "loss": 2.3011, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 7.557042537740183e-07, | |
| "loss": 2.3478, | |
| "step": 1251 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 7.546380824203277e-07, | |
| "loss": 2.3414, | |
| "step": 1254 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 7.535703455068835e-07, | |
| "loss": 2.3388, | |
| "step": 1257 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 7.525010495983201e-07, | |
| "loss": 2.3752, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 2.316869020462036, | |
| "eval_runtime": 423.6284, | |
| "eval_samples_per_second": 20.15, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 7.514302012688574e-07, | |
| "loss": 2.2594, | |
| "step": 1263 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 7.503578071022587e-07, | |
| "loss": 2.2831, | |
| "step": 1266 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 7.492838736917927e-07, | |
| "loss": 2.2945, | |
| "step": 1269 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 7.482084076401908e-07, | |
| "loss": 2.2828, | |
| "step": 1272 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 7.471314155596075e-07, | |
| "loss": 2.2738, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 7.4605290407158e-07, | |
| "loss": 2.3049, | |
| "step": 1278 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 2.3168187141418457, | |
| "eval_runtime": 423.5196, | |
| "eval_samples_per_second": 20.155, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 7.449728798069863e-07, | |
| "loss": 2.3274, | |
| "step": 1281 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 7.438913494060062e-07, | |
| "loss": 2.3031, | |
| "step": 1284 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 7.428083195180787e-07, | |
| "loss": 2.3463, | |
| "step": 1287 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 7.417237968018623e-07, | |
| "loss": 2.2969, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 7.406377879251935e-07, | |
| "loss": 2.3231, | |
| "step": 1293 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 7.395502995650462e-07, | |
| "loss": 2.2752, | |
| "step": 1296 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 7.384613384074898e-07, | |
| "loss": 2.3099, | |
| "step": 1299 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_loss": 2.31632924079895, | |
| "eval_runtime": 423.6273, | |
| "eval_samples_per_second": 20.15, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 7.373709111476497e-07, | |
| "loss": 2.2691, | |
| "step": 1302 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 7.362790244896644e-07, | |
| "loss": 2.3205, | |
| "step": 1305 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 7.351856851466454e-07, | |
| "loss": 2.2233, | |
| "step": 1308 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 7.340908998406352e-07, | |
| "loss": 2.305, | |
| "step": 1311 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 7.329946753025668e-07, | |
| "loss": 2.3221, | |
| "step": 1314 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 7.318970182722216e-07, | |
| "loss": 2.3171, | |
| "step": 1317 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 7.30797935498188e-07, | |
| "loss": 2.2663, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "eval_loss": 2.3159472942352295, | |
| "eval_runtime": 423.528, | |
| "eval_samples_per_second": 20.155, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 7.296974337378207e-07, | |
| "loss": 2.2756, | |
| "step": 1323 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 7.285955197571982e-07, | |
| "loss": 2.308, | |
| "step": 1326 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 7.274922003310812e-07, | |
| "loss": 2.3399, | |
| "step": 1329 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 7.263874822428723e-07, | |
| "loss": 2.2725, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 7.252813722845724e-07, | |
| "loss": 2.2886, | |
| "step": 1335 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 7.241738772567404e-07, | |
| "loss": 2.3081, | |
| "step": 1338 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_loss": 2.315493106842041, | |
| "eval_runtime": 423.5508, | |
| "eval_samples_per_second": 20.153, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 7.230650039684505e-07, | |
| "loss": 2.3301, | |
| "step": 1341 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 7.219547592372511e-07, | |
| "loss": 2.3124, | |
| "step": 1344 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 7.208431498891221e-07, | |
| "loss": 2.2829, | |
| "step": 1347 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 7.197301827584335e-07, | |
| "loss": 2.3014, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 7.18615864687903e-07, | |
| "loss": 2.3313, | |
| "step": 1353 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 7.175002025285546e-07, | |
| "loss": 2.2866, | |
| "step": 1356 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 7.163832031396751e-07, | |
| "loss": 2.3324, | |
| "step": 1359 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 2.3150970935821533, | |
| "eval_runtime": 423.5225, | |
| "eval_samples_per_second": 20.155, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 7.152648733887738e-07, | |
| "loss": 2.3364, | |
| "step": 1362 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 7.141452201515385e-07, | |
| "loss": 2.3039, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 7.130242503117949e-07, | |
| "loss": 2.3022, | |
| "step": 1368 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 7.119019707614626e-07, | |
| "loss": 2.3087, | |
| "step": 1371 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 7.107783884005136e-07, | |
| "loss": 2.4119, | |
| "step": 1374 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 7.096535101369304e-07, | |
| "loss": 2.3349, | |
| "step": 1377 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 7.085273428866624e-07, | |
| "loss": 2.2818, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "eval_loss": 2.3148207664489746, | |
| "eval_runtime": 423.6185, | |
| "eval_samples_per_second": 20.15, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 7.073998935735841e-07, | |
| "loss": 2.3156, | |
| "step": 1383 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 7.062711691294524e-07, | |
| "loss": 2.2651, | |
| "step": 1386 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 7.051411764938638e-07, | |
| "loss": 2.2672, | |
| "step": 1389 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 7.04009922614212e-07, | |
| "loss": 2.3123, | |
| "step": 1392 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 7.028774144456451e-07, | |
| "loss": 2.2977, | |
| "step": 1395 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 7.017436589510222e-07, | |
| "loss": 2.3032, | |
| "step": 1398 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_loss": 2.3144261837005615, | |
| "eval_runtime": 423.4989, | |
| "eval_samples_per_second": 20.156, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 7.006086631008721e-07, | |
| "loss": 2.2844, | |
| "step": 1401 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 6.994724338733489e-07, | |
| "loss": 2.3115, | |
| "step": 1404 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 6.983349782541901e-07, | |
| "loss": 2.2636, | |
| "step": 1407 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 6.971963032366727e-07, | |
| "loss": 2.3014, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 6.960564158215714e-07, | |
| "loss": 2.2709, | |
| "step": 1413 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 6.949153230171146e-07, | |
| "loss": 2.2757, | |
| "step": 1416 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 6.937730318389419e-07, | |
| "loss": 2.2968, | |
| "step": 1419 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_loss": 2.314065456390381, | |
| "eval_runtime": 423.7021, | |
| "eval_samples_per_second": 20.146, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 6.926295493100602e-07, | |
| "loss": 2.2748, | |
| "step": 1422 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 6.914848824608016e-07, | |
| "loss": 2.3398, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 6.903390383287794e-07, | |
| "loss": 2.3015, | |
| "step": 1428 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 6.891920239588449e-07, | |
| "loss": 2.296, | |
| "step": 1431 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 6.880438464030444e-07, | |
| "loss": 2.3183, | |
| "step": 1434 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 6.868945127205756e-07, | |
| "loss": 2.2845, | |
| "step": 1437 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 6.857440299777445e-07, | |
| "loss": 2.2872, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "eval_loss": 2.313587188720703, | |
| "eval_runtime": 423.2156, | |
| "eval_samples_per_second": 20.169, | |
| "eval_steps_per_second": 0.631, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 6.845924052479212e-07, | |
| "loss": 2.3286, | |
| "step": 1443 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 6.834396456114975e-07, | |
| "loss": 2.2985, | |
| "step": 1446 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 6.822857581558422e-07, | |
| "loss": 2.2685, | |
| "step": 1449 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 6.81130749975259e-07, | |
| "loss": 2.2893, | |
| "step": 1452 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 6.799746281709412e-07, | |
| "loss": 2.2832, | |
| "step": 1455 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 6.788173998509293e-07, | |
| "loss": 2.3542, | |
| "step": 1458 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_loss": 2.3132660388946533, | |
| "eval_runtime": 423.6025, | |
| "eval_samples_per_second": 20.151, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 6.776590721300663e-07, | |
| "loss": 2.2681, | |
| "step": 1461 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 6.764996521299555e-07, | |
| "loss": 2.2491, | |
| "step": 1464 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 6.75339146978915e-07, | |
| "loss": 2.2629, | |
| "step": 1467 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 6.741775638119344e-07, | |
| "loss": 2.2829, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 6.730149097706318e-07, | |
| "loss": 2.2667, | |
| "step": 1473 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 6.718511920032088e-07, | |
| "loss": 2.3181, | |
| "step": 1476 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 6.706864176644073e-07, | |
| "loss": 2.3007, | |
| "step": 1479 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "eval_loss": 2.3128092288970947, | |
| "eval_runtime": 423.6014, | |
| "eval_samples_per_second": 20.151, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 6.695205939154645e-07, | |
| "loss": 2.2827, | |
| "step": 1482 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 6.683537279240705e-07, | |
| "loss": 2.2754, | |
| "step": 1485 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 6.671858268643225e-07, | |
| "loss": 2.2312, | |
| "step": 1488 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 6.660168979166819e-07, | |
| "loss": 2.3098, | |
| "step": 1491 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 6.648469482679297e-07, | |
| "loss": 2.2561, | |
| "step": 1494 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 6.636759851111222e-07, | |
| "loss": 2.2789, | |
| "step": 1497 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 6.625040156455471e-07, | |
| "loss": 2.2531, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "eval_loss": 2.312640905380249, | |
| "eval_runtime": 423.502, | |
| "eval_samples_per_second": 20.156, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 6.613310470766787e-07, | |
| "loss": 2.3494, | |
| "step": 1503 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 6.601570866161345e-07, | |
| "loss": 2.2634, | |
| "step": 1506 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 6.589821414816301e-07, | |
| "loss": 2.296, | |
| "step": 1509 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 6.578062188969349e-07, | |
| "loss": 2.2437, | |
| "step": 1512 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 6.566293260918279e-07, | |
| "loss": 2.3483, | |
| "step": 1515 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 6.554514703020533e-07, | |
| "loss": 2.2712, | |
| "step": 1518 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 2.312190532684326, | |
| "eval_runtime": 423.5944, | |
| "eval_samples_per_second": 20.151, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 6.542726587692756e-07, | |
| "loss": 2.288, | |
| "step": 1521 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 6.530928987410361e-07, | |
| "loss": 2.2557, | |
| "step": 1524 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 6.519121974707066e-07, | |
| "loss": 2.3426, | |
| "step": 1527 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 6.507305622174467e-07, | |
| "loss": 2.2903, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 6.495480002461577e-07, | |
| "loss": 2.294, | |
| "step": 1533 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 6.48364518827439e-07, | |
| "loss": 2.284, | |
| "step": 1536 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 6.471801252375425e-07, | |
| "loss": 2.2413, | |
| "step": 1539 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "eval_loss": 2.312066078186035, | |
| "eval_runtime": 423.5569, | |
| "eval_samples_per_second": 20.153, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 6.459948267583285e-07, | |
| "loss": 2.3278, | |
| "step": 1542 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 6.448086306772207e-07, | |
| "loss": 2.3135, | |
| "step": 1545 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 6.436215442871615e-07, | |
| "loss": 2.2751, | |
| "step": 1548 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 6.424335748865668e-07, | |
| "loss": 2.3304, | |
| "step": 1551 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 6.412447297792818e-07, | |
| "loss": 2.3364, | |
| "step": 1554 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 6.400550162745354e-07, | |
| "loss": 2.2637, | |
| "step": 1557 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 6.388644416868956e-07, | |
| "loss": 2.2676, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "eval_loss": 2.311553478240967, | |
| "eval_runtime": 423.529, | |
| "eval_samples_per_second": 20.154, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 6.376730133362247e-07, | |
| "loss": 2.1986, | |
| "step": 1563 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 6.364807385476336e-07, | |
| "loss": 2.2948, | |
| "step": 1566 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 6.352876246514378e-07, | |
| "loss": 2.34, | |
| "step": 1569 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 6.340936789831115e-07, | |
| "loss": 2.2766, | |
| "step": 1572 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 6.32898908883243e-07, | |
| "loss": 2.3154, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 6.317033216974889e-07, | |
| "loss": 2.2639, | |
| "step": 1578 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_loss": 2.3112854957580566, | |
| "eval_runtime": 423.6669, | |
| "eval_samples_per_second": 20.148, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 6.305069247765299e-07, | |
| "loss": 2.251, | |
| "step": 1581 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 6.293097254760247e-07, | |
| "loss": 2.3302, | |
| "step": 1584 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 6.281117311565654e-07, | |
| "loss": 2.2488, | |
| "step": 1587 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 6.269129491836321e-07, | |
| "loss": 2.2853, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 6.257133869275472e-07, | |
| "loss": 2.3204, | |
| "step": 1593 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 6.245130517634306e-07, | |
| "loss": 2.2984, | |
| "step": 1596 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 6.233119510711543e-07, | |
| "loss": 2.3206, | |
| "step": 1599 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "eval_loss": 2.3111162185668945, | |
| "eval_runtime": 423.5824, | |
| "eval_samples_per_second": 20.152, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 6.221100922352968e-07, | |
| "loss": 2.2511, | |
| "step": 1602 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 6.209074826450974e-07, | |
| "loss": 2.2552, | |
| "step": 1605 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 6.197041296944122e-07, | |
| "loss": 2.2893, | |
| "step": 1608 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 6.185000407816663e-07, | |
| "loss": 2.3363, | |
| "step": 1611 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 6.172952233098109e-07, | |
| "loss": 2.3269, | |
| "step": 1614 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 6.160896846862753e-07, | |
| "loss": 2.33, | |
| "step": 1617 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 6.148834323229238e-07, | |
| "loss": 2.2845, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_loss": 2.3106329441070557, | |
| "eval_runtime": 423.3773, | |
| "eval_samples_per_second": 20.162, | |
| "eval_steps_per_second": 0.631, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 6.136764736360076e-07, | |
| "loss": 2.2542, | |
| "step": 1623 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 6.124688160461217e-07, | |
| "loss": 2.2704, | |
| "step": 1626 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 6.112604669781572e-07, | |
| "loss": 2.3159, | |
| "step": 1629 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 6.100514338612571e-07, | |
| "loss": 2.2634, | |
| "step": 1632 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 6.088417241287696e-07, | |
| "loss": 2.2725, | |
| "step": 1635 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 6.076313452182032e-07, | |
| "loss": 2.2322, | |
| "step": 1638 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "eval_loss": 2.3104732036590576, | |
| "eval_runtime": 423.6269, | |
| "eval_samples_per_second": 20.15, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 6.064203045711807e-07, | |
| "loss": 2.2647, | |
| "step": 1641 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 6.052086096333927e-07, | |
| "loss": 2.3305, | |
| "step": 1644 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 6.039962678545535e-07, | |
| "loss": 2.2913, | |
| "step": 1647 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 6.027832866883532e-07, | |
| "loss": 2.2252, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 6.015696735924141e-07, | |
| "loss": 2.3144, | |
| "step": 1653 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 6.003554360282425e-07, | |
| "loss": 2.3081, | |
| "step": 1656 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 5.991405814611855e-07, | |
| "loss": 2.284, | |
| "step": 1659 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_loss": 2.3101911544799805, | |
| "eval_runtime": 423.606, | |
| "eval_samples_per_second": 20.151, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 5.97925117360382e-07, | |
| "loss": 2.3429, | |
| "step": 1662 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 5.967090511987198e-07, | |
| "loss": 2.3258, | |
| "step": 1665 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 5.954923904527876e-07, | |
| "loss": 2.3345, | |
| "step": 1668 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 5.942751426028296e-07, | |
| "loss": 2.2829, | |
| "step": 1671 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 5.930573151327e-07, | |
| "loss": 2.3246, | |
| "step": 1674 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 5.918389155298166e-07, | |
| "loss": 2.2878, | |
| "step": 1677 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 5.906199512851144e-07, | |
| "loss": 2.2834, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_loss": 2.3097965717315674, | |
| "eval_runtime": 423.5642, | |
| "eval_samples_per_second": 20.153, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 5.894004298930003e-07, | |
| "loss": 2.2633, | |
| "step": 1683 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 5.881803588513065e-07, | |
| "loss": 2.2489, | |
| "step": 1686 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 5.869597456612441e-07, | |
| "loss": 2.2432, | |
| "step": 1689 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 5.857385978273587e-07, | |
| "loss": 2.3146, | |
| "step": 1692 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 5.845169228574813e-07, | |
| "loss": 2.2641, | |
| "step": 1695 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 5.832947282626852e-07, | |
| "loss": 2.3092, | |
| "step": 1698 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "eval_loss": 2.309492826461792, | |
| "eval_runtime": 423.6808, | |
| "eval_samples_per_second": 20.147, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 5.820720215572374e-07, | |
| "loss": 2.2735, | |
| "step": 1701 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 5.808488102585547e-07, | |
| "loss": 2.3068, | |
| "step": 1704 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 5.796251018871547e-07, | |
| "loss": 2.2826, | |
| "step": 1707 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 5.784009039666124e-07, | |
| "loss": 2.1923, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 5.771762240235119e-07, | |
| "loss": 2.3212, | |
| "step": 1713 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 5.759510695874012e-07, | |
| "loss": 2.2999, | |
| "step": 1716 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 5.747254481907451e-07, | |
| "loss": 2.2863, | |
| "step": 1719 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_loss": 2.3091623783111572, | |
| "eval_runtime": 423.6551, | |
| "eval_samples_per_second": 20.148, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 5.7349936736888e-07, | |
| "loss": 2.3533, | |
| "step": 1722 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 5.722728346599667e-07, | |
| "loss": 2.2678, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 5.710458576049438e-07, | |
| "loss": 2.2349, | |
| "step": 1728 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 5.698184437474826e-07, | |
| "loss": 2.3027, | |
| "step": 1731 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 5.685906006339391e-07, | |
| "loss": 2.3294, | |
| "step": 1734 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 5.673623358133095e-07, | |
| "loss": 2.2783, | |
| "step": 1737 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 5.661336568371815e-07, | |
| "loss": 2.3281, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "eval_loss": 2.309011936187744, | |
| "eval_runtime": 423.8896, | |
| "eval_samples_per_second": 20.137, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 5.649045712596903e-07, | |
| "loss": 2.1963, | |
| "step": 1743 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 5.636750866374698e-07, | |
| "loss": 2.2346, | |
| "step": 1746 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 5.624452105296086e-07, | |
| "loss": 2.3149, | |
| "step": 1749 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 5.612149504976008e-07, | |
| "loss": 2.2763, | |
| "step": 1752 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 5.59984314105302e-07, | |
| "loss": 2.2088, | |
| "step": 1755 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 5.587533089188814e-07, | |
| "loss": 2.2591, | |
| "step": 1758 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_loss": 2.3086211681365967, | |
| "eval_runtime": 423.8256, | |
| "eval_samples_per_second": 20.14, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 5.575219425067753e-07, | |
| "loss": 2.2959, | |
| "step": 1761 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 5.562902224396415e-07, | |
| "loss": 2.25, | |
| "step": 1764 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 5.550581562903114e-07, | |
| "loss": 2.2962, | |
| "step": 1767 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 5.538257516337449e-07, | |
| "loss": 2.251, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 5.525930160469825e-07, | |
| "loss": 2.3452, | |
| "step": 1773 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 5.513599571090999e-07, | |
| "loss": 2.2982, | |
| "step": 1776 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 5.501265824011601e-07, | |
| "loss": 2.2629, | |
| "step": 1779 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_loss": 2.308394432067871, | |
| "eval_runtime": 423.8076, | |
| "eval_samples_per_second": 20.141, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 5.488928995061684e-07, | |
| "loss": 2.2443, | |
| "step": 1782 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 5.476589160090237e-07, | |
| "loss": 2.3114, | |
| "step": 1785 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 5.464246394964746e-07, | |
| "loss": 2.248, | |
| "step": 1788 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 5.451900775570697e-07, | |
| "loss": 2.2687, | |
| "step": 1791 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 5.439552377811134e-07, | |
| "loss": 2.3112, | |
| "step": 1794 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 5.42720127760618e-07, | |
| "loss": 2.3296, | |
| "step": 1797 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 5.414847550892571e-07, | |
| "loss": 2.3287, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "eval_loss": 2.3081881999969482, | |
| "eval_runtime": 423.7599, | |
| "eval_samples_per_second": 20.143, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 5.402491273623198e-07, | |
| "loss": 2.2917, | |
| "step": 1803 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 5.390132521766625e-07, | |
| "loss": 2.3018, | |
| "step": 1806 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 5.377771371306635e-07, | |
| "loss": 2.2418, | |
| "step": 1809 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 5.365407898241755e-07, | |
| "loss": 2.2849, | |
| "step": 1812 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 5.353042178584797e-07, | |
| "loss": 2.2288, | |
| "step": 1815 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 5.340674288362379e-07, | |
| "loss": 2.2505, | |
| "step": 1818 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_loss": 2.307854175567627, | |
| "eval_runtime": 423.7254, | |
| "eval_samples_per_second": 20.145, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 5.32830430361447e-07, | |
| "loss": 2.2766, | |
| "step": 1821 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 5.315932300393912e-07, | |
| "loss": 2.3088, | |
| "step": 1824 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 5.303558354765959e-07, | |
| "loss": 2.3131, | |
| "step": 1827 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 5.291182542807806e-07, | |
| "loss": 2.3099, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 5.278804940608125e-07, | |
| "loss": 2.2755, | |
| "step": 1833 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 5.266425624266593e-07, | |
| "loss": 2.3089, | |
| "step": 1836 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 5.254044669893424e-07, | |
| "loss": 2.223, | |
| "step": 1839 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "eval_loss": 2.3075809478759766, | |
| "eval_runtime": 423.9002, | |
| "eval_samples_per_second": 20.137, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 5.241662153608906e-07, | |
| "loss": 2.3372, | |
| "step": 1842 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 5.229278151542929e-07, | |
| "loss": 2.3305, | |
| "step": 1845 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 5.216892739834519e-07, | |
| "loss": 2.2677, | |
| "step": 1848 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 5.204505994631362e-07, | |
| "loss": 2.3112, | |
| "step": 1851 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 5.192117992089356e-07, | |
| "loss": 2.2879, | |
| "step": 1854 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 5.179728808372112e-07, | |
| "loss": 2.2813, | |
| "step": 1857 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 5.167338519650521e-07, | |
| "loss": 2.2174, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 2.3073344230651855, | |
| "eval_runtime": 423.7318, | |
| "eval_samples_per_second": 20.145, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 5.154947202102254e-07, | |
| "loss": 2.2635, | |
| "step": 1863 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 5.142554931911315e-07, | |
| "loss": 2.2595, | |
| "step": 1866 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 5.13016178526756e-07, | |
| "loss": 2.3065, | |
| "step": 1869 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 5.117767838366238e-07, | |
| "loss": 2.3224, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 5.105373167407516e-07, | |
| "loss": 2.226, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 5.092977848596011e-07, | |
| "loss": 2.3372, | |
| "step": 1878 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_loss": 2.307128429412842, | |
| "eval_runtime": 423.6944, | |
| "eval_samples_per_second": 20.147, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 5.080581958140327e-07, | |
| "loss": 2.3131, | |
| "step": 1881 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 5.068185572252579e-07, | |
| "loss": 2.3115, | |
| "step": 1884 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 5.05578876714793e-07, | |
| "loss": 2.3032, | |
| "step": 1887 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 5.043391619044122e-07, | |
| "loss": 2.2818, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 5.030994204161003e-07, | |
| "loss": 2.2672, | |
| "step": 1893 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 5.018596598720058e-07, | |
| "loss": 2.3055, | |
| "step": 1896 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 5.006198878943954e-07, | |
| "loss": 2.2662, | |
| "step": 1899 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_loss": 2.3069169521331787, | |
| "eval_runtime": 423.6523, | |
| "eval_samples_per_second": 20.149, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 4.993801121056048e-07, | |
| "loss": 2.2982, | |
| "step": 1902 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 4.981403401279943e-07, | |
| "loss": 2.2884, | |
| "step": 1905 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 4.969005795838998e-07, | |
| "loss": 2.2941, | |
| "step": 1908 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 4.956608380955877e-07, | |
| "loss": 2.3172, | |
| "step": 1911 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 4.94421123285207e-07, | |
| "loss": 2.2671, | |
| "step": 1914 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 4.931814427747421e-07, | |
| "loss": 2.2642, | |
| "step": 1917 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 4.919418041859674e-07, | |
| "loss": 2.3282, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_loss": 2.3066823482513428, | |
| "eval_runtime": 423.8373, | |
| "eval_samples_per_second": 20.14, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 4.907022151403991e-07, | |
| "loss": 2.2661, | |
| "step": 1923 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 4.894626832592485e-07, | |
| "loss": 2.2434, | |
| "step": 1926 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 4.882232161633762e-07, | |
| "loss": 2.2517, | |
| "step": 1929 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 4.86983821473244e-07, | |
| "loss": 2.2487, | |
| "step": 1932 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 4.857445068088687e-07, | |
| "loss": 2.2646, | |
| "step": 1935 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 4.845052797897746e-07, | |
| "loss": 2.1408, | |
| "step": 1938 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "eval_loss": 2.3063833713531494, | |
| "eval_runtime": 423.8484, | |
| "eval_samples_per_second": 20.139, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 4.832661480349479e-07, | |
| "loss": 2.3191, | |
| "step": 1941 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 4.820271191627886e-07, | |
| "loss": 2.2882, | |
| "step": 1944 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 4.807882007910646e-07, | |
| "loss": 2.3442, | |
| "step": 1947 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 4.795494005368639e-07, | |
| "loss": 2.3082, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 4.783107260165483e-07, | |
| "loss": 2.2433, | |
| "step": 1953 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 4.770721848457071e-07, | |
| "loss": 2.3025, | |
| "step": 1956 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 4.7583378463910945e-07, | |
| "loss": 2.2559, | |
| "step": 1959 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "eval_loss": 2.3061537742614746, | |
| "eval_runtime": 423.8032, | |
| "eval_samples_per_second": 20.141, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 4.745955330106577e-07, | |
| "loss": 2.2355, | |
| "step": 1962 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 4.733574375733408e-07, | |
| "loss": 2.3659, | |
| "step": 1965 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 4.7211950593918756e-07, | |
| "loss": 2.3009, | |
| "step": 1968 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 4.7088174571921946e-07, | |
| "loss": 2.301, | |
| "step": 1971 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 4.696441645234041e-07, | |
| "loss": 2.2812, | |
| "step": 1974 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 4.684067699606088e-07, | |
| "loss": 2.3294, | |
| "step": 1977 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 4.671695696385531e-07, | |
| "loss": 2.337, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "eval_loss": 2.3059725761413574, | |
| "eval_runtime": 423.7698, | |
| "eval_samples_per_second": 20.143, | |
| "eval_steps_per_second": 0.63, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 4.659325711637621e-07, | |
| "loss": 2.2814, | |
| "step": 1983 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 4.646957821415203e-07, | |
| "loss": 2.3117, | |
| "step": 1986 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 4.6345921017582444e-07, | |
| "loss": 2.2646, | |
| "step": 1989 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 4.6222286286933667e-07, | |
| "loss": 2.3307, | |
| "step": 1992 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 4.609867478233376e-07, | |
| "loss": 2.2327, | |
| "step": 1995 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 4.5975087263768024e-07, | |
| "loss": 2.2712, | |
| "step": 1998 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "eval_loss": 2.305758476257324, | |
| "eval_runtime": 423.7395, | |
| "eval_samples_per_second": 20.144, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 4.5851524491074265e-07, | |
| "loss": 2.3103, | |
| "step": 2001 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 4.5727987223938203e-07, | |
| "loss": 2.2437, | |
| "step": 2004 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 4.560447622188866e-07, | |
| "loss": 2.2446, | |
| "step": 2007 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 4.548099224429303e-07, | |
| "loss": 2.2253, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 4.535753605035256e-07, | |
| "loss": 2.2397, | |
| "step": 2013 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 4.523410839909763e-07, | |
| "loss": 2.3447, | |
| "step": 2016 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 4.5110710049383173e-07, | |
| "loss": 2.3251, | |
| "step": 2019 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "eval_loss": 2.3055238723754883, | |
| "eval_runtime": 423.7668, | |
| "eval_samples_per_second": 20.143, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 4.4987341759883985e-07, | |
| "loss": 2.2572, | |
| "step": 2022 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 4.486400428909002e-07, | |
| "loss": 2.3107, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 4.4781796804540905e-07, | |
| "loss": 2.2396, | |
| "step": 2028 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 4.465851238327215e-07, | |
| "loss": 2.3031, | |
| "step": 2031 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 4.457634096698275e-07, | |
| "loss": 2.2643, | |
| "step": 2034 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 4.4453111700721476e-07, | |
| "loss": 2.2851, | |
| "step": 2037 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 4.4329916537705867e-07, | |
| "loss": 2.2894, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "eval_loss": 2.3053619861602783, | |
| "eval_runtime": 423.6799, | |
| "eval_samples_per_second": 20.147, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 4.4206756235361475e-07, | |
| "loss": 2.2917, | |
| "step": 2043 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 4.408363155089951e-07, | |
| "loss": 2.2395, | |
| "step": 2046 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 4.396054324131219e-07, | |
| "loss": 2.2643, | |
| "step": 2049 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 4.383749206336813e-07, | |
| "loss": 2.3527, | |
| "step": 2052 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 4.3714478773607625e-07, | |
| "loss": 2.2174, | |
| "step": 2055 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 4.3591504128338055e-07, | |
| "loss": 2.2587, | |
| "step": 2058 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "eval_loss": 2.3052470684051514, | |
| "eval_runtime": 423.7595, | |
| "eval_samples_per_second": 20.143, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 4.346856888362914e-07, | |
| "loss": 2.2754, | |
| "step": 2061 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 4.3345673795308427e-07, | |
| "loss": 2.2893, | |
| "step": 2064 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 4.3222819618956584e-07, | |
| "loss": 2.222, | |
| "step": 2067 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 4.310000710990265e-07, | |
| "loss": 2.333, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 4.297723702321959e-07, | |
| "loss": 2.2997, | |
| "step": 2073 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 4.2854510113719506e-07, | |
| "loss": 2.2541, | |
| "step": 2076 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 4.273182713594904e-07, | |
| "loss": 2.2966, | |
| "step": 2079 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_loss": 2.3049557209014893, | |
| "eval_runtime": 423.917, | |
| "eval_samples_per_second": 20.136, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 4.2609188844184705e-07, | |
| "loss": 2.2776, | |
| "step": 2082 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 4.2527455180925484e-07, | |
| "loss": 2.2846, | |
| "step": 2085 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 4.240489304125989e-07, | |
| "loss": 2.2439, | |
| "step": 2088 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 4.2282377597648807e-07, | |
| "loss": 2.335, | |
| "step": 2091 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 4.215990960333874e-07, | |
| "loss": 2.2774, | |
| "step": 2094 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 4.203748981128453e-07, | |
| "loss": 2.2459, | |
| "step": 2097 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 4.1915118974144533e-07, | |
| "loss": 2.2533, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "eval_loss": 2.3047776222229004, | |
| "eval_runtime": 424.029, | |
| "eval_samples_per_second": 20.131, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 4.179279784427624e-07, | |
| "loss": 2.2719, | |
| "step": 2103 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 4.1670527173731494e-07, | |
| "loss": 2.3111, | |
| "step": 2106 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 4.1548307714251875e-07, | |
| "loss": 2.3206, | |
| "step": 2109 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 4.1426140217264136e-07, | |
| "loss": 2.3619, | |
| "step": 2112 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 4.130402543387557e-07, | |
| "loss": 2.2922, | |
| "step": 2115 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 4.118196411486937e-07, | |
| "loss": 2.2691, | |
| "step": 2118 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "eval_loss": 2.304494619369507, | |
| "eval_runtime": 424.0274, | |
| "eval_samples_per_second": 20.131, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 4.1059957010699976e-07, | |
| "loss": 2.2847, | |
| "step": 2121 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 4.0938004871488564e-07, | |
| "loss": 2.2344, | |
| "step": 2124 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 4.0816108447018337e-07, | |
| "loss": 2.2626, | |
| "step": 2127 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 4.0694268486729997e-07, | |
| "loss": 2.3064, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 4.057248573971704e-07, | |
| "loss": 2.28, | |
| "step": 2133 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 4.0450760954721253e-07, | |
| "loss": 2.2872, | |
| "step": 2136 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 4.032909488012803e-07, | |
| "loss": 2.2976, | |
| "step": 2139 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "eval_loss": 2.304422378540039, | |
| "eval_runtime": 423.8457, | |
| "eval_samples_per_second": 20.139, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 4.02074882639618e-07, | |
| "loss": 2.2723, | |
| "step": 2142 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 4.0085941853881456e-07, | |
| "loss": 2.2608, | |
| "step": 2145 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 3.996445639717573e-07, | |
| "loss": 2.3145, | |
| "step": 2148 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 3.984303264075861e-07, | |
| "loss": 2.2487, | |
| "step": 2151 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 3.9721671331164687e-07, | |
| "loss": 2.2996, | |
| "step": 2154 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 3.9600373214544655e-07, | |
| "loss": 2.2845, | |
| "step": 2157 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 3.9479139036660726e-07, | |
| "loss": 2.2886, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "eval_loss": 2.3043317794799805, | |
| "eval_runtime": 423.8407, | |
| "eval_samples_per_second": 20.14, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 3.935796954288194e-07, | |
| "loss": 2.3522, | |
| "step": 2163 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 3.923686547817968e-07, | |
| "loss": 2.2845, | |
| "step": 2166 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 3.911582758712304e-07, | |
| "loss": 2.3067, | |
| "step": 2169 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 3.899485661387429e-07, | |
| "loss": 2.2995, | |
| "step": 2172 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 3.8873953302184283e-07, | |
| "loss": 2.3704, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 3.8753118395387835e-07, | |
| "loss": 2.2079, | |
| "step": 2178 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "eval_loss": 2.3040771484375, | |
| "eval_runtime": 423.8379, | |
| "eval_samples_per_second": 20.14, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 3.8632352636399236e-07, | |
| "loss": 2.321, | |
| "step": 2181 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 3.851165676770764e-07, | |
| "loss": 2.3197, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 3.839103153137247e-07, | |
| "loss": 2.2741, | |
| "step": 2187 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 3.8270477669018915e-07, | |
| "loss": 2.2377, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 3.8149995921833357e-07, | |
| "loss": 2.3662, | |
| "step": 2193 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 3.80295870305588e-07, | |
| "loss": 2.3399, | |
| "step": 2196 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 3.7909251735490253e-07, | |
| "loss": 2.2561, | |
| "step": 2199 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "eval_loss": 2.30399227142334, | |
| "eval_runtime": 423.7849, | |
| "eval_samples_per_second": 20.142, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 3.7788990776470324e-07, | |
| "loss": 2.2898, | |
| "step": 2202 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 3.7668804892884567e-07, | |
| "loss": 2.2755, | |
| "step": 2205 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 3.754869482365694e-07, | |
| "loss": 2.2196, | |
| "step": 2208 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.7428661307245286e-07, | |
| "loss": 2.2588, | |
| "step": 2211 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.730870508163679e-07, | |
| "loss": 2.269, | |
| "step": 2214 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.718882688434344e-07, | |
| "loss": 2.3169, | |
| "step": 2217 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.706902745239754e-07, | |
| "loss": 2.2847, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_loss": 2.303743839263916, | |
| "eval_runtime": 423.861, | |
| "eval_samples_per_second": 20.139, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.6949307522347005e-07, | |
| "loss": 2.3122, | |
| "step": 2223 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 3.6829667830251104e-07, | |
| "loss": 2.2039, | |
| "step": 2226 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 3.671010911167571e-07, | |
| "loss": 2.2844, | |
| "step": 2229 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 3.6590632101688853e-07, | |
| "loss": 2.2644, | |
| "step": 2232 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 3.6471237534856213e-07, | |
| "loss": 2.2826, | |
| "step": 2235 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 3.635192614523664e-07, | |
| "loss": 2.2901, | |
| "step": 2238 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "eval_loss": 2.303476095199585, | |
| "eval_runtime": 423.895, | |
| "eval_samples_per_second": 20.137, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 3.623269866637755e-07, | |
| "loss": 2.2458, | |
| "step": 2241 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 3.6113555831310446e-07, | |
| "loss": 2.2776, | |
| "step": 2244 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 3.599449837254646e-07, | |
| "loss": 2.2093, | |
| "step": 2247 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 3.5875527022071806e-07, | |
| "loss": 2.2796, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 3.5756642511343316e-07, | |
| "loss": 2.2667, | |
| "step": 2253 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 3.5637845571283855e-07, | |
| "loss": 2.2485, | |
| "step": 2256 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 3.5519136932277925e-07, | |
| "loss": 2.2958, | |
| "step": 2259 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "eval_loss": 2.303359031677246, | |
| "eval_runtime": 424.3049, | |
| "eval_samples_per_second": 20.118, | |
| "eval_steps_per_second": 0.629, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 3.5400517324167146e-07, | |
| "loss": 2.2098, | |
| "step": 2262 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 3.528198747624577e-07, | |
| "loss": 2.2349, | |
| "step": 2265 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 3.5163548117256106e-07, | |
| "loss": 2.2503, | |
| "step": 2268 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 3.504519997538422e-07, | |
| "loss": 2.3013, | |
| "step": 2271 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 3.4926943778255344e-07, | |
| "loss": 2.2884, | |
| "step": 2274 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 3.480878025292935e-07, | |
| "loss": 2.2343, | |
| "step": 2277 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 3.4690710125896396e-07, | |
| "loss": 2.2947, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_loss": 2.3031911849975586, | |
| "eval_runtime": 423.931, | |
| "eval_samples_per_second": 20.135, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 3.4572734123072426e-07, | |
| "loss": 2.2812, | |
| "step": 2283 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 3.4454852969794685e-07, | |
| "loss": 2.2455, | |
| "step": 2286 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 3.433706739081722e-07, | |
| "loss": 2.3179, | |
| "step": 2289 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 3.421937811030652e-07, | |
| "loss": 2.2778, | |
| "step": 2292 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 3.410178585183698e-07, | |
| "loss": 2.2567, | |
| "step": 2295 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 3.398429133838654e-07, | |
| "loss": 2.2701, | |
| "step": 2298 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "eval_loss": 2.3029837608337402, | |
| "eval_runtime": 423.7445, | |
| "eval_samples_per_second": 20.144, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 3.386689529233213e-07, | |
| "loss": 2.3341, | |
| "step": 2301 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 3.37495984354453e-07, | |
| "loss": 2.2603, | |
| "step": 2304 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 3.3632401488887774e-07, | |
| "loss": 2.2587, | |
| "step": 2307 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 3.3515305173207044e-07, | |
| "loss": 2.1969, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 3.3398310208331803e-07, | |
| "loss": 2.2755, | |
| "step": 2313 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 3.328141731356775e-07, | |
| "loss": 2.2577, | |
| "step": 2316 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 3.3164627207592963e-07, | |
| "loss": 2.4315, | |
| "step": 2319 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "eval_loss": 2.30289363861084, | |
| "eval_runtime": 423.7495, | |
| "eval_samples_per_second": 20.144, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 3.304794060845355e-07, | |
| "loss": 2.2716, | |
| "step": 2322 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 3.2931358233559276e-07, | |
| "loss": 2.3602, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 3.281488079967911e-07, | |
| "loss": 2.2675, | |
| "step": 2328 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 3.269850902293683e-07, | |
| "loss": 2.2746, | |
| "step": 2331 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 3.258224361880657e-07, | |
| "loss": 2.2504, | |
| "step": 2334 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 3.2466085302108516e-07, | |
| "loss": 2.2465, | |
| "step": 2337 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 3.2350034787004444e-07, | |
| "loss": 2.2611, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "eval_loss": 2.3026528358459473, | |
| "eval_runtime": 423.646, | |
| "eval_samples_per_second": 20.149, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 3.223409278699337e-07, | |
| "loss": 2.21, | |
| "step": 2343 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 3.2118260014907084e-07, | |
| "loss": 2.3432, | |
| "step": 2346 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 3.200253718290589e-07, | |
| "loss": 2.3252, | |
| "step": 2349 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 3.1886925002474107e-07, | |
| "loss": 2.2402, | |
| "step": 2352 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 3.177142418441578e-07, | |
| "loss": 2.2978, | |
| "step": 2355 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 3.165603543885026e-07, | |
| "loss": 2.2621, | |
| "step": 2358 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_loss": 2.3024840354919434, | |
| "eval_runtime": 423.7045, | |
| "eval_samples_per_second": 20.146, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 3.154075947520788e-07, | |
| "loss": 2.2844, | |
| "step": 2361 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 3.142559700222556e-07, | |
| "loss": 2.305, | |
| "step": 2364 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 3.131054872794244e-07, | |
| "loss": 2.331, | |
| "step": 2367 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 3.119561535969556e-07, | |
| "loss": 2.3065, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 3.1080797604115503e-07, | |
| "loss": 2.2734, | |
| "step": 2373 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 3.096609616712207e-07, | |
| "loss": 2.3741, | |
| "step": 2376 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 3.0851511753919844e-07, | |
| "loss": 2.3104, | |
| "step": 2379 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "eval_loss": 2.302408218383789, | |
| "eval_runtime": 423.7207, | |
| "eval_samples_per_second": 20.145, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 3.073704506899398e-07, | |
| "loss": 2.3035, | |
| "step": 2382 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 3.062269681610581e-07, | |
| "loss": 2.3006, | |
| "step": 2385 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 3.0508467698288554e-07, | |
| "loss": 2.2715, | |
| "step": 2388 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 3.0394358417842864e-07, | |
| "loss": 2.2669, | |
| "step": 2391 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 3.0280369676332735e-07, | |
| "loss": 2.2766, | |
| "step": 2394 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 3.016650217458101e-07, | |
| "loss": 2.2612, | |
| "step": 2397 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 3.005275661266512e-07, | |
| "loss": 2.2564, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "eval_loss": 2.3022682666778564, | |
| "eval_runtime": 423.7641, | |
| "eval_samples_per_second": 20.143, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 2.9939133689912787e-07, | |
| "loss": 2.2989, | |
| "step": 2403 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 2.982563410489778e-07, | |
| "loss": 2.2291, | |
| "step": 2406 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 2.971225855543551e-07, | |
| "loss": 2.299, | |
| "step": 2409 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 2.95990077385788e-07, | |
| "loss": 2.3035, | |
| "step": 2412 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 2.9485882350613617e-07, | |
| "loss": 2.2798, | |
| "step": 2415 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 2.9372883087054744e-07, | |
| "loss": 2.3361, | |
| "step": 2418 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "eval_loss": 2.3021554946899414, | |
| "eval_runtime": 423.6838, | |
| "eval_samples_per_second": 20.147, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 2.9260010642641584e-07, | |
| "loss": 2.3625, | |
| "step": 2421 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 2.9147265711333767e-07, | |
| "loss": 2.2619, | |
| "step": 2424 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 2.903464898630696e-07, | |
| "loss": 2.2578, | |
| "step": 2427 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 2.8922161159948626e-07, | |
| "loss": 2.2522, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 2.8809802923853744e-07, | |
| "loss": 2.3074, | |
| "step": 2433 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 2.8697574968820514e-07, | |
| "loss": 2.2928, | |
| "step": 2436 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 2.858547798484613e-07, | |
| "loss": 2.3322, | |
| "step": 2439 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "eval_loss": 2.301987886428833, | |
| "eval_runtime": 423.6603, | |
| "eval_samples_per_second": 20.148, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 2.8473512661122633e-07, | |
| "loss": 2.2035, | |
| "step": 2442 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 2.8361679686032487e-07, | |
| "loss": 2.2739, | |
| "step": 2445 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 2.8249979747144557e-07, | |
| "loss": 2.28, | |
| "step": 2448 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 2.8138413531209687e-07, | |
| "loss": 2.2528, | |
| "step": 2451 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 2.802698172415665e-07, | |
| "loss": 2.2959, | |
| "step": 2454 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 2.791568501108778e-07, | |
| "loss": 2.3417, | |
| "step": 2457 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 2.7804524076274896e-07, | |
| "loss": 2.291, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "eval_loss": 2.3019022941589355, | |
| "eval_runtime": 423.6817, | |
| "eval_samples_per_second": 20.147, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 2.7693499603154933e-07, | |
| "loss": 2.282, | |
| "step": 2463 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 2.758261227432597e-07, | |
| "loss": 2.3196, | |
| "step": 2466 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 2.747186277154277e-07, | |
| "loss": 2.193, | |
| "step": 2469 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 2.736125177571277e-07, | |
| "loss": 2.2603, | |
| "step": 2472 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 2.725077996689186e-07, | |
| "loss": 2.2661, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 2.714044802428019e-07, | |
| "loss": 2.2643, | |
| "step": 2478 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "eval_loss": 2.3017375469207764, | |
| "eval_runtime": 423.6679, | |
| "eval_samples_per_second": 20.148, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 2.7030256626217927e-07, | |
| "loss": 2.2504, | |
| "step": 2481 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 2.6920206450181194e-07, | |
| "loss": 2.2563, | |
| "step": 2484 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 2.6810298172777853e-07, | |
| "loss": 2.2404, | |
| "step": 2487 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 2.6700532469743315e-07, | |
| "loss": 2.3408, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 2.6590910015936485e-07, | |
| "loss": 2.2653, | |
| "step": 2493 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 2.648143148533546e-07, | |
| "loss": 2.2583, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 2.6372097551033563e-07, | |
| "loss": 2.2709, | |
| "step": 2499 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_loss": 2.3016295433044434, | |
| "eval_runtime": 423.8646, | |
| "eval_samples_per_second": 20.139, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 2.626290888523504e-07, | |
| "loss": 2.2721, | |
| "step": 2502 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 2.6153866159251015e-07, | |
| "loss": 2.1841, | |
| "step": 2505 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 2.6044970043495386e-07, | |
| "loss": 2.3263, | |
| "step": 2508 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 2.5936221207480645e-07, | |
| "loss": 2.2907, | |
| "step": 2511 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 2.5827620319813773e-07, | |
| "loss": 2.1769, | |
| "step": 2514 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 2.571916804819212e-07, | |
| "loss": 2.2677, | |
| "step": 2517 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 2.5610865059399367e-07, | |
| "loss": 2.2676, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_loss": 2.30149245262146, | |
| "eval_runtime": 423.885, | |
| "eval_samples_per_second": 20.138, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 2.5502712019301357e-07, | |
| "loss": 2.2708, | |
| "step": 2523 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 2.539470959284201e-07, | |
| "loss": 2.2794, | |
| "step": 2526 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 2.5286858444039245e-07, | |
| "loss": 2.2938, | |
| "step": 2529 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 2.517915923598093e-07, | |
| "loss": 2.3511, | |
| "step": 2532 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 2.5071612630820727e-07, | |
| "loss": 2.2386, | |
| "step": 2535 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 2.496421928977412e-07, | |
| "loss": 2.2732, | |
| "step": 2538 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.301475763320923, | |
| "eval_runtime": 424.3098, | |
| "eval_samples_per_second": 20.117, | |
| "eval_steps_per_second": 0.629, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2.485697987311426e-07, | |
| "loss": 2.2122, | |
| "step": 2541 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2.4749895040167977e-07, | |
| "loss": 2.2602, | |
| "step": 2544 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2.4642965449311657e-07, | |
| "loss": 2.1993, | |
| "step": 2547 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2.453619175796723e-07, | |
| "loss": 2.2088, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2.442957462259816e-07, | |
| "loss": 2.2474, | |
| "step": 2553 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 2.4323114698705397e-07, | |
| "loss": 2.2621, | |
| "step": 2556 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 2.421681264082326e-07, | |
| "loss": 2.2827, | |
| "step": 2559 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "eval_loss": 2.301480531692505, | |
| "eval_runtime": 424.0525, | |
| "eval_samples_per_second": 20.13, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 2.411066910251549e-07, | |
| "loss": 2.215, | |
| "step": 2562 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 2.400468473637127e-07, | |
| "loss": 2.2449, | |
| "step": 2565 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 2.3898860194001165e-07, | |
| "loss": 2.2532, | |
| "step": 2568 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 2.379319612603306e-07, | |
| "loss": 2.3317, | |
| "step": 2571 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 2.3687693182108232e-07, | |
| "loss": 2.2752, | |
| "step": 2574 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 2.3582352010877381e-07, | |
| "loss": 2.2865, | |
| "step": 2577 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 2.3477173259996541e-07, | |
| "loss": 2.2986, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "eval_loss": 2.3014891147613525, | |
| "eval_runtime": 424.1884, | |
| "eval_samples_per_second": 20.123, | |
| "eval_steps_per_second": 0.629, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 2.337215757612322e-07, | |
| "loss": 2.2623, | |
| "step": 2583 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 2.3267305604912296e-07, | |
| "loss": 2.281, | |
| "step": 2586 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 2.3162617991012173e-07, | |
| "loss": 2.3224, | |
| "step": 2589 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 2.3058095378060715e-07, | |
| "loss": 2.2695, | |
| "step": 2592 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 2.2953738408681327e-07, | |
| "loss": 2.3021, | |
| "step": 2595 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 2.284954772447905e-07, | |
| "loss": 2.3108, | |
| "step": 2598 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "eval_loss": 2.3014276027679443, | |
| "eval_runtime": 423.7571, | |
| "eval_samples_per_second": 20.144, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 2.2745523966036561e-07, | |
| "loss": 2.1925, | |
| "step": 2601 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 2.2641667772910217e-07, | |
| "loss": 2.2689, | |
| "step": 2604 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 2.2537979783626165e-07, | |
| "loss": 2.3145, | |
| "step": 2607 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 2.243446063567645e-07, | |
| "loss": 2.277, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 2.2331110965514976e-07, | |
| "loss": 2.2525, | |
| "step": 2613 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 2.2227931408553747e-07, | |
| "loss": 2.2333, | |
| "step": 2616 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 2.2124922599158795e-07, | |
| "loss": 2.2867, | |
| "step": 2619 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "eval_loss": 2.3013503551483154, | |
| "eval_runtime": 423.8767, | |
| "eval_samples_per_second": 20.138, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 2.2022085170646464e-07, | |
| "loss": 2.2512, | |
| "step": 2622 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 2.191941975527934e-07, | |
| "loss": 2.3615, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 2.181692698426245e-07, | |
| "loss": 2.2471, | |
| "step": 2628 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 2.171460748773941e-07, | |
| "loss": 2.2726, | |
| "step": 2631 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 2.161246189478852e-07, | |
| "loss": 2.2978, | |
| "step": 2634 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 2.1510490833418838e-07, | |
| "loss": 2.2591, | |
| "step": 2637 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 2.1408694930566383e-07, | |
| "loss": 2.2827, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "eval_loss": 2.3013150691986084, | |
| "eval_runtime": 423.5356, | |
| "eval_samples_per_second": 20.154, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 2.1307074812090308e-07, | |
| "loss": 2.2449, | |
| "step": 2643 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 2.1205631102769e-07, | |
| "loss": 2.2686, | |
| "step": 2646 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 2.1104364426296233e-07, | |
| "loss": 2.2174, | |
| "step": 2649 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 2.1003275405277332e-07, | |
| "loss": 2.2562, | |
| "step": 2652 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 2.090236466122543e-07, | |
| "loss": 2.2223, | |
| "step": 2655 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 2.0801632814557508e-07, | |
| "loss": 2.2721, | |
| "step": 2658 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "eval_loss": 2.301299810409546, | |
| "eval_runtime": 423.6078, | |
| "eval_samples_per_second": 20.151, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 2.0701080484590732e-07, | |
| "loss": 2.2413, | |
| "step": 2661 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 2.0600708289538488e-07, | |
| "loss": 2.2998, | |
| "step": 2664 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 2.0500516846506733e-07, | |
| "loss": 2.2751, | |
| "step": 2667 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 2.0400506771490077e-07, | |
| "loss": 2.2682, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 2.030067867936805e-07, | |
| "loss": 2.3002, | |
| "step": 2673 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 2.020103318390135e-07, | |
| "loss": 2.3029, | |
| "step": 2676 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 2.0101570897728044e-07, | |
| "loss": 2.2781, | |
| "step": 2679 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "eval_loss": 2.301173210144043, | |
| "eval_runtime": 423.7282, | |
| "eval_samples_per_second": 20.145, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 2.000229243235976e-07, | |
| "loss": 2.2415, | |
| "step": 2682 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 1.990319839817795e-07, | |
| "loss": 2.175, | |
| "step": 2685 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 1.9804289404430203e-07, | |
| "loss": 2.2062, | |
| "step": 2688 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 1.9705566059226447e-07, | |
| "loss": 2.2741, | |
| "step": 2691 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 1.960702896953516e-07, | |
| "loss": 2.2501, | |
| "step": 2694 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 1.9508678741179706e-07, | |
| "loss": 2.289, | |
| "step": 2697 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 1.941051597883463e-07, | |
| "loss": 2.2014, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_loss": 2.301100254058838, | |
| "eval_runtime": 423.7829, | |
| "eval_samples_per_second": 20.142, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 1.9312541286021833e-07, | |
| "loss": 2.2905, | |
| "step": 2703 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1.9214755265107018e-07, | |
| "loss": 2.2611, | |
| "step": 2706 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1.9117158517295816e-07, | |
| "loss": 2.2603, | |
| "step": 2709 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1.901975164263025e-07, | |
| "loss": 2.2208, | |
| "step": 2712 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1.8922535239984906e-07, | |
| "loss": 2.2823, | |
| "step": 2715 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 1.8825509907063326e-07, | |
| "loss": 2.2059, | |
| "step": 2718 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "eval_loss": 2.3010268211364746, | |
| "eval_runtime": 423.7014, | |
| "eval_samples_per_second": 20.146, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 1.872867624039436e-07, | |
| "loss": 2.2688, | |
| "step": 2721 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 1.8632034835328443e-07, | |
| "loss": 2.2891, | |
| "step": 2724 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 1.8535586286033932e-07, | |
| "loss": 2.2176, | |
| "step": 2727 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 1.8439331185493472e-07, | |
| "loss": 2.2586, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 1.8343270125500377e-07, | |
| "loss": 2.1833, | |
| "step": 2733 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 1.8247403696654966e-07, | |
| "loss": 2.311, | |
| "step": 2736 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 1.8151732488360916e-07, | |
| "loss": 2.2836, | |
| "step": 2739 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "eval_loss": 2.3009707927703857, | |
| "eval_runtime": 423.6795, | |
| "eval_samples_per_second": 20.147, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 1.8056257088821625e-07, | |
| "loss": 2.2633, | |
| "step": 2742 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.7960978085036692e-07, | |
| "loss": 2.2118, | |
| "step": 2745 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.7865896062798197e-07, | |
| "loss": 2.3445, | |
| "step": 2748 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.777101160668712e-07, | |
| "loss": 2.3142, | |
| "step": 2751 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.7676325300069822e-07, | |
| "loss": 2.2825, | |
| "step": 2754 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 1.75818377250944e-07, | |
| "loss": 2.2622, | |
| "step": 2757 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 1.748754946268708e-07, | |
| "loss": 2.3294, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "eval_loss": 2.3009371757507324, | |
| "eval_runtime": 423.6974, | |
| "eval_samples_per_second": 20.146, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 1.7393461092548677e-07, | |
| "loss": 2.2989, | |
| "step": 2763 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 1.7299573193151075e-07, | |
| "loss": 2.2718, | |
| "step": 2766 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1.7205886341733618e-07, | |
| "loss": 2.2669, | |
| "step": 2769 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1.7112401114299542e-07, | |
| "loss": 2.2736, | |
| "step": 2772 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1.7019118085612472e-07, | |
| "loss": 2.2803, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1.6926037829192897e-07, | |
| "loss": 2.2741, | |
| "step": 2778 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "eval_loss": 2.3007988929748535, | |
| "eval_runtime": 423.7773, | |
| "eval_samples_per_second": 20.143, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1.6833160917314644e-07, | |
| "loss": 2.3159, | |
| "step": 2781 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 1.674048792100129e-07, | |
| "loss": 2.2096, | |
| "step": 2784 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 1.6648019410022711e-07, | |
| "loss": 2.2167, | |
| "step": 2787 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 1.6555755952891638e-07, | |
| "loss": 2.2509, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 1.6463698116860009e-07, | |
| "loss": 2.2823, | |
| "step": 2793 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 1.6371846467915602e-07, | |
| "loss": 2.2866, | |
| "step": 2796 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 1.628020157077854e-07, | |
| "loss": 2.2796, | |
| "step": 2799 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "eval_loss": 2.300727367401123, | |
| "eval_runtime": 424.0574, | |
| "eval_samples_per_second": 20.129, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 1.618876398889779e-07, | |
| "loss": 2.2732, | |
| "step": 2802 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 1.6097534284447689e-07, | |
| "loss": 2.3093, | |
| "step": 2805 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 1.6006513018324504e-07, | |
| "loss": 2.2459, | |
| "step": 2808 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 1.591570075014302e-07, | |
| "loss": 2.3028, | |
| "step": 2811 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 1.5825098038233054e-07, | |
| "loss": 2.2875, | |
| "step": 2814 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 1.5734705439636014e-07, | |
| "loss": 2.293, | |
| "step": 2817 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 1.5644523510101498e-07, | |
| "loss": 2.2647, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "eval_loss": 2.3006794452667236, | |
| "eval_runtime": 423.7507, | |
| "eval_samples_per_second": 20.144, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 1.555455280408391e-07, | |
| "loss": 2.2789, | |
| "step": 2823 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 1.5464793874738956e-07, | |
| "loss": 2.2478, | |
| "step": 2826 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 1.5375247273920367e-07, | |
| "loss": 2.2291, | |
| "step": 2829 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 1.528591355217637e-07, | |
| "loss": 2.2975, | |
| "step": 2832 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 1.5196793258746454e-07, | |
| "loss": 2.2117, | |
| "step": 2835 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 1.510788694155785e-07, | |
| "loss": 2.2724, | |
| "step": 2838 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "eval_loss": 2.3006186485290527, | |
| "eval_runtime": 423.685, | |
| "eval_samples_per_second": 20.147, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 1.5019195147222225e-07, | |
| "loss": 2.1983, | |
| "step": 2841 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 1.4930718421032363e-07, | |
| "loss": 2.3009, | |
| "step": 2844 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 1.4842457306958767e-07, | |
| "loss": 2.3078, | |
| "step": 2847 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 1.4754412347646285e-07, | |
| "loss": 2.3127, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 1.4666584084410804e-07, | |
| "loss": 2.2781, | |
| "step": 2853 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 1.457897305723597e-07, | |
| "loss": 2.2852, | |
| "step": 2856 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 1.4491579804769815e-07, | |
| "loss": 2.2122, | |
| "step": 2859 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "eval_loss": 2.3005518913269043, | |
| "eval_runtime": 423.7052, | |
| "eval_samples_per_second": 20.146, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 1.4404404864321425e-07, | |
| "loss": 2.2656, | |
| "step": 2862 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 1.4317448771857654e-07, | |
| "loss": 2.284, | |
| "step": 2865 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 1.4230712061999904e-07, | |
| "loss": 2.2285, | |
| "step": 2868 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 1.4144195268020704e-07, | |
| "loss": 2.3214, | |
| "step": 2871 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 1.405789892184056e-07, | |
| "loss": 2.2994, | |
| "step": 2874 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 1.397182355402457e-07, | |
| "loss": 2.2861, | |
| "step": 2877 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 1.3885969693779276e-07, | |
| "loss": 2.2816, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_loss": 2.3004748821258545, | |
| "eval_runtime": 423.7032, | |
| "eval_samples_per_second": 20.146, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 1.3800337868949307e-07, | |
| "loss": 2.2926, | |
| "step": 2883 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 1.371492860601418e-07, | |
| "loss": 2.2583, | |
| "step": 2886 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 1.36297424300851e-07, | |
| "loss": 2.3241, | |
| "step": 2889 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 1.3544779864901678e-07, | |
| "loss": 2.2666, | |
| "step": 2892 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 1.3460041432828712e-07, | |
| "loss": 2.267, | |
| "step": 2895 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 1.337552765485298e-07, | |
| "loss": 2.2765, | |
| "step": 2898 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "eval_loss": 2.3004419803619385, | |
| "eval_runtime": 423.7381, | |
| "eval_samples_per_second": 20.145, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 1.3291239050580083e-07, | |
| "loss": 2.3155, | |
| "step": 2901 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 1.3207176138231208e-07, | |
| "loss": 2.2445, | |
| "step": 2904 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 1.3123339434639923e-07, | |
| "loss": 2.2625, | |
| "step": 2907 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 1.3039729455249027e-07, | |
| "loss": 2.303, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 1.295634671410742e-07, | |
| "loss": 2.1328, | |
| "step": 2913 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 1.2873191723866856e-07, | |
| "loss": 2.281, | |
| "step": 2916 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 1.2790264995778838e-07, | |
| "loss": 2.3013, | |
| "step": 2919 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "eval_loss": 2.3004138469696045, | |
| "eval_runtime": 423.726, | |
| "eval_samples_per_second": 20.145, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 1.2707567039691502e-07, | |
| "loss": 2.2248, | |
| "step": 2922 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 1.2625098364046454e-07, | |
| "loss": 2.2735, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 1.2542859475875611e-07, | |
| "loss": 2.2606, | |
| "step": 2928 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 1.246085088079813e-07, | |
| "loss": 2.265, | |
| "step": 2931 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 1.237907308301729e-07, | |
| "loss": 2.2569, | |
| "step": 2934 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 1.2297526585317408e-07, | |
| "loss": 2.2557, | |
| "step": 2937 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 1.221621188906069e-07, | |
| "loss": 2.3185, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "eval_loss": 2.3003499507904053, | |
| "eval_runtime": 423.9623, | |
| "eval_samples_per_second": 20.134, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 1.2135129494184187e-07, | |
| "loss": 2.2078, | |
| "step": 2943 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 1.2054279899196757e-07, | |
| "loss": 2.2205, | |
| "step": 2946 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 1.1973663601175942e-07, | |
| "loss": 2.3166, | |
| "step": 2949 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 1.1893281095764934e-07, | |
| "loss": 2.2881, | |
| "step": 2952 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 1.1813132877169502e-07, | |
| "loss": 2.2296, | |
| "step": 2955 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 1.1733219438155029e-07, | |
| "loss": 2.3117, | |
| "step": 2958 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "eval_loss": 2.300266981124878, | |
| "eval_runtime": 423.7888, | |
| "eval_samples_per_second": 20.142, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 1.1653541270043393e-07, | |
| "loss": 2.2171, | |
| "step": 2961 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 1.1574098862709992e-07, | |
| "loss": 2.2274, | |
| "step": 2964 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 1.1494892704580727e-07, | |
| "loss": 2.3187, | |
| "step": 2967 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 1.141592328262903e-07, | |
| "loss": 2.2714, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 1.1337191082372788e-07, | |
| "loss": 2.2141, | |
| "step": 2973 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 1.1258696587871408e-07, | |
| "loss": 2.3156, | |
| "step": 2976 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 1.118044028172288e-07, | |
| "loss": 2.3267, | |
| "step": 2979 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "eval_loss": 2.300215721130371, | |
| "eval_runtime": 423.6752, | |
| "eval_samples_per_second": 20.148, | |
| "eval_steps_per_second": 0.63, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 1.110242264506076e-07, | |
| "loss": 2.2584, | |
| "step": 2982 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 1.1024644157551205e-07, | |
| "loss": 2.2517, | |
| "step": 2985 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 1.094710529739002e-07, | |
| "loss": 2.2194, | |
| "step": 2988 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 1.0869806541299787e-07, | |
| "loss": 2.2743, | |
| "step": 2991 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 1.0792748364526883e-07, | |
| "loss": 2.2713, | |
| "step": 2994 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 1.0715931240838522e-07, | |
| "loss": 2.3314, | |
| "step": 2997 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 1.0639355642519893e-07, | |
| "loss": 2.2287, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "eval_loss": 2.300197124481201, | |
| "eval_runtime": 423.7461, | |
| "eval_samples_per_second": 20.144, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 1.0563022040371278e-07, | |
| "loss": 2.3382, | |
| "step": 3003 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 1.0486930903705094e-07, | |
| "loss": 2.223, | |
| "step": 3006 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 1.0411082700343016e-07, | |
| "loss": 2.3025, | |
| "step": 3009 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 1.0335477896613171e-07, | |
| "loss": 2.1982, | |
| "step": 3012 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 1.0260116957347214e-07, | |
| "loss": 2.2945, | |
| "step": 3015 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 1.0185000345877454e-07, | |
| "loss": 2.2744, | |
| "step": 3018 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "eval_loss": 2.3001396656036377, | |
| "eval_runtime": 423.7517, | |
| "eval_samples_per_second": 20.144, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 1.0110128524034023e-07, | |
| "loss": 2.3053, | |
| "step": 3021 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 1.0035501952142078e-07, | |
| "loss": 2.2525, | |
| "step": 3024 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 9.961121089018931e-08, | |
| "loss": 2.3048, | |
| "step": 3027 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 9.886986391971208e-08, | |
| "loss": 2.2963, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 9.813098316792056e-08, | |
| "loss": 2.257, | |
| "step": 3033 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 9.739457317758409e-08, | |
| "loss": 2.2602, | |
| "step": 3036 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 9.666063847628065e-08, | |
| "loss": 2.2635, | |
| "step": 3039 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_loss": 2.3001034259796143, | |
| "eval_runtime": 423.7899, | |
| "eval_samples_per_second": 20.142, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 9.592918357636992e-08, | |
| "loss": 2.2341, | |
| "step": 3042 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 9.520021297496545e-08, | |
| "loss": 2.1765, | |
| "step": 3045 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 9.4473731153907e-08, | |
| "loss": 2.2441, | |
| "step": 3048 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 9.374974257973256e-08, | |
| "loss": 2.1989, | |
| "step": 3051 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 9.302825170365114e-08, | |
| "loss": 2.1661, | |
| "step": 3054 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 9.230926296151581e-08, | |
| "loss": 2.2788, | |
| "step": 3057 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 9.159278077379606e-08, | |
| "loss": 2.2209, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "eval_loss": 2.300053119659424, | |
| "eval_runtime": 424.0357, | |
| "eval_samples_per_second": 20.13, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 9.087880954555032e-08, | |
| "loss": 2.2684, | |
| "step": 3063 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 9.016735366639933e-08, | |
| "loss": 2.2857, | |
| "step": 3066 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 8.945841751049916e-08, | |
| "loss": 2.286, | |
| "step": 3069 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 8.875200543651417e-08, | |
| "loss": 2.2638, | |
| "step": 3072 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 8.804812178759003e-08, | |
| "loss": 2.251, | |
| "step": 3075 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 8.734677089132725e-08, | |
| "loss": 2.235, | |
| "step": 3078 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "eval_loss": 2.30000638961792, | |
| "eval_runtime": 423.8005, | |
| "eval_samples_per_second": 20.142, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 8.664795705975481e-08, | |
| "loss": 2.2703, | |
| "step": 3081 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 8.595168458930297e-08, | |
| "loss": 2.2184, | |
| "step": 3084 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 8.525795776077744e-08, | |
| "loss": 2.265, | |
| "step": 3087 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 8.456678083933289e-08, | |
| "loss": 2.2504, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 8.387815807444687e-08, | |
| "loss": 2.3111, | |
| "step": 3093 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 8.319209369989321e-08, | |
| "loss": 2.2806, | |
| "step": 3096 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 8.250859193371639e-08, | |
| "loss": 2.2143, | |
| "step": 3099 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "eval_loss": 2.299983263015747, | |
| "eval_runtime": 423.988, | |
| "eval_samples_per_second": 20.133, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 8.18276569782056e-08, | |
| "loss": 2.2681, | |
| "step": 3102 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 8.114929301986901e-08, | |
| "loss": 2.3132, | |
| "step": 3105 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 8.047350422940752e-08, | |
| "loss": 2.2929, | |
| "step": 3108 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 7.980029476168942e-08, | |
| "loss": 2.2603, | |
| "step": 3111 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 7.912966875572513e-08, | |
| "loss": 2.2735, | |
| "step": 3114 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 7.846163033464154e-08, | |
| "loss": 2.239, | |
| "step": 3117 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 7.779618360565626e-08, | |
| "loss": 2.2915, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "eval_loss": 2.299947500228882, | |
| "eval_runtime": 423.9687, | |
| "eval_samples_per_second": 20.134, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 7.713333266005296e-08, | |
| "loss": 2.2205, | |
| "step": 3123 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 7.647308157315596e-08, | |
| "loss": 2.2693, | |
| "step": 3126 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 7.581543440430522e-08, | |
| "loss": 2.2387, | |
| "step": 3129 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 7.516039519683104e-08, | |
| "loss": 2.2807, | |
| "step": 3132 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 7.450796797803e-08, | |
| "loss": 2.2665, | |
| "step": 3135 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 7.385815675913959e-08, | |
| "loss": 2.3436, | |
| "step": 3138 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "eval_loss": 2.299905300140381, | |
| "eval_runtime": 423.7973, | |
| "eval_samples_per_second": 20.142, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 7.321096553531336e-08, | |
| "loss": 2.1821, | |
| "step": 3141 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 7.256639828559686e-08, | |
| "loss": 2.3041, | |
| "step": 3144 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 7.192445897290306e-08, | |
| "loss": 2.3107, | |
| "step": 3147 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 7.128515154398801e-08, | |
| "loss": 2.2411, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 7.064847992942613e-08, | |
| "loss": 2.2451, | |
| "step": 3153 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 7.001444804358653e-08, | |
| "loss": 2.2617, | |
| "step": 3156 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 6.938305978460896e-08, | |
| "loss": 2.2742, | |
| "step": 3159 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "eval_loss": 2.2998573780059814, | |
| "eval_runtime": 423.7274, | |
| "eval_samples_per_second": 20.145, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 6.875431903437978e-08, | |
| "loss": 2.2443, | |
| "step": 3162 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 6.812822965850739e-08, | |
| "loss": 2.2786, | |
| "step": 3165 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 6.750479550629962e-08, | |
| "loss": 2.2476, | |
| "step": 3168 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 6.688402041073954e-08, | |
| "loss": 2.2073, | |
| "step": 3171 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 6.626590818846162e-08, | |
| "loss": 2.2585, | |
| "step": 3174 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 6.565046263972845e-08, | |
| "loss": 2.2583, | |
| "step": 3177 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 6.503768754840777e-08, | |
| "loss": 2.3714, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "eval_loss": 2.299828290939331, | |
| "eval_runtime": 423.874, | |
| "eval_samples_per_second": 20.138, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 6.442758668194875e-08, | |
| "loss": 2.2807, | |
| "step": 3183 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 6.382016379135886e-08, | |
| "loss": 2.2595, | |
| "step": 3186 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 6.321542261118079e-08, | |
| "loss": 2.2182, | |
| "step": 3189 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 6.261336685946989e-08, | |
| "loss": 2.2711, | |
| "step": 3192 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 6.201400023777103e-08, | |
| "loss": 2.2551, | |
| "step": 3195 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 6.141732643109554e-08, | |
| "loss": 2.3001, | |
| "step": 3198 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "eval_loss": 2.299809217453003, | |
| "eval_runtime": 424.005, | |
| "eval_samples_per_second": 20.132, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 6.0823349107899e-08, | |
| "loss": 2.297, | |
| "step": 3201 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 6.023207192005858e-08, | |
| "loss": 2.2696, | |
| "step": 3204 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 5.964349850285072e-08, | |
| "loss": 2.2183, | |
| "step": 3207 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 5.9057632474928065e-08, | |
| "loss": 2.3571, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 5.84744774382982e-08, | |
| "loss": 2.2842, | |
| "step": 3213 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 5.789403697830103e-08, | |
| "loss": 2.2502, | |
| "step": 3216 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 5.7316314663586604e-08, | |
| "loss": 2.2196, | |
| "step": 3219 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "eval_loss": 2.2997987270355225, | |
| "eval_runtime": 423.6473, | |
| "eval_samples_per_second": 20.149, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 5.6741314046093335e-08, | |
| "loss": 2.2229, | |
| "step": 3222 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 5.616903866102635e-08, | |
| "loss": 2.1726, | |
| "step": 3225 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 5.5599492026835504e-08, | |
| "loss": 2.2637, | |
| "step": 3228 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 5.5032677645193645e-08, | |
| "loss": 2.3016, | |
| "step": 3231 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 5.4468599000975277e-08, | |
| "loss": 2.2967, | |
| "step": 3234 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 5.39072595622353e-08, | |
| "loss": 2.2489, | |
| "step": 3237 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 5.334866278018757e-08, | |
| "loss": 2.2858, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "eval_loss": 2.299781084060669, | |
| "eval_runtime": 423.7516, | |
| "eval_samples_per_second": 20.144, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 5.279281208918318e-08, | |
| "loss": 2.2487, | |
| "step": 3243 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 5.22397109066901e-08, | |
| "loss": 2.2369, | |
| "step": 3246 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 5.1689362633271785e-08, | |
| "loss": 2.2462, | |
| "step": 3249 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 5.114177065256631e-08, | |
| "loss": 2.2625, | |
| "step": 3252 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 5.059693833126544e-08, | |
| "loss": 2.2559, | |
| "step": 3255 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 5.005486901909428e-08, | |
| "loss": 2.2967, | |
| "step": 3258 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "eval_loss": 2.2997615337371826, | |
| "eval_runtime": 423.7801, | |
| "eval_samples_per_second": 20.143, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 4.951556604879048e-08, | |
| "loss": 2.303, | |
| "step": 3261 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 4.8979032736083505e-08, | |
| "loss": 2.3076, | |
| "step": 3264 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 4.844527237967455e-08, | |
| "loss": 2.274, | |
| "step": 3267 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 4.791428826121635e-08, | |
| "loss": 2.2408, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 4.738608364529273e-08, | |
| "loss": 2.2476, | |
| "step": 3273 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 4.686066177939868e-08, | |
| "loss": 2.2794, | |
| "step": 3276 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 4.6338025893920164e-08, | |
| "loss": 2.2006, | |
| "step": 3279 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "eval_loss": 2.2997195720672607, | |
| "eval_runtime": 423.7291, | |
| "eval_samples_per_second": 20.145, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 4.581817920211473e-08, | |
| "loss": 2.273, | |
| "step": 3282 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 4.530112490009147e-08, | |
| "loss": 2.2454, | |
| "step": 3285 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 4.478686616679089e-08, | |
| "loss": 2.2191, | |
| "step": 3288 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 4.427540616396647e-08, | |
| "loss": 2.3154, | |
| "step": 3291 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 4.376674803616431e-08, | |
| "loss": 2.3211, | |
| "step": 3294 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 4.3260894910704115e-08, | |
| "loss": 2.3233, | |
| "step": 3297 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 4.275784989765985e-08, | |
| "loss": 2.2443, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "eval_loss": 2.299701690673828, | |
| "eval_runtime": 423.6806, | |
| "eval_samples_per_second": 20.147, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 4.22576160898408e-08, | |
| "loss": 2.1774, | |
| "step": 3303 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 4.176019656277269e-08, | |
| "loss": 2.1979, | |
| "step": 3306 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 4.126559437467814e-08, | |
| "loss": 2.255, | |
| "step": 3309 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 4.0773812566458456e-08, | |
| "loss": 2.2893, | |
| "step": 3312 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 4.0284854161674766e-08, | |
| "loss": 2.3453, | |
| "step": 3315 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 3.979872216652958e-08, | |
| "loss": 2.2928, | |
| "step": 3318 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "eval_loss": 2.2996888160705566, | |
| "eval_runtime": 423.7635, | |
| "eval_samples_per_second": 20.143, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 3.93154195698478e-08, | |
| "loss": 2.2614, | |
| "step": 3321 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 3.883494934305886e-08, | |
| "loss": 2.3164, | |
| "step": 3324 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 3.835731444017837e-08, | |
| "loss": 2.1937, | |
| "step": 3327 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 3.788251779778989e-08, | |
| "loss": 2.2311, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 3.741056233502649e-08, | |
| "loss": 2.3136, | |
| "step": 3333 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 3.694145095355355e-08, | |
| "loss": 2.2684, | |
| "step": 3336 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 3.6475186537550495e-08, | |
| "loss": 2.2994, | |
| "step": 3339 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "eval_loss": 2.29967999458313, | |
| "eval_runtime": 423.9449, | |
| "eval_samples_per_second": 20.135, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 3.601177195369304e-08, | |
| "loss": 2.2188, | |
| "step": 3342 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 3.5551210051135425e-08, | |
| "loss": 2.2188, | |
| "step": 3345 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 3.509350366149344e-08, | |
| "loss": 2.3, | |
| "step": 3348 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 3.463865559882656e-08, | |
| "loss": 2.2883, | |
| "step": 3351 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 3.4186668659620774e-08, | |
| "loss": 2.3155, | |
| "step": 3354 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 3.3737545622771146e-08, | |
| "loss": 2.1916, | |
| "step": 3357 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 3.3291289249565314e-08, | |
| "loss": 2.2551, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "eval_loss": 2.2996506690979004, | |
| "eval_runtime": 423.813, | |
| "eval_samples_per_second": 20.141, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 3.284790228366602e-08, | |
| "loss": 2.3237, | |
| "step": 3363 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 3.240738745109439e-08, | |
| "loss": 2.2697, | |
| "step": 3366 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 3.196974746021303e-08, | |
| "loss": 2.2862, | |
| "step": 3369 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 3.15349850017097e-08, | |
| "loss": 2.3031, | |
| "step": 3372 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 3.110310274858074e-08, | |
| "loss": 2.2972, | |
| "step": 3375 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 3.067410335611392e-08, | |
| "loss": 2.2685, | |
| "step": 3378 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "eval_loss": 2.299644947052002, | |
| "eval_runtime": 423.8041, | |
| "eval_samples_per_second": 20.141, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 3.0247989461873124e-08, | |
| "loss": 2.3283, | |
| "step": 3381 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 2.9824763685681765e-08, | |
| "loss": 2.2633, | |
| "step": 3384 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 2.9404428629606237e-08, | |
| "loss": 2.3731, | |
| "step": 3387 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 2.8986986877940434e-08, | |
| "loss": 2.2055, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 2.857244099718975e-08, | |
| "loss": 2.241, | |
| "step": 3393 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 2.8160793536055382e-08, | |
| "loss": 2.2104, | |
| "step": 3396 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 2.775204702541828e-08, | |
| "loss": 2.2593, | |
| "step": 3399 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "eval_loss": 2.2996127605438232, | |
| "eval_runtime": 423.799, | |
| "eval_samples_per_second": 20.142, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 2.7346203978323822e-08, | |
| "loss": 2.2573, | |
| "step": 3402 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 2.694326688996662e-08, | |
| "loss": 2.2599, | |
| "step": 3405 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 2.6543238237674958e-08, | |
| "loss": 2.2886, | |
| "step": 3408 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 2.614612048089515e-08, | |
| "loss": 2.2429, | |
| "step": 3411 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 2.5751916061177104e-08, | |
| "loss": 2.2698, | |
| "step": 3414 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 2.536062740215911e-08, | |
| "loss": 2.2962, | |
| "step": 3417 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 2.4972256909552792e-08, | |
| "loss": 2.2712, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "eval_loss": 2.299607276916504, | |
| "eval_runtime": 423.6873, | |
| "eval_samples_per_second": 20.147, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 2.458680697112797e-08, | |
| "loss": 2.3089, | |
| "step": 3423 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 2.420427995669899e-08, | |
| "loss": 2.2821, | |
| "step": 3426 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 2.382467821810924e-08, | |
| "loss": 2.2812, | |
| "step": 3429 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 2.3448004089216988e-08, | |
| "loss": 2.3195, | |
| "step": 3432 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 2.307425988588102e-08, | |
| "loss": 2.2965, | |
| "step": 3435 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 2.2703447905946526e-08, | |
| "loss": 2.2411, | |
| "step": 3438 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "eval_loss": 2.299588441848755, | |
| "eval_runtime": 423.7482, | |
| "eval_samples_per_second": 20.144, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 2.2335570429230956e-08, | |
| "loss": 2.2508, | |
| "step": 3441 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 2.197062971750968e-08, | |
| "loss": 2.236, | |
| "step": 3444 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 2.160862801450236e-08, | |
| "loss": 2.3015, | |
| "step": 3447 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 2.124956754585927e-08, | |
| "loss": 2.1736, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 2.0893450519147537e-08, | |
| "loss": 2.2258, | |
| "step": 3453 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 2.0540279123837044e-08, | |
| "loss": 2.2241, | |
| "step": 3456 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 2.0190055531287776e-08, | |
| "loss": 2.2478, | |
| "step": 3459 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "eval_loss": 2.2995758056640625, | |
| "eval_runtime": 423.8788, | |
| "eval_samples_per_second": 20.138, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 1.984278189473615e-08, | |
| "loss": 2.3455, | |
| "step": 3462 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 1.949846034928154e-08, | |
| "loss": 2.233, | |
| "step": 3465 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 1.9157093011873348e-08, | |
| "loss": 2.307, | |
| "step": 3468 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 1.88186819812981e-08, | |
| "loss": 2.2145, | |
| "step": 3471 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 1.8483229338166483e-08, | |
| "loss": 2.237, | |
| "step": 3474 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 1.8150737144900286e-08, | |
| "loss": 2.2738, | |
| "step": 3477 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 1.782120744572002e-08, | |
| "loss": 2.2321, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "eval_loss": 2.299563407897949, | |
| "eval_runtime": 423.6364, | |
| "eval_samples_per_second": 20.149, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 1.749464226663233e-08, | |
| "loss": 2.2035, | |
| "step": 3483 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 1.717104361541749e-08, | |
| "loss": 2.2364, | |
| "step": 3486 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 1.6850413481616867e-08, | |
| "loss": 2.3076, | |
| "step": 3489 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 1.6532753836520974e-08, | |
| "loss": 2.2324, | |
| "step": 3492 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 1.621806663315717e-08, | |
| "loss": 2.2394, | |
| "step": 3495 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 1.5906353806278027e-08, | |
| "loss": 2.2977, | |
| "step": 3498 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "eval_loss": 2.299553871154785, | |
| "eval_runtime": 423.8609, | |
| "eval_samples_per_second": 20.139, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 1.559761727234854e-08, | |
| "loss": 2.2334, | |
| "step": 3501 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 1.529185892953544e-08, | |
| "loss": 2.2822, | |
| "step": 3504 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 1.4989080657694887e-08, | |
| "loss": 2.2329, | |
| "step": 3507 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 1.4689284318360918e-08, | |
| "loss": 2.2896, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 1.4392471754734181e-08, | |
| "loss": 2.2596, | |
| "step": 3513 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 1.4098644791670555e-08, | |
| "loss": 2.2584, | |
| "step": 3516 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 1.3807805235670044e-08, | |
| "loss": 2.2909, | |
| "step": 3519 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "eval_loss": 2.2995445728302, | |
| "eval_runtime": 423.9529, | |
| "eval_samples_per_second": 20.134, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 1.3519954874865292e-08, | |
| "loss": 2.2004, | |
| "step": 3522 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 1.3235095479011082e-08, | |
| "loss": 2.2613, | |
| "step": 3525 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 1.2953228799473027e-08, | |
| "loss": 2.2471, | |
| "step": 3528 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 1.2674356569217282e-08, | |
| "loss": 2.276, | |
| "step": 3531 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 1.239848050279918e-08, | |
| "loss": 2.3065, | |
| "step": 3534 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 1.2125602296353399e-08, | |
| "loss": 2.2593, | |
| "step": 3537 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 1.1855723627583247e-08, | |
| "loss": 2.3601, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "eval_loss": 2.2995386123657227, | |
| "eval_runtime": 424.0706, | |
| "eval_samples_per_second": 20.129, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 1.1588846155750398e-08, | |
| "loss": 2.3294, | |
| "step": 3543 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 1.1324971521664229e-08, | |
| "loss": 2.2418, | |
| "step": 3546 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 1.106410134767266e-08, | |
| "loss": 2.2601, | |
| "step": 3549 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 1.080623723765134e-08, | |
| "loss": 2.1942, | |
| "step": 3552 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 1.0551380776994301e-08, | |
| "loss": 2.2841, | |
| "step": 3555 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 1.0299533532603822e-08, | |
| "loss": 2.2464, | |
| "step": 3558 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "eval_loss": 2.2995383739471436, | |
| "eval_runtime": 424.0883, | |
| "eval_samples_per_second": 20.128, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 1.0050697052881142e-08, | |
| "loss": 2.2325, | |
| "step": 3561 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 9.804872867716807e-09, | |
| "loss": 2.308, | |
| "step": 3564 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 9.562062488481071e-09, | |
| "loss": 2.2985, | |
| "step": 3567 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 9.32226740801495e-09, | |
| "loss": 2.235, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 9.085489100620735e-09, | |
| "loss": 2.2331, | |
| "step": 3573 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 8.851729022053279e-09, | |
| "loss": 2.2931, | |
| "step": 3576 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 8.620988609510494e-09, | |
| "loss": 2.2943, | |
| "step": 3579 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "eval_loss": 2.299535036087036, | |
| "eval_runtime": 423.8942, | |
| "eval_samples_per_second": 20.137, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 8.393269281625204e-09, | |
| "loss": 2.3126, | |
| "step": 3582 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 8.168572438455922e-09, | |
| "loss": 2.2633, | |
| "step": 3585 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 7.946899461478307e-09, | |
| "loss": 2.2687, | |
| "step": 3588 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 7.728251713576883e-09, | |
| "loss": 2.2891, | |
| "step": 3591 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 7.512630539036502e-09, | |
| "loss": 2.1957, | |
| "step": 3594 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 7.30003726353412e-09, | |
| "loss": 2.3084, | |
| "step": 3597 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 7.09047319413053e-09, | |
| "loss": 2.2906, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "eval_loss": 2.299527406692505, | |
| "eval_runtime": 423.6823, | |
| "eval_samples_per_second": 20.147, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 6.883939619262591e-09, | |
| "loss": 2.279, | |
| "step": 3603 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 6.680437808735117e-09, | |
| "loss": 2.299, | |
| "step": 3606 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 6.479969013712949e-09, | |
| "loss": 2.312, | |
| "step": 3609 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 6.282534466713618e-09, | |
| "loss": 2.2274, | |
| "step": 3612 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 6.0881353815994126e-09, | |
| "loss": 2.3221, | |
| "step": 3615 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 5.896772953570161e-09, | |
| "loss": 2.2872, | |
| "step": 3618 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "eval_loss": 2.2995247840881348, | |
| "eval_runtime": 423.7609, | |
| "eval_samples_per_second": 20.143, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 5.708448359155848e-09, | |
| "loss": 2.2979, | |
| "step": 3621 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 5.52316275620901e-09, | |
| "loss": 2.2459, | |
| "step": 3624 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 5.340917283898294e-09, | |
| "loss": 2.2217, | |
| "step": 3627 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 5.161713062700912e-09, | |
| "loss": 2.2791, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 4.985551194395976e-09, | |
| "loss": 2.2942, | |
| "step": 3633 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 4.812432762057672e-09, | |
| "loss": 2.2379, | |
| "step": 3636 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 4.642358830048543e-09, | |
| "loss": 2.2559, | |
| "step": 3639 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "eval_loss": 2.2995212078094482, | |
| "eval_runtime": 423.6266, | |
| "eval_samples_per_second": 20.15, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 4.475330444013103e-09, | |
| "loss": 2.2677, | |
| "step": 3642 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 4.311348630871292e-09, | |
| "loss": 2.25, | |
| "step": 3645 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 4.150414398812086e-09, | |
| "loss": 2.2852, | |
| "step": 3648 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 3.992528737287559e-09, | |
| "loss": 2.3615, | |
| "step": 3651 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 3.888965760035445e-09, | |
| "loss": 2.2651, | |
| "step": 3654 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 3.7361631972741556e-09, | |
| "loss": 2.2711, | |
| "step": 3657 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 3.586411751936802e-09, | |
| "loss": 2.2915, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "eval_loss": 2.299520969390869, | |
| "eval_runtime": 423.7203, | |
| "eval_samples_per_second": 20.145, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 3.4397123447216234e-09, | |
| "loss": 2.3214, | |
| "step": 3663 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 3.296065877562426e-09, | |
| "loss": 2.2542, | |
| "step": 3666 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 3.1554732336229185e-09, | |
| "loss": 2.2717, | |
| "step": 3669 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 3.0179352772914944e-09, | |
| "loss": 2.2931, | |
| "step": 3672 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 2.8834528541757385e-09, | |
| "loss": 2.1745, | |
| "step": 3675 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 2.7520267910971505e-09, | |
| "loss": 2.2972, | |
| "step": 3678 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "eval_loss": 2.29951548576355, | |
| "eval_runtime": 423.7495, | |
| "eval_samples_per_second": 20.144, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 2.6236578960864288e-09, | |
| "loss": 2.1784, | |
| "step": 3681 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 2.498346958378028e-09, | |
| "loss": 2.2984, | |
| "step": 3684 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 2.376094748405666e-09, | |
| "loss": 2.2609, | |
| "step": 3687 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 2.2569020177975462e-09, | |
| "loss": 2.3127, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 2.140769499371475e-09, | |
| "loss": 2.1933, | |
| "step": 3693 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 2.0276979071305877e-09, | |
| "loss": 2.2936, | |
| "step": 3696 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 1.917687936259016e-09, | |
| "loss": 2.3334, | |
| "step": 3699 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "eval_loss": 2.2995197772979736, | |
| "eval_runtime": 423.6689, | |
| "eval_samples_per_second": 20.148, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 1.810740263117394e-09, | |
| "loss": 2.2581, | |
| "step": 3702 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 1.7068555452388612e-09, | |
| "loss": 2.24, | |
| "step": 3705 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 1.6060344213248978e-09, | |
| "loss": 2.2293, | |
| "step": 3708 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 1.5082775112415513e-09, | |
| "loss": 2.2348, | |
| "step": 3711 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 1.4135854160154947e-09, | |
| "loss": 2.2998, | |
| "step": 3714 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 1.321958717830418e-09, | |
| "loss": 2.3125, | |
| "step": 3717 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 1.2333979800234206e-09, | |
| "loss": 2.2323, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "eval_loss": 2.2995173931121826, | |
| "eval_runtime": 423.6809, | |
| "eval_samples_per_second": 20.147, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 1.147903747081458e-09, | |
| "loss": 2.271, | |
| "step": 3723 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 1.065476544638122e-09, | |
| "loss": 2.2147, | |
| "step": 3726 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 9.861168794704223e-10, | |
| "loss": 2.2953, | |
| "step": 3729 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 9.098252394954542e-10, | |
| "loss": 2.3159, | |
| "step": 3732 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 8.366020937677354e-10, | |
| "loss": 2.2447, | |
| "step": 3735 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 7.664478924760409e-10, | |
| "loss": 2.3015, | |
| "step": 3738 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "eval_loss": 2.2995147705078125, | |
| "eval_runtime": 424.0084, | |
| "eval_samples_per_second": 20.132, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 6.993630669406835e-10, | |
| "loss": 2.2466, | |
| "step": 3741 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 6.353480296110714e-10, | |
| "loss": 2.2891, | |
| "step": 3744 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 5.744031740628208e-10, | |
| "loss": 2.2337, | |
| "step": 3747 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 5.165288749957586e-10, | |
| "loss": 2.3282, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 4.617254882311461e-10, | |
| "loss": 2.2669, | |
| "step": 3753 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 4.099933507099029e-10, | |
| "loss": 2.2943, | |
| "step": 3756 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 3.61332780490331e-10, | |
| "loss": 2.2493, | |
| "step": 3759 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "eval_loss": 2.2995152473449707, | |
| "eval_runtime": 423.7012, | |
| "eval_samples_per_second": 20.146, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 3.1574407674617165e-10, | |
| "loss": 2.2758, | |
| "step": 3762 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 2.732275197647738e-10, | |
| "loss": 2.3086, | |
| "step": 3765 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 2.337833709454284e-10, | |
| "loss": 2.2877, | |
| "step": 3768 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 1.9741187279770366e-10, | |
| "loss": 2.1814, | |
| "step": 3771 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 1.64113248940001e-10, | |
| "loss": 2.2774, | |
| "step": 3774 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 1.3388770409805684e-10, | |
| "loss": 2.2262, | |
| "step": 3777 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 1.0673542410388758e-10, | |
| "loss": 2.239, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "eval_loss": 2.299513339996338, | |
| "eval_runtime": 423.8086, | |
| "eval_samples_per_second": 20.141, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 8.265657589451302e-11, | |
| "loss": 2.2842, | |
| "step": 3783 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 6.165130751090153e-11, | |
| "loss": 2.2156, | |
| "step": 3786 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 4.371974809713741e-11, | |
| "loss": 2.1915, | |
| "step": 3789 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 2.8862007899588258e-11, | |
| "loss": 2.2198, | |
| "step": 3792 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 1.7078178266294318e-11, | |
| "loss": 2.2502, | |
| "step": 3795 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 8.368331646302351e-12, | |
| "loss": 2.2936, | |
| "step": 3798 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 2.29951810836792, | |
| "eval_runtime": 423.9362, | |
| "eval_samples_per_second": 20.135, | |
| "eval_steps_per_second": 0.63, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 2.7325215892770593e-12, | |
| "loss": 2.229, | |
| "step": 3801 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 3801, | |
| "total_flos": 3.389353837045429e+19, | |
| "train_loss": 2.2972320921952334, | |
| "train_runtime": 174891.5263, | |
| "train_samples_per_second": 2.782, | |
| "train_steps_per_second": 0.022 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 3801, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 30000, | |
| "total_flos": 3.389353837045429e+19, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |