| { | |
| "best_metric": 2.3393449783325195, | |
| "best_model_checkpoint": "/mnt/d/robertalarge_biomedical/checkpoint-6550", | |
| "epoch": 4.974349659495153, | |
| "global_step": 6950, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.788908765652952e-07, | |
| "loss": 3.2407, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 8.944543828264759e-06, | |
| "loss": 2.7077, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 3.4396915435791016, | |
| "eval_runtime": 16.4722, | |
| "eval_samples_per_second": 64.412, | |
| "eval_steps_per_second": 4.067, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.7889087656529517e-05, | |
| "loss": 2.5129, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 3.3453807830810547, | |
| "eval_runtime": 15.7784, | |
| "eval_samples_per_second": 67.244, | |
| "eval_steps_per_second": 4.246, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 2.6833631484794274e-05, | |
| "loss": 2.4739, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 3.2746219635009766, | |
| "eval_runtime": 15.4205, | |
| "eval_samples_per_second": 68.805, | |
| "eval_steps_per_second": 4.345, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 3.5778175313059034e-05, | |
| "loss": 2.4546, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 3.246519088745117, | |
| "eval_runtime": 15.432, | |
| "eval_samples_per_second": 68.753, | |
| "eval_steps_per_second": 4.342, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.472271914132379e-05, | |
| "loss": 2.4442, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 3.183640241622925, | |
| "eval_runtime": 15.4658, | |
| "eval_samples_per_second": 68.603, | |
| "eval_steps_per_second": 4.332, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 5.366726296958855e-05, | |
| "loss": 2.4264, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 3.180060386657715, | |
| "eval_runtime": 15.4178, | |
| "eval_samples_per_second": 68.817, | |
| "eval_steps_per_second": 4.346, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 6.261180679785331e-05, | |
| "loss": 2.4195, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 3.1306841373443604, | |
| "eval_runtime": 15.4309, | |
| "eval_samples_per_second": 68.758, | |
| "eval_steps_per_second": 4.342, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 7.155635062611807e-05, | |
| "loss": 2.4104, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 3.0838072299957275, | |
| "eval_runtime": 15.4426, | |
| "eval_samples_per_second": 68.706, | |
| "eval_steps_per_second": 4.339, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 8.050089445438284e-05, | |
| "loss": 2.4024, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 3.0821988582611084, | |
| "eval_runtime": 15.4315, | |
| "eval_samples_per_second": 68.755, | |
| "eval_steps_per_second": 4.342, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 8.944543828264758e-05, | |
| "loss": 2.4004, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 3.046294689178467, | |
| "eval_runtime": 15.3324, | |
| "eval_samples_per_second": 69.2, | |
| "eval_steps_per_second": 4.37, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 9.838998211091235e-05, | |
| "loss": 2.3934, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 3.01847505569458, | |
| "eval_runtime": 15.5503, | |
| "eval_samples_per_second": 68.23, | |
| "eval_steps_per_second": 4.309, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 9.936196700902583e-05, | |
| "loss": 2.3912, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 3.002716541290283, | |
| "eval_runtime": 15.9752, | |
| "eval_samples_per_second": 66.415, | |
| "eval_steps_per_second": 4.194, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 9.85838779956427e-05, | |
| "loss": 2.3802, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 3.0039303302764893, | |
| "eval_runtime": 17.2357, | |
| "eval_samples_per_second": 61.558, | |
| "eval_steps_per_second": 3.887, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 9.780578898225957e-05, | |
| "loss": 2.3706, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 2.9694342613220215, | |
| "eval_runtime": 16.096, | |
| "eval_samples_per_second": 65.917, | |
| "eval_steps_per_second": 4.163, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.702769996887644e-05, | |
| "loss": 2.3612, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 2.935302495956421, | |
| "eval_runtime": 16.2283, | |
| "eval_samples_per_second": 65.38, | |
| "eval_steps_per_second": 4.129, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 9.62496109554933e-05, | |
| "loss": 2.3612, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 2.909855842590332, | |
| "eval_runtime": 16.1383, | |
| "eval_samples_per_second": 65.744, | |
| "eval_steps_per_second": 4.152, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 9.547152194211019e-05, | |
| "loss": 2.3529, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 2.8925089836120605, | |
| "eval_runtime": 16.1755, | |
| "eval_samples_per_second": 65.593, | |
| "eval_steps_per_second": 4.142, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 9.469343292872706e-05, | |
| "loss": 2.3483, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 2.8811819553375244, | |
| "eval_runtime": 16.1525, | |
| "eval_samples_per_second": 65.686, | |
| "eval_steps_per_second": 4.148, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 9.391534391534393e-05, | |
| "loss": 2.3416, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 2.883502244949341, | |
| "eval_runtime": 16.1426, | |
| "eval_samples_per_second": 65.727, | |
| "eval_steps_per_second": 4.151, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 9.313725490196079e-05, | |
| "loss": 2.3449, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 2.8285071849823, | |
| "eval_runtime": 16.2132, | |
| "eval_samples_per_second": 65.441, | |
| "eval_steps_per_second": 4.132, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 9.235916588857766e-05, | |
| "loss": 2.3339, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 2.8209173679351807, | |
| "eval_runtime": 16.1462, | |
| "eval_samples_per_second": 65.712, | |
| "eval_steps_per_second": 4.15, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 9.158107687519453e-05, | |
| "loss": 2.3269, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 2.8276333808898926, | |
| "eval_runtime": 16.1372, | |
| "eval_samples_per_second": 65.749, | |
| "eval_steps_per_second": 4.152, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9.08029878618114e-05, | |
| "loss": 2.3279, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 2.7980849742889404, | |
| "eval_runtime": 16.2178, | |
| "eval_samples_per_second": 65.422, | |
| "eval_steps_per_second": 4.131, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 9.002489884842827e-05, | |
| "loss": 2.3207, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_loss": 2.7847139835357666, | |
| "eval_runtime": 16.2194, | |
| "eval_samples_per_second": 65.415, | |
| "eval_steps_per_second": 4.131, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 8.924680983504513e-05, | |
| "loss": 2.32, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": 2.7734076976776123, | |
| "eval_runtime": 16.1394, | |
| "eval_samples_per_second": 65.74, | |
| "eval_steps_per_second": 4.151, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 8.8468720821662e-05, | |
| "loss": 2.3135, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 2.786221742630005, | |
| "eval_runtime": 16.2004, | |
| "eval_samples_per_second": 65.492, | |
| "eval_steps_per_second": 4.136, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 8.769063180827887e-05, | |
| "loss": 2.3158, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 2.756885290145874, | |
| "eval_runtime": 16.2115, | |
| "eval_samples_per_second": 65.447, | |
| "eval_steps_per_second": 4.133, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 8.691254279489574e-05, | |
| "loss": 2.349, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.73188853263855, | |
| "eval_runtime": 16.1915, | |
| "eval_samples_per_second": 65.528, | |
| "eval_steps_per_second": 4.138, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 8.613445378151261e-05, | |
| "loss": 2.2968, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "eval_loss": 2.7212417125701904, | |
| "eval_runtime": 16.1464, | |
| "eval_samples_per_second": 65.711, | |
| "eval_steps_per_second": 4.15, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 8.535636476812948e-05, | |
| "loss": 2.2972, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 2.720673084259033, | |
| "eval_runtime": 16.1142, | |
| "eval_samples_per_second": 65.842, | |
| "eval_steps_per_second": 4.158, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 8.457827575474635e-05, | |
| "loss": 2.288, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "eval_loss": 2.7066142559051514, | |
| "eval_runtime": 16.1655, | |
| "eval_samples_per_second": 65.634, | |
| "eval_steps_per_second": 4.145, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 8.380018674136322e-05, | |
| "loss": 2.2979, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_loss": 2.696605920791626, | |
| "eval_runtime": 16.922, | |
| "eval_samples_per_second": 62.7, | |
| "eval_steps_per_second": 3.959, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 8.302209772798009e-05, | |
| "loss": 2.2809, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "eval_loss": 2.6909220218658447, | |
| "eval_runtime": 16.1973, | |
| "eval_samples_per_second": 65.505, | |
| "eval_steps_per_second": 4.136, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 8.224400871459695e-05, | |
| "loss": 2.284, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "eval_loss": 2.705894947052002, | |
| "eval_runtime": 15.4841, | |
| "eval_samples_per_second": 68.522, | |
| "eval_steps_per_second": 4.327, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 8.146591970121382e-05, | |
| "loss": 2.2734, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_loss": 2.69627046585083, | |
| "eval_runtime": 15.5405, | |
| "eval_samples_per_second": 68.273, | |
| "eval_steps_per_second": 4.311, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 8.068783068783069e-05, | |
| "loss": 2.2689, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "eval_loss": 2.6974661350250244, | |
| "eval_runtime": 15.5232, | |
| "eval_samples_per_second": 68.349, | |
| "eval_steps_per_second": 4.316, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 7.990974167444756e-05, | |
| "loss": 2.2747, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "eval_loss": 2.665536642074585, | |
| "eval_runtime": 15.6492, | |
| "eval_samples_per_second": 67.799, | |
| "eval_steps_per_second": 4.281, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 7.913165266106442e-05, | |
| "loss": 2.2705, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_loss": 2.6571662425994873, | |
| "eval_runtime": 15.6605, | |
| "eval_samples_per_second": 67.75, | |
| "eval_steps_per_second": 4.278, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 7.835356364768129e-05, | |
| "loss": 2.2677, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_loss": 2.678373098373413, | |
| "eval_runtime": 15.5437, | |
| "eval_samples_per_second": 68.259, | |
| "eval_steps_per_second": 4.31, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 7.757547463429816e-05, | |
| "loss": 2.2619, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "eval_loss": 2.6495842933654785, | |
| "eval_runtime": 15.6017, | |
| "eval_samples_per_second": 68.006, | |
| "eval_steps_per_second": 4.294, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 7.679738562091505e-05, | |
| "loss": 2.2658, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 2.654540777206421, | |
| "eval_runtime": 15.6668, | |
| "eval_samples_per_second": 67.723, | |
| "eval_steps_per_second": 4.277, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 7.60192966075319e-05, | |
| "loss": 2.2612, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_loss": 2.6398253440856934, | |
| "eval_runtime": 15.5459, | |
| "eval_samples_per_second": 68.25, | |
| "eval_steps_per_second": 4.31, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 7.524120759414877e-05, | |
| "loss": 2.2623, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "eval_loss": 2.6319923400878906, | |
| "eval_runtime": 15.5493, | |
| "eval_samples_per_second": 68.235, | |
| "eval_steps_per_second": 4.309, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 7.446311858076564e-05, | |
| "loss": 2.2529, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "eval_loss": 2.6172051429748535, | |
| "eval_runtime": 15.5885, | |
| "eval_samples_per_second": 68.063, | |
| "eval_steps_per_second": 4.298, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 7.368502956738252e-05, | |
| "loss": 2.2545, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "eval_loss": 2.6302292346954346, | |
| "eval_runtime": 15.5322, | |
| "eval_samples_per_second": 68.31, | |
| "eval_steps_per_second": 4.314, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 7.290694055399939e-05, | |
| "loss": 2.2522, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "eval_loss": 2.611330032348633, | |
| "eval_runtime": 15.6406, | |
| "eval_samples_per_second": 67.836, | |
| "eval_steps_per_second": 4.284, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 7.212885154061624e-05, | |
| "loss": 2.2487, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "eval_loss": 2.6002895832061768, | |
| "eval_runtime": 16.1054, | |
| "eval_samples_per_second": 65.879, | |
| "eval_steps_per_second": 4.16, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 7.135076252723311e-05, | |
| "loss": 2.2517, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "eval_loss": 2.6024696826934814, | |
| "eval_runtime": 15.5909, | |
| "eval_samples_per_second": 68.053, | |
| "eval_steps_per_second": 4.297, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 7.057267351384999e-05, | |
| "loss": 2.2427, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_loss": 2.592979669570923, | |
| "eval_runtime": 15.5688, | |
| "eval_samples_per_second": 68.149, | |
| "eval_steps_per_second": 4.303, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 6.979458450046686e-05, | |
| "loss": 2.2376, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "eval_loss": 2.600585460662842, | |
| "eval_runtime": 15.6632, | |
| "eval_samples_per_second": 67.738, | |
| "eval_steps_per_second": 4.278, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 6.901649548708373e-05, | |
| "loss": 2.25, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "eval_loss": 2.5825278759002686, | |
| "eval_runtime": 15.5619, | |
| "eval_samples_per_second": 68.179, | |
| "eval_steps_per_second": 4.305, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 6.82384064737006e-05, | |
| "loss": 2.2424, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_loss": 2.5783889293670654, | |
| "eval_runtime": 15.5691, | |
| "eval_samples_per_second": 68.148, | |
| "eval_steps_per_second": 4.303, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 6.746031746031747e-05, | |
| "loss": 2.237, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "eval_loss": 2.5440621376037598, | |
| "eval_runtime": 16.2594, | |
| "eval_samples_per_second": 65.255, | |
| "eval_steps_per_second": 4.121, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 6.668222844693434e-05, | |
| "loss": 2.2319, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "eval_loss": 2.582082748413086, | |
| "eval_runtime": 15.4145, | |
| "eval_samples_per_second": 68.831, | |
| "eval_steps_per_second": 4.347, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 6.590413943355121e-05, | |
| "loss": 2.2321, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_loss": 2.5679547786712646, | |
| "eval_runtime": 15.3943, | |
| "eval_samples_per_second": 68.921, | |
| "eval_steps_per_second": 4.352, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6.512605042016807e-05, | |
| "loss": 2.2703, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.5684449672698975, | |
| "eval_runtime": 15.6772, | |
| "eval_samples_per_second": 67.678, | |
| "eval_steps_per_second": 4.274, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 6.434796140678494e-05, | |
| "loss": 2.217, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "eval_loss": 2.5685508251190186, | |
| "eval_runtime": 15.5996, | |
| "eval_samples_per_second": 68.015, | |
| "eval_steps_per_second": 4.295, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 6.356987239340181e-05, | |
| "loss": 2.2194, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "eval_loss": 2.572051763534546, | |
| "eval_runtime": 15.6446, | |
| "eval_samples_per_second": 67.819, | |
| "eval_steps_per_second": 4.283, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 6.279178338001868e-05, | |
| "loss": 2.2215, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "eval_loss": 2.5475494861602783, | |
| "eval_runtime": 15.5563, | |
| "eval_samples_per_second": 68.204, | |
| "eval_steps_per_second": 4.307, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 6.201369436663555e-05, | |
| "loss": 2.2181, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "eval_loss": 2.5376882553100586, | |
| "eval_runtime": 15.5452, | |
| "eval_samples_per_second": 68.253, | |
| "eval_steps_per_second": 4.31, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 6.123560535325241e-05, | |
| "loss": 2.2152, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "eval_loss": 2.5125858783721924, | |
| "eval_runtime": 15.545, | |
| "eval_samples_per_second": 68.254, | |
| "eval_steps_per_second": 4.31, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 6.045751633986928e-05, | |
| "loss": 2.2115, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "eval_loss": 2.535728693008423, | |
| "eval_runtime": 15.6209, | |
| "eval_samples_per_second": 67.922, | |
| "eval_steps_per_second": 4.289, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 5.967942732648615e-05, | |
| "loss": 2.2136, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "eval_loss": 2.5309102535247803, | |
| "eval_runtime": 15.5441, | |
| "eval_samples_per_second": 68.257, | |
| "eval_steps_per_second": 4.31, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 5.890133831310303e-05, | |
| "loss": 2.2127, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "eval_loss": 2.532686233520508, | |
| "eval_runtime": 15.5343, | |
| "eval_samples_per_second": 68.3, | |
| "eval_steps_per_second": 4.313, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 5.81232492997199e-05, | |
| "loss": 2.2167, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "eval_loss": 2.5230135917663574, | |
| "eval_runtime": 15.5476, | |
| "eval_samples_per_second": 68.242, | |
| "eval_steps_per_second": 4.309, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 5.734516028633676e-05, | |
| "loss": 2.2039, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "eval_loss": 2.526108503341675, | |
| "eval_runtime": 15.3675, | |
| "eval_samples_per_second": 69.042, | |
| "eval_steps_per_second": 4.36, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 5.656707127295363e-05, | |
| "loss": 2.2052, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_loss": 2.51080322265625, | |
| "eval_runtime": 15.3426, | |
| "eval_samples_per_second": 69.154, | |
| "eval_steps_per_second": 4.367, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 5.57889822595705e-05, | |
| "loss": 2.2046, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "eval_loss": 2.515516757965088, | |
| "eval_runtime": 15.5617, | |
| "eval_samples_per_second": 68.18, | |
| "eval_steps_per_second": 4.305, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 5.501089324618737e-05, | |
| "loss": 2.2039, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "eval_loss": 2.5019383430480957, | |
| "eval_runtime": 15.5302, | |
| "eval_samples_per_second": 68.319, | |
| "eval_steps_per_second": 4.314, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 5.423280423280423e-05, | |
| "loss": 2.1989, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "eval_loss": 2.502457618713379, | |
| "eval_runtime": 15.5947, | |
| "eval_samples_per_second": 68.036, | |
| "eval_steps_per_second": 4.296, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 5.34547152194211e-05, | |
| "loss": 2.1928, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "eval_loss": 2.513399362564087, | |
| "eval_runtime": 15.4282, | |
| "eval_samples_per_second": 68.77, | |
| "eval_steps_per_second": 4.343, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 5.2676626206037974e-05, | |
| "loss": 2.1999, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "eval_loss": 2.4870197772979736, | |
| "eval_runtime": 15.5839, | |
| "eval_samples_per_second": 68.083, | |
| "eval_steps_per_second": 4.299, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 5.189853719265484e-05, | |
| "loss": 2.1949, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "eval_loss": 2.4832944869995117, | |
| "eval_runtime": 15.427, | |
| "eval_samples_per_second": 68.776, | |
| "eval_steps_per_second": 4.343, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 5.112044817927171e-05, | |
| "loss": 2.1902, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "eval_loss": 2.4658384323120117, | |
| "eval_runtime": 16.5822, | |
| "eval_samples_per_second": 63.984, | |
| "eval_steps_per_second": 4.04, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 5.034235916588857e-05, | |
| "loss": 2.1952, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "eval_loss": 2.4997782707214355, | |
| "eval_runtime": 15.5692, | |
| "eval_samples_per_second": 68.147, | |
| "eval_steps_per_second": 4.303, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 4.956427015250545e-05, | |
| "loss": 2.1879, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "eval_loss": 2.4686079025268555, | |
| "eval_runtime": 15.6574, | |
| "eval_samples_per_second": 67.764, | |
| "eval_steps_per_second": 4.279, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 4.8786181139122314e-05, | |
| "loss": 2.1847, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "eval_loss": 2.4735190868377686, | |
| "eval_runtime": 15.8166, | |
| "eval_samples_per_second": 67.081, | |
| "eval_steps_per_second": 4.236, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 4.8008092125739185e-05, | |
| "loss": 2.1908, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "eval_loss": 2.4766366481781006, | |
| "eval_runtime": 15.5592, | |
| "eval_samples_per_second": 68.191, | |
| "eval_steps_per_second": 4.306, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 4.7230003112356056e-05, | |
| "loss": 2.1865, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "eval_loss": 2.4564003944396973, | |
| "eval_runtime": 15.984, | |
| "eval_samples_per_second": 66.379, | |
| "eval_steps_per_second": 4.192, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 4.6451914098972927e-05, | |
| "loss": 2.1785, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "eval_loss": 2.4674360752105713, | |
| "eval_runtime": 16.0232, | |
| "eval_samples_per_second": 66.216, | |
| "eval_steps_per_second": 4.181, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 4.56738250855898e-05, | |
| "loss": 2.1871, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "eval_loss": 2.4695048332214355, | |
| "eval_runtime": 16.0422, | |
| "eval_samples_per_second": 66.138, | |
| "eval_steps_per_second": 4.176, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 4.489573607220666e-05, | |
| "loss": 2.1739, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "eval_loss": 2.457801580429077, | |
| "eval_runtime": 15.9657, | |
| "eval_samples_per_second": 66.455, | |
| "eval_steps_per_second": 4.196, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 4.411764705882353e-05, | |
| "loss": 2.1805, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "eval_loss": 2.463817834854126, | |
| "eval_runtime": 15.9774, | |
| "eval_samples_per_second": 66.406, | |
| "eval_steps_per_second": 4.193, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 4.3339558045440396e-05, | |
| "loss": 2.2247, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "eval_loss": 2.4646642208099365, | |
| "eval_runtime": 15.9901, | |
| "eval_samples_per_second": 66.354, | |
| "eval_steps_per_second": 4.19, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 4.2561469032057274e-05, | |
| "loss": 2.1644, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "eval_loss": 2.474022626876831, | |
| "eval_runtime": 16.055, | |
| "eval_samples_per_second": 66.086, | |
| "eval_steps_per_second": 4.173, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 4.178338001867414e-05, | |
| "loss": 2.1618, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "eval_loss": 2.447143793106079, | |
| "eval_runtime": 16.0407, | |
| "eval_samples_per_second": 66.144, | |
| "eval_steps_per_second": 4.177, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 4.100529100529101e-05, | |
| "loss": 2.1693, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "eval_loss": 2.455711603164673, | |
| "eval_runtime": 16.0024, | |
| "eval_samples_per_second": 66.303, | |
| "eval_steps_per_second": 4.187, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 4.022720199190787e-05, | |
| "loss": 2.1701, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "eval_loss": 2.430957555770874, | |
| "eval_runtime": 15.9813, | |
| "eval_samples_per_second": 66.39, | |
| "eval_steps_per_second": 4.192, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 3.9449112978524744e-05, | |
| "loss": 2.1731, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "eval_loss": 2.437666177749634, | |
| "eval_runtime": 16.0682, | |
| "eval_samples_per_second": 66.031, | |
| "eval_steps_per_second": 4.17, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 3.8671023965141615e-05, | |
| "loss": 2.1645, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "eval_loss": 2.4568722248077393, | |
| "eval_runtime": 16.0303, | |
| "eval_samples_per_second": 66.187, | |
| "eval_steps_per_second": 4.18, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 3.7892934951758485e-05, | |
| "loss": 2.1662, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "eval_loss": 2.4170446395874023, | |
| "eval_runtime": 16.0751, | |
| "eval_samples_per_second": 66.003, | |
| "eval_steps_per_second": 4.168, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 3.7114845938375356e-05, | |
| "loss": 2.1583, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "eval_loss": 2.4338526725769043, | |
| "eval_runtime": 16.1091, | |
| "eval_samples_per_second": 65.863, | |
| "eval_steps_per_second": 4.159, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 3.633675692499222e-05, | |
| "loss": 2.166, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "eval_loss": 2.426081418991089, | |
| "eval_runtime": 15.5957, | |
| "eval_samples_per_second": 68.032, | |
| "eval_steps_per_second": 4.296, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 3.555866791160909e-05, | |
| "loss": 2.1651, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "eval_loss": 2.425640821456909, | |
| "eval_runtime": 15.6372, | |
| "eval_samples_per_second": 67.851, | |
| "eval_steps_per_second": 4.285, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 3.4780578898225955e-05, | |
| "loss": 2.1613, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "eval_loss": 2.421271562576294, | |
| "eval_runtime": 15.6082, | |
| "eval_samples_per_second": 67.977, | |
| "eval_steps_per_second": 4.293, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 3.4002489884842826e-05, | |
| "loss": 2.1558, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "eval_loss": 2.42092227935791, | |
| "eval_runtime": 15.5906, | |
| "eval_samples_per_second": 68.054, | |
| "eval_steps_per_second": 4.297, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 3.32244008714597e-05, | |
| "loss": 2.1633, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "eval_loss": 2.4205520153045654, | |
| "eval_runtime": 15.5971, | |
| "eval_samples_per_second": 68.025, | |
| "eval_steps_per_second": 4.296, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 3.244631185807657e-05, | |
| "loss": 2.1592, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "eval_loss": 2.3962574005126953, | |
| "eval_runtime": 15.6355, | |
| "eval_samples_per_second": 67.858, | |
| "eval_steps_per_second": 4.285, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 3.166822284469343e-05, | |
| "loss": 2.1534, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "eval_loss": 2.4084994792938232, | |
| "eval_runtime": 15.9803, | |
| "eval_samples_per_second": 66.394, | |
| "eval_steps_per_second": 4.193, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 3.08901338313103e-05, | |
| "loss": 2.1529, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "eval_loss": 2.410832643508911, | |
| "eval_runtime": 16.3795, | |
| "eval_samples_per_second": 64.776, | |
| "eval_steps_per_second": 4.09, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 3.011204481792717e-05, | |
| "loss": 2.1472, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "eval_loss": 2.3861536979675293, | |
| "eval_runtime": 16.1053, | |
| "eval_samples_per_second": 65.879, | |
| "eval_steps_per_second": 4.16, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 2.9333955804544037e-05, | |
| "loss": 2.1589, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "eval_loss": 2.401296854019165, | |
| "eval_runtime": 15.9187, | |
| "eval_samples_per_second": 66.651, | |
| "eval_steps_per_second": 4.209, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 2.855586679116091e-05, | |
| "loss": 2.1411, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "eval_loss": 2.404986619949341, | |
| "eval_runtime": 15.9451, | |
| "eval_samples_per_second": 66.541, | |
| "eval_steps_per_second": 4.202, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 2.1483, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "eval_loss": 2.4035959243774414, | |
| "eval_runtime": 16.0523, | |
| "eval_samples_per_second": 66.096, | |
| "eval_steps_per_second": 4.174, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 2.699968876439465e-05, | |
| "loss": 2.1497, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "eval_loss": 2.4140477180480957, | |
| "eval_runtime": 16.0149, | |
| "eval_samples_per_second": 66.251, | |
| "eval_steps_per_second": 4.184, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 2.6221599751011517e-05, | |
| "loss": 2.1405, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "eval_loss": 2.3900160789489746, | |
| "eval_runtime": 15.9313, | |
| "eval_samples_per_second": 66.598, | |
| "eval_steps_per_second": 4.206, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 2.5443510737628385e-05, | |
| "loss": 2.1419, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "eval_loss": 2.3757221698760986, | |
| "eval_runtime": 16.0352, | |
| "eval_samples_per_second": 66.167, | |
| "eval_steps_per_second": 4.178, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 2.4665421724245256e-05, | |
| "loss": 2.1407, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "eval_loss": 2.3808810710906982, | |
| "eval_runtime": 15.9424, | |
| "eval_samples_per_second": 66.552, | |
| "eval_steps_per_second": 4.203, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 2.3887332710862123e-05, | |
| "loss": 2.1427, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "eval_loss": 2.379969835281372, | |
| "eval_runtime": 15.7805, | |
| "eval_samples_per_second": 67.235, | |
| "eval_steps_per_second": 4.246, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 2.3109243697478994e-05, | |
| "loss": 2.1414, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "eval_loss": 2.3836679458618164, | |
| "eval_runtime": 16.0084, | |
| "eval_samples_per_second": 66.278, | |
| "eval_steps_per_second": 4.185, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 2.233115468409586e-05, | |
| "loss": 2.1429, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "eval_loss": 2.3959357738494873, | |
| "eval_runtime": 16.0313, | |
| "eval_samples_per_second": 66.183, | |
| "eval_steps_per_second": 4.179, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 2.155306567071273e-05, | |
| "loss": 2.1746, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "eval_loss": 2.3913469314575195, | |
| "eval_runtime": 16.0943, | |
| "eval_samples_per_second": 65.924, | |
| "eval_steps_per_second": 4.163, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 2.07749766573296e-05, | |
| "loss": 2.1257, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "eval_loss": 2.3878540992736816, | |
| "eval_runtime": 16.055, | |
| "eval_samples_per_second": 66.085, | |
| "eval_steps_per_second": 4.173, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 1.9996887643946467e-05, | |
| "loss": 2.1367, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "eval_loss": 2.381118059158325, | |
| "eval_runtime": 16.0622, | |
| "eval_samples_per_second": 66.056, | |
| "eval_steps_per_second": 4.171, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 1.9218798630563338e-05, | |
| "loss": 2.1319, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "eval_loss": 2.379357099533081, | |
| "eval_runtime": 16.1235, | |
| "eval_samples_per_second": 65.804, | |
| "eval_steps_per_second": 4.155, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 1.844070961718021e-05, | |
| "loss": 2.13, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "eval_loss": 2.401723861694336, | |
| "eval_runtime": 16.3123, | |
| "eval_samples_per_second": 65.043, | |
| "eval_steps_per_second": 4.107, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 1.7662620603797076e-05, | |
| "loss": 2.1344, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "eval_loss": 2.3839223384857178, | |
| "eval_runtime": 15.4787, | |
| "eval_samples_per_second": 68.546, | |
| "eval_steps_per_second": 4.329, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 1.6884531590413944e-05, | |
| "loss": 2.1345, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "eval_loss": 2.3824682235717773, | |
| "eval_runtime": 15.4877, | |
| "eval_samples_per_second": 68.506, | |
| "eval_steps_per_second": 4.326, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 1.6106442577030814e-05, | |
| "loss": 2.128, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "eval_loss": 2.3865807056427, | |
| "eval_runtime": 15.4809, | |
| "eval_samples_per_second": 68.536, | |
| "eval_steps_per_second": 4.328, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 1.5328353563647682e-05, | |
| "loss": 2.1254, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "eval_loss": 2.365614414215088, | |
| "eval_runtime": 15.5033, | |
| "eval_samples_per_second": 68.437, | |
| "eval_steps_per_second": 4.322, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 1.455026455026455e-05, | |
| "loss": 2.127, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "eval_loss": 2.3737831115722656, | |
| "eval_runtime": 15.4797, | |
| "eval_samples_per_second": 68.541, | |
| "eval_steps_per_second": 4.328, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 1.377217553688142e-05, | |
| "loss": 2.1254, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "eval_loss": 2.3705029487609863, | |
| "eval_runtime": 15.5162, | |
| "eval_samples_per_second": 68.38, | |
| "eval_steps_per_second": 4.318, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 1.299408652349829e-05, | |
| "loss": 2.1221, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "eval_loss": 2.3749847412109375, | |
| "eval_runtime": 15.5114, | |
| "eval_samples_per_second": 68.401, | |
| "eval_steps_per_second": 4.319, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 1.2215997510115158e-05, | |
| "loss": 2.1257, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "eval_loss": 2.373291015625, | |
| "eval_runtime": 15.5367, | |
| "eval_samples_per_second": 68.29, | |
| "eval_steps_per_second": 4.312, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 1.1437908496732026e-05, | |
| "loss": 2.1234, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "eval_loss": 2.352591037750244, | |
| "eval_runtime": 15.5395, | |
| "eval_samples_per_second": 68.278, | |
| "eval_steps_per_second": 4.312, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 1.0659819483348895e-05, | |
| "loss": 2.1267, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "eval_loss": 2.377469062805176, | |
| "eval_runtime": 16.3047, | |
| "eval_samples_per_second": 65.073, | |
| "eval_steps_per_second": 4.109, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 9.881730469965766e-06, | |
| "loss": 2.1294, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "eval_loss": 2.3666629791259766, | |
| "eval_runtime": 15.4021, | |
| "eval_samples_per_second": 68.887, | |
| "eval_steps_per_second": 4.35, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 9.103641456582633e-06, | |
| "loss": 2.1131, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "eval_loss": 2.344421148300171, | |
| "eval_runtime": 15.4051, | |
| "eval_samples_per_second": 68.873, | |
| "eval_steps_per_second": 4.349, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 8.325552443199502e-06, | |
| "loss": 2.1213, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "eval_loss": 2.3720242977142334, | |
| "eval_runtime": 16.0393, | |
| "eval_samples_per_second": 66.15, | |
| "eval_steps_per_second": 4.177, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 7.547463429816372e-06, | |
| "loss": 2.1212, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "eval_loss": 2.3477375507354736, | |
| "eval_runtime": 15.4362, | |
| "eval_samples_per_second": 68.735, | |
| "eval_steps_per_second": 4.34, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 6.76937441643324e-06, | |
| "loss": 2.1168, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "eval_loss": 2.3393449783325195, | |
| "eval_runtime": 15.4423, | |
| "eval_samples_per_second": 68.708, | |
| "eval_steps_per_second": 4.339, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 5.991285403050109e-06, | |
| "loss": 2.1157, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "eval_loss": 2.3649890422821045, | |
| "eval_runtime": 15.7907, | |
| "eval_samples_per_second": 67.192, | |
| "eval_steps_per_second": 4.243, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 5.213196389666978e-06, | |
| "loss": 2.1162, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "eval_loss": 2.3481333255767822, | |
| "eval_runtime": 15.793, | |
| "eval_samples_per_second": 67.182, | |
| "eval_steps_per_second": 4.242, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 4.435107376283847e-06, | |
| "loss": 2.1188, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "eval_loss": 2.3730874061584473, | |
| "eval_runtime": 15.3826, | |
| "eval_samples_per_second": 68.974, | |
| "eval_steps_per_second": 4.356, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 3.657018362900716e-06, | |
| "loss": 2.1139, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "eval_loss": 2.367178440093994, | |
| "eval_runtime": 15.4036, | |
| "eval_samples_per_second": 68.88, | |
| "eval_steps_per_second": 4.35, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 2.878929349517585e-06, | |
| "loss": 2.1213, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "eval_loss": 2.3709657192230225, | |
| "eval_runtime": 15.3953, | |
| "eval_samples_per_second": 68.917, | |
| "eval_steps_per_second": 4.352, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 2.1008403361344543e-06, | |
| "loss": 2.122, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "eval_loss": 2.367561101913452, | |
| "eval_runtime": 15.38, | |
| "eval_samples_per_second": 68.986, | |
| "eval_steps_per_second": 4.356, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 1.3227513227513228e-06, | |
| "loss": 2.1172, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "eval_loss": 2.349937677383423, | |
| "eval_runtime": 15.3829, | |
| "eval_samples_per_second": 68.973, | |
| "eval_steps_per_second": 4.355, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "learning_rate": 5.446623093681918e-07, | |
| "loss": 2.1163, | |
| "step": 6950 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "eval_loss": 2.341893434524536, | |
| "eval_runtime": 15.6393, | |
| "eval_samples_per_second": 67.842, | |
| "eval_steps_per_second": 4.284, | |
| "step": 6950 | |
| } | |
| ], | |
| "max_steps": 6985, | |
| "num_train_epochs": 5, | |
| "total_flos": 1.3273460503020749e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |