| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.16038492381716118, | |
| "eval_steps": 500, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.99999449047447e-05, | |
| "loss": 2.7413, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.9999779619221645e-05, | |
| "loss": 2.6684, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.999950414415935e-05, | |
| "loss": 2.6511, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.999911848077199e-05, | |
| "loss": 2.72, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.999862263075944e-05, | |
| "loss": 2.7222, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.999801659630722e-05, | |
| "loss": 2.7479, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.999730038008649e-05, | |
| "loss": 2.6063, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.9996473985254055e-05, | |
| "loss": 2.576, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.999553741545237e-05, | |
| "loss": 2.579, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.999449067480945e-05, | |
| "loss": 2.5114, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.9993333767938954e-05, | |
| "loss": 2.6174, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.9992066699940085e-05, | |
| "loss": 2.6581, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.9990689476397586e-05, | |
| "loss": 2.586, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.998920210338175e-05, | |
| "loss": 2.4642, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.9987604587448343e-05, | |
| "loss": 2.6262, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.998589693563861e-05, | |
| "loss": 2.5678, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.998407915547924e-05, | |
| "loss": 2.5597, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.9982151254982304e-05, | |
| "loss": 2.6578, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.998011324264527e-05, | |
| "loss": 2.4825, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.997796512745091e-05, | |
| "loss": 2.6197, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.997570691886732e-05, | |
| "loss": 2.4921, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.99733386268478e-05, | |
| "loss": 2.5126, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.99708602618309e-05, | |
| "loss": 2.584, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.9968271834740305e-05, | |
| "loss": 2.4991, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.996557335698482e-05, | |
| "loss": 2.5242, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.996276484045832e-05, | |
| "loss": 2.4506, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.995984629753967e-05, | |
| "loss": 2.5479, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.9956817741092696e-05, | |
| "loss": 2.5316, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.995367918446613e-05, | |
| "loss": 2.6053, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.995043064149354e-05, | |
| "loss": 2.4533, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.9947072126493276e-05, | |
| "loss": 2.5279, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.994360365426839e-05, | |
| "loss": 2.4994, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.994002524010659e-05, | |
| "loss": 2.4675, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.9936336899780166e-05, | |
| "loss": 2.5233, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.993253864954592e-05, | |
| "loss": 2.4974, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.992863050614511e-05, | |
| "loss": 2.6295, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.9924612486803346e-05, | |
| "loss": 2.4744, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.992048460923052e-05, | |
| "loss": 2.5248, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.991624689162076e-05, | |
| "loss": 2.5727, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.991189935265231e-05, | |
| "loss": 2.4845, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.990744201148748e-05, | |
| "loss": 2.4544, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.990287488777253e-05, | |
| "loss": 2.4383, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.989819800163761e-05, | |
| "loss": 2.5263, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.989341137369666e-05, | |
| "loss": 2.5219, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.9888515025047316e-05, | |
| "loss": 2.4512, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.988350897727083e-05, | |
| "loss": 2.491, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.9878393252431953e-05, | |
| "loss": 2.5404, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.987316787307888e-05, | |
| "loss": 2.4777, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.9867832862243055e-05, | |
| "loss": 2.4498, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.986238824343923e-05, | |
| "loss": 2.4174, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.985683404066519e-05, | |
| "loss": 2.4589, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.985117027840175e-05, | |
| "loss": 2.5029, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.984539698161264e-05, | |
| "loss": 2.4376, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.983951417574436e-05, | |
| "loss": 2.526, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.983352188672608e-05, | |
| "loss": 2.5214, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.982742014096952e-05, | |
| "loss": 2.5188, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.982120896536888e-05, | |
| "loss": 2.4175, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.981488838730066e-05, | |
| "loss": 2.5346, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.980845843462357e-05, | |
| "loss": 2.496, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.98019191356784e-05, | |
| "loss": 2.477, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.9795270519287886e-05, | |
| "loss": 2.4205, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.9788512614756624e-05, | |
| "loss": 2.4621, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.9781645451870875e-05, | |
| "loss": 2.5098, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.9774669060898496e-05, | |
| "loss": 2.4847, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.976758347258877e-05, | |
| "loss": 2.4873, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.976038871817228e-05, | |
| "loss": 2.4462, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.9753084829360776e-05, | |
| "loss": 2.4994, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.974567183834702e-05, | |
| "loss": 2.4994, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.9738149777804665e-05, | |
| "loss": 2.4584, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.97305186808881e-05, | |
| "loss": 2.4294, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.9722778581232305e-05, | |
| "loss": 2.4499, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.9714929512952704e-05, | |
| "loss": 2.5851, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.9706971510645e-05, | |
| "loss": 2.4746, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.969890460938505e-05, | |
| "loss": 2.4184, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.9690728844728704e-05, | |
| "loss": 2.4716, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.968244425271161e-05, | |
| "loss": 2.4477, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.9674050869849124e-05, | |
| "loss": 2.4563, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.966554873313608e-05, | |
| "loss": 2.3708, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.9656937880046676e-05, | |
| "loss": 2.4351, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.9648218348534284e-05, | |
| "loss": 2.3933, | |
| "step": 400 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 7482, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 5163016243445760.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |