| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 400, | |
| "global_step": 21234, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.992935857586889e-05, | |
| "loss": 14.6395, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.985871715173778e-05, | |
| "loss": 8.6304, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.978807572760667e-05, | |
| "loss": 6.1691, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.9717434303475558e-05, | |
| "loss": 5.4462, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.964679287934445e-05, | |
| "loss": 4.827, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.9576151455213337e-05, | |
| "loss": 4.2751, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.9505510031082228e-05, | |
| "loss": 3.9951, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 2.9434868606951115e-05, | |
| "loss": 3.8793, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.5431909561157227, | |
| "eval_runtime": 146.3919, | |
| "eval_samples_per_second": 51.499, | |
| "eval_steps_per_second": 6.442, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 2.9364227182820006e-05, | |
| "loss": 3.5368, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 2.9293585758688894e-05, | |
| "loss": 3.243, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 2.9222944334557785e-05, | |
| "loss": 3.3564, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 2.9152302910426676e-05, | |
| "loss": 3.1593, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 2.9081661486295564e-05, | |
| "loss": 2.9504, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 2.901102006216445e-05, | |
| "loss": 2.6833, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 2.8940378638033346e-05, | |
| "loss": 2.5516, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 2.8869737213902233e-05, | |
| "loss": 2.3584, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 2.064560651779175, | |
| "eval_runtime": 146.3705, | |
| "eval_samples_per_second": 51.506, | |
| "eval_steps_per_second": 6.443, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 2.879909578977112e-05, | |
| "loss": 2.3706, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 2.8728454365640012e-05, | |
| "loss": 2.3712, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 2.8657812941508903e-05, | |
| "loss": 2.454, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 2.858717151737779e-05, | |
| "loss": 2.3754, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 2.851653009324668e-05, | |
| "loss": 2.2086, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2.844588866911557e-05, | |
| "loss": 2.4654, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2.837524724498446e-05, | |
| "loss": 2.2728, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 2.8304605820853348e-05, | |
| "loss": 2.1175, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 1.9099233150482178, | |
| "eval_runtime": 146.2849, | |
| "eval_samples_per_second": 51.536, | |
| "eval_steps_per_second": 6.446, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 2.823396439672224e-05, | |
| "loss": 1.9796, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 2.8163322972591127e-05, | |
| "loss": 2.1218, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 2.8092681548460018e-05, | |
| "loss": 2.0264, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 2.802204012432891e-05, | |
| "loss": 2.0893, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 2.7951398700197796e-05, | |
| "loss": 2.0299, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 2.7880757276066684e-05, | |
| "loss": 1.8765, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 2.781011585193558e-05, | |
| "loss": 1.8572, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 2.7739474427804466e-05, | |
| "loss": 1.7761, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 1.8229914903640747, | |
| "eval_runtime": 146.5454, | |
| "eval_samples_per_second": 51.445, | |
| "eval_steps_per_second": 6.435, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 2.7668833003673354e-05, | |
| "loss": 1.7773, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 2.7598191579542245e-05, | |
| "loss": 1.8014, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 2.7527550155411136e-05, | |
| "loss": 1.8682, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 2.7456908731280023e-05, | |
| "loss": 1.9171, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 2.7386267307148914e-05, | |
| "loss": 1.7615, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 2.7315625883017802e-05, | |
| "loss": 1.7201, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 2.7244984458886693e-05, | |
| "loss": 1.6485, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 2.717434303475558e-05, | |
| "loss": 1.6427, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 1.7565761804580688, | |
| "eval_runtime": 146.4911, | |
| "eval_samples_per_second": 51.464, | |
| "eval_steps_per_second": 6.437, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 2.710370161062447e-05, | |
| "loss": 1.9137, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 2.703306018649336e-05, | |
| "loss": 1.8964, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 2.696241876236225e-05, | |
| "loss": 1.7006, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 2.689177733823114e-05, | |
| "loss": 1.7578, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 2.682113591410003e-05, | |
| "loss": 1.7194, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 2.6750494489968917e-05, | |
| "loss": 1.8679, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2.667985306583781e-05, | |
| "loss": 1.5503, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 2.66092116417067e-05, | |
| "loss": 1.5331, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 1.6002424955368042, | |
| "eval_runtime": 146.4497, | |
| "eval_samples_per_second": 51.478, | |
| "eval_steps_per_second": 6.439, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 2.6538570217575586e-05, | |
| "loss": 1.5046, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 2.6467928793444477e-05, | |
| "loss": 1.4923, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 2.6397287369313365e-05, | |
| "loss": 1.4884, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 2.6326645945182256e-05, | |
| "loss": 1.4889, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 2.6256004521051143e-05, | |
| "loss": 1.4259, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 2.6185363096920034e-05, | |
| "loss": 1.4368, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 2.6114721672788922e-05, | |
| "loss": 1.3874, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2.6044080248657813e-05, | |
| "loss": 1.2631, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.2792493104934692, | |
| "eval_runtime": 146.3888, | |
| "eval_samples_per_second": 51.5, | |
| "eval_steps_per_second": 6.442, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2.5973438824526704e-05, | |
| "loss": 1.3781, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 2.5902797400395592e-05, | |
| "loss": 1.2868, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 2.583215597626448e-05, | |
| "loss": 1.3965, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 2.5761514552133374e-05, | |
| "loss": 1.1789, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 2.569087312800226e-05, | |
| "loss": 1.1915, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 2.562023170387115e-05, | |
| "loss": 1.1582, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2.554959027974004e-05, | |
| "loss": 1.3444, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2.547894885560893e-05, | |
| "loss": 1.3403, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 1.1806565523147583, | |
| "eval_runtime": 146.4657, | |
| "eval_samples_per_second": 51.473, | |
| "eval_steps_per_second": 6.438, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2.540830743147782e-05, | |
| "loss": 1.2903, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.533766600734671e-05, | |
| "loss": 1.2086, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.5267024583215597e-05, | |
| "loss": 1.2047, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.519638315908449e-05, | |
| "loss": 1.1538, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.5125741734953376e-05, | |
| "loss": 1.184, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.5055100310822267e-05, | |
| "loss": 1.0577, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.4984458886691155e-05, | |
| "loss": 1.1838, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 2.4913817462560046e-05, | |
| "loss": 1.1105, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 1.1069550514221191, | |
| "eval_runtime": 146.67, | |
| "eval_samples_per_second": 51.401, | |
| "eval_steps_per_second": 6.429, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.4843176038428937e-05, | |
| "loss": 1.0968, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.4772534614297824e-05, | |
| "loss": 1.0911, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.4701893190166712e-05, | |
| "loss": 0.9316, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.4631251766035606e-05, | |
| "loss": 1.1932, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.4560610341904494e-05, | |
| "loss": 1.1092, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.448996891777338e-05, | |
| "loss": 0.9679, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.4419327493642273e-05, | |
| "loss": 1.0059, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 2.4348686069511164e-05, | |
| "loss": 1.1187, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 1.0644315481185913, | |
| "eval_runtime": 146.3933, | |
| "eval_samples_per_second": 51.498, | |
| "eval_steps_per_second": 6.442, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 2.427804464538005e-05, | |
| "loss": 1.0207, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2.420740322124894e-05, | |
| "loss": 1.074, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 2.413676179711783e-05, | |
| "loss": 1.0159, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 2.406612037298672e-05, | |
| "loss": 1.0128, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 2.399547894885561e-05, | |
| "loss": 1.0398, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 2.39248375247245e-05, | |
| "loss": 1.0713, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 2.3854196100593387e-05, | |
| "loss": 0.9827, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 2.378355467646228e-05, | |
| "loss": 1.0307, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 1.053775668144226, | |
| "eval_runtime": 146.3869, | |
| "eval_samples_per_second": 51.501, | |
| "eval_steps_per_second": 6.442, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 2.371291325233117e-05, | |
| "loss": 0.9596, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2.3642271828200057e-05, | |
| "loss": 0.9598, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2.3571630404068945e-05, | |
| "loss": 0.9912, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 2.350098897993784e-05, | |
| "loss": 0.9629, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 2.3430347555806727e-05, | |
| "loss": 0.9623, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 2.3359706131675614e-05, | |
| "loss": 0.9315, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.3289064707544505e-05, | |
| "loss": 0.9403, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.3218423283413396e-05, | |
| "loss": 0.9285, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 1.0219874382019043, | |
| "eval_runtime": 146.3894, | |
| "eval_samples_per_second": 51.5, | |
| "eval_steps_per_second": 6.442, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.3147781859282284e-05, | |
| "loss": 0.8947, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.307714043515117e-05, | |
| "loss": 0.9009, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.3006499011020063e-05, | |
| "loss": 0.888, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.2935857586888954e-05, | |
| "loss": 0.9096, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.286521616275784e-05, | |
| "loss": 0.926, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.2794574738626732e-05, | |
| "loss": 0.9217, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.272393331449562e-05, | |
| "loss": 0.9105, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.2653291890364508e-05, | |
| "loss": 0.8917, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 0.9944532513618469, | |
| "eval_runtime": 146.4135, | |
| "eval_samples_per_second": 51.491, | |
| "eval_steps_per_second": 6.441, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 2.2582650466233402e-05, | |
| "loss": 0.8959, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 2.251200904210229e-05, | |
| "loss": 0.8332, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 2.2441367617971177e-05, | |
| "loss": 0.9235, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 2.2370726193840068e-05, | |
| "loss": 0.7935, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 2.230008476970896e-05, | |
| "loss": 0.9101, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2.2229443345577847e-05, | |
| "loss": 0.9317, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2.2158801921446738e-05, | |
| "loss": 0.9412, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 2.2088160497315626e-05, | |
| "loss": 0.9018, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 0.961943507194519, | |
| "eval_runtime": 146.3492, | |
| "eval_samples_per_second": 51.514, | |
| "eval_steps_per_second": 6.443, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 2.2017519073184517e-05, | |
| "loss": 0.9469, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 2.1946877649053404e-05, | |
| "loss": 0.8957, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 2.1876236224922295e-05, | |
| "loss": 0.9212, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 2.1805594800791183e-05, | |
| "loss": 0.9815, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 2.1734953376660074e-05, | |
| "loss": 0.8364, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 2.1664311952528965e-05, | |
| "loss": 0.9239, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 2.1593670528397852e-05, | |
| "loss": 0.8507, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 2.152302910426674e-05, | |
| "loss": 0.8455, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 0.9640973210334778, | |
| "eval_runtime": 146.216, | |
| "eval_samples_per_second": 51.561, | |
| "eval_steps_per_second": 6.449, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 2.1452387680135635e-05, | |
| "loss": 0.873, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 2.1381746256004522e-05, | |
| "loss": 0.9022, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 2.131110483187341e-05, | |
| "loss": 0.9067, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 2.12404634077423e-05, | |
| "loss": 0.8156, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 2.1169821983611192e-05, | |
| "loss": 0.7626, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 2.109918055948008e-05, | |
| "loss": 0.9551, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 2.1028539135348967e-05, | |
| "loss": 0.7957, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 2.0957897711217858e-05, | |
| "loss": 0.8259, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 0.9384291768074036, | |
| "eval_runtime": 146.2207, | |
| "eval_samples_per_second": 51.559, | |
| "eval_steps_per_second": 6.449, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.088725628708675e-05, | |
| "loss": 0.7219, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2.0816614862955637e-05, | |
| "loss": 0.8212, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.0745973438824528e-05, | |
| "loss": 0.7422, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.0675332014693415e-05, | |
| "loss": 0.8335, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 2.0604690590562306e-05, | |
| "loss": 0.8139, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 2.0534049166431197e-05, | |
| "loss": 0.8703, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 2.0463407742300085e-05, | |
| "loss": 0.9146, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 2.0392766318168973e-05, | |
| "loss": 0.7593, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 0.9210972785949707, | |
| "eval_runtime": 146.1977, | |
| "eval_samples_per_second": 51.567, | |
| "eval_steps_per_second": 6.45, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 2.0322124894037867e-05, | |
| "loss": 0.8349, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 2.0251483469906755e-05, | |
| "loss": 0.8791, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 2.0180842045775642e-05, | |
| "loss": 0.9861, | |
| "step": 6950 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 2.0110200621644533e-05, | |
| "loss": 0.7273, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 2.0039559197513424e-05, | |
| "loss": 0.8075, | |
| "step": 7050 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.9968917773382312e-05, | |
| "loss": 0.7553, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 1.98982763492512e-05, | |
| "loss": 0.7873, | |
| "step": 7150 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 1.982763492512009e-05, | |
| "loss": 0.8176, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_loss": 0.910588264465332, | |
| "eval_runtime": 146.2211, | |
| "eval_samples_per_second": 51.559, | |
| "eval_steps_per_second": 6.449, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 1.9756993500988982e-05, | |
| "loss": 0.7748, | |
| "step": 7250 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 1.968635207685787e-05, | |
| "loss": 0.8337, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 1.961571065272676e-05, | |
| "loss": 0.7968, | |
| "step": 7350 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 1.9545069228595648e-05, | |
| "loss": 0.7117, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 1.947442780446454e-05, | |
| "loss": 0.7323, | |
| "step": 7450 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 1.940378638033343e-05, | |
| "loss": 0.7593, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 1.9333144956202318e-05, | |
| "loss": 0.7826, | |
| "step": 7550 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 1.9262503532071205e-05, | |
| "loss": 0.881, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 0.8992499709129333, | |
| "eval_runtime": 146.4953, | |
| "eval_samples_per_second": 51.462, | |
| "eval_steps_per_second": 6.437, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 1.9191862107940096e-05, | |
| "loss": 0.6995, | |
| "step": 7650 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 1.9121220683808987e-05, | |
| "loss": 0.6882, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 1.9050579259677875e-05, | |
| "loss": 0.7669, | |
| "step": 7750 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 1.8979937835546766e-05, | |
| "loss": 0.7485, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 1.8909296411415654e-05, | |
| "loss": 0.8179, | |
| "step": 7850 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 1.8838654987284545e-05, | |
| "loss": 0.6935, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 1.8768013563153432e-05, | |
| "loss": 0.7565, | |
| "step": 7950 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 1.8697372139022323e-05, | |
| "loss": 0.7842, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "eval_loss": 0.8948126435279846, | |
| "eval_runtime": 146.2227, | |
| "eval_samples_per_second": 51.558, | |
| "eval_steps_per_second": 6.449, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 1.862673071489121e-05, | |
| "loss": 0.7082, | |
| "step": 8050 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 1.8556089290760102e-05, | |
| "loss": 0.712, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 1.8485447866628993e-05, | |
| "loss": 0.7024, | |
| "step": 8150 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 1.841480644249788e-05, | |
| "loss": 0.7146, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 1.8344165018366768e-05, | |
| "loss": 0.7073, | |
| "step": 8250 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 1.8273523594235663e-05, | |
| "loss": 0.72, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 1.820288217010455e-05, | |
| "loss": 0.7678, | |
| "step": 8350 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 1.8132240745973438e-05, | |
| "loss": 0.698, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "eval_loss": 0.8967130780220032, | |
| "eval_runtime": 146.58, | |
| "eval_samples_per_second": 51.433, | |
| "eval_steps_per_second": 6.433, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 1.806159932184233e-05, | |
| "loss": 0.6976, | |
| "step": 8450 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 1.799095789771122e-05, | |
| "loss": 0.74, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 1.7920316473580108e-05, | |
| "loss": 0.7858, | |
| "step": 8550 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 1.7849675049448995e-05, | |
| "loss": 0.6905, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 1.7779033625317886e-05, | |
| "loss": 0.7195, | |
| "step": 8650 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 1.7708392201186777e-05, | |
| "loss": 0.6889, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 1.7637750777055665e-05, | |
| "loss": 0.7499, | |
| "step": 8750 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 1.7567109352924556e-05, | |
| "loss": 0.649, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "eval_loss": 0.8673287630081177, | |
| "eval_runtime": 146.2981, | |
| "eval_samples_per_second": 51.532, | |
| "eval_steps_per_second": 6.446, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 1.7496467928793444e-05, | |
| "loss": 0.6689, | |
| "step": 8850 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 1.7425826504662335e-05, | |
| "loss": 0.7401, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 1.7355185080531226e-05, | |
| "loss": 0.6371, | |
| "step": 8950 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 1.7284543656400113e-05, | |
| "loss": 0.6743, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 1.7213902232269e-05, | |
| "loss": 0.7858, | |
| "step": 9050 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 1.7143260808137895e-05, | |
| "loss": 0.6682, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 1.7072619384006783e-05, | |
| "loss": 0.6313, | |
| "step": 9150 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 1.700197795987567e-05, | |
| "loss": 0.7243, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "eval_loss": 0.8753476738929749, | |
| "eval_runtime": 146.7694, | |
| "eval_samples_per_second": 51.366, | |
| "eval_steps_per_second": 6.425, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 1.693133653574456e-05, | |
| "loss": 0.723, | |
| "step": 9250 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 1.6860695111613453e-05, | |
| "loss": 0.6731, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 1.679005368748234e-05, | |
| "loss": 0.7232, | |
| "step": 9350 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 1.6719412263351228e-05, | |
| "loss": 0.802, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 1.664877083922012e-05, | |
| "loss": 0.7172, | |
| "step": 9450 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 1.657812941508901e-05, | |
| "loss": 0.6294, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 1.6507487990957897e-05, | |
| "loss": 0.6319, | |
| "step": 9550 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 1.643684656682679e-05, | |
| "loss": 0.7411, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_loss": 0.8756875991821289, | |
| "eval_runtime": 146.4905, | |
| "eval_samples_per_second": 51.464, | |
| "eval_steps_per_second": 6.437, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 1.6366205142695676e-05, | |
| "loss": 0.6805, | |
| "step": 9650 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 1.6295563718564567e-05, | |
| "loss": 0.7114, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 1.6224922294433458e-05, | |
| "loss": 0.6841, | |
| "step": 9750 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 1.6154280870302346e-05, | |
| "loss": 0.6689, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 1.6083639446171233e-05, | |
| "loss": 0.7589, | |
| "step": 9850 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.6012998022040128e-05, | |
| "loss": 0.7229, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 1.5942356597909015e-05, | |
| "loss": 0.6673, | |
| "step": 9950 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 1.5871715173777903e-05, | |
| "loss": 0.702, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "eval_loss": 0.8556445837020874, | |
| "eval_runtime": 146.5096, | |
| "eval_samples_per_second": 51.457, | |
| "eval_steps_per_second": 6.436, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 1.580107374964679e-05, | |
| "loss": 0.7646, | |
| "step": 10050 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 1.5730432325515685e-05, | |
| "loss": 0.7534, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 1.5659790901384573e-05, | |
| "loss": 0.6328, | |
| "step": 10150 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 1.558914947725346e-05, | |
| "loss": 0.62, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 1.551850805312235e-05, | |
| "loss": 0.6525, | |
| "step": 10250 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 1.544786662899124e-05, | |
| "loss": 0.7223, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 1.537722520486013e-05, | |
| "loss": 0.6904, | |
| "step": 10350 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 1.530658378072902e-05, | |
| "loss": 0.6655, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 0.8510493040084839, | |
| "eval_runtime": 146.5188, | |
| "eval_samples_per_second": 51.454, | |
| "eval_steps_per_second": 6.436, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 1.5235942356597909e-05, | |
| "loss": 0.6835, | |
| "step": 10450 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 1.5165300932466798e-05, | |
| "loss": 0.6766, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 1.5094659508335689e-05, | |
| "loss": 0.6127, | |
| "step": 10550 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 1.5024018084204578e-05, | |
| "loss": 0.6755, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 1.4953376660073466e-05, | |
| "loss": 0.749, | |
| "step": 10650 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 1.4882735235942357e-05, | |
| "loss": 0.6164, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 1.4812093811811246e-05, | |
| "loss": 0.6659, | |
| "step": 10750 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 1.4741452387680136e-05, | |
| "loss": 0.6577, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "eval_loss": 0.8637193441390991, | |
| "eval_runtime": 146.2948, | |
| "eval_samples_per_second": 51.533, | |
| "eval_steps_per_second": 6.446, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 1.4670810963549025e-05, | |
| "loss": 0.7381, | |
| "step": 10850 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 1.4600169539417916e-05, | |
| "loss": 0.6131, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 1.4529528115286804e-05, | |
| "loss": 0.6697, | |
| "step": 10950 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 1.4458886691155695e-05, | |
| "loss": 0.6415, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 1.4388245267024582e-05, | |
| "loss": 0.6193, | |
| "step": 11050 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 1.4317603842893473e-05, | |
| "loss": 0.6082, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 1.4246962418762363e-05, | |
| "loss": 0.7267, | |
| "step": 11150 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 1.4176320994631252e-05, | |
| "loss": 0.5725, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "eval_loss": 0.8456605076789856, | |
| "eval_runtime": 146.5267, | |
| "eval_samples_per_second": 51.451, | |
| "eval_steps_per_second": 6.436, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 1.4105679570500141e-05, | |
| "loss": 0.6639, | |
| "step": 11250 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 1.4035038146369032e-05, | |
| "loss": 0.6161, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 1.396439672223792e-05, | |
| "loss": 0.6083, | |
| "step": 11350 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 1.3893755298106811e-05, | |
| "loss": 0.5692, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 1.3823113873975699e-05, | |
| "loss": 0.6962, | |
| "step": 11450 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 1.375247244984459e-05, | |
| "loss": 0.6135, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 1.3681831025713479e-05, | |
| "loss": 0.6544, | |
| "step": 11550 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 1.3611189601582368e-05, | |
| "loss": 0.6225, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_loss": 0.8483865857124329, | |
| "eval_runtime": 146.5858, | |
| "eval_samples_per_second": 51.431, | |
| "eval_steps_per_second": 6.433, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 1.3540548177451258e-05, | |
| "loss": 0.6596, | |
| "step": 11650 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 1.3469906753320149e-05, | |
| "loss": 0.624, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 1.3399265329189036e-05, | |
| "loss": 0.6327, | |
| "step": 11750 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 1.3328623905057927e-05, | |
| "loss": 0.6095, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 1.3257982480926815e-05, | |
| "loss": 0.6864, | |
| "step": 11850 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 1.3187341056795706e-05, | |
| "loss": 0.7451, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 1.3116699632664595e-05, | |
| "loss": 0.6118, | |
| "step": 11950 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 1.3046058208533485e-05, | |
| "loss": 0.6571, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "eval_loss": 0.8351559638977051, | |
| "eval_runtime": 146.3219, | |
| "eval_samples_per_second": 51.523, | |
| "eval_steps_per_second": 6.445, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 1.2975416784402374e-05, | |
| "loss": 0.6203, | |
| "step": 12050 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 1.2904775360271263e-05, | |
| "loss": 0.7048, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 1.2834133936140153e-05, | |
| "loss": 0.6577, | |
| "step": 12150 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 1.2763492512009044e-05, | |
| "loss": 0.5403, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 1.2692851087877931e-05, | |
| "loss": 0.6941, | |
| "step": 12250 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 1.2622209663746822e-05, | |
| "loss": 0.6098, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 1.2551568239615712e-05, | |
| "loss": 0.5796, | |
| "step": 12350 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 1.2480926815484601e-05, | |
| "loss": 0.6302, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_loss": 0.8377495408058167, | |
| "eval_runtime": 146.3733, | |
| "eval_samples_per_second": 51.505, | |
| "eval_steps_per_second": 6.442, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 1.241028539135349e-05, | |
| "loss": 0.6653, | |
| "step": 12450 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 1.233964396722238e-05, | |
| "loss": 0.5894, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 1.2269002543091269e-05, | |
| "loss": 0.6507, | |
| "step": 12550 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 1.219836111896016e-05, | |
| "loss": 0.6557, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 1.2127719694829047e-05, | |
| "loss": 0.6185, | |
| "step": 12650 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 1.2057078270697937e-05, | |
| "loss": 0.5889, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 1.1986436846566828e-05, | |
| "loss": 0.6514, | |
| "step": 12750 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 1.1915795422435715e-05, | |
| "loss": 0.6231, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "eval_loss": 0.8342207670211792, | |
| "eval_runtime": 146.3255, | |
| "eval_samples_per_second": 51.522, | |
| "eval_steps_per_second": 6.445, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 1.1845153998304606e-05, | |
| "loss": 0.7848, | |
| "step": 12850 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 1.1774512574173494e-05, | |
| "loss": 0.762, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 1.1703871150042385e-05, | |
| "loss": 0.586, | |
| "step": 12950 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 1.1633229725911274e-05, | |
| "loss": 0.6209, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 1.1562588301780164e-05, | |
| "loss": 0.6537, | |
| "step": 13050 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 1.1491946877649053e-05, | |
| "loss": 0.5856, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 1.1421305453517944e-05, | |
| "loss": 0.7796, | |
| "step": 13150 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 1.1350664029386832e-05, | |
| "loss": 0.5718, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_loss": 0.8108465671539307, | |
| "eval_runtime": 146.303, | |
| "eval_samples_per_second": 51.53, | |
| "eval_steps_per_second": 6.446, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 1.1280022605255723e-05, | |
| "loss": 0.6347, | |
| "step": 13250 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 1.120938118112461e-05, | |
| "loss": 0.6508, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 1.1138739756993501e-05, | |
| "loss": 0.6238, | |
| "step": 13350 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 1.106809833286239e-05, | |
| "loss": 0.6448, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 1.099745690873128e-05, | |
| "loss": 0.6704, | |
| "step": 13450 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 1.092681548460017e-05, | |
| "loss": 0.574, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 1.085617406046906e-05, | |
| "loss": 0.7448, | |
| "step": 13550 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 1.0785532636337948e-05, | |
| "loss": 0.6936, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_loss": 0.8107577562332153, | |
| "eval_runtime": 146.3517, | |
| "eval_samples_per_second": 51.513, | |
| "eval_steps_per_second": 6.443, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.0714891212206839e-05, | |
| "loss": 0.6312, | |
| "step": 13650 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 1.0644249788075727e-05, | |
| "loss": 0.62, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 1.0573608363944618e-05, | |
| "loss": 0.686, | |
| "step": 13750 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 1.0502966939813507e-05, | |
| "loss": 0.7155, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 1.0432325515682396e-05, | |
| "loss": 0.6248, | |
| "step": 13850 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 1.0361684091551286e-05, | |
| "loss": 0.6356, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 1.0291042667420175e-05, | |
| "loss": 0.6264, | |
| "step": 13950 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 1.0220401243289064e-05, | |
| "loss": 0.6367, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "eval_loss": 0.8052195906639099, | |
| "eval_runtime": 146.3569, | |
| "eval_samples_per_second": 51.511, | |
| "eval_steps_per_second": 6.443, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 1.0149759819157955e-05, | |
| "loss": 0.5832, | |
| "step": 14050 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 1.0079118395026843e-05, | |
| "loss": 0.7692, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.0008476970895734e-05, | |
| "loss": 0.6246, | |
| "step": 14150 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 9.937835546764623e-06, | |
| "loss": 0.562, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 9.867194122633513e-06, | |
| "loss": 0.6346, | |
| "step": 14250 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 9.796552698502402e-06, | |
| "loss": 0.6442, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 9.725911274371291e-06, | |
| "loss": 0.534, | |
| "step": 14350 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 9.65526985024018e-06, | |
| "loss": 0.5806, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_loss": 0.815026044845581, | |
| "eval_runtime": 146.3828, | |
| "eval_samples_per_second": 51.502, | |
| "eval_steps_per_second": 6.442, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 9.584628426109072e-06, | |
| "loss": 0.5669, | |
| "step": 14450 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 9.51398700197796e-06, | |
| "loss": 0.5238, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 9.44334557784685e-06, | |
| "loss": 0.6376, | |
| "step": 14550 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 9.37270415371574e-06, | |
| "loss": 0.6301, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 9.302062729584629e-06, | |
| "loss": 0.5822, | |
| "step": 14650 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 9.231421305453518e-06, | |
| "loss": 0.533, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 9.160779881322408e-06, | |
| "loss": 0.5156, | |
| "step": 14750 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 9.090138457191297e-06, | |
| "loss": 0.6329, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "eval_loss": 0.8057652711868286, | |
| "eval_runtime": 146.3678, | |
| "eval_samples_per_second": 51.507, | |
| "eval_steps_per_second": 6.443, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 9.019497033060188e-06, | |
| "loss": 0.555, | |
| "step": 14850 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 8.948855608929076e-06, | |
| "loss": 0.546, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 8.878214184797967e-06, | |
| "loss": 0.6075, | |
| "step": 14950 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 8.807572760666856e-06, | |
| "loss": 0.5868, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 8.736931336535745e-06, | |
| "loss": 0.6193, | |
| "step": 15050 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 8.666289912404635e-06, | |
| "loss": 0.6052, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 8.595648488273524e-06, | |
| "loss": 0.6021, | |
| "step": 15150 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 8.525007064142413e-06, | |
| "loss": 0.5913, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "eval_loss": 0.8025009036064148, | |
| "eval_runtime": 146.3582, | |
| "eval_samples_per_second": 51.511, | |
| "eval_steps_per_second": 6.443, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 8.454365640011303e-06, | |
| "loss": 0.587, | |
| "step": 15250 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 8.383724215880192e-06, | |
| "loss": 0.5106, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 8.313082791749081e-06, | |
| "loss": 0.5606, | |
| "step": 15350 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 8.242441367617972e-06, | |
| "loss": 0.5843, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 8.17179994348686e-06, | |
| "loss": 0.5879, | |
| "step": 15450 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 8.101158519355751e-06, | |
| "loss": 0.5804, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 8.030517095224639e-06, | |
| "loss": 0.5332, | |
| "step": 15550 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 7.95987567109353e-06, | |
| "loss": 0.5891, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "eval_loss": 0.8068730235099792, | |
| "eval_runtime": 146.6368, | |
| "eval_samples_per_second": 51.413, | |
| "eval_steps_per_second": 6.431, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 7.889234246962419e-06, | |
| "loss": 0.6205, | |
| "step": 15650 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 7.818592822831308e-06, | |
| "loss": 0.5775, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 7.747951398700198e-06, | |
| "loss": 0.5515, | |
| "step": 15750 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 7.677309974569087e-06, | |
| "loss": 0.6581, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 7.606668550437977e-06, | |
| "loss": 0.5393, | |
| "step": 15850 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 7.536027126306867e-06, | |
| "loss": 0.6666, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 7.4653857021757565e-06, | |
| "loss": 0.6101, | |
| "step": 15950 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 7.394744278044646e-06, | |
| "loss": 0.5265, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "eval_loss": 0.7969786524772644, | |
| "eval_runtime": 146.4757, | |
| "eval_samples_per_second": 51.469, | |
| "eval_steps_per_second": 6.438, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 7.324102853913535e-06, | |
| "loss": 0.5849, | |
| "step": 16050 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 7.2534614297824245e-06, | |
| "loss": 0.4989, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 7.182820005651315e-06, | |
| "loss": 0.5835, | |
| "step": 16150 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 7.112178581520204e-06, | |
| "loss": 0.598, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 7.041537157389093e-06, | |
| "loss": 0.5479, | |
| "step": 16250 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 6.970895733257983e-06, | |
| "loss": 0.6026, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 6.900254309126873e-06, | |
| "loss": 0.4896, | |
| "step": 16350 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 6.829612884995762e-06, | |
| "loss": 0.6014, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "eval_loss": 0.7993112802505493, | |
| "eval_runtime": 146.4005, | |
| "eval_samples_per_second": 51.496, | |
| "eval_steps_per_second": 6.441, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 6.7589714608646515e-06, | |
| "loss": 0.6562, | |
| "step": 16450 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 6.688330036733541e-06, | |
| "loss": 0.5241, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 6.61768861260243e-06, | |
| "loss": 0.6455, | |
| "step": 16550 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 6.5470471884713194e-06, | |
| "loss": 0.5524, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 6.476405764340209e-06, | |
| "loss": 0.5883, | |
| "step": 16650 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 6.405764340209098e-06, | |
| "loss": 0.6005, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 6.335122916077988e-06, | |
| "loss": 0.6611, | |
| "step": 16750 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 6.264481491946878e-06, | |
| "loss": 0.5392, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "eval_loss": 0.8024877905845642, | |
| "eval_runtime": 146.2872, | |
| "eval_samples_per_second": 51.536, | |
| "eval_steps_per_second": 6.446, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 6.193840067815767e-06, | |
| "loss": 0.5831, | |
| "step": 16850 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 6.123198643684656e-06, | |
| "loss": 0.5662, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 6.052557219553546e-06, | |
| "loss": 0.5643, | |
| "step": 16950 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 5.981915795422436e-06, | |
| "loss": 0.6554, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 5.911274371291325e-06, | |
| "loss": 0.5664, | |
| "step": 17050 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 5.840632947160214e-06, | |
| "loss": 0.586, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 5.7699915230291046e-06, | |
| "loss": 0.53, | |
| "step": 17150 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 5.699350098897994e-06, | |
| "loss": 0.6073, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "eval_loss": 0.7982571125030518, | |
| "eval_runtime": 146.4741, | |
| "eval_samples_per_second": 51.47, | |
| "eval_steps_per_second": 6.438, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 5.628708674766883e-06, | |
| "loss": 0.5988, | |
| "step": 17250 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 5.5580672506357725e-06, | |
| "loss": 0.5899, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 5.487425826504663e-06, | |
| "loss": 0.5709, | |
| "step": 17350 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 5.416784402373552e-06, | |
| "loss": 0.6798, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 5.346142978242441e-06, | |
| "loss": 0.6366, | |
| "step": 17450 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 5.275501554111331e-06, | |
| "loss": 0.678, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 5.204860129980221e-06, | |
| "loss": 0.5061, | |
| "step": 17550 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 5.13421870584911e-06, | |
| "loss": 0.5536, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "eval_loss": 0.7959641814231873, | |
| "eval_runtime": 146.5594, | |
| "eval_samples_per_second": 51.44, | |
| "eval_steps_per_second": 6.434, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 5.0635772817179995e-06, | |
| "loss": 0.6453, | |
| "step": 17650 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 4.992935857586889e-06, | |
| "loss": 0.5388, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 4.922294433455779e-06, | |
| "loss": 0.5864, | |
| "step": 17750 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 4.851653009324668e-06, | |
| "loss": 0.5365, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 4.781011585193558e-06, | |
| "loss": 0.5472, | |
| "step": 17850 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 4.710370161062447e-06, | |
| "loss": 0.6661, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 4.639728736931336e-06, | |
| "loss": 0.6971, | |
| "step": 17950 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 4.5690873128002265e-06, | |
| "loss": 0.5196, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "eval_loss": 0.7836597561836243, | |
| "eval_runtime": 146.6328, | |
| "eval_samples_per_second": 51.414, | |
| "eval_steps_per_second": 6.431, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 4.498445888669116e-06, | |
| "loss": 0.6394, | |
| "step": 18050 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 4.427804464538005e-06, | |
| "loss": 0.4884, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 4.3571630404068945e-06, | |
| "loss": 0.514, | |
| "step": 18150 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 4.286521616275785e-06, | |
| "loss": 0.5209, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 4.215880192144674e-06, | |
| "loss": 0.5669, | |
| "step": 18250 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 4.145238768013563e-06, | |
| "loss": 0.5224, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 4.074597343882453e-06, | |
| "loss": 0.5607, | |
| "step": 18350 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 4.003955919751343e-06, | |
| "loss": 0.5776, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "eval_loss": 0.7881141901016235, | |
| "eval_runtime": 146.3758, | |
| "eval_samples_per_second": 51.504, | |
| "eval_steps_per_second": 6.442, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 3.933314495620232e-06, | |
| "loss": 0.5759, | |
| "step": 18450 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 3.8626730714891214e-06, | |
| "loss": 0.5871, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 3.7920316473580103e-06, | |
| "loss": 0.5992, | |
| "step": 18550 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 3.7213902232269e-06, | |
| "loss": 0.5106, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 3.65074879909579e-06, | |
| "loss": 0.5211, | |
| "step": 18650 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 3.580107374964679e-06, | |
| "loss": 0.5794, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 3.509465950833569e-06, | |
| "loss": 0.6017, | |
| "step": 18750 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 3.4388245267024582e-06, | |
| "loss": 0.5981, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "eval_loss": 0.7939748167991638, | |
| "eval_runtime": 146.5246, | |
| "eval_samples_per_second": 51.452, | |
| "eval_steps_per_second": 6.436, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 3.368183102571348e-06, | |
| "loss": 0.6937, | |
| "step": 18850 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 3.2975416784402373e-06, | |
| "loss": 0.6696, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 3.226900254309127e-06, | |
| "loss": 0.639, | |
| "step": 18950 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 3.1562588301780164e-06, | |
| "loss": 0.5565, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 3.085617406046906e-06, | |
| "loss": 0.4692, | |
| "step": 19050 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 3.0149759819157954e-06, | |
| "loss": 0.5703, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 2.944334557784685e-06, | |
| "loss": 0.4944, | |
| "step": 19150 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 2.8736931336535745e-06, | |
| "loss": 0.6101, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "eval_loss": 0.7930362224578857, | |
| "eval_runtime": 146.3443, | |
| "eval_samples_per_second": 51.515, | |
| "eval_steps_per_second": 6.444, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 2.8030517095224643e-06, | |
| "loss": 0.59, | |
| "step": 19250 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 2.7324102853913536e-06, | |
| "loss": 0.5799, | |
| "step": 19300 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 2.6617688612602433e-06, | |
| "loss": 0.5569, | |
| "step": 19350 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 2.5911274371291327e-06, | |
| "loss": 0.5548, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 2.5204860129980224e-06, | |
| "loss": 0.5544, | |
| "step": 19450 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 2.4498445888669117e-06, | |
| "loss": 0.6427, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 2.3792031647358015e-06, | |
| "loss": 0.5027, | |
| "step": 19550 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 2.308561740604691e-06, | |
| "loss": 0.5696, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "eval_loss": 0.7890626192092896, | |
| "eval_runtime": 146.5527, | |
| "eval_samples_per_second": 51.442, | |
| "eval_steps_per_second": 6.435, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 2.2379203164735806e-06, | |
| "loss": 0.509, | |
| "step": 19650 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 2.1672788923424695e-06, | |
| "loss": 0.5078, | |
| "step": 19700 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 2.096637468211359e-06, | |
| "loss": 0.563, | |
| "step": 19750 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 2.0259960440802485e-06, | |
| "loss": 0.6039, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 1.955354619949138e-06, | |
| "loss": 0.5289, | |
| "step": 19850 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 1.8847131958180278e-06, | |
| "loss": 0.5394, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 1.8140717716869174e-06, | |
| "loss": 0.6539, | |
| "step": 19950 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 1.743430347555807e-06, | |
| "loss": 0.563, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "eval_loss": 0.7903943657875061, | |
| "eval_runtime": 146.7425, | |
| "eval_samples_per_second": 51.376, | |
| "eval_steps_per_second": 6.426, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 1.6727889234246962e-06, | |
| "loss": 0.5043, | |
| "step": 20050 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 1.6021474992935858e-06, | |
| "loss": 0.5243, | |
| "step": 20100 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 1.5315060751624753e-06, | |
| "loss": 0.6144, | |
| "step": 20150 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 1.4608646510313648e-06, | |
| "loss": 0.5324, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 1.3902232269002544e-06, | |
| "loss": 0.5494, | |
| "step": 20250 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 1.319581802769144e-06, | |
| "loss": 0.5302, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 1.2489403786380335e-06, | |
| "loss": 0.6458, | |
| "step": 20350 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 1.178298954506923e-06, | |
| "loss": 0.5361, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "eval_loss": 0.7929331660270691, | |
| "eval_runtime": 146.7924, | |
| "eval_samples_per_second": 51.358, | |
| "eval_steps_per_second": 6.424, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 1.1076575303758125e-06, | |
| "loss": 0.5857, | |
| "step": 20450 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 1.037016106244702e-06, | |
| "loss": 0.5542, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 9.663746821135916e-07, | |
| "loss": 0.6382, | |
| "step": 20550 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 8.957332579824809e-07, | |
| "loss": 0.5708, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 8.250918338513705e-07, | |
| "loss": 0.5726, | |
| "step": 20650 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 7.5445040972026e-07, | |
| "loss": 0.5438, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 6.838089855891495e-07, | |
| "loss": 0.5833, | |
| "step": 20750 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 6.13167561458039e-07, | |
| "loss": 0.5654, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "eval_loss": 0.7940900325775146, | |
| "eval_runtime": 146.3661, | |
| "eval_samples_per_second": 51.508, | |
| "eval_steps_per_second": 6.443, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 5.425261373269285e-07, | |
| "loss": 0.5341, | |
| "step": 20850 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 4.7188471319581804e-07, | |
| "loss": 0.5934, | |
| "step": 20900 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 4.012432890647076e-07, | |
| "loss": 0.6293, | |
| "step": 20950 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 3.3060186493359706e-07, | |
| "loss": 0.6117, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 2.5996044080248655e-07, | |
| "loss": 0.602, | |
| "step": 21050 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 1.8931901667137608e-07, | |
| "loss": 0.538, | |
| "step": 21100 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 1.1867759254026561e-07, | |
| "loss": 0.5409, | |
| "step": 21150 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4.803616840915513e-08, | |
| "loss": 0.5808, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.7935702800750732, | |
| "eval_runtime": 146.4206, | |
| "eval_samples_per_second": 51.489, | |
| "eval_steps_per_second": 6.44, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 21234, | |
| "total_flos": 9.26174715028439e+16, | |
| "train_loss": 0.9690902242330864, | |
| "train_runtime": 18755.4157, | |
| "train_samples_per_second": 9.056, | |
| "train_steps_per_second": 1.132 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 21234, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 400, | |
| "total_flos": 9.26174715028439e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |