| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.7651779499684249, | |
| "eval_steps": 100, | |
| "global_step": 16600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 9.999999924359191e-05, | |
| "loss": 3.375, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 9.999969743706657e-05, | |
| "loss": 3.2368, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 9.999878975192804e-05, | |
| "loss": 3.125, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 9.999727695556968e-05, | |
| "loss": 3.1125, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 9.999515906630015e-05, | |
| "loss": 3.125, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.999243610975122e-05, | |
| "loss": 3.075, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 3.4407286643981934, | |
| "eval_runtime": 47.8206, | |
| "eval_samples_per_second": 185.778, | |
| "eval_steps_per_second": 23.233, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.998910811887753e-05, | |
| "loss": 3.075, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.998517513395618e-05, | |
| "loss": 3.0875, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.998063720258612e-05, | |
| "loss": 3.05, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.997549437968781e-05, | |
| "loss": 3.075, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.99697467275023e-05, | |
| "loss": 3.05, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 3.436079978942871, | |
| "eval_runtime": 44.9925, | |
| "eval_samples_per_second": 197.455, | |
| "eval_steps_per_second": 24.693, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.996339431559068e-05, | |
| "loss": 3.0375, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.995643722083312e-05, | |
| "loss": 3.0625, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.9948875527428e-05, | |
| "loss": 3.05, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.994070932689079e-05, | |
| "loss": 3.075, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.993193871805313e-05, | |
| "loss": 3.0625, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 3.4281463623046875, | |
| "eval_runtime": 43.3797, | |
| "eval_samples_per_second": 204.796, | |
| "eval_steps_per_second": 25.611, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.993493000474458e-05, | |
| "loss": 2.775, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.992654413004669e-05, | |
| "loss": 2.975, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.991765053314131e-05, | |
| "loss": 3.15, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.990824930447085e-05, | |
| "loss": 3.075, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.989834053964e-05, | |
| "loss": 3.125, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 3.4483063220977783, | |
| "eval_runtime": 46.761, | |
| "eval_samples_per_second": 189.987, | |
| "eval_steps_per_second": 23.759, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.988792433941482e-05, | |
| "loss": 3.125, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.987700080972167e-05, | |
| "loss": 3.0875, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.986557006164606e-05, | |
| "loss": 3.075, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.985363221143172e-05, | |
| "loss": 3.1, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.984118738047918e-05, | |
| "loss": 3.075, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 3.4331181049346924, | |
| "eval_runtime": 47.2526, | |
| "eval_samples_per_second": 188.011, | |
| "eval_steps_per_second": 23.512, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.982823569534475e-05, | |
| "loss": 3.1, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.981477728773907e-05, | |
| "loss": 3.0375, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.980081229452586e-05, | |
| "loss": 3.075, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.97863408577205e-05, | |
| "loss": 3.1, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.97713631244886e-05, | |
| "loss": 3.075, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 3.434506893157959, | |
| "eval_runtime": 47.9631, | |
| "eval_samples_per_second": 185.226, | |
| "eval_steps_per_second": 23.164, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.975587924714449e-05, | |
| "loss": 3.075, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.973988938314965e-05, | |
| "loss": 3.0375, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.972339369511113e-05, | |
| "loss": 3.0625, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.970639235077997e-05, | |
| "loss": 3.1, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.968888552304934e-05, | |
| "loss": 3.05, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 3.424459218978882, | |
| "eval_runtime": 48.3341, | |
| "eval_samples_per_second": 183.804, | |
| "eval_steps_per_second": 22.986, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.967087338995289e-05, | |
| "loss": 3.05, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.965235613466294e-05, | |
| "loss": 3.05, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.963333394548857e-05, | |
| "loss": 3.075, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.961380701587372e-05, | |
| "loss": 3.075, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.959377554439524e-05, | |
| "loss": 3.0125, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 3.4213478565216064, | |
| "eval_runtime": 46.7992, | |
| "eval_samples_per_second": 189.832, | |
| "eval_steps_per_second": 23.74, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.957323973476087e-05, | |
| "loss": 3.025, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.955219979580715e-05, | |
| "loss": 3.025, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.953065594149726e-05, | |
| "loss": 3.1, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.950860839091901e-05, | |
| "loss": 3.025, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.948605736828233e-05, | |
| "loss": 3.075, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 3.4135727882385254, | |
| "eval_runtime": 45.2339, | |
| "eval_samples_per_second": 196.401, | |
| "eval_steps_per_second": 24.561, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.946300310291728e-05, | |
| "loss": 3.025, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.943944582927151e-05, | |
| "loss": 3.075, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.941538578690803e-05, | |
| "loss": 3.025, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.939082322050261e-05, | |
| "loss": 2.975, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.936575837984145e-05, | |
| "loss": 3.05, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 3.414569854736328, | |
| "eval_runtime": 46.6567, | |
| "eval_samples_per_second": 190.412, | |
| "eval_steps_per_second": 23.812, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.934019151981855e-05, | |
| "loss": 3.075, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.931412290043311e-05, | |
| "loss": 3.0, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.928755278678694e-05, | |
| "loss": 3.0, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.926048144908173e-05, | |
| "loss": 3.025, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.923290916261633e-05, | |
| "loss": 3.0375, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 3.4042751789093018, | |
| "eval_runtime": 46.6401, | |
| "eval_samples_per_second": 190.48, | |
| "eval_steps_per_second": 23.821, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.920483620778389e-05, | |
| "loss": 3.075, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.917626287006911e-05, | |
| "loss": 3.0, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.91471894400452e-05, | |
| "loss": 3.0, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.911761621337104e-05, | |
| "loss": 3.0, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.908754349078815e-05, | |
| "loss": 3.025, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 3.406078815460205, | |
| "eval_runtime": 46.6265, | |
| "eval_samples_per_second": 190.535, | |
| "eval_steps_per_second": 23.828, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.905697157811761e-05, | |
| "loss": 3.0375, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.902590078625691e-05, | |
| "loss": 3.0875, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.899433143117692e-05, | |
| "loss": 3.0625, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.896226383391846e-05, | |
| "loss": 3.0375, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.892969832058934e-05, | |
| "loss": 3.0125, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 3.3987860679626465, | |
| "eval_runtime": 45.6807, | |
| "eval_samples_per_second": 194.48, | |
| "eval_steps_per_second": 24.321, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.88966352223607e-05, | |
| "loss": 3.025, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.886307487546393e-05, | |
| "loss": 3.0, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.882901762118709e-05, | |
| "loss": 3.025, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.879446380587144e-05, | |
| "loss": 3.025, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.875941378090805e-05, | |
| "loss": 3.0375, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 3.3974123001098633, | |
| "eval_runtime": 44.2161, | |
| "eval_samples_per_second": 200.922, | |
| "eval_steps_per_second": 25.127, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.872386790273407e-05, | |
| "loss": 3.0125, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.86878265328292e-05, | |
| "loss": 3.025, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.865129003771195e-05, | |
| "loss": 3.0, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.8614258788936e-05, | |
| "loss": 3.025, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.857673316308635e-05, | |
| "loss": 3.0, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 3.401176691055298, | |
| "eval_runtime": 43.9787, | |
| "eval_samples_per_second": 202.007, | |
| "eval_steps_per_second": 25.262, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.853871354177548e-05, | |
| "loss": 3.0125, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.850020031163956e-05, | |
| "loss": 3.025, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.84611938643344e-05, | |
| "loss": 3.025, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.842169459653154e-05, | |
| "loss": 3.0, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.838170290991423e-05, | |
| "loss": 2.9875, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 3.396237373352051, | |
| "eval_runtime": 44.0193, | |
| "eval_samples_per_second": 201.821, | |
| "eval_steps_per_second": 25.239, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.834121921117325e-05, | |
| "loss": 3.025, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.830024391200294e-05, | |
| "loss": 3.0, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.825877742909685e-05, | |
| "loss": 2.9625, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.821682018414355e-05, | |
| "loss": 3.0, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.81743726038224e-05, | |
| "loss": 3.0, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 3.3904049396514893, | |
| "eval_runtime": 44.2972, | |
| "eval_samples_per_second": 200.554, | |
| "eval_steps_per_second": 25.081, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.813143511979915e-05, | |
| "loss": 3.0, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.808800816872155e-05, | |
| "loss": 2.975, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.804409219221497e-05, | |
| "loss": 3.025, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.799968763687784e-05, | |
| "loss": 2.9875, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.795479495427715e-05, | |
| "loss": 3.0, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 3.3834683895111084, | |
| "eval_runtime": 44.0789, | |
| "eval_samples_per_second": 201.547, | |
| "eval_steps_per_second": 25.205, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.790941460094383e-05, | |
| "loss": 2.9875, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.786354703836813e-05, | |
| "loss": 3.0125, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.78171927329949e-05, | |
| "loss": 2.975, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.77703521562189e-05, | |
| "loss": 2.9875, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.772302578437993e-05, | |
| "loss": 3.025, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 3.3825738430023193, | |
| "eval_runtime": 46.5341, | |
| "eval_samples_per_second": 190.914, | |
| "eval_steps_per_second": 23.875, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.767521409875807e-05, | |
| "loss": 2.9875, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.76269175855687e-05, | |
| "loss": 2.9625, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.757813673595762e-05, | |
| "loss": 3.025, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.752887204599602e-05, | |
| "loss": 2.95, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.747912401667549e-05, | |
| "loss": 2.9875, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 3.3757646083831787, | |
| "eval_runtime": 44.0535, | |
| "eval_samples_per_second": 201.664, | |
| "eval_steps_per_second": 25.219, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.742889315390282e-05, | |
| "loss": 2.975, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.737817996849497e-05, | |
| "loss": 3.0125, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.732698497617378e-05, | |
| "loss": 3.0, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.727530869756083e-05, | |
| "loss": 3.05, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.722315165817202e-05, | |
| "loss": 3.0, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 3.3752329349517822, | |
| "eval_runtime": 45.7979, | |
| "eval_samples_per_second": 193.983, | |
| "eval_steps_per_second": 24.259, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.717051438841234e-05, | |
| "loss": 3.0, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.711739742357038e-05, | |
| "loss": 2.925, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.7063801303813e-05, | |
| "loss": 3.0, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.700972657417972e-05, | |
| "loss": 2.9875, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.695517378457722e-05, | |
| "loss": 3.0, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 3.373331308364868, | |
| "eval_runtime": 45.8228, | |
| "eval_samples_per_second": 193.877, | |
| "eval_steps_per_second": 24.246, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.690014348977378e-05, | |
| "loss": 2.9625, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.684463624939363e-05, | |
| "loss": 3.0, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.678865262791121e-05, | |
| "loss": 2.975, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.673219319464546e-05, | |
| "loss": 2.975, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.667525852375406e-05, | |
| "loss": 2.975, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 3.365558385848999, | |
| "eval_runtime": 46.0139, | |
| "eval_samples_per_second": 193.072, | |
| "eval_steps_per_second": 24.145, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.719920832308002e-05, | |
| "loss": 2.8375, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.715117649384126e-05, | |
| "loss": 2.825, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.650160889936038e-05, | |
| "loss": 3.4, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.64427791161119e-05, | |
| "loss": 3.025, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.638347703840073e-05, | |
| "loss": 2.9875, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 3.375772476196289, | |
| "eval_runtime": 45.3781, | |
| "eval_samples_per_second": 195.777, | |
| "eval_steps_per_second": 24.483, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.632370326929247e-05, | |
| "loss": 2.975, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.626345841664953e-05, | |
| "loss": 2.975, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.620274309312497e-05, | |
| "loss": 2.975, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.614155791615624e-05, | |
| "loss": 3.0125, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.607990350795892e-05, | |
| "loss": 2.975, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 3.3692703247070312, | |
| "eval_runtime": 45.3611, | |
| "eval_samples_per_second": 195.85, | |
| "eval_steps_per_second": 24.492, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.601778049552035e-05, | |
| "loss": 2.975, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.595518951059332e-05, | |
| "loss": 2.975, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.58921311896896e-05, | |
| "loss": 2.9625, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.582860617407349e-05, | |
| "loss": 3.0, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.576461510975529e-05, | |
| "loss": 2.9875, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 3.367400646209717, | |
| "eval_runtime": 46.0623, | |
| "eval_samples_per_second": 192.869, | |
| "eval_steps_per_second": 24.12, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.570015864748467e-05, | |
| "loss": 2.9625, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.563523744274418e-05, | |
| "loss": 2.9625, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.556985215574253e-05, | |
| "loss": 2.925, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.550400345140775e-05, | |
| "loss": 2.95, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.543769199938066e-05, | |
| "loss": 2.975, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 3.3634161949157715, | |
| "eval_runtime": 46.5968, | |
| "eval_samples_per_second": 190.657, | |
| "eval_steps_per_second": 23.843, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.53709184740079e-05, | |
| "loss": 2.975, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.530368355433506e-05, | |
| "loss": 2.9875, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.52359879240999e-05, | |
| "loss": 2.95, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.516783227172527e-05, | |
| "loss": 3.0125, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.509921729031221e-05, | |
| "loss": 2.95, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 3.3650927543640137, | |
| "eval_runtime": 43.5108, | |
| "eval_samples_per_second": 204.179, | |
| "eval_steps_per_second": 25.534, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.50301436776328e-05, | |
| "loss": 2.975, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.496061213612315e-05, | |
| "loss": 2.975, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.489062337287622e-05, | |
| "loss": 2.975, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.482017809963463e-05, | |
| "loss": 2.975, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.474927703278343e-05, | |
| "loss": 2.9625, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 3.3596906661987305, | |
| "eval_runtime": 47.7219, | |
| "eval_samples_per_second": 186.162, | |
| "eval_steps_per_second": 23.281, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.46779208933428e-05, | |
| "loss": 2.95, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.460611040696072e-05, | |
| "loss": 2.95, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.453384630390566e-05, | |
| "loss": 2.975, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.446112931905899e-05, | |
| "loss": 2.975, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.438796019190772e-05, | |
| "loss": 2.95, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 3.3532304763793945, | |
| "eval_runtime": 46.7609, | |
| "eval_samples_per_second": 189.988, | |
| "eval_steps_per_second": 23.759, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.431433966653676e-05, | |
| "loss": 2.95, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.424026849162155e-05, | |
| "loss": 2.9875, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.416574742042033e-05, | |
| "loss": 2.9625, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.409077721076646e-05, | |
| "loss": 2.9625, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.401535862506083e-05, | |
| "loss": 2.95, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 3.3577165603637695, | |
| "eval_runtime": 45.3577, | |
| "eval_samples_per_second": 195.865, | |
| "eval_steps_per_second": 24.494, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.393949243026403e-05, | |
| "loss": 2.975, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.386317939788852e-05, | |
| "loss": 2.9375, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.378642030399082e-05, | |
| "loss": 2.95, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.370921592916369e-05, | |
| "loss": 2.95, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.363156705852803e-05, | |
| "loss": 2.95, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 3.352811336517334, | |
| "eval_runtime": 45.6296, | |
| "eval_samples_per_second": 194.698, | |
| "eval_steps_per_second": 24.348, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.355347448172507e-05, | |
| "loss": 2.95, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.347493899290823e-05, | |
| "loss": 2.9625, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.339596139073504e-05, | |
| "loss": 2.975, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.33165424783591e-05, | |
| "loss": 2.95, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.323668306342181e-05, | |
| "loss": 2.9625, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 3.3555846214294434, | |
| "eval_runtime": 46.6131, | |
| "eval_samples_per_second": 190.59, | |
| "eval_steps_per_second": 23.834, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.315638395804427e-05, | |
| "loss": 2.95, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.307564597881892e-05, | |
| "loss": 2.95, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.299446994680129e-05, | |
| "loss": 2.95, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.291285668750164e-05, | |
| "loss": 2.9625, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.283080703087654e-05, | |
| "loss": 2.9625, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 3.3486101627349854, | |
| "eval_runtime": 46.5267, | |
| "eval_samples_per_second": 190.944, | |
| "eval_steps_per_second": 23.879, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.274832181132047e-05, | |
| "loss": 2.95, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.266540186765734e-05, | |
| "loss": 2.975, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.258204804313188e-05, | |
| "loss": 2.95, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.24982611854012e-05, | |
| "loss": 2.925, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.2414042146526e-05, | |
| "loss": 2.975, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 3.3436102867126465, | |
| "eval_runtime": 45.8729, | |
| "eval_samples_per_second": 193.665, | |
| "eval_steps_per_second": 24.219, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.232939178296205e-05, | |
| "loss": 2.95, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.224431095555142e-05, | |
| "loss": 2.95, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.215880052951375e-05, | |
| "loss": 2.95, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.207286137443738e-05, | |
| "loss": 2.95, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.198649436427063e-05, | |
| "loss": 2.95, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 3.3440802097320557, | |
| "eval_runtime": 46.4221, | |
| "eval_samples_per_second": 191.375, | |
| "eval_steps_per_second": 23.933, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.189970037731275e-05, | |
| "loss": 2.925, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.18124802962052e-05, | |
| "loss": 2.9375, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.172483500792244e-05, | |
| "loss": 2.925, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.163676540376313e-05, | |
| "loss": 2.925, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.154827237934086e-05, | |
| "loss": 2.95, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 3.3465864658355713, | |
| "eval_runtime": 46.4585, | |
| "eval_samples_per_second": 191.225, | |
| "eval_steps_per_second": 23.914, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.14593568345752e-05, | |
| "loss": 2.975, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.137001967368252e-05, | |
| "loss": 2.925, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.128026180516669e-05, | |
| "loss": 2.925, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.119008414180997e-05, | |
| "loss": 2.9375, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.109948760066367e-05, | |
| "loss": 2.95, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 3.3428447246551514, | |
| "eval_runtime": 46.6755, | |
| "eval_samples_per_second": 190.335, | |
| "eval_steps_per_second": 23.803, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.100847310303882e-05, | |
| "loss": 2.95, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.091704157449679e-05, | |
| "loss": 2.95, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.082519394483992e-05, | |
| "loss": 2.925, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.073293114810209e-05, | |
| "loss": 2.975, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.064025412253906e-05, | |
| "loss": 2.95, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 3.343625068664551, | |
| "eval_runtime": 45.3374, | |
| "eval_samples_per_second": 195.953, | |
| "eval_steps_per_second": 24.505, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.054716381061916e-05, | |
| "loss": 2.95, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.04536611590135e-05, | |
| "loss": 2.95, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.035974711858647e-05, | |
| "loss": 2.95, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.026542264438605e-05, | |
| "loss": 2.9625, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.017068869563401e-05, | |
| "loss": 2.975, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 3.341850996017456, | |
| "eval_runtime": 45.5544, | |
| "eval_samples_per_second": 195.02, | |
| "eval_steps_per_second": 24.388, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.007554623571631e-05, | |
| "loss": 2.925, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 8.997999623217316e-05, | |
| "loss": 2.925, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 8.988403965668925e-05, | |
| "loss": 2.9375, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 8.978767748508386e-05, | |
| "loss": 2.9375, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 8.969091069730094e-05, | |
| "loss": 2.95, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 3.337675094604492, | |
| "eval_runtime": 47.058, | |
| "eval_samples_per_second": 188.788, | |
| "eval_steps_per_second": 23.609, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 8.959374027739913e-05, | |
| "loss": 2.925, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 8.949616721354176e-05, | |
| "loss": 2.95, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 8.939819249798679e-05, | |
| "loss": 2.95, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 8.929981712707675e-05, | |
| "loss": 2.925, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 8.920104210122857e-05, | |
| "loss": 2.95, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 3.3335466384887695, | |
| "eval_runtime": 51.4473, | |
| "eval_samples_per_second": 172.681, | |
| "eval_steps_per_second": 21.595, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 8.910186842492346e-05, | |
| "loss": 2.9375, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 8.900229710669658e-05, | |
| "loss": 2.925, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 8.890232915912698e-05, | |
| "loss": 2.925, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 8.88019655988271e-05, | |
| "loss": 2.925, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 8.870120744643253e-05, | |
| "loss": 2.9625, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 3.334672212600708, | |
| "eval_runtime": 45.7545, | |
| "eval_samples_per_second": 194.167, | |
| "eval_steps_per_second": 24.282, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 8.860005572659162e-05, | |
| "loss": 2.95, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 8.84985114679551e-05, | |
| "loss": 2.9375, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 8.839657570316553e-05, | |
| "loss": 2.9375, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 8.829424946884687e-05, | |
| "loss": 2.925, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 8.81915338055939e-05, | |
| "loss": 2.925, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 3.3262383937835693, | |
| "eval_runtime": 44.7349, | |
| "eval_samples_per_second": 198.592, | |
| "eval_steps_per_second": 24.835, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 8.808842975796165e-05, | |
| "loss": 2.9375, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 8.798493837445482e-05, | |
| "loss": 2.925, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 8.788106070751701e-05, | |
| "loss": 2.9125, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 8.777679781352014e-05, | |
| "loss": 2.925, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 8.767215075275366e-05, | |
| "loss": 2.95, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 3.3293297290802, | |
| "eval_runtime": 45.3065, | |
| "eval_samples_per_second": 196.086, | |
| "eval_steps_per_second": 24.522, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 8.756712058941368e-05, | |
| "loss": 2.975, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 8.746170839159232e-05, | |
| "loss": 2.925, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 8.735591523126669e-05, | |
| "loss": 2.95, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 8.724974218428811e-05, | |
| "loss": 2.9125, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 8.714319033037105e-05, | |
| "loss": 2.975, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 3.3268916606903076, | |
| "eval_runtime": 46.039, | |
| "eval_samples_per_second": 192.967, | |
| "eval_steps_per_second": 24.132, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 8.703626075308226e-05, | |
| "loss": 2.925, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 8.692895453982971e-05, | |
| "loss": 2.925, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 8.682127278185148e-05, | |
| "loss": 2.9125, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 8.671321657420475e-05, | |
| "loss": 2.95, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 8.660478701575458e-05, | |
| "loss": 2.9375, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 3.3328793048858643, | |
| "eval_runtime": 45.617, | |
| "eval_samples_per_second": 194.752, | |
| "eval_steps_per_second": 24.355, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 8.649598520916285e-05, | |
| "loss": 2.925, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 8.63868122608769e-05, | |
| "loss": 2.925, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 8.627726928111837e-05, | |
| "loss": 2.9125, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 8.616735738387194e-05, | |
| "loss": 2.95, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 8.60570776868739e-05, | |
| "loss": 2.95, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 3.3268396854400635, | |
| "eval_runtime": 45.6543, | |
| "eval_samples_per_second": 194.593, | |
| "eval_steps_per_second": 24.335, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 8.594643131160084e-05, | |
| "loss": 2.95, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 8.583541938325829e-05, | |
| "loss": 2.925, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 8.8097503111286e-05, | |
| "loss": 3.1625, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 8.800346560949554e-05, | |
| "loss": 2.85, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 8.790910870059963e-05, | |
| "loss": 2.85, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 3.3341128826141357, | |
| "eval_runtime": 44.1972, | |
| "eval_samples_per_second": 201.008, | |
| "eval_steps_per_second": 25.137, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 8.78144331776382e-05, | |
| "loss": 2.825, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 8.771943983632912e-05, | |
| "loss": 2.825, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 8.516173467720004e-05, | |
| "loss": 3.3, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 8.504819569393931e-05, | |
| "loss": 2.9375, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 8.493430029211216e-05, | |
| "loss": 2.925, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 3.32954740524292, | |
| "eval_runtime": 44.7353, | |
| "eval_samples_per_second": 198.59, | |
| "eval_steps_per_second": 24.835, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 8.482004962996468e-05, | |
| "loss": 2.925, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 8.470544486935572e-05, | |
| "loss": 2.95, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 8.459048717574514e-05, | |
| "loss": 2.9375, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 8.447517771818187e-05, | |
| "loss": 2.9375, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 8.435951766929209e-05, | |
| "loss": 2.925, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 3.3254106044769287, | |
| "eval_runtime": 43.2801, | |
| "eval_samples_per_second": 205.268, | |
| "eval_steps_per_second": 25.67, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 8.424350820526727e-05, | |
| "loss": 2.925, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 8.412715050585222e-05, | |
| "loss": 2.925, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 8.401044575433311e-05, | |
| "loss": 2.9, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 8.389339513752534e-05, | |
| "loss": 2.9125, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 8.377599984576165e-05, | |
| "loss": 2.925, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 3.3228042125701904, | |
| "eval_runtime": 44.4861, | |
| "eval_samples_per_second": 199.703, | |
| "eval_steps_per_second": 24.974, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 8.365826107287982e-05, | |
| "loss": 2.9, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 8.35401800162107e-05, | |
| "loss": 2.9125, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 8.34217578765659e-05, | |
| "loss": 2.925, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 8.330299585822565e-05, | |
| "loss": 2.95, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 8.318389516892653e-05, | |
| "loss": 2.925, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 3.3222899436950684, | |
| "eval_runtime": 43.3931, | |
| "eval_samples_per_second": 204.733, | |
| "eval_steps_per_second": 25.603, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 8.306445701984923e-05, | |
| "loss": 2.9, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 8.294468262560616e-05, | |
| "loss": 2.9125, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.064827889947988e-05, | |
| "loss": 3.175, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.0580642178795e-05, | |
| "loss": 2.8875, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.051278717085247e-05, | |
| "loss": 2.9, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 3.337049961090088, | |
| "eval_runtime": 44.8516, | |
| "eval_samples_per_second": 198.076, | |
| "eval_steps_per_second": 24.771, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 8.246224700864346e-05, | |
| "loss": 2.925, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 8.234080972700282e-05, | |
| "loss": 2.9125, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 8.221904355924374e-05, | |
| "loss": 2.9625, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 8.209694974365316e-05, | |
| "loss": 2.95, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 8.197452952184999e-05, | |
| "loss": 2.9375, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 3.3219408988952637, | |
| "eval_runtime": 44.389, | |
| "eval_samples_per_second": 200.139, | |
| "eval_steps_per_second": 25.029, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 8.185178413877247e-05, | |
| "loss": 2.9375, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 8.17287148426656e-05, | |
| "loss": 2.9375, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 8.16053228850683e-05, | |
| "loss": 2.925, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 8.148160952080079e-05, | |
| "loss": 2.95, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 8.135757600795181e-05, | |
| "loss": 2.9, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 3.3177073001861572, | |
| "eval_runtime": 43.8736, | |
| "eval_samples_per_second": 202.491, | |
| "eval_steps_per_second": 25.323, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 8.123322360786581e-05, | |
| "loss": 2.925, | |
| "step": 5620 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 8.110855358513013e-05, | |
| "loss": 2.9125, | |
| "step": 5640 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 8.098356720756207e-05, | |
| "loss": 2.9125, | |
| "step": 5660 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 8.085826574619614e-05, | |
| "loss": 2.9, | |
| "step": 5680 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 8.07326504752711e-05, | |
| "loss": 2.925, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 3.315720319747925, | |
| "eval_runtime": 43.7798, | |
| "eval_samples_per_second": 202.925, | |
| "eval_steps_per_second": 25.377, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 8.060672267221681e-05, | |
| "loss": 2.9, | |
| "step": 5720 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 8.048048361764153e-05, | |
| "loss": 2.925, | |
| "step": 5740 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 8.035393459531868e-05, | |
| "loss": 2.9, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 8.02270768921739e-05, | |
| "loss": 2.9, | |
| "step": 5780 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 8.00999117982719e-05, | |
| "loss": 2.9, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 3.31453275680542, | |
| "eval_runtime": 43.9257, | |
| "eval_samples_per_second": 202.251, | |
| "eval_steps_per_second": 25.293, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.997244060680337e-05, | |
| "loss": 2.95, | |
| "step": 5820 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.984466461407184e-05, | |
| "loss": 2.925, | |
| "step": 5840 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.971658511948045e-05, | |
| "loss": 2.9125, | |
| "step": 5860 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.95882034255188e-05, | |
| "loss": 2.9125, | |
| "step": 5880 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.945952083774964e-05, | |
| "loss": 2.8875, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 3.315502643585205, | |
| "eval_runtime": 44.0538, | |
| "eval_samples_per_second": 201.662, | |
| "eval_steps_per_second": 25.219, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.933053866479564e-05, | |
| "loss": 2.925, | |
| "step": 5920 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.920125821832609e-05, | |
| "loss": 2.925, | |
| "step": 5940 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.90716808130435e-05, | |
| "loss": 2.925, | |
| "step": 5960 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.894180776667029e-05, | |
| "loss": 2.9, | |
| "step": 5980 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.881164039993537e-05, | |
| "loss": 2.9, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 3.311098575592041, | |
| "eval_runtime": 43.9408, | |
| "eval_samples_per_second": 202.181, | |
| "eval_steps_per_second": 25.284, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 7.868118003656065e-05, | |
| "loss": 2.9, | |
| "step": 6020 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 7.855042800324775e-05, | |
| "loss": 2.925, | |
| "step": 6040 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 7.841938562966429e-05, | |
| "loss": 2.925, | |
| "step": 6060 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 7.828805424843052e-05, | |
| "loss": 2.9, | |
| "step": 6080 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 7.81564351951057e-05, | |
| "loss": 2.9, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 3.3125574588775635, | |
| "eval_runtime": 44.0278, | |
| "eval_samples_per_second": 201.782, | |
| "eval_steps_per_second": 25.234, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 7.802452980817456e-05, | |
| "loss": 2.925, | |
| "step": 6120 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 7.789233942903365e-05, | |
| "loss": 2.9375, | |
| "step": 6140 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 7.775986540197771e-05, | |
| "loss": 2.9125, | |
| "step": 6160 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 7.762710907418604e-05, | |
| "loss": 2.9, | |
| "step": 6180 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 7.749407179570869e-05, | |
| "loss": 2.9, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 3.3099308013916016, | |
| "eval_runtime": 43.8967, | |
| "eval_samples_per_second": 202.384, | |
| "eval_steps_per_second": 25.309, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 8.101719628029329e-05, | |
| "loss": 2.8375, | |
| "step": 6220 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 8.090337416944871e-05, | |
| "loss": 2.85, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 7.709328779943762e-05, | |
| "loss": 3.3, | |
| "step": 6260 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 7.695914027565401e-05, | |
| "loss": 2.925, | |
| "step": 6280 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 7.68247185940161e-05, | |
| "loss": 2.9, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 3.3130953311920166, | |
| "eval_runtime": 44.9311, | |
| "eval_samples_per_second": 197.725, | |
| "eval_steps_per_second": 24.727, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 7.669002412150956e-05, | |
| "loss": 2.925, | |
| "step": 6320 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 7.655505822789428e-05, | |
| "loss": 2.925, | |
| "step": 6340 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 7.641982228569022e-05, | |
| "loss": 2.9, | |
| "step": 6360 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 7.628431767016368e-05, | |
| "loss": 2.925, | |
| "step": 6380 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 7.614854575931314e-05, | |
| "loss": 2.9, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 3.309799909591675, | |
| "eval_runtime": 44.3468, | |
| "eval_samples_per_second": 200.33, | |
| "eval_steps_per_second": 25.053, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 7.60125079338553e-05, | |
| "loss": 2.925, | |
| "step": 6420 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 7.587620557721109e-05, | |
| "loss": 2.875, | |
| "step": 6440 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 7.573964007549155e-05, | |
| "loss": 2.9125, | |
| "step": 6460 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 7.560281281748369e-05, | |
| "loss": 2.9, | |
| "step": 6480 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 7.546572519463649e-05, | |
| "loss": 2.925, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 3.306143283843994, | |
| "eval_runtime": 43.9845, | |
| "eval_samples_per_second": 201.98, | |
| "eval_steps_per_second": 25.259, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 7.532837860104665e-05, | |
| "loss": 2.9, | |
| "step": 6520 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 7.519077443344445e-05, | |
| "loss": 2.925, | |
| "step": 6540 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 7.50529140911795e-05, | |
| "loss": 2.9125, | |
| "step": 6560 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 7.491479897620664e-05, | |
| "loss": 2.9125, | |
| "step": 6580 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 7.477643049307146e-05, | |
| "loss": 2.9125, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 3.3044984340667725, | |
| "eval_runtime": 43.9627, | |
| "eval_samples_per_second": 202.08, | |
| "eval_steps_per_second": 25.271, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 7.463781004889628e-05, | |
| "loss": 2.9125, | |
| "step": 6620 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 7.449893905336564e-05, | |
| "loss": 2.925, | |
| "step": 6640 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 7.435981891871201e-05, | |
| "loss": 2.9, | |
| "step": 6660 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 7.422045105970154e-05, | |
| "loss": 2.9, | |
| "step": 6680 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 7.40808368936195e-05, | |
| "loss": 2.925, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 3.3060998916625977, | |
| "eval_runtime": 44.368, | |
| "eval_samples_per_second": 200.234, | |
| "eval_steps_per_second": 25.041, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 7.394097784025598e-05, | |
| "loss": 2.8875, | |
| "step": 6720 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 7.38008753218914e-05, | |
| "loss": 2.8875, | |
| "step": 6740 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 7.366053076328214e-05, | |
| "loss": 2.9, | |
| "step": 6760 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 7.351994559164589e-05, | |
| "loss": 2.9125, | |
| "step": 6780 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 7.33791212366473e-05, | |
| "loss": 2.9125, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 3.3047516345977783, | |
| "eval_runtime": 44.3084, | |
| "eval_samples_per_second": 200.504, | |
| "eval_steps_per_second": 25.074, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 7.323805913038333e-05, | |
| "loss": 2.925, | |
| "step": 6820 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 7.309676070736871e-05, | |
| "loss": 2.8875, | |
| "step": 6840 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 7.295522740452138e-05, | |
| "loss": 2.9, | |
| "step": 6860 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 7.281346066114794e-05, | |
| "loss": 2.9125, | |
| "step": 6880 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 7.267146191892878e-05, | |
| "loss": 2.925, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 3.304474353790283, | |
| "eval_runtime": 45.7201, | |
| "eval_samples_per_second": 194.313, | |
| "eval_steps_per_second": 24.3, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 7.252923262190368e-05, | |
| "loss": 2.9, | |
| "step": 6920 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 7.238677421645705e-05, | |
| "loss": 2.9, | |
| "step": 6940 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 7.22440881513031e-05, | |
| "loss": 2.875, | |
| "step": 6960 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 7.210117587747124e-05, | |
| "loss": 2.9, | |
| "step": 6980 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 7.195803884829133e-05, | |
| "loss": 2.9, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 3.2992727756500244, | |
| "eval_runtime": 44.5604, | |
| "eval_samples_per_second": 199.37, | |
| "eval_steps_per_second": 24.932, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 7.181467851937874e-05, | |
| "loss": 2.9, | |
| "step": 7020 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 7.167109634861978e-05, | |
| "loss": 2.9125, | |
| "step": 7040 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 7.152729379615671e-05, | |
| "loss": 2.8875, | |
| "step": 7060 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 7.138327232437287e-05, | |
| "loss": 2.9, | |
| "step": 7080 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 7.123903339787801e-05, | |
| "loss": 2.875, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 3.3000950813293457, | |
| "eval_runtime": 44.3576, | |
| "eval_samples_per_second": 200.281, | |
| "eval_steps_per_second": 25.046, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 7.109457848349314e-05, | |
| "loss": 2.9, | |
| "step": 7120 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 7.094990905023578e-05, | |
| "loss": 2.8875, | |
| "step": 7140 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 7.0805026569305e-05, | |
| "loss": 2.9, | |
| "step": 7160 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 7.065993251406639e-05, | |
| "loss": 2.9, | |
| "step": 7180 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 7.051462836003712e-05, | |
| "loss": 2.875, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 3.2999911308288574, | |
| "eval_runtime": 44.2882, | |
| "eval_samples_per_second": 200.595, | |
| "eval_steps_per_second": 25.086, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 7.036911558487101e-05, | |
| "loss": 2.9, | |
| "step": 7220 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 7.02233956683433e-05, | |
| "loss": 2.9, | |
| "step": 7240 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 7.007747009233585e-05, | |
| "loss": 2.9, | |
| "step": 7260 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.993134034082191e-05, | |
| "loss": 2.9, | |
| "step": 7280 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.978500789985103e-05, | |
| "loss": 2.925, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 3.29707932472229, | |
| "eval_runtime": 44.7959, | |
| "eval_samples_per_second": 198.322, | |
| "eval_steps_per_second": 24.801, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.963847425753403e-05, | |
| "loss": 2.875, | |
| "step": 7320 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.949174090402783e-05, | |
| "loss": 2.875, | |
| "step": 7340 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.934480933152024e-05, | |
| "loss": 2.9, | |
| "step": 7360 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.919768103421487e-05, | |
| "loss": 2.9, | |
| "step": 7380 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.905035750831595e-05, | |
| "loss": 2.8875, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 3.294090747833252, | |
| "eval_runtime": 44.8493, | |
| "eval_samples_per_second": 198.085, | |
| "eval_steps_per_second": 24.772, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.890284025201295e-05, | |
| "loss": 2.9, | |
| "step": 7420 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.875513076546553e-05, | |
| "loss": 2.875, | |
| "step": 7440 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.860723055078823e-05, | |
| "loss": 2.875, | |
| "step": 7460 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.845914111203515e-05, | |
| "loss": 2.8875, | |
| "step": 7480 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.831086395518466e-05, | |
| "loss": 2.8875, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 3.2986342906951904, | |
| "eval_runtime": 44.8205, | |
| "eval_samples_per_second": 198.213, | |
| "eval_steps_per_second": 24.788, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 7.312179993377315e-05, | |
| "loss": 2.8375, | |
| "step": 7520 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 7.299317890913563e-05, | |
| "loss": 2.825, | |
| "step": 7540 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.78649212643754e-05, | |
| "loss": 3.3, | |
| "step": 7560 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.771590833286872e-05, | |
| "loss": 2.9, | |
| "step": 7580 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.756671524148425e-05, | |
| "loss": 2.8875, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 3.3002877235412598, | |
| "eval_runtime": 45.1381, | |
| "eval_samples_per_second": 196.818, | |
| "eval_steps_per_second": 24.613, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.741734350742393e-05, | |
| "loss": 2.925, | |
| "step": 7620 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.72677946497063e-05, | |
| "loss": 2.8875, | |
| "step": 7640 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.71180701891511e-05, | |
| "loss": 2.875, | |
| "step": 7660 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.696817164836391e-05, | |
| "loss": 2.925, | |
| "step": 7680 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.68181005517206e-05, | |
| "loss": 2.9, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 3.2993860244750977, | |
| "eval_runtime": 44.8339, | |
| "eval_samples_per_second": 198.154, | |
| "eval_steps_per_second": 24.78, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.666785842535179e-05, | |
| "loss": 2.9125, | |
| "step": 7720 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.651744679712737e-05, | |
| "loss": 2.925, | |
| "step": 7740 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.636686719664099e-05, | |
| "loss": 2.875, | |
| "step": 7760 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.621612115519444e-05, | |
| "loss": 2.9, | |
| "step": 7780 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.606521020578213e-05, | |
| "loss": 2.9, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 3.294872522354126, | |
| "eval_runtime": 43.9099, | |
| "eval_samples_per_second": 202.324, | |
| "eval_steps_per_second": 25.302, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.59141358830755e-05, | |
| "loss": 2.925, | |
| "step": 7820 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.576289972340735e-05, | |
| "loss": 2.9, | |
| "step": 7840 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.561150326475629e-05, | |
| "loss": 2.875, | |
| "step": 7860 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.545994804673108e-05, | |
| "loss": 2.9125, | |
| "step": 7880 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.530823561055494e-05, | |
| "loss": 2.875, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 3.292506694793701, | |
| "eval_runtime": 43.4451, | |
| "eval_samples_per_second": 204.488, | |
| "eval_steps_per_second": 25.573, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.515636749904995e-05, | |
| "loss": 2.9, | |
| "step": 7920 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.500434525662124e-05, | |
| "loss": 2.875, | |
| "step": 7940 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.485217042924143e-05, | |
| "loss": 2.875, | |
| "step": 7960 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 6.469984456443477e-05, | |
| "loss": 2.875, | |
| "step": 7980 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 6.454736921126152e-05, | |
| "loss": 2.9, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 3.2918550968170166, | |
| "eval_runtime": 44.0979, | |
| "eval_samples_per_second": 201.461, | |
| "eval_steps_per_second": 25.194, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 6.439474592030211e-05, | |
| "loss": 2.9, | |
| "step": 8020 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 6.424197624364141e-05, | |
| "loss": 2.9, | |
| "step": 8040 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 6.408906173485299e-05, | |
| "loss": 2.9, | |
| "step": 8060 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 6.393600394898318e-05, | |
| "loss": 2.8875, | |
| "step": 8080 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 6.378280444253545e-05, | |
| "loss": 2.925, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 3.2895259857177734, | |
| "eval_runtime": 43.7569, | |
| "eval_samples_per_second": 203.031, | |
| "eval_steps_per_second": 25.39, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 6.362946477345442e-05, | |
| "loss": 2.9, | |
| "step": 8120 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 6.347598650111009e-05, | |
| "loss": 2.925, | |
| "step": 8140 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 6.332237118628198e-05, | |
| "loss": 2.9, | |
| "step": 8160 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 6.316862039114322e-05, | |
| "loss": 2.875, | |
| "step": 8180 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 6.301473567924474e-05, | |
| "loss": 2.9125, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 3.288275957107544, | |
| "eval_runtime": 44.1754, | |
| "eval_samples_per_second": 201.108, | |
| "eval_steps_per_second": 25.15, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 6.286071861549928e-05, | |
| "loss": 2.9, | |
| "step": 8220 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 6.270657076616552e-05, | |
| "loss": 2.875, | |
| "step": 8240 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 6.25522936988322e-05, | |
| "loss": 2.9375, | |
| "step": 8260 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 6.239788898240203e-05, | |
| "loss": 2.875, | |
| "step": 8280 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 6.224335818707591e-05, | |
| "loss": 2.8875, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 3.2923879623413086, | |
| "eval_runtime": 45.191, | |
| "eval_samples_per_second": 196.588, | |
| "eval_steps_per_second": 24.585, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 6.20887028843369e-05, | |
| "loss": 2.9, | |
| "step": 8320 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 6.193392464693412e-05, | |
| "loss": 2.8875, | |
| "step": 8340 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 6.177902504886699e-05, | |
| "loss": 2.9, | |
| "step": 8360 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 6.162400566536898e-05, | |
| "loss": 2.875, | |
| "step": 8380 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 6.146886807289178e-05, | |
| "loss": 2.9, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 3.291586399078369, | |
| "eval_runtime": 43.2478, | |
| "eval_samples_per_second": 205.421, | |
| "eval_steps_per_second": 25.689, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 6.131361384908918e-05, | |
| "loss": 2.8875, | |
| "step": 8420 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 6.115824457280099e-05, | |
| "loss": 2.8875, | |
| "step": 8440 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 6.100276182403711e-05, | |
| "loss": 2.875, | |
| "step": 8460 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 6.0847167183961304e-05, | |
| "loss": 2.9, | |
| "step": 8480 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 6.069146223487527e-05, | |
| "loss": 2.875, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 3.290816307067871, | |
| "eval_runtime": 44.0351, | |
| "eval_samples_per_second": 201.748, | |
| "eval_steps_per_second": 25.23, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 6.053564856020245e-05, | |
| "loss": 2.8875, | |
| "step": 8520 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 6.0379727744471936e-05, | |
| "loss": 2.9, | |
| "step": 8540 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 6.022370137330243e-05, | |
| "loss": 2.9, | |
| "step": 8560 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 6.006757103338603e-05, | |
| "loss": 2.9, | |
| "step": 8580 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 5.991133831247214e-05, | |
| "loss": 2.9, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 3.287986993789673, | |
| "eval_runtime": 43.8869, | |
| "eval_samples_per_second": 202.429, | |
| "eval_steps_per_second": 25.315, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 5.975500479935133e-05, | |
| "loss": 2.9, | |
| "step": 8620 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 5.9598572083839144e-05, | |
| "loss": 2.8875, | |
| "step": 8640 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 5.944204175675996e-05, | |
| "loss": 2.9, | |
| "step": 8660 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 5.928541540993081e-05, | |
| "loss": 2.875, | |
| "step": 8680 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 5.91286946361452e-05, | |
| "loss": 2.925, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 3.285693883895874, | |
| "eval_runtime": 43.7853, | |
| "eval_samples_per_second": 202.899, | |
| "eval_steps_per_second": 25.374, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 5.8971881029156865e-05, | |
| "loss": 2.9, | |
| "step": 8720 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 5.881497618366363e-05, | |
| "loss": 2.9, | |
| "step": 8740 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 5.865798169529114e-05, | |
| "loss": 2.9, | |
| "step": 8760 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 5.850089916057667e-05, | |
| "loss": 2.9125, | |
| "step": 8780 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 5.834373017695285e-05, | |
| "loss": 2.9, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 3.2880167961120605, | |
| "eval_runtime": 43.9131, | |
| "eval_samples_per_second": 202.309, | |
| "eval_steps_per_second": 25.3, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 6.440777952949619e-05, | |
| "loss": 2.85, | |
| "step": 8820 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 6.426891340025895e-05, | |
| "loss": 2.85, | |
| "step": 8840 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 5.7871720520041196e-05, | |
| "loss": 3.25, | |
| "step": 8860 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 5.771422173244519e-05, | |
| "loss": 2.8875, | |
| "step": 8880 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 5.755664449596483e-05, | |
| "loss": 2.875, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 3.289705753326416, | |
| "eval_runtime": 45.5843, | |
| "eval_samples_per_second": 194.892, | |
| "eval_steps_per_second": 24.372, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 5.739899041306357e-05, | |
| "loss": 2.8875, | |
| "step": 8920 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 5.724126108698633e-05, | |
| "loss": 2.9, | |
| "step": 8940 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 5.708345812174323e-05, | |
| "loss": 2.875, | |
| "step": 8960 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 5.692558312209324e-05, | |
| "loss": 2.8875, | |
| "step": 8980 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 5.67676376935279e-05, | |
| "loss": 2.8875, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 3.289069652557373, | |
| "eval_runtime": 43.7649, | |
| "eval_samples_per_second": 202.994, | |
| "eval_steps_per_second": 25.386, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 5.660962344225493e-05, | |
| "loss": 2.9125, | |
| "step": 9020 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 5.645154197518196e-05, | |
| "loss": 2.9, | |
| "step": 9040 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 5.629339489990018e-05, | |
| "loss": 2.9125, | |
| "step": 9060 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 5.613518382466793e-05, | |
| "loss": 2.9, | |
| "step": 9080 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 5.597691035839441e-05, | |
| "loss": 2.875, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 3.2875235080718994, | |
| "eval_runtime": 43.2798, | |
| "eval_samples_per_second": 205.269, | |
| "eval_steps_per_second": 25.67, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 5.581857611062331e-05, | |
| "loss": 2.875, | |
| "step": 9120 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 5.566018269151644e-05, | |
| "loss": 2.9, | |
| "step": 9140 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 5.55017317118373e-05, | |
| "loss": 2.9125, | |
| "step": 9160 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 5.53432247829348e-05, | |
| "loss": 2.85, | |
| "step": 9180 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 5.518466351672678e-05, | |
| "loss": 2.8625, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 3.2881598472595215, | |
| "eval_runtime": 44.3122, | |
| "eval_samples_per_second": 200.487, | |
| "eval_steps_per_second": 25.072, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 5.502604952568366e-05, | |
| "loss": 2.8875, | |
| "step": 9220 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 5.486738442281207e-05, | |
| "loss": 2.875, | |
| "step": 9240 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 5.470866982163839e-05, | |
| "loss": 2.875, | |
| "step": 9260 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 5.454990733619236e-05, | |
| "loss": 2.875, | |
| "step": 9280 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 5.439109858099071e-05, | |
| "loss": 2.875, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 3.2853100299835205, | |
| "eval_runtime": 43.9763, | |
| "eval_samples_per_second": 202.018, | |
| "eval_steps_per_second": 25.264, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 5.423224517102067e-05, | |
| "loss": 2.875, | |
| "step": 9320 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 5.407334872172356e-05, | |
| "loss": 2.85, | |
| "step": 9340 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5.391441084897846e-05, | |
| "loss": 2.8625, | |
| "step": 9360 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5.375543316908566e-05, | |
| "loss": 2.875, | |
| "step": 9380 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5.3596417298750215e-05, | |
| "loss": 2.8875, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 3.2836618423461914, | |
| "eval_runtime": 44.1159, | |
| "eval_samples_per_second": 201.379, | |
| "eval_steps_per_second": 25.184, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5.343736485506563e-05, | |
| "loss": 2.875, | |
| "step": 9420 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5.3278277455497326e-05, | |
| "loss": 2.875, | |
| "step": 9440 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5.3119156717866146e-05, | |
| "loss": 2.9, | |
| "step": 9460 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5.296000426033202e-05, | |
| "loss": 2.875, | |
| "step": 9480 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5.280082170137745e-05, | |
| "loss": 2.875, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 3.2830088138580322, | |
| "eval_runtime": 43.7878, | |
| "eval_samples_per_second": 202.888, | |
| "eval_steps_per_second": 25.372, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5.264161065979098e-05, | |
| "loss": 2.8875, | |
| "step": 9520 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5.24823727546509e-05, | |
| "loss": 2.875, | |
| "step": 9540 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 5.232310960530864e-05, | |
| "loss": 2.875, | |
| "step": 9560 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 5.216382283137232e-05, | |
| "loss": 2.9, | |
| "step": 9580 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 5.2004514052690353e-05, | |
| "loss": 2.875, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 3.2835006713867188, | |
| "eval_runtime": 43.6695, | |
| "eval_samples_per_second": 203.437, | |
| "eval_steps_per_second": 25.441, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 5.184518488933493e-05, | |
| "loss": 2.875, | |
| "step": 9620 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 5.168583696158549e-05, | |
| "loss": 2.9, | |
| "step": 9640 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 5.152647188991234e-05, | |
| "loss": 2.9, | |
| "step": 9660 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 5.1367091294960135e-05, | |
| "loss": 2.875, | |
| "step": 9680 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 5.1207696797531336e-05, | |
| "loss": 2.875, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 3.2844936847686768, | |
| "eval_runtime": 43.5715, | |
| "eval_samples_per_second": 203.895, | |
| "eval_steps_per_second": 25.498, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 5.104829001856985e-05, | |
| "loss": 2.9, | |
| "step": 9720 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 5.088887257914446e-05, | |
| "loss": 2.9, | |
| "step": 9740 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.072944610043232e-05, | |
| "loss": 2.8875, | |
| "step": 9760 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.057001220370255e-05, | |
| "loss": 2.875, | |
| "step": 9780 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.041057251029973e-05, | |
| "loss": 2.875, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 3.28381609916687, | |
| "eval_runtime": 44.0298, | |
| "eval_samples_per_second": 201.773, | |
| "eval_steps_per_second": 25.233, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.0251128641627275e-05, | |
| "loss": 2.875, | |
| "step": 9820 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.009168221913122e-05, | |
| "loss": 2.8875, | |
| "step": 9840 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.993223486428345e-05, | |
| "loss": 2.9, | |
| "step": 9860 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.977278819856539e-05, | |
| "loss": 2.925, | |
| "step": 9880 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.961334384345141e-05, | |
| "loss": 2.8625, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 3.2820160388946533, | |
| "eval_runtime": 44.6702, | |
| "eval_samples_per_second": 198.88, | |
| "eval_steps_per_second": 24.871, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 5.662300475024714e-05, | |
| "loss": 2.8625, | |
| "step": 9920 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 5.6479300193990494e-05, | |
| "loss": 2.85, | |
| "step": 9940 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.913504085602665e-05, | |
| "loss": 3.275, | |
| "step": 9960 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.897562195735575e-05, | |
| "loss": 2.9, | |
| "step": 9980 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.881621347597873e-05, | |
| "loss": 2.875, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 3.2850983142852783, | |
| "eval_runtime": 45.0808, | |
| "eval_samples_per_second": 197.068, | |
| "eval_steps_per_second": 24.645, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.8656817032981624e-05, | |
| "loss": 2.875, | |
| "step": 10020 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.849743424932812e-05, | |
| "loss": 2.9, | |
| "step": 10040 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.833806674584297e-05, | |
| "loss": 2.875, | |
| "step": 10060 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.8178716143195545e-05, | |
| "loss": 2.875, | |
| "step": 10080 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.8019384061883345e-05, | |
| "loss": 2.8875, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 3.282227039337158, | |
| "eval_runtime": 45.341, | |
| "eval_samples_per_second": 195.937, | |
| "eval_steps_per_second": 24.503, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 5.51836537279109e-05, | |
| "loss": 2.825, | |
| "step": 10120 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 5.503945902974707e-05, | |
| "loss": 2.8625, | |
| "step": 10140 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 5.48952219765244e-05, | |
| "loss": 2.85, | |
| "step": 10160 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 5.475094378050969e-05, | |
| "loss": 2.8625, | |
| "step": 10180 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 5.4606625654315545e-05, | |
| "loss": 2.85, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 3.2852959632873535, | |
| "eval_runtime": 44.4843, | |
| "eval_samples_per_second": 199.711, | |
| "eval_steps_per_second": 24.975, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 5.446226881089015e-05, | |
| "loss": 2.85, | |
| "step": 10220 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 5.4317874463507114e-05, | |
| "loss": 2.875, | |
| "step": 10240 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 5.417344382575523e-05, | |
| "loss": 2.875, | |
| "step": 10260 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 5.402897811152833e-05, | |
| "loss": 2.875, | |
| "step": 10280 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5.3884478535015034e-05, | |
| "loss": 2.85, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 3.285360336303711, | |
| "eval_runtime": 44.1112, | |
| "eval_samples_per_second": 201.4, | |
| "eval_steps_per_second": 25.186, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5.373994631068856e-05, | |
| "loss": 2.8375, | |
| "step": 10320 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5.359538265329653e-05, | |
| "loss": 2.875, | |
| "step": 10340 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5.3450788777850766e-05, | |
| "loss": 2.85, | |
| "step": 10360 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5.3306165899617036e-05, | |
| "loss": 2.85, | |
| "step": 10380 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5.316151523410487e-05, | |
| "loss": 2.85, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 3.2869389057159424, | |
| "eval_runtime": 43.3708, | |
| "eval_samples_per_second": 204.838, | |
| "eval_steps_per_second": 25.616, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5.301683799705735e-05, | |
| "loss": 2.8375, | |
| "step": 10420 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5.287213540444089e-05, | |
| "loss": 2.875, | |
| "step": 10440 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5.2727408672434996e-05, | |
| "loss": 2.85, | |
| "step": 10460 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5.258265901742209e-05, | |
| "loss": 2.875, | |
| "step": 10480 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5.243788765597718e-05, | |
| "loss": 2.85, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 3.2872684001922607, | |
| "eval_runtime": 44.339, | |
| "eval_samples_per_second": 200.365, | |
| "eval_steps_per_second": 25.057, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.468055598239177e-05, | |
| "loss": 2.8875, | |
| "step": 10520 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.4522040800119974e-05, | |
| "loss": 2.9, | |
| "step": 10540 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.436358132531976e-05, | |
| "loss": 2.875, | |
| "step": 10560 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.420517916942639e-05, | |
| "loss": 2.875, | |
| "step": 10580 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.404683594329222e-05, | |
| "loss": 2.875, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 3.283797264099121, | |
| "eval_runtime": 44.0955, | |
| "eval_samples_per_second": 201.472, | |
| "eval_steps_per_second": 25.195, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.3888553257170373e-05, | |
| "loss": 2.8875, | |
| "step": 10620 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.373033272069827e-05, | |
| "loss": 2.875, | |
| "step": 10640 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.3572175942881347e-05, | |
| "loss": 2.8625, | |
| "step": 10660 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.3414084532076625e-05, | |
| "loss": 2.8875, | |
| "step": 10680 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.325606009597643e-05, | |
| "loss": 2.875, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 3.2804203033447266, | |
| "eval_runtime": 43.9858, | |
| "eval_samples_per_second": 201.974, | |
| "eval_steps_per_second": 25.258, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.30981042415919e-05, | |
| "loss": 2.9, | |
| "step": 10720 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.294021857523684e-05, | |
| "loss": 2.9, | |
| "step": 10740 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.2782404702511234e-05, | |
| "loss": 2.9, | |
| "step": 10760 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.262466422828498e-05, | |
| "loss": 2.8625, | |
| "step": 10780 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.246699875668157e-05, | |
| "loss": 2.875, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 3.2785210609436035, | |
| "eval_runtime": 43.8832, | |
| "eval_samples_per_second": 202.446, | |
| "eval_steps_per_second": 25.317, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.230940989106176e-05, | |
| "loss": 2.85, | |
| "step": 10820 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.215189923400724e-05, | |
| "loss": 2.875, | |
| "step": 10840 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.199446838730441e-05, | |
| "loss": 2.9125, | |
| "step": 10860 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.1837118951928026e-05, | |
| "loss": 2.875, | |
| "step": 10880 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.167985252802492e-05, | |
| "loss": 2.9, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 3.278226613998413, | |
| "eval_runtime": 43.5345, | |
| "eval_samples_per_second": 204.068, | |
| "eval_steps_per_second": 25.52, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.1522670714897826e-05, | |
| "loss": 2.8875, | |
| "step": 10920 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.1365575110988964e-05, | |
| "loss": 2.8625, | |
| "step": 10940 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.9104955544589224e-05, | |
| "loss": 3.2, | |
| "step": 10960 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.8960028522665646e-05, | |
| "loss": 2.8625, | |
| "step": 10980 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.8815110241373314e-05, | |
| "loss": 2.8625, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 3.283653497695923, | |
| "eval_runtime": 48.3603, | |
| "eval_samples_per_second": 183.705, | |
| "eval_steps_per_second": 22.973, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.867020191870454e-05, | |
| "loss": 2.85, | |
| "step": 11020 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.8525304772567955e-05, | |
| "loss": 2.8625, | |
| "step": 11040 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.042490128137424e-05, | |
| "loss": 3.225, | |
| "step": 11060 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.0268453822687507e-05, | |
| "loss": 2.875, | |
| "step": 11080 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.011210532783241e-05, | |
| "loss": 2.8625, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 3.280545473098755, | |
| "eval_runtime": 50.2847, | |
| "eval_samples_per_second": 176.674, | |
| "eval_steps_per_second": 22.094, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 3.995585738677685e-05, | |
| "loss": 2.875, | |
| "step": 11120 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 3.9799711588466173e-05, | |
| "loss": 2.875, | |
| "step": 11140 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 3.9643669520806986e-05, | |
| "loss": 2.9, | |
| "step": 11160 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 3.948773277065103e-05, | |
| "loss": 2.8625, | |
| "step": 11180 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 3.933190292377901e-05, | |
| "loss": 2.8875, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 3.278350353240967, | |
| "eval_runtime": 49.3834, | |
| "eval_samples_per_second": 179.898, | |
| "eval_steps_per_second": 22.497, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 3.917618156488451e-05, | |
| "loss": 2.8625, | |
| "step": 11220 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 3.902057027755786e-05, | |
| "loss": 2.9, | |
| "step": 11240 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 3.886507064426998e-05, | |
| "loss": 2.875, | |
| "step": 11260 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 3.8709684246356466e-05, | |
| "loss": 2.8625, | |
| "step": 11280 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 3.855441266400119e-05, | |
| "loss": 2.85, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 3.27763032913208, | |
| "eval_runtime": 48.0477, | |
| "eval_samples_per_second": 184.899, | |
| "eval_steps_per_second": 23.123, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 3.83992574762206e-05, | |
| "loss": 2.875, | |
| "step": 11320 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 3.8244220260847364e-05, | |
| "loss": 2.9, | |
| "step": 11340 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 3.808930259451451e-05, | |
| "loss": 2.8875, | |
| "step": 11360 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 3.793450605263927e-05, | |
| "loss": 2.8875, | |
| "step": 11380 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 3.7779832209407213e-05, | |
| "loss": 2.875, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 3.2772319316864014, | |
| "eval_runtime": 48.8755, | |
| "eval_samples_per_second": 181.768, | |
| "eval_steps_per_second": 22.731, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 3.7625282637755986e-05, | |
| "loss": 2.875, | |
| "step": 11420 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 3.7470858909359616e-05, | |
| "loss": 2.9, | |
| "step": 11440 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 3.7316562594612295e-05, | |
| "loss": 2.8875, | |
| "step": 11460 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 3.716239526261254e-05, | |
| "loss": 2.875, | |
| "step": 11480 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 3.700835848114715e-05, | |
| "loss": 2.9, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 3.276888132095337, | |
| "eval_runtime": 49.0771, | |
| "eval_samples_per_second": 181.021, | |
| "eval_steps_per_second": 22.638, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 3.6854453816675384e-05, | |
| "loss": 2.85, | |
| "step": 11520 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 3.670068283431283e-05, | |
| "loss": 2.9, | |
| "step": 11540 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 3.6547047097815734e-05, | |
| "loss": 2.9, | |
| "step": 11560 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 3.6393548169564904e-05, | |
| "loss": 2.9, | |
| "step": 11580 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 3.624018761054992e-05, | |
| "loss": 2.8625, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 3.2761170864105225, | |
| "eval_runtime": 50.4269, | |
| "eval_samples_per_second": 176.176, | |
| "eval_steps_per_second": 22.032, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 3.60869669803532e-05, | |
| "loss": 2.8875, | |
| "step": 11620 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 3.593388783713424e-05, | |
| "loss": 2.875, | |
| "step": 11640 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 3.57809517376136e-05, | |
| "loss": 2.9, | |
| "step": 11660 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 3.5628160237057264e-05, | |
| "loss": 2.875, | |
| "step": 11680 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 3.547551488926069e-05, | |
| "loss": 2.8625, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 3.2762629985809326, | |
| "eval_runtime": 49.2716, | |
| "eval_samples_per_second": 180.307, | |
| "eval_steps_per_second": 22.548, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 3.5323017246533066e-05, | |
| "loss": 2.875, | |
| "step": 11720 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.517066885968149e-05, | |
| "loss": 2.875, | |
| "step": 11740 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.501847127799528e-05, | |
| "loss": 2.85, | |
| "step": 11760 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.486642604923005e-05, | |
| "loss": 2.9, | |
| "step": 11780 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.4714534719592186e-05, | |
| "loss": 2.9, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 3.277094602584839, | |
| "eval_runtime": 48.4048, | |
| "eval_samples_per_second": 183.535, | |
| "eval_steps_per_second": 22.952, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.456279883372295e-05, | |
| "loss": 2.8875, | |
| "step": 11820 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.441121993468288e-05, | |
| "loss": 2.875, | |
| "step": 11840 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.4259799563936e-05, | |
| "loss": 2.875, | |
| "step": 11860 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.410853926133428e-05, | |
| "loss": 2.8875, | |
| "step": 11880 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.3957440565101796e-05, | |
| "loss": 2.8875, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 3.276407480239868, | |
| "eval_runtime": 49.3088, | |
| "eval_samples_per_second": 180.171, | |
| "eval_steps_per_second": 22.531, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.3806505011819256e-05, | |
| "loss": 2.8625, | |
| "step": 11920 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.365573413640829e-05, | |
| "loss": 2.875, | |
| "step": 11940 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.3505129472115854e-05, | |
| "loss": 2.875, | |
| "step": 11960 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.335469255049864e-05, | |
| "loss": 2.8625, | |
| "step": 11980 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.3204424901407484e-05, | |
| "loss": 2.9, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 3.27502179145813, | |
| "eval_runtime": 48.5106, | |
| "eval_samples_per_second": 183.135, | |
| "eval_steps_per_second": 22.902, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.3054328052971824e-05, | |
| "loss": 2.875, | |
| "step": 12020 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.290440353158421e-05, | |
| "loss": 2.875, | |
| "step": 12040 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.275465286188467e-05, | |
| "loss": 2.875, | |
| "step": 12060 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.2605077566745314e-05, | |
| "loss": 2.875, | |
| "step": 12080 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.2455679167254784e-05, | |
| "loss": 2.9, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 3.2745859622955322, | |
| "eval_runtime": 48.3768, | |
| "eval_samples_per_second": 183.642, | |
| "eval_steps_per_second": 22.966, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.2306459182702765e-05, | |
| "loss": 2.875, | |
| "step": 12120 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.2157419130564616e-05, | |
| "loss": 2.875, | |
| "step": 12140 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.2008560526485906e-05, | |
| "loss": 2.9, | |
| "step": 12160 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.185988488426695e-05, | |
| "loss": 2.9, | |
| "step": 12180 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.1711393715847476e-05, | |
| "loss": 2.8625, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 3.2757885456085205, | |
| "eval_runtime": 48.9204, | |
| "eval_samples_per_second": 181.601, | |
| "eval_steps_per_second": 22.71, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.156308853129123e-05, | |
| "loss": 2.875, | |
| "step": 12220 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.141497083877058e-05, | |
| "loss": 2.9, | |
| "step": 12240 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.126704214455126e-05, | |
| "loss": 2.8625, | |
| "step": 12260 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.111930395297701e-05, | |
| "loss": 2.875, | |
| "step": 12280 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.0971757766454225e-05, | |
| "loss": 2.875, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 3.2748875617980957, | |
| "eval_runtime": 48.5507, | |
| "eval_samples_per_second": 182.984, | |
| "eval_steps_per_second": 22.883, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.082440508543677e-05, | |
| "loss": 2.875, | |
| "step": 12320 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.0677247408410685e-05, | |
| "loss": 2.875, | |
| "step": 12340 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.053028623187889e-05, | |
| "loss": 2.8875, | |
| "step": 12360 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.0383523050346054e-05, | |
| "loss": 2.875, | |
| "step": 12380 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.0236959356303372e-05, | |
| "loss": 2.8625, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 3.2739577293395996, | |
| "eval_runtime": 47.8513, | |
| "eval_samples_per_second": 185.659, | |
| "eval_steps_per_second": 23.218, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.0090596640213338e-05, | |
| "loss": 2.875, | |
| "step": 12420 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 2.9944436390494646e-05, | |
| "loss": 2.9, | |
| "step": 12440 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 3.834165101057631e-05, | |
| "loss": 3.225, | |
| "step": 12460 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 3.820074140227797e-05, | |
| "loss": 2.85, | |
| "step": 12480 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 3.805993096301526e-05, | |
| "loss": 2.85, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 3.273886203765869, | |
| "eval_runtime": 49.5352, | |
| "eval_samples_per_second": 179.347, | |
| "eval_steps_per_second": 22.428, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 3.791922087625538e-05, | |
| "loss": 2.875, | |
| "step": 12520 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 3.777861232462211e-05, | |
| "loss": 2.85, | |
| "step": 12540 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2.9071809776095615e-05, | |
| "loss": 3.25, | |
| "step": 12560 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2.8927108291845207e-05, | |
| "loss": 2.9, | |
| "step": 12580 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2.8782621105926104e-05, | |
| "loss": 2.875, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 3.2757480144500732, | |
| "eval_runtime": 48.8512, | |
| "eval_samples_per_second": 181.859, | |
| "eval_steps_per_second": 22.743, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2.863834968768405e-05, | |
| "loss": 2.85, | |
| "step": 12620 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2.8494295504270496e-05, | |
| "loss": 2.875, | |
| "step": 12640 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2.8350460020627766e-05, | |
| "loss": 2.875, | |
| "step": 12660 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2.8206844699474217e-05, | |
| "loss": 2.875, | |
| "step": 12680 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2.8063451001289126e-05, | |
| "loss": 2.875, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 3.2743403911590576, | |
| "eval_runtime": 48.9886, | |
| "eval_samples_per_second": 181.348, | |
| "eval_steps_per_second": 22.679, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 2.7920280384298146e-05, | |
| "loss": 2.85, | |
| "step": 12720 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 2.7777334304458297e-05, | |
| "loss": 2.85, | |
| "step": 12740 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 2.7634614215443145e-05, | |
| "loss": 2.8625, | |
| "step": 12760 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 2.7492121568628116e-05, | |
| "loss": 2.9, | |
| "step": 12780 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 2.734985781307573e-05, | |
| "loss": 2.8625, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 3.2736618518829346, | |
| "eval_runtime": 49.2228, | |
| "eval_samples_per_second": 180.485, | |
| "eval_steps_per_second": 22.571, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 2.7207824395520676e-05, | |
| "loss": 2.875, | |
| "step": 12820 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 2.7066022760355397e-05, | |
| "loss": 2.875, | |
| "step": 12840 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 2.6924454349615204e-05, | |
| "loss": 2.8875, | |
| "step": 12860 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 2.6783120602963618e-05, | |
| "loss": 2.875, | |
| "step": 12880 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 2.6642022957677826e-05, | |
| "loss": 2.875, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 3.2744781970977783, | |
| "eval_runtime": 47.1379, | |
| "eval_samples_per_second": 188.468, | |
| "eval_steps_per_second": 23.569, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 2.650116284863402e-05, | |
| "loss": 2.9, | |
| "step": 12920 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 2.6360541708292686e-05, | |
| "loss": 2.8625, | |
| "step": 12940 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 2.622016096668427e-05, | |
| "loss": 2.875, | |
| "step": 12960 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 2.608002205139448e-05, | |
| "loss": 2.875, | |
| "step": 12980 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 2.594012638754974e-05, | |
| "loss": 2.875, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 3.2738068103790283, | |
| "eval_runtime": 49.1337, | |
| "eval_samples_per_second": 180.813, | |
| "eval_steps_per_second": 22.612, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 2.580047539780282e-05, | |
| "loss": 2.875, | |
| "step": 13020 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 2.5661070502318322e-05, | |
| "loss": 2.875, | |
| "step": 13040 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 2.552191311875811e-05, | |
| "loss": 2.8625, | |
| "step": 13060 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 2.5383004662267108e-05, | |
| "loss": 2.85, | |
| "step": 13080 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 2.5244346545458803e-05, | |
| "loss": 2.875, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 3.272632598876953, | |
| "eval_runtime": 48.0481, | |
| "eval_samples_per_second": 184.898, | |
| "eval_steps_per_second": 23.123, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.510594017840081e-05, | |
| "loss": 2.875, | |
| "step": 13120 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.4967786968600664e-05, | |
| "loss": 2.85, | |
| "step": 13140 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.4829888320991475e-05, | |
| "loss": 2.9, | |
| "step": 13160 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.4692245637917477e-05, | |
| "loss": 2.875, | |
| "step": 13180 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.4554860319120044e-05, | |
| "loss": 2.85, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 3.272722005844116, | |
| "eval_runtime": 49.0622, | |
| "eval_samples_per_second": 181.076, | |
| "eval_steps_per_second": 22.645, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.4417733761723277e-05, | |
| "loss": 2.875, | |
| "step": 13220 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.4280867360219778e-05, | |
| "loss": 2.875, | |
| "step": 13240 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.4144262506456582e-05, | |
| "loss": 2.875, | |
| "step": 13260 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.400792058962097e-05, | |
| "loss": 2.875, | |
| "step": 13280 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.387184299622619e-05, | |
| "loss": 2.9, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 3.2735912799835205, | |
| "eval_runtime": 49.1039, | |
| "eval_samples_per_second": 180.922, | |
| "eval_steps_per_second": 22.625, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.3736031110097606e-05, | |
| "loss": 2.85, | |
| "step": 13320 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.3600486312358487e-05, | |
| "loss": 2.8625, | |
| "step": 13340 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.346520998141591e-05, | |
| "loss": 2.875, | |
| "step": 13360 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.3330203492946867e-05, | |
| "loss": 2.9, | |
| "step": 13380 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.319546821988425e-05, | |
| "loss": 2.875, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 3.2729640007019043, | |
| "eval_runtime": 44.9265, | |
| "eval_samples_per_second": 197.745, | |
| "eval_steps_per_second": 24.729, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.306100553240274e-05, | |
| "loss": 2.9, | |
| "step": 13420 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.2926816797905093e-05, | |
| "loss": 2.85, | |
| "step": 13440 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.279290338100812e-05, | |
| "loss": 2.875, | |
| "step": 13460 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.2659266643528764e-05, | |
| "loss": 2.875, | |
| "step": 13480 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.2525907944470393e-05, | |
| "loss": 2.875, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 3.2734763622283936, | |
| "eval_runtime": 44.9914, | |
| "eval_samples_per_second": 197.46, | |
| "eval_steps_per_second": 24.694, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.239282864000882e-05, | |
| "loss": 2.875, | |
| "step": 13520 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.2260030083478613e-05, | |
| "loss": 2.875, | |
| "step": 13540 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.212751362535932e-05, | |
| "loss": 2.875, | |
| "step": 13560 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.1995280613261725e-05, | |
| "loss": 2.8875, | |
| "step": 13580 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.1863332391914103e-05, | |
| "loss": 2.85, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 3.2720718383789062, | |
| "eval_runtime": 44.7577, | |
| "eval_samples_per_second": 198.491, | |
| "eval_steps_per_second": 24.823, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.173167030314864e-05, | |
| "loss": 2.875, | |
| "step": 13620 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.1600295685887674e-05, | |
| "loss": 2.875, | |
| "step": 13640 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.1469209876130137e-05, | |
| "loss": 2.8625, | |
| "step": 13660 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.1338414206938017e-05, | |
| "loss": 2.8625, | |
| "step": 13680 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.1207910008422738e-05, | |
| "loss": 2.8875, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 3.2721304893493652, | |
| "eval_runtime": 44.2064, | |
| "eval_samples_per_second": 200.966, | |
| "eval_steps_per_second": 25.132, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.107769860773159e-05, | |
| "loss": 2.875, | |
| "step": 13720 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.0947781329034367e-05, | |
| "loss": 2.875, | |
| "step": 13740 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.0818159493509765e-05, | |
| "loss": 2.9, | |
| "step": 13760 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.068883441933201e-05, | |
| "loss": 2.9, | |
| "step": 13780 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.0559807421657485e-05, | |
| "loss": 2.875, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 3.2723329067230225, | |
| "eval_runtime": 44.1642, | |
| "eval_samples_per_second": 201.158, | |
| "eval_steps_per_second": 25.156, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.0431079812611315e-05, | |
| "loss": 2.875, | |
| "step": 13820 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.0302652901273966e-05, | |
| "loss": 2.875, | |
| "step": 13840 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.0174527993668084e-05, | |
| "loss": 2.875, | |
| "step": 13860 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.0046706392745056e-05, | |
| "loss": 2.875, | |
| "step": 13880 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.9919189398371823e-05, | |
| "loss": 2.85, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 3.271775960922241, | |
| "eval_runtime": 44.0619, | |
| "eval_samples_per_second": 201.625, | |
| "eval_steps_per_second": 25.215, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.979197830731771e-05, | |
| "loss": 2.875, | |
| "step": 13920 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.9665074413241186e-05, | |
| "loss": 2.875, | |
| "step": 13940 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.9538479006676675e-05, | |
| "loss": 2.875, | |
| "step": 13960 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.941219337502153e-05, | |
| "loss": 2.875, | |
| "step": 13980 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.9286218802522844e-05, | |
| "loss": 2.85, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 3.2724153995513916, | |
| "eval_runtime": 44.1627, | |
| "eval_samples_per_second": 201.165, | |
| "eval_steps_per_second": 25.157, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.916055657026441e-05, | |
| "loss": 2.875, | |
| "step": 14020 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.9035207956153772e-05, | |
| "loss": 2.8875, | |
| "step": 14040 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.891017423490915e-05, | |
| "loss": 2.85, | |
| "step": 14060 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.8785456678046464e-05, | |
| "loss": 2.8625, | |
| "step": 14080 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.8661056553866495e-05, | |
| "loss": 2.8875, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 3.27160906791687, | |
| "eval_runtime": 43.8905, | |
| "eval_samples_per_second": 202.413, | |
| "eval_steps_per_second": 25.313, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 2.7090528455101472e-05, | |
| "loss": 2.875, | |
| "step": 14120 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 2.6961781694639832e-05, | |
| "loss": 2.8875, | |
| "step": 14140 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.8289773411931636e-05, | |
| "loss": 3.225, | |
| "step": 14160 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.8166655636735263e-05, | |
| "loss": 2.8625, | |
| "step": 14180 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.80438615870471e-05, | |
| "loss": 2.875, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 3.271629810333252, | |
| "eval_runtime": 45.3513, | |
| "eval_samples_per_second": 195.893, | |
| "eval_steps_per_second": 24.498, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.7921392511606998e-05, | |
| "loss": 2.875, | |
| "step": 14220 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.7799249655850064e-05, | |
| "loss": 2.875, | |
| "step": 14240 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.7677434261893894e-05, | |
| "loss": 2.8875, | |
| "step": 14260 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.7555947568526032e-05, | |
| "loss": 2.875, | |
| "step": 14280 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.7434790811191365e-05, | |
| "loss": 2.875, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 3.271775245666504, | |
| "eval_runtime": 44.548, | |
| "eval_samples_per_second": 199.425, | |
| "eval_steps_per_second": 24.939, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.7313965221979473e-05, | |
| "loss": 2.875, | |
| "step": 14320 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.7193472029612184e-05, | |
| "loss": 2.875, | |
| "step": 14340 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.707331245943109e-05, | |
| "loss": 2.875, | |
| "step": 14360 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.6953487733384986e-05, | |
| "loss": 2.875, | |
| "step": 14380 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.683399907001757e-05, | |
| "loss": 2.85, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 3.2709953784942627, | |
| "eval_runtime": 44.5496, | |
| "eval_samples_per_second": 199.418, | |
| "eval_steps_per_second": 24.938, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.671484768445497e-05, | |
| "loss": 2.875, | |
| "step": 14420 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.6596034788393383e-05, | |
| "loss": 2.9, | |
| "step": 14440 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.6477561590086786e-05, | |
| "loss": 2.875, | |
| "step": 14460 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.6359429294334673e-05, | |
| "loss": 2.875, | |
| "step": 14480 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.6241639102469706e-05, | |
| "loss": 2.8625, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 3.2717020511627197, | |
| "eval_runtime": 43.9339, | |
| "eval_samples_per_second": 202.213, | |
| "eval_steps_per_second": 25.288, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.6124192212345622e-05, | |
| "loss": 2.875, | |
| "step": 14520 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.6007089818324983e-05, | |
| "loss": 2.875, | |
| "step": 14540 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.5890333111266993e-05, | |
| "loss": 2.9, | |
| "step": 14560 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.5773923278515456e-05, | |
| "loss": 2.8875, | |
| "step": 14580 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.5657861503886705e-05, | |
| "loss": 2.9, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 3.2711338996887207, | |
| "eval_runtime": 44.1879, | |
| "eval_samples_per_second": 201.051, | |
| "eval_steps_per_second": 25.143, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.5542148967657492e-05, | |
| "loss": 2.875, | |
| "step": 14620 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.542678684655306e-05, | |
| "loss": 2.875, | |
| "step": 14640 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.5311776313735155e-05, | |
| "loss": 2.875, | |
| "step": 14660 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.5197118538790051e-05, | |
| "loss": 2.85, | |
| "step": 14680 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.5082814687716696e-05, | |
| "loss": 2.875, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 3.2713921070098877, | |
| "eval_runtime": 44.4981, | |
| "eval_samples_per_second": 199.649, | |
| "eval_steps_per_second": 24.967, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.4968865922914893e-05, | |
| "loss": 2.875, | |
| "step": 14720 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.4855273403173376e-05, | |
| "loss": 2.875, | |
| "step": 14740 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.3071970436238573e-05, | |
| "loss": 3.25, | |
| "step": 14760 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.29499472640538e-05, | |
| "loss": 2.875, | |
| "step": 14780 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.28281514390046e-05, | |
| "loss": 2.85, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 3.2713191509246826, | |
| "eval_runtime": 50.4122, | |
| "eval_samples_per_second": 176.227, | |
| "eval_steps_per_second": 22.038, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.2706583984746316e-05, | |
| "loss": 2.8375, | |
| "step": 14820 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.2585245923014925e-05, | |
| "loss": 2.9, | |
| "step": 14840 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.2464138273618494e-05, | |
| "loss": 2.875, | |
| "step": 14860 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.2343262054428477e-05, | |
| "loss": 2.85, | |
| "step": 14880 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.2222618281371232e-05, | |
| "loss": 2.875, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 3.272068977355957, | |
| "eval_runtime": 48.3121, | |
| "eval_samples_per_second": 183.888, | |
| "eval_steps_per_second": 22.996, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.2102207968419554e-05, | |
| "loss": 2.8625, | |
| "step": 14920 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.1982032127584e-05, | |
| "loss": 2.875, | |
| "step": 14940 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.186209176890448e-05, | |
| "loss": 2.85, | |
| "step": 14960 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.1742387900441795e-05, | |
| "loss": 2.875, | |
| "step": 14980 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.162292152826908e-05, | |
| "loss": 2.875, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 3.272015333175659, | |
| "eval_runtime": 45.0456, | |
| "eval_samples_per_second": 197.222, | |
| "eval_steps_per_second": 24.664, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.1503693656463392e-05, | |
| "loss": 2.85, | |
| "step": 15020 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.138470528709725e-05, | |
| "loss": 2.875, | |
| "step": 15040 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.1265957420230303e-05, | |
| "loss": 2.8875, | |
| "step": 15060 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.114745105390078e-05, | |
| "loss": 2.875, | |
| "step": 15080 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.1029187184117183e-05, | |
| "loss": 2.875, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 3.271845579147339, | |
| "eval_runtime": 49.422, | |
| "eval_samples_per_second": 179.758, | |
| "eval_steps_per_second": 22.48, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.2766216471293301e-05, | |
| "loss": 2.875, | |
| "step": 15120 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.2659986534347884e-05, | |
| "loss": 2.85, | |
| "step": 15140 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.2554136322344272e-05, | |
| "loss": 2.8625, | |
| "step": 15160 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.2448666911713925e-05, | |
| "loss": 2.875, | |
| "step": 15180 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.2343579375015818e-05, | |
| "loss": 2.875, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 3.271632671356201, | |
| "eval_runtime": 46.406, | |
| "eval_samples_per_second": 191.441, | |
| "eval_steps_per_second": 23.941, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.2238874780925457e-05, | |
| "loss": 2.8875, | |
| "step": 15220 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.2134554194224096e-05, | |
| "loss": 2.875, | |
| "step": 15240 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.203061867578788e-05, | |
| "loss": 2.8625, | |
| "step": 15260 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.1927069282577003e-05, | |
| "loss": 2.9, | |
| "step": 15280 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.1823907067625011e-05, | |
| "loss": 2.85, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": 3.2716362476348877, | |
| "eval_runtime": 47.8751, | |
| "eval_samples_per_second": 185.566, | |
| "eval_steps_per_second": 23.206, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.1721133080028134e-05, | |
| "loss": 2.8625, | |
| "step": 15320 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.16187483649345e-05, | |
| "loss": 2.875, | |
| "step": 15340 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.1516753963533628e-05, | |
| "loss": 2.875, | |
| "step": 15360 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.1415150913045774e-05, | |
| "loss": 2.9, | |
| "step": 15380 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.1313940246711392e-05, | |
| "loss": 2.9125, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": 3.2710213661193848, | |
| "eval_runtime": 50.1039, | |
| "eval_samples_per_second": 177.312, | |
| "eval_steps_per_second": 22.174, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.1213122993780605e-05, | |
| "loss": 2.8875, | |
| "step": 15420 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.1112700179502822e-05, | |
| "loss": 2.8875, | |
| "step": 15440 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.1012672825116189e-05, | |
| "loss": 2.9, | |
| "step": 15460 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.0913041947837316e-05, | |
| "loss": 2.875, | |
| "step": 15480 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.0813808560850886e-05, | |
| "loss": 2.9, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 3.2712323665618896, | |
| "eval_runtime": 47.8099, | |
| "eval_samples_per_second": 185.819, | |
| "eval_steps_per_second": 23.238, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.0714973673299311e-05, | |
| "loss": 2.9, | |
| "step": 15520 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.0616538290272526e-05, | |
| "loss": 2.875, | |
| "step": 15540 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.051850341279778e-05, | |
| "loss": 2.875, | |
| "step": 15560 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.0420870037829383e-05, | |
| "loss": 2.9, | |
| "step": 15580 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.032363915823864e-05, | |
| "loss": 2.875, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 3.2711994647979736, | |
| "eval_runtime": 49.7498, | |
| "eval_samples_per_second": 178.573, | |
| "eval_steps_per_second": 22.332, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.022681176280374e-05, | |
| "loss": 2.875, | |
| "step": 15620 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.0130388836199639e-05, | |
| "loss": 2.85, | |
| "step": 15640 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.0034371358988115e-05, | |
| "loss": 2.85, | |
| "step": 15660 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 9.938760307607803e-06, | |
| "loss": 2.875, | |
| "step": 15680 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 9.8435566543642e-06, | |
| "loss": 2.875, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 3.271230459213257, | |
| "eval_runtime": 48.6091, | |
| "eval_samples_per_second": 182.764, | |
| "eval_steps_per_second": 22.856, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 9.74876136741984e-06, | |
| "loss": 2.875, | |
| "step": 15720 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 9.6543754107844e-06, | |
| "loss": 2.875, | |
| "step": 15740 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 9.560399744304954e-06, | |
| "loss": 2.875, | |
| "step": 15760 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 9.466835323656137e-06, | |
| "loss": 2.85, | |
| "step": 15780 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 9.373683100330499e-06, | |
| "loss": 2.875, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 3.2713022232055664, | |
| "eval_runtime": 48.3659, | |
| "eval_samples_per_second": 183.683, | |
| "eval_steps_per_second": 22.971, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 9.280944021628773e-06, | |
| "loss": 2.875, | |
| "step": 15820 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 9.188619030650298e-06, | |
| "loss": 2.85, | |
| "step": 15840 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 9.096709066283354e-06, | |
| "loss": 2.875, | |
| "step": 15860 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 9.005215063195694e-06, | |
| "loss": 2.9, | |
| "step": 15880 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 8.91413795182497e-06, | |
| "loss": 2.875, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 3.2710063457489014, | |
| "eval_runtime": 47.7202, | |
| "eval_samples_per_second": 186.169, | |
| "eval_steps_per_second": 23.282, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 8.823478658369332e-06, | |
| "loss": 2.8875, | |
| "step": 15920 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 8.733238104777947e-06, | |
| "loss": 2.9, | |
| "step": 15940 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 8.643417208741694e-06, | |
| "loss": 2.875, | |
| "step": 15960 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 8.554016883683746e-06, | |
| "loss": 2.8875, | |
| "step": 15980 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 8.465038038750373e-06, | |
| "loss": 2.875, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 3.270718812942505, | |
| "eval_runtime": 48.8464, | |
| "eval_samples_per_second": 181.876, | |
| "eval_steps_per_second": 22.745, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 8.376481578801614e-06, | |
| "loss": 2.875, | |
| "step": 16020 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 8.288348404402158e-06, | |
| "loss": 2.8875, | |
| "step": 16040 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 8.200639411812083e-06, | |
| "loss": 2.875, | |
| "step": 16060 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 8.113355492977854e-06, | |
| "loss": 2.9, | |
| "step": 16080 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 8.026497535523147e-06, | |
| "loss": 2.8625, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 3.270862340927124, | |
| "eval_runtime": 47.9076, | |
| "eval_samples_per_second": 185.44, | |
| "eval_steps_per_second": 23.19, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 7.940066422739933e-06, | |
| "loss": 2.8625, | |
| "step": 16120 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 7.854063033579373e-06, | |
| "loss": 2.875, | |
| "step": 16140 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 7.76848824264299e-06, | |
| "loss": 2.875, | |
| "step": 16160 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 7.683342920173691e-06, | |
| "loss": 2.8625, | |
| "step": 16180 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 7.598627932046998e-06, | |
| "loss": 2.875, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 3.27109432220459, | |
| "eval_runtime": 47.7949, | |
| "eval_samples_per_second": 185.878, | |
| "eval_steps_per_second": 23.245, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 7.514344139762136e-06, | |
| "loss": 2.8875, | |
| "step": 16220 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 7.430492400433392e-06, | |
| "loss": 2.875, | |
| "step": 16240 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.4617765427997676e-05, | |
| "loss": 3.3, | |
| "step": 16260 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.451549418460877e-05, | |
| "loss": 2.875, | |
| "step": 16280 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.4413521177265155e-05, | |
| "loss": 2.875, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 3.2713921070098877, | |
| "eval_runtime": 50.2432, | |
| "eval_samples_per_second": 176.82, | |
| "eval_steps_per_second": 22.112, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 7.099422961003044e-06, | |
| "loss": 2.875, | |
| "step": 16320 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 7.017744189086284e-06, | |
| "loss": 2.875, | |
| "step": 16340 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 6.9365025202413225e-06, | |
| "loss": 2.875, | |
| "step": 16360 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 6.855698780645875e-06, | |
| "loss": 2.875, | |
| "step": 16380 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 6.775333792024241e-06, | |
| "loss": 2.8875, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_loss": 3.2707746028900146, | |
| "eval_runtime": 50.2605, | |
| "eval_samples_per_second": 176.759, | |
| "eval_steps_per_second": 22.105, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 6.7585885444098275e-06, | |
| "loss": 2.85, | |
| "step": 16420 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 6.678831820152903e-06, | |
| "loss": 2.825, | |
| "step": 16440 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 6.5995147970642765e-06, | |
| "loss": 2.8625, | |
| "step": 16460 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 6.52063828019584e-06, | |
| "loss": 2.8625, | |
| "step": 16480 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 6.442203070128405e-06, | |
| "loss": 2.875, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 3.270683765411377, | |
| "eval_runtime": 43.13, | |
| "eval_samples_per_second": 205.982, | |
| "eval_steps_per_second": 25.759, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 6.364209962963624e-06, | |
| "loss": 2.875, | |
| "step": 16520 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 6.286659750315893e-06, | |
| "loss": 2.85, | |
| "step": 16540 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.3193936741259499e-05, | |
| "loss": 3.225, | |
| "step": 16560 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.3096074012358694e-05, | |
| "loss": 2.85, | |
| "step": 16580 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.299852084908475e-05, | |
| "loss": 2.85, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 3.270526170730591, | |
| "eval_runtime": 50.184, | |
| "eval_samples_per_second": 177.028, | |
| "eval_steps_per_second": 22.139, | |
| "step": 16600 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 21694, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "total_flos": 1.946592978000675e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |