| { | |
| "best_metric": 2.1131954193115234, | |
| "best_model_checkpoint": "output/andre-3000/checkpoint-1089", | |
| "epoch": 11.0, | |
| "global_step": 1089, | |
| "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 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 3.4251213229711433e-06, | |
| "loss": 2.7141, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 5.15, | |
| "learning_rate": 7.625888222272204e-06, | |
| "loss": 3.1031, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "learning_rate": 1.3358460333369401e-05, | |
| "loss": 2.7596, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 5.25, | |
| "learning_rate": 2.0478822703346315e-05, | |
| "loss": 2.747, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 2.880809600341567e-05, | |
| "loss": 2.8618, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 5.35, | |
| "learning_rate": 3.8137030375243876e-05, | |
| "loss": 2.811, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "learning_rate": 4.823126225248023e-05, | |
| "loss": 2.8491, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "learning_rate": 5.883720209445242e-05, | |
| "loss": 2.5856, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 5.51, | |
| "learning_rate": 6.968840511906774e-05, | |
| "loss": 2.9258, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "learning_rate": 8.051226498795124e-05, | |
| "loss": 2.9732, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "learning_rate": 9.10368622835751e-05, | |
| "loss": 2.9297, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 5.66, | |
| "learning_rate": 0.0001009977957294059, | |
| "loss": 2.5333, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 0.00011014482453764393, | |
| "loss": 2.7163, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "learning_rate": 0.00011824815501400774, | |
| "loss": 2.575, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 5.81, | |
| "learning_rate": 0.00012510421348608654, | |
| "loss": 2.6619, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 0.0001305407605264622, | |
| "loss": 2.8522, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "learning_rate": 0.00013442121798995453, | |
| "loss": 2.9609, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "learning_rate": 0.00013664810016019257, | |
| "loss": 2.7212, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 2.8283281326293945, | |
| "eval_runtime": 3.2672, | |
| "eval_samples_per_second": 43.462, | |
| "eval_steps_per_second": 5.509, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 0.0001371654628074865, | |
| "loss": 2.8262, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "learning_rate": 0.00013596030863222166, | |
| "loss": 2.45, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "learning_rate": 0.00013306291378591335, | |
| "loss": 2.7517, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 6.16, | |
| "learning_rate": 0.00012854606726698723, | |
| "loss": 2.4939, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 6.21, | |
| "learning_rate": 0.00012252324229935523, | |
| "loss": 2.6832, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 6.26, | |
| "learning_rate": 0.0001151457456328192, | |
| "loss": 2.5246, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 6.31, | |
| "learning_rate": 0.00010659891638121517, | |
| "loss": 2.8753, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 6.36, | |
| "learning_rate": 9.70974698919295e-05, | |
| "loss": 2.8246, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 8.688010361913636e-05, | |
| "loss": 2.5406, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 6.46, | |
| "learning_rate": 7.620350051320941e-05, | |
| "loss": 2.3994, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 6.52, | |
| "learning_rate": 6.53358805744912e-05, | |
| "loss": 2.4749, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "learning_rate": 5.4550262570727935e-05, | |
| "loss": 2.2935, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "learning_rate": 4.4117605198797704e-05, | |
| "loss": 2.142, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 3.429999999999998e-05, | |
| "loss": 2.6776, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 2.5344087038001816e-05, | |
| "loss": 2.6633, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 6.77, | |
| "learning_rate": 1.7474858752243343e-05, | |
| "loss": 2.7227, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 6.82, | |
| "learning_rate": 1.0890007647780993e-05, | |
| "loss": 2.7123, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 6.87, | |
| "learning_rate": 5.754959820160079e-06, | |
| "loss": 2.7949, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "learning_rate": 2.1987190842099613e-06, | |
| "loss": 2.6913, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 6.97, | |
| "learning_rate": 3.106261114864048e-07, | |
| "loss": 2.5163, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 2.7900161743164062, | |
| "eval_runtime": 3.2724, | |
| "eval_samples_per_second": 43.393, | |
| "eval_steps_per_second": 5.501, | |
| "step": 693 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 1.3811399402871997e-07, | |
| "loss": 2.5678, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 7.07, | |
| "learning_rate": 1.6855166196610614e-06, | |
| "loss": 2.4848, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 7.12, | |
| "learning_rate": 4.913959795097361e-06, | |
| "loss": 2.603, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 7.17, | |
| "learning_rate": 9.742337852080565e-06, | |
| "loss": 2.26, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 7.22, | |
| "learning_rate": 1.604935120203803e-05, | |
| "loss": 2.3438, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 7.27, | |
| "learning_rate": 2.367655365135328e-05, | |
| "loss": 2.4659, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 7.32, | |
| "learning_rate": 3.243233292191947e-05, | |
| "loss": 2.1382, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "learning_rate": 4.2096724377451216e-05, | |
| "loss": 2.2814, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 7.42, | |
| "learning_rate": 5.242693702405326e-05, | |
| "loss": 2.212, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 7.47, | |
| "learning_rate": 6.316345295962419e-05, | |
| "loss": 2.4038, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 7.53, | |
| "learning_rate": 7.403654704037569e-05, | |
| "loss": 2.4106, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "learning_rate": 8.477306297594661e-05, | |
| "loss": 2.4768, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "learning_rate": 9.510327562254866e-05, | |
| "loss": 2.3888, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "learning_rate": 0.00010476766707808043, | |
| "loss": 2.4749, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 7.73, | |
| "learning_rate": 0.00011352344634864663, | |
| "loss": 2.5513, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 7.78, | |
| "learning_rate": 0.00012115064879796188, | |
| "loss": 2.5604, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 7.83, | |
| "learning_rate": 0.00012745766214791938, | |
| "loss": 2.3697, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 7.88, | |
| "learning_rate": 0.0001322860402049026, | |
| "loss": 2.3862, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 7.93, | |
| "learning_rate": 0.0001355144833803389, | |
| "loss": 2.323, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 7.98, | |
| "learning_rate": 0.00013706188600597126, | |
| "loss": 2.6325, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 2.807237148284912, | |
| "eval_runtime": 3.2933, | |
| "eval_samples_per_second": 43.118, | |
| "eval_steps_per_second": 5.466, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "learning_rate": 0.00013688937388851358, | |
| "loss": 2.3013, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 8.08, | |
| "learning_rate": 0.00013500128091579002, | |
| "loss": 2.5725, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 8.13, | |
| "learning_rate": 0.00013144504017983998, | |
| "loss": 2.2264, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 8.18, | |
| "learning_rate": 0.00012630999235221907, | |
| "loss": 1.9343, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 8.23, | |
| "learning_rate": 0.0001197251412477569, | |
| "loss": 2.2098, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 8.28, | |
| "learning_rate": 0.00011185591296199847, | |
| "loss": 1.9414, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 8.33, | |
| "learning_rate": 0.00010289999999999993, | |
| "loss": 2.5007, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 8.38, | |
| "learning_rate": 9.308239480120242e-05, | |
| "loss": 2.2473, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 8.43, | |
| "learning_rate": 8.264973742927219e-05, | |
| "loss": 2.648, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 8.48, | |
| "learning_rate": 7.186411942550894e-05, | |
| "loss": 2.4495, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 8.54, | |
| "learning_rate": 6.0996499486790955e-05, | |
| "loss": 2.3626, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 8.59, | |
| "learning_rate": 5.0319896380863535e-05, | |
| "loss": 2.3541, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 4.0102530108070616e-05, | |
| "loss": 2.1531, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "learning_rate": 3.0601083618784945e-05, | |
| "loss": 2.3576, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 8.74, | |
| "learning_rate": 2.20542543671809e-05, | |
| "loss": 1.9389, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 8.79, | |
| "learning_rate": 1.4676757700644984e-05, | |
| "loss": 2.3032, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 8.84, | |
| "learning_rate": 8.653932733012724e-06, | |
| "loss": 2.5286, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "learning_rate": 4.137086214086705e-06, | |
| "loss": 2.1202, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 8.94, | |
| "learning_rate": 1.2396913677783503e-06, | |
| "loss": 2.24, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "learning_rate": 3.4537192513510953e-08, | |
| "loss": 2.1317, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 2.797985315322876, | |
| "eval_runtime": 3.2929, | |
| "eval_samples_per_second": 43.124, | |
| "eval_steps_per_second": 5.466, | |
| "step": 891 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "learning_rate": 5.51899839807432e-07, | |
| "loss": 2.1029, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 2.778782010045488e-06, | |
| "loss": 1.9706, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 9.14, | |
| "learning_rate": 6.6592394735377576e-06, | |
| "loss": 2.1198, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 9.19, | |
| "learning_rate": 1.2095786513913378e-05, | |
| "loss": 2.1092, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 9.24, | |
| "learning_rate": 1.895184498599217e-05, | |
| "loss": 2.1326, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 9.29, | |
| "learning_rate": 2.7055175462355963e-05, | |
| "loss": 2.0587, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 9.34, | |
| "learning_rate": 3.6202204270593973e-05, | |
| "loss": 1.9377, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 9.39, | |
| "learning_rate": 4.6163137716425034e-05, | |
| "loss": 2.0585, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 9.44, | |
| "learning_rate": 5.6687735012048636e-05, | |
| "loss": 1.9919, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 9.49, | |
| "learning_rate": 6.751159488093214e-05, | |
| "loss": 1.8915, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 9.55, | |
| "learning_rate": 7.836279790554722e-05, | |
| "loss": 1.871, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 8.896873774751943e-05, | |
| "loss": 2.1734, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 9.65, | |
| "learning_rate": 9.906296962475623e-05, | |
| "loss": 2.1848, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "learning_rate": 0.00010839190399658423, | |
| "loss": 2.1742, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 9.75, | |
| "learning_rate": 0.00011672117729665359, | |
| "loss": 2.3443, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 9.8, | |
| "learning_rate": 0.00012384153966663053, | |
| "loss": 1.857, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 9.85, | |
| "learning_rate": 0.00012957411177772762, | |
| "loss": 2.2031, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 9.9, | |
| "learning_rate": 0.0001337748786770289, | |
| "loss": 2.1931, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 9.95, | |
| "learning_rate": 0.00013633830776320065, | |
| "loss": 2.0811, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.0001372, | |
| "loss": 2.3998, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 2.7857184410095215, | |
| "eval_runtime": 3.2779, | |
| "eval_samples_per_second": 43.32, | |
| "eval_steps_per_second": 5.491, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 10.05, | |
| "learning_rate": 0.00013633830776320067, | |
| "loss": 2.2465, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 10.1, | |
| "learning_rate": 0.00013377487867702895, | |
| "loss": 2.0385, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 10.15, | |
| "learning_rate": 0.0001295741117777277, | |
| "loss": 2.0847, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 10.2, | |
| "learning_rate": 0.00012384153966663063, | |
| "loss": 2.0744, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 10.25, | |
| "learning_rate": 0.00011672117729665371, | |
| "loss": 2.2347, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 10.3, | |
| "learning_rate": 0.00010839190399658435, | |
| "loss": 2.3577, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 10.35, | |
| "learning_rate": 9.906296962475639e-05, | |
| "loss": 2.1928, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 10.4, | |
| "learning_rate": 8.896873774751959e-05, | |
| "loss": 2.3981, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 10.45, | |
| "learning_rate": 7.836279790554739e-05, | |
| "loss": 2.1466, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 10.51, | |
| "learning_rate": 6.75115948809323e-05, | |
| "loss": 2.0252, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "learning_rate": 5.66877350120488e-05, | |
| "loss": 2.1059, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 10.61, | |
| "learning_rate": 4.616313771642518e-05, | |
| "loss": 2.251, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 10.66, | |
| "learning_rate": 3.620220427059434e-05, | |
| "loss": 2.332, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 10.71, | |
| "learning_rate": 2.7055175462356102e-05, | |
| "loss": 2.0934, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 10.76, | |
| "learning_rate": 1.8951844985992284e-05, | |
| "loss": 2.2116, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 10.81, | |
| "learning_rate": 1.2095786513913607e-05, | |
| "loss": 2.1227, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 10.86, | |
| "learning_rate": 6.659239473537932e-06, | |
| "loss": 2.1152, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 10.91, | |
| "learning_rate": 2.7787820100456023e-06, | |
| "loss": 1.9454, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 10.96, | |
| "learning_rate": 5.518998398074473e-07, | |
| "loss": 2.208, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 2.1131954193115234, | |
| "eval_runtime": 1.8527, | |
| "eval_samples_per_second": 75.565, | |
| "eval_steps_per_second": 9.716, | |
| "step": 1089 | |
| } | |
| ], | |
| "max_steps": 1287, | |
| "num_train_epochs": 13, | |
| "total_flos": 1135575171072000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |