| { | |
| "best_metric": 3.5885772705078125, | |
| "best_model_checkpoint": "output/andre-3000/checkpoint-500", | |
| "epoch": 5.0, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00013635542016482644, | |
| "loss": 3.842, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00013384247701784754, | |
| "loss": 4.137, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00012972304755932203, | |
| "loss": 3.733, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0001240985658141214, | |
| "loss": 3.9016, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00011710752518939715, | |
| "loss": 3.9056, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00010892206830726365, | |
| "loss": 3.4673, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 9.974374828213291e-05, | |
| "loss": 3.4192, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 8.97985658141214e-05, | |
| "loss": 3.5188, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 7.933140430175984e-05, | |
| "loss": 3.6982, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 6.86e-05, | |
| "loss": 3.6325, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 5.786859569824015e-05, | |
| "loss": 3.5144, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.740143418587861e-05, | |
| "loss": 3.6288, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.745625171786709e-05, | |
| "loss": 3.5069, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.8277931692736352e-05, | |
| "loss": 3.7103, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 2.0092474810602843e-05, | |
| "loss": 3.5622, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.3101434185878613e-05, | |
| "loss": 3.5587, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 7.476952440677969e-06, | |
| "loss": 3.5987, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.357522982152468e-06, | |
| "loss": 3.4558, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 8.445798351735566e-07, | |
| "loss": 3.528, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0, | |
| "loss": 3.5143, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 3.681246519088745, | |
| "eval_runtime": 2.8995, | |
| "eval_samples_per_second": 46.215, | |
| "eval_steps_per_second": 5.863, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 8.445798351735489e-07, | |
| "loss": 3.5508, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 3.357522982152468e-06, | |
| "loss": 3.6326, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 7.4769524406779465e-06, | |
| "loss": 3.3899, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 1.3101434185878598e-05, | |
| "loss": 3.3572, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 2.009247481060283e-05, | |
| "loss": 3.5502, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 2.8277931692736335e-05, | |
| "loss": 3.3994, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 3.745625171786708e-05, | |
| "loss": 3.2566, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 4.74014341858786e-05, | |
| "loss": 3.503, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 5.786859569824015e-05, | |
| "loss": 3.0786, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 6.859999999999999e-05, | |
| "loss": 3.2728, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 7.933140430175983e-05, | |
| "loss": 3.1862, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 8.979856581412138e-05, | |
| "loss": 3.2618, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 9.974374828213291e-05, | |
| "loss": 3.4498, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.00010892206830726364, | |
| "loss": 3.1053, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.00011710752518939715, | |
| "loss": 3.3994, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.0001240985658141214, | |
| "loss": 3.3686, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.00012972304755932203, | |
| "loss": 3.4802, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.00013384247701784754, | |
| "loss": 3.4496, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.00013635542016482644, | |
| "loss": 3.341, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0001372, | |
| "loss": 3.2332, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 3.6474390029907227, | |
| "eval_runtime": 3.0601, | |
| "eval_samples_per_second": 43.789, | |
| "eval_steps_per_second": 5.555, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 0.00013635542016482644, | |
| "loss": 3.2607, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 0.00013384247701784754, | |
| "loss": 3.3, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 0.00012972304755932206, | |
| "loss": 3.3456, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 0.00012409856581412136, | |
| "loss": 3.0185, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 0.00011710752518939717, | |
| "loss": 2.9552, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 0.00010892206830726372, | |
| "loss": 3.0603, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 9.974374828213292e-05, | |
| "loss": 3.2515, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 8.979856581412141e-05, | |
| "loss": 3.1474, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 7.93314043017598e-05, | |
| "loss": 3.1997, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 6.860000000000001e-05, | |
| "loss": 3.2995, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 5.786859569824025e-05, | |
| "loss": 3.0081, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 4.7401434185878625e-05, | |
| "loss": 3.0519, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 3.745625171786717e-05, | |
| "loss": 3.1474, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 2.827793169273636e-05, | |
| "loss": 3.0318, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 2.0092474810602897e-05, | |
| "loss": 3.0418, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 1.310143418587862e-05, | |
| "loss": 3.2108, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 7.4769524406779465e-06, | |
| "loss": 2.8269, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 3.3575229821524754e-06, | |
| "loss": 3.0926, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 8.445798351735489e-07, | |
| "loss": 3.1617, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.8832, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 3.5949366092681885, | |
| "eval_runtime": 3.0805, | |
| "eval_samples_per_second": 43.5, | |
| "eval_steps_per_second": 5.519, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 8.445798351735413e-07, | |
| "loss": 2.8947, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 3.35752298215246e-06, | |
| "loss": 2.8681, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 7.4769524406779245e-06, | |
| "loss": 2.925, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 1.310143418587859e-05, | |
| "loss": 3.0341, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 2.0092474810602867e-05, | |
| "loss": 2.923, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 2.827793169273632e-05, | |
| "loss": 3.1311, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 3.7456251717867126e-05, | |
| "loss": 2.9954, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 4.740143418587858e-05, | |
| "loss": 2.9511, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 5.7868595698240195e-05, | |
| "loss": 2.9837, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 6.859999999999997e-05, | |
| "loss": 3.0341, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 7.933140430175976e-05, | |
| "loss": 2.9587, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 8.979856581412137e-05, | |
| "loss": 2.9158, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 9.974374828213283e-05, | |
| "loss": 2.8452, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 0.00010892206830726364, | |
| "loss": 2.9248, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 0.0001171075251893971, | |
| "loss": 2.9796, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 0.00012409856581412136, | |
| "loss": 3.0723, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 0.00012972304755932206, | |
| "loss": 2.7475, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 0.00013384247701784751, | |
| "loss": 2.9859, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 0.00013635542016482644, | |
| "loss": 2.8605, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 0.0001372, | |
| "loss": 2.8721, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 3.6242599487304688, | |
| "eval_runtime": 3.0946, | |
| "eval_samples_per_second": 43.301, | |
| "eval_steps_per_second": 5.493, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 0.00013635542016482647, | |
| "loss": 3.0586, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 0.0001338424770178476, | |
| "loss": 2.5264, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 0.00012972304755932203, | |
| "loss": 2.591, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 0.00012409856581412142, | |
| "loss": 2.7559, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 0.00011710752518939714, | |
| "loss": 2.6444, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 0.00010892206830726369, | |
| "loss": 3.0661, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 9.9743748282133e-05, | |
| "loss": 2.639, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 8.97985658141213e-05, | |
| "loss": 2.8619, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 7.933140430175981e-05, | |
| "loss": 2.6417, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 6.860000000000003e-05, | |
| "loss": 2.7156, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 5.786859569824026e-05, | |
| "loss": 2.9429, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 4.740143418587876e-05, | |
| "loss": 2.7116, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 3.745625171786707e-05, | |
| "loss": 2.6837, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 2.8277931692736372e-05, | |
| "loss": 2.8497, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 2.0092474810602914e-05, | |
| "loss": 2.713, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 1.3101434185878628e-05, | |
| "loss": 2.7103, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 7.4769524406780075e-06, | |
| "loss": 2.6698, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 3.3575229821524373e-06, | |
| "loss": 2.8479, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 8.445798351735489e-07, | |
| "loss": 2.7422, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.8229, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 3.5885772705078125, | |
| "eval_runtime": 3.0956, | |
| "eval_samples_per_second": 43.288, | |
| "eval_steps_per_second": 5.492, | |
| "step": 500 | |
| } | |
| ], | |
| "max_steps": 1000, | |
| "num_train_epochs": 10, | |
| "total_flos": 521277603840000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |