| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 107670, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.9953561809231916e-05, | |
| "loss": 2.0977, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.990712361846382e-05, | |
| "loss": 2.0174, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.986068542769574e-05, | |
| "loss": 1.9844, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.9814247236927655e-05, | |
| "loss": 1.9164, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.976780904615956e-05, | |
| "loss": 1.9451, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.9721370855391474e-05, | |
| "loss": 1.8884, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.967493266462339e-05, | |
| "loss": 1.9468, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.96284944738553e-05, | |
| "loss": 1.9071, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.9582056283087214e-05, | |
| "loss": 1.9196, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.953561809231913e-05, | |
| "loss": 1.9623, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_gen_len": 18.999625972471573, | |
| "eval_loss": 1.7499970197677612, | |
| "eval_rouge1": 24.1039, | |
| "eval_rouge2": 11.368, | |
| "eval_rougeL": 19.813, | |
| "eval_rougeLsum": 22.671, | |
| "eval_runtime": 1022.1998, | |
| "eval_samples_per_second": 13.078, | |
| "eval_steps_per_second": 1.635, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.948917990155103e-05, | |
| "loss": 1.9252, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.944274171078295e-05, | |
| "loss": 1.9163, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.9396303520014866e-05, | |
| "loss": 1.9168, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.934986532924677e-05, | |
| "loss": 1.9531, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.9303427138478686e-05, | |
| "loss": 1.9297, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.92569889477106e-05, | |
| "loss": 1.9387, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.921055075694251e-05, | |
| "loss": 1.9241, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.9164112566174425e-05, | |
| "loss": 1.8848, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.911767437540634e-05, | |
| "loss": 1.8753, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.9071236184638245e-05, | |
| "loss": 1.8827, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_gen_len": 18.999326750448834, | |
| "eval_loss": 1.7382432222366333, | |
| "eval_rouge1": 24.1445, | |
| "eval_rouge2": 11.4497, | |
| "eval_rougeL": 19.8683, | |
| "eval_rougeLsum": 22.7376, | |
| "eval_runtime": 1035.6817, | |
| "eval_samples_per_second": 12.907, | |
| "eval_steps_per_second": 1.613, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.902479799387016e-05, | |
| "loss": 1.881, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.897835980310208e-05, | |
| "loss": 1.9097, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.8931921612333984e-05, | |
| "loss": 1.9231, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.88854834215659e-05, | |
| "loss": 1.9248, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.883904523079781e-05, | |
| "loss": 1.8999, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.8792607040029724e-05, | |
| "loss": 1.9033, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.874616884926164e-05, | |
| "loss": 1.8797, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.869973065849355e-05, | |
| "loss": 1.8714, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.8653292467725456e-05, | |
| "loss": 1.9069, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.860685427695737e-05, | |
| "loss": 1.8988, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_gen_len": 18.99985038898863, | |
| "eval_loss": 1.7309753894805908, | |
| "eval_rouge1": 24.329, | |
| "eval_rouge2": 11.5899, | |
| "eval_rougeL": 20.0409, | |
| "eval_rougeLsum": 22.9104, | |
| "eval_runtime": 1044.308, | |
| "eval_samples_per_second": 12.801, | |
| "eval_steps_per_second": 1.6, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.856041608618929e-05, | |
| "loss": 1.9302, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.8513977895421196e-05, | |
| "loss": 1.8743, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.846753970465311e-05, | |
| "loss": 1.9361, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.842110151388502e-05, | |
| "loss": 1.8986, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.837466332311693e-05, | |
| "loss": 1.8377, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.832822513234885e-05, | |
| "loss": 1.8887, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.828178694158076e-05, | |
| "loss": 1.9125, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.823534875081267e-05, | |
| "loss": 1.8511, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.818891056004458e-05, | |
| "loss": 1.8827, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.81424723692765e-05, | |
| "loss": 1.8778, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.7176508903503418, | |
| "eval_rouge1": 24.3886, | |
| "eval_rouge2": 11.6472, | |
| "eval_rougeL": 20.1048, | |
| "eval_rougeLsum": 22.988, | |
| "eval_runtime": 1029.4955, | |
| "eval_samples_per_second": 12.985, | |
| "eval_steps_per_second": 1.623, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.809603417850841e-05, | |
| "loss": 1.9031, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.804959598774032e-05, | |
| "loss": 1.8762, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.800315779697223e-05, | |
| "loss": 1.926, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.795671960620414e-05, | |
| "loss": 1.8523, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.791028141543606e-05, | |
| "loss": 1.9052, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.786384322466797e-05, | |
| "loss": 1.8762, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.781740503389988e-05, | |
| "loss": 1.9174, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.777096684313179e-05, | |
| "loss": 1.8726, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.7724528652363705e-05, | |
| "loss": 1.8676, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.767809046159562e-05, | |
| "loss": 1.9173, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_gen_len": 18.99955116696589, | |
| "eval_loss": 1.7139595746994019, | |
| "eval_rouge1": 24.3508, | |
| "eval_rouge2": 11.5594, | |
| "eval_rougeL": 20.075, | |
| "eval_rougeLsum": 22.932, | |
| "eval_runtime": 1027.8379, | |
| "eval_samples_per_second": 13.006, | |
| "eval_steps_per_second": 1.626, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.763165227082753e-05, | |
| "loss": 1.8869, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.7585214080059445e-05, | |
| "loss": 1.8744, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.753877588929135e-05, | |
| "loss": 1.8609, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.749233769852327e-05, | |
| "loss": 1.896, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.7445899507755184e-05, | |
| "loss": 1.8804, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.739946131698709e-05, | |
| "loss": 1.8525, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.7353023126219004e-05, | |
| "loss": 1.8503, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.730658493545092e-05, | |
| "loss": 1.8688, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.726014674468283e-05, | |
| "loss": 1.8533, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.721370855391474e-05, | |
| "loss": 1.9009, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_gen_len": 18.999476361460204, | |
| "eval_loss": 1.7133935689926147, | |
| "eval_rouge1": 24.28, | |
| "eval_rouge2": 11.6075, | |
| "eval_rougeL": 20.0581, | |
| "eval_rougeLsum": 22.8833, | |
| "eval_runtime": 1031.4088, | |
| "eval_samples_per_second": 12.961, | |
| "eval_steps_per_second": 1.62, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.7167270363146656e-05, | |
| "loss": 1.8704, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.712083217237856e-05, | |
| "loss": 1.8674, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.7074393981610476e-05, | |
| "loss": 1.8743, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.7027955790842396e-05, | |
| "loss": 1.8418, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.69815176000743e-05, | |
| "loss": 1.8522, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.6935079409306215e-05, | |
| "loss": 1.8921, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.688864121853813e-05, | |
| "loss": 1.8509, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.684220302777004e-05, | |
| "loss": 1.8358, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.6795764837001954e-05, | |
| "loss": 1.8946, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.674932664623387e-05, | |
| "loss": 1.8975, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_gen_len": 18.999401555954517, | |
| "eval_loss": 1.7081294059753418, | |
| "eval_rouge1": 24.3203, | |
| "eval_rouge2": 11.6175, | |
| "eval_rougeL": 20.035, | |
| "eval_rougeLsum": 22.9167, | |
| "eval_runtime": 1038.9823, | |
| "eval_samples_per_second": 12.866, | |
| "eval_steps_per_second": 1.608, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.6702888455465774e-05, | |
| "loss": 1.8714, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.665645026469769e-05, | |
| "loss": 1.8574, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.661001207392961e-05, | |
| "loss": 1.8721, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.656357388316151e-05, | |
| "loss": 1.8528, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.6517135692393426e-05, | |
| "loss": 1.8688, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.647069750162534e-05, | |
| "loss": 1.8845, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.6424259310857246e-05, | |
| "loss": 1.85, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.6377821120089166e-05, | |
| "loss": 1.8522, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.633138292932108e-05, | |
| "loss": 1.8589, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.6284944738552985e-05, | |
| "loss": 1.8835, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_gen_len": 18.99955116696589, | |
| "eval_loss": 1.7061101198196411, | |
| "eval_rouge1": 24.2729, | |
| "eval_rouge2": 11.6324, | |
| "eval_rougeL": 20.0728, | |
| "eval_rougeLsum": 22.8747, | |
| "eval_runtime": 1042.8871, | |
| "eval_samples_per_second": 12.818, | |
| "eval_steps_per_second": 1.602, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.62385065477849e-05, | |
| "loss": 1.8593, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.619206835701682e-05, | |
| "loss": 1.846, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.6145630166248725e-05, | |
| "loss": 1.8914, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.609919197548064e-05, | |
| "loss": 1.8554, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.605275378471255e-05, | |
| "loss": 1.901, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.600631559394446e-05, | |
| "loss": 1.893, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.595987740317638e-05, | |
| "loss": 1.8421, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.591343921240829e-05, | |
| "loss": 1.8392, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.58670010216402e-05, | |
| "loss": 1.9094, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.582056283087211e-05, | |
| "loss": 1.8725, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.6995261907577515, | |
| "eval_rouge1": 24.2542, | |
| "eval_rouge2": 11.5763, | |
| "eval_rougeL": 20.0241, | |
| "eval_rougeLsum": 22.8713, | |
| "eval_runtime": 1028.0211, | |
| "eval_samples_per_second": 13.004, | |
| "eval_steps_per_second": 1.625, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.577412464010402e-05, | |
| "loss": 1.8004, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.5727686449335936e-05, | |
| "loss": 1.8418, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.568124825856785e-05, | |
| "loss": 1.833, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.563481006779976e-05, | |
| "loss": 1.8684, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.558837187703167e-05, | |
| "loss": 1.8496, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.554193368626358e-05, | |
| "loss": 1.8498, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.54954954954955e-05, | |
| "loss": 1.869, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.544905730472741e-05, | |
| "loss": 1.863, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.540261911395932e-05, | |
| "loss": 1.8227, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.5356180923191235e-05, | |
| "loss": 1.837, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_gen_len": 18.99970077797726, | |
| "eval_loss": 1.6998443603515625, | |
| "eval_rouge1": 24.3321, | |
| "eval_rouge2": 11.599, | |
| "eval_rougeL": 20.1028, | |
| "eval_rougeLsum": 22.9562, | |
| "eval_runtime": 1035.1096, | |
| "eval_samples_per_second": 12.915, | |
| "eval_steps_per_second": 1.614, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.530974273242315e-05, | |
| "loss": 1.8373, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.526330454165506e-05, | |
| "loss": 1.8523, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.5216866350886974e-05, | |
| "loss": 1.8533, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.517042816011888e-05, | |
| "loss": 1.8649, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.5123989969350793e-05, | |
| "loss": 1.845, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.507755177858271e-05, | |
| "loss": 1.8403, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.503111358781462e-05, | |
| "loss": 1.8796, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.498467539704653e-05, | |
| "loss": 1.8508, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.4938237206278446e-05, | |
| "loss": 1.9008, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.489179901551035e-05, | |
| "loss": 1.8629, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.6944048404693604, | |
| "eval_rouge1": 24.4161, | |
| "eval_rouge2": 11.6208, | |
| "eval_rougeL": 20.1374, | |
| "eval_rougeLsum": 23.024, | |
| "eval_runtime": 1022.6375, | |
| "eval_samples_per_second": 13.072, | |
| "eval_steps_per_second": 1.634, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.484536082474227e-05, | |
| "loss": 1.8599, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.4798922633974185e-05, | |
| "loss": 1.85, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.475248444320609e-05, | |
| "loss": 1.8512, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.4706046252438005e-05, | |
| "loss": 1.8551, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.4659608061669925e-05, | |
| "loss": 1.8278, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.461316987090183e-05, | |
| "loss": 1.8991, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.4566731680133744e-05, | |
| "loss": 1.8555, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.452029348936566e-05, | |
| "loss": 1.8394, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.4473855298597564e-05, | |
| "loss": 1.8479, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.4427417107829484e-05, | |
| "loss": 1.85, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_gen_len": 18.999027528426094, | |
| "eval_loss": 1.70017409324646, | |
| "eval_rouge1": 24.3514, | |
| "eval_rouge2": 11.6883, | |
| "eval_rougeL": 20.134, | |
| "eval_rougeLsum": 22.9515, | |
| "eval_runtime": 1029.569, | |
| "eval_samples_per_second": 12.984, | |
| "eval_steps_per_second": 1.623, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.43809789170614e-05, | |
| "loss": 1.8509, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.43345407262933e-05, | |
| "loss": 1.846, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.4288102535525216e-05, | |
| "loss": 1.8238, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.424166434475713e-05, | |
| "loss": 1.8519, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.419522615398904e-05, | |
| "loss": 1.8366, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.4148787963220956e-05, | |
| "loss": 1.8822, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.410234977245287e-05, | |
| "loss": 1.864, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.4055911581684775e-05, | |
| "loss": 1.8388, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.4009473390916695e-05, | |
| "loss": 1.8891, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.396303520014861e-05, | |
| "loss": 1.8506, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_gen_len": 18.998653500897667, | |
| "eval_loss": 1.6894251108169556, | |
| "eval_rouge1": 24.3812, | |
| "eval_rouge2": 11.6592, | |
| "eval_rougeL": 20.1641, | |
| "eval_rougeLsum": 23.0108, | |
| "eval_runtime": 1023.0391, | |
| "eval_samples_per_second": 13.067, | |
| "eval_steps_per_second": 1.633, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.3916597009380515e-05, | |
| "loss": 1.8513, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.387015881861243e-05, | |
| "loss": 1.9267, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.382372062784434e-05, | |
| "loss": 1.8639, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.3777282437076254e-05, | |
| "loss": 1.8481, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.373084424630817e-05, | |
| "loss": 1.83, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.368440605554008e-05, | |
| "loss": 1.8801, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.3637967864771987e-05, | |
| "loss": 1.8352, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.35915296740039e-05, | |
| "loss": 1.8361, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.354509148323582e-05, | |
| "loss": 1.8487, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.3498653292467726e-05, | |
| "loss": 1.8869, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_gen_len": 18.999476361460204, | |
| "eval_loss": 1.6880699396133423, | |
| "eval_rouge1": 24.3956, | |
| "eval_rouge2": 11.6817, | |
| "eval_rougeL": 20.1654, | |
| "eval_rougeLsum": 23.0284, | |
| "eval_runtime": 1045.0589, | |
| "eval_samples_per_second": 12.792, | |
| "eval_steps_per_second": 1.599, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.345221510169964e-05, | |
| "loss": 1.8472, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.340577691093155e-05, | |
| "loss": 1.8419, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.3359338720163465e-05, | |
| "loss": 1.8654, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.331290052939538e-05, | |
| "loss": 1.8605, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.326646233862729e-05, | |
| "loss": 1.8943, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.32200241478592e-05, | |
| "loss": 1.8725, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.317358595709111e-05, | |
| "loss": 1.8538, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.312714776632303e-05, | |
| "loss": 1.8818, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.308070957555494e-05, | |
| "loss": 1.836, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.303427138478685e-05, | |
| "loss": 1.8327, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_gen_len": 18.999251944943147, | |
| "eval_loss": 1.690325379371643, | |
| "eval_rouge1": 24.3707, | |
| "eval_rouge2": 11.6446, | |
| "eval_rougeL": 20.1353, | |
| "eval_rougeLsum": 22.9801, | |
| "eval_runtime": 1037.5831, | |
| "eval_samples_per_second": 12.884, | |
| "eval_steps_per_second": 1.61, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.2987833194018764e-05, | |
| "loss": 1.8389, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.294139500325067e-05, | |
| "loss": 1.8339, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.289495681248259e-05, | |
| "loss": 1.8757, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.28485186217145e-05, | |
| "loss": 1.8118, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.280208043094641e-05, | |
| "loss": 1.8513, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.275564224017832e-05, | |
| "loss": 1.8791, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.270920404941024e-05, | |
| "loss": 1.8822, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.266276585864215e-05, | |
| "loss": 1.8793, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.261632766787406e-05, | |
| "loss": 1.8132, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.2569889477105975e-05, | |
| "loss": 1.8204, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_gen_len": 18.999326750448834, | |
| "eval_loss": 1.6896474361419678, | |
| "eval_rouge1": 24.3663, | |
| "eval_rouge2": 11.6963, | |
| "eval_rougeL": 20.1357, | |
| "eval_rougeLsum": 22.9898, | |
| "eval_runtime": 1023.2223, | |
| "eval_samples_per_second": 13.065, | |
| "eval_steps_per_second": 1.633, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.252345128633788e-05, | |
| "loss": 1.8534, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.24770130955698e-05, | |
| "loss": 1.7864, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.2430574904801715e-05, | |
| "loss": 1.8649, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 4.238413671403362e-05, | |
| "loss": 1.8562, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 4.2337698523265534e-05, | |
| "loss": 1.8897, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 4.229126033249745e-05, | |
| "loss": 1.8949, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.224482214172936e-05, | |
| "loss": 1.8548, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.2198383950961273e-05, | |
| "loss": 1.8514, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.2151945760193187e-05, | |
| "loss": 1.8525, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.210550756942509e-05, | |
| "loss": 1.8764, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_gen_len": 18.997830640335128, | |
| "eval_loss": 1.6845980882644653, | |
| "eval_rouge1": 24.4212, | |
| "eval_rouge2": 11.652, | |
| "eval_rougeL": 20.1455, | |
| "eval_rougeLsum": 23.0326, | |
| "eval_runtime": 1022.189, | |
| "eval_samples_per_second": 13.078, | |
| "eval_steps_per_second": 1.635, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.205906937865701e-05, | |
| "loss": 1.8621, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.2012631187888926e-05, | |
| "loss": 1.8591, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.196619299712083e-05, | |
| "loss": 1.8448, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.1919754806352745e-05, | |
| "loss": 1.8966, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.187331661558466e-05, | |
| "loss": 1.8307, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.182687842481657e-05, | |
| "loss": 1.8801, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.1780440234048485e-05, | |
| "loss": 1.8006, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.17340020432804e-05, | |
| "loss": 1.8394, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.1687563852512304e-05, | |
| "loss": 1.8494, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.164112566174422e-05, | |
| "loss": 1.8213, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_gen_len": 18.999177139437464, | |
| "eval_loss": 1.6816905736923218, | |
| "eval_rouge1": 24.452, | |
| "eval_rouge2": 11.7014, | |
| "eval_rougeL": 20.1898, | |
| "eval_rougeLsum": 23.0668, | |
| "eval_runtime": 1033.0047, | |
| "eval_samples_per_second": 12.941, | |
| "eval_steps_per_second": 1.618, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.159468747097614e-05, | |
| "loss": 1.8428, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.1548249280208044e-05, | |
| "loss": 1.8512, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.150181108943996e-05, | |
| "loss": 1.8383, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.145537289867187e-05, | |
| "loss": 1.8308, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.140893470790378e-05, | |
| "loss": 1.8504, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.1362496517135696e-05, | |
| "loss": 1.84, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.131605832636761e-05, | |
| "loss": 1.8717, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.1269620135599516e-05, | |
| "loss": 1.8768, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.122318194483143e-05, | |
| "loss": 1.8493, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.117674375406335e-05, | |
| "loss": 1.8424, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_gen_len": 18.998952722920407, | |
| "eval_loss": 1.6843751668930054, | |
| "eval_rouge1": 24.4206, | |
| "eval_rouge2": 11.7049, | |
| "eval_rougeL": 20.1931, | |
| "eval_rougeLsum": 23.0358, | |
| "eval_runtime": 1022.1365, | |
| "eval_samples_per_second": 13.078, | |
| "eval_steps_per_second": 1.635, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.1130305563295255e-05, | |
| "loss": 1.8629, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.108386737252717e-05, | |
| "loss": 1.8285, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.103742918175908e-05, | |
| "loss": 1.8237, | |
| "step": 19300 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.099099099099099e-05, | |
| "loss": 1.833, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.094455280022291e-05, | |
| "loss": 1.8349, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.089811460945482e-05, | |
| "loss": 1.8581, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.085167641868673e-05, | |
| "loss": 1.8623, | |
| "step": 19700 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.080523822791864e-05, | |
| "loss": 1.8653, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.0758800037150553e-05, | |
| "loss": 1.8228, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.071236184638247e-05, | |
| "loss": 1.8721, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_gen_len": 18.999625972471573, | |
| "eval_loss": 1.6814035177230835, | |
| "eval_rouge1": 24.4483, | |
| "eval_rouge2": 11.6789, | |
| "eval_rougeL": 20.1798, | |
| "eval_rougeLsum": 23.0508, | |
| "eval_runtime": 1031.5868, | |
| "eval_samples_per_second": 12.959, | |
| "eval_steps_per_second": 1.62, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.066592365561438e-05, | |
| "loss": 1.8544, | |
| "step": 20100 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.061948546484629e-05, | |
| "loss": 1.8699, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.05730472740782e-05, | |
| "loss": 1.8262, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.052660908331012e-05, | |
| "loss": 1.8274, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.048017089254203e-05, | |
| "loss": 1.8406, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.043373270177394e-05, | |
| "loss": 1.8882, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.038729451100585e-05, | |
| "loss": 1.8563, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.0340856320237765e-05, | |
| "loss": 1.861, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.029441812946968e-05, | |
| "loss": 1.8437, | |
| "step": 20900 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.024797993870159e-05, | |
| "loss": 1.87, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_gen_len": 18.999625972471573, | |
| "eval_loss": 1.6796290874481201, | |
| "eval_rouge1": 24.4799, | |
| "eval_rouge2": 11.6789, | |
| "eval_rougeL": 20.1919, | |
| "eval_rougeLsum": 23.0831, | |
| "eval_runtime": 1027.2545, | |
| "eval_samples_per_second": 13.013, | |
| "eval_steps_per_second": 1.627, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.0201541747933504e-05, | |
| "loss": 1.8364, | |
| "step": 21100 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.015510355716541e-05, | |
| "loss": 1.8659, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.0108665366397324e-05, | |
| "loss": 1.8246, | |
| "step": 21300 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.0062227175629244e-05, | |
| "loss": 1.8523, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.001578898486115e-05, | |
| "loss": 1.8709, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.996935079409306e-05, | |
| "loss": 1.838, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.9922912603324976e-05, | |
| "loss": 1.8308, | |
| "step": 21700 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.987647441255689e-05, | |
| "loss": 1.8366, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.98300362217888e-05, | |
| "loss": 1.8366, | |
| "step": 21900 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.9783598031020716e-05, | |
| "loss": 1.844, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_gen_len": 18.999625972471573, | |
| "eval_loss": 1.6769678592681885, | |
| "eval_rouge1": 24.4741, | |
| "eval_rouge2": 11.7433, | |
| "eval_rougeL": 20.2031, | |
| "eval_rougeLsum": 23.0535, | |
| "eval_runtime": 1029.6436, | |
| "eval_samples_per_second": 12.983, | |
| "eval_steps_per_second": 1.623, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.973715984025262e-05, | |
| "loss": 1.8852, | |
| "step": 22100 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.9690721649484535e-05, | |
| "loss": 1.8251, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.9644283458716455e-05, | |
| "loss": 1.8515, | |
| "step": 22300 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.959784526794836e-05, | |
| "loss": 1.8349, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.9551407077180275e-05, | |
| "loss": 1.813, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.950496888641219e-05, | |
| "loss": 1.8574, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.9458530695644094e-05, | |
| "loss": 1.8541, | |
| "step": 22700 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.9412092504876014e-05, | |
| "loss": 1.8456, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.936565431410793e-05, | |
| "loss": 1.8051, | |
| "step": 22900 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.9319216123339834e-05, | |
| "loss": 1.8611, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_gen_len": 18.99857869539198, | |
| "eval_loss": 1.6784615516662598, | |
| "eval_rouge1": 24.4837, | |
| "eval_rouge2": 11.7572, | |
| "eval_rougeL": 20.219, | |
| "eval_rougeLsum": 23.088, | |
| "eval_runtime": 1026.7838, | |
| "eval_samples_per_second": 13.019, | |
| "eval_steps_per_second": 1.627, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.927277793257175e-05, | |
| "loss": 1.8259, | |
| "step": 23100 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.9226339741803667e-05, | |
| "loss": 1.8995, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.917990155103557e-05, | |
| "loss": 1.8324, | |
| "step": 23300 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.9133463360267486e-05, | |
| "loss": 1.8685, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.90870251694994e-05, | |
| "loss": 1.8533, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.9040586978731306e-05, | |
| "loss": 1.8458, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.8994148787963225e-05, | |
| "loss": 1.8748, | |
| "step": 23700 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.894771059719514e-05, | |
| "loss": 1.8468, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.8901272406427045e-05, | |
| "loss": 1.8464, | |
| "step": 23900 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.885483421565896e-05, | |
| "loss": 1.8201, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_gen_len": 18.999326750448834, | |
| "eval_loss": 1.679620385169983, | |
| "eval_rouge1": 24.3955, | |
| "eval_rouge2": 11.6978, | |
| "eval_rougeL": 20.173, | |
| "eval_rougeLsum": 23.0302, | |
| "eval_runtime": 1032.6621, | |
| "eval_samples_per_second": 12.945, | |
| "eval_steps_per_second": 1.618, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.880839602489087e-05, | |
| "loss": 1.8332, | |
| "step": 24100 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.8761957834122784e-05, | |
| "loss": 1.8076, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.87155196433547e-05, | |
| "loss": 1.8539, | |
| "step": 24300 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.866908145258661e-05, | |
| "loss": 1.832, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.862264326181852e-05, | |
| "loss": 1.8395, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.857620507105044e-05, | |
| "loss": 1.8648, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.852976688028235e-05, | |
| "loss": 1.8629, | |
| "step": 24700 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.8483328689514256e-05, | |
| "loss": 1.8374, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.843689049874617e-05, | |
| "loss": 1.8363, | |
| "step": 24900 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.839045230797808e-05, | |
| "loss": 1.8506, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_gen_len": 18.999476361460204, | |
| "eval_loss": 1.6769764423370361, | |
| "eval_rouge1": 24.4084, | |
| "eval_rouge2": 11.711, | |
| "eval_rougeL": 20.1851, | |
| "eval_rougeLsum": 23.0266, | |
| "eval_runtime": 1026.6424, | |
| "eval_samples_per_second": 13.021, | |
| "eval_steps_per_second": 1.628, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.8344014117209996e-05, | |
| "loss": 1.8393, | |
| "step": 25100 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.829757592644191e-05, | |
| "loss": 1.8468, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.825113773567382e-05, | |
| "loss": 1.8548, | |
| "step": 25300 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.820469954490573e-05, | |
| "loss": 1.8017, | |
| "step": 25400 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.815826135413764e-05, | |
| "loss": 1.8355, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.811182316336956e-05, | |
| "loss": 1.841, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.806538497260147e-05, | |
| "loss": 1.8751, | |
| "step": 25700 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.801894678183338e-05, | |
| "loss": 1.8258, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.7972508591065294e-05, | |
| "loss": 1.8243, | |
| "step": 25900 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.792607040029721e-05, | |
| "loss": 1.846, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_gen_len": 18.998952722920407, | |
| "eval_loss": 1.6765128374099731, | |
| "eval_rouge1": 24.4272, | |
| "eval_rouge2": 11.6779, | |
| "eval_rougeL": 20.1785, | |
| "eval_rougeLsum": 23.0352, | |
| "eval_runtime": 1042.1434, | |
| "eval_samples_per_second": 12.827, | |
| "eval_steps_per_second": 1.603, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.787963220952912e-05, | |
| "loss": 1.8538, | |
| "step": 26100 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.7833194018761034e-05, | |
| "loss": 1.8498, | |
| "step": 26200 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.778675582799294e-05, | |
| "loss": 1.8562, | |
| "step": 26300 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.774031763722485e-05, | |
| "loss": 1.8432, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.769387944645677e-05, | |
| "loss": 1.871, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.764744125568868e-05, | |
| "loss": 1.8444, | |
| "step": 26600 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.760100306492059e-05, | |
| "loss": 1.8634, | |
| "step": 26700 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.7554564874152506e-05, | |
| "loss": 1.8377, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.750812668338441e-05, | |
| "loss": 1.862, | |
| "step": 26900 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.746168849261633e-05, | |
| "loss": 1.8431, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_gen_len": 18.999775583482943, | |
| "eval_loss": 1.6757032871246338, | |
| "eval_rouge1": 24.4484, | |
| "eval_rouge2": 11.7154, | |
| "eval_rougeL": 20.2156, | |
| "eval_rougeLsum": 23.0646, | |
| "eval_runtime": 1031.148, | |
| "eval_samples_per_second": 12.964, | |
| "eval_steps_per_second": 1.621, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 3.7415250301848245e-05, | |
| "loss": 1.8086, | |
| "step": 27100 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 3.736881211108015e-05, | |
| "loss": 1.8057, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 3.7322373920312064e-05, | |
| "loss": 1.8122, | |
| "step": 27300 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 3.7275935729543984e-05, | |
| "loss": 1.8436, | |
| "step": 27400 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 3.722949753877589e-05, | |
| "loss": 1.8109, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 3.7183059348007804e-05, | |
| "loss": 1.8281, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 3.713662115723972e-05, | |
| "loss": 1.8217, | |
| "step": 27700 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 3.709018296647162e-05, | |
| "loss": 1.8251, | |
| "step": 27800 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 3.704374477570354e-05, | |
| "loss": 1.814, | |
| "step": 27900 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 3.6997306584935456e-05, | |
| "loss": 1.8208, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_gen_len": 18.999326750448834, | |
| "eval_loss": 1.6763582229614258, | |
| "eval_rouge1": 24.412, | |
| "eval_rouge2": 11.6887, | |
| "eval_rougeL": 20.1752, | |
| "eval_rougeLsum": 23.0151, | |
| "eval_runtime": 1029.8014, | |
| "eval_samples_per_second": 12.981, | |
| "eval_steps_per_second": 1.623, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 3.695086839416736e-05, | |
| "loss": 1.8216, | |
| "step": 28100 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 3.6904430203399276e-05, | |
| "loss": 1.8218, | |
| "step": 28200 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 3.685799201263119e-05, | |
| "loss": 1.8148, | |
| "step": 28300 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 3.68115538218631e-05, | |
| "loss": 1.8116, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 3.6765115631095015e-05, | |
| "loss": 1.8221, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 3.671867744032693e-05, | |
| "loss": 1.8084, | |
| "step": 28600 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 3.6672239249558835e-05, | |
| "loss": 1.8018, | |
| "step": 28700 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 3.662580105879075e-05, | |
| "loss": 1.8693, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.657936286802267e-05, | |
| "loss": 1.8269, | |
| "step": 28900 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.6532924677254574e-05, | |
| "loss": 1.8108, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_gen_len": 18.99970077797726, | |
| "eval_loss": 1.673341155052185, | |
| "eval_rouge1": 24.4051, | |
| "eval_rouge2": 11.7155, | |
| "eval_rougeL": 20.1773, | |
| "eval_rougeLsum": 23.0215, | |
| "eval_runtime": 1021.7828, | |
| "eval_samples_per_second": 13.083, | |
| "eval_steps_per_second": 1.635, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.648648648648649e-05, | |
| "loss": 1.8227, | |
| "step": 29100 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.64400482957184e-05, | |
| "loss": 1.7996, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 3.6393610104950314e-05, | |
| "loss": 1.8666, | |
| "step": 29300 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 3.634717191418223e-05, | |
| "loss": 1.8661, | |
| "step": 29400 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 3.630073372341414e-05, | |
| "loss": 1.8567, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 3.6254295532646046e-05, | |
| "loss": 1.8299, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.620785734187796e-05, | |
| "loss": 1.8452, | |
| "step": 29700 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.616141915110988e-05, | |
| "loss": 1.8044, | |
| "step": 29800 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.6114980960341786e-05, | |
| "loss": 1.7938, | |
| "step": 29900 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 3.60685427695737e-05, | |
| "loss": 1.847, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_gen_len": 18.999401555954517, | |
| "eval_loss": 1.6737741231918335, | |
| "eval_rouge1": 24.5531, | |
| "eval_rouge2": 11.7949, | |
| "eval_rougeL": 20.2834, | |
| "eval_rougeLsum": 23.1588, | |
| "eval_runtime": 1026.8053, | |
| "eval_samples_per_second": 13.019, | |
| "eval_steps_per_second": 1.627, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 3.602210457880561e-05, | |
| "loss": 1.8155, | |
| "step": 30100 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 3.597566638803752e-05, | |
| "loss": 1.8121, | |
| "step": 30200 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 3.592922819726944e-05, | |
| "loss": 1.8644, | |
| "step": 30300 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.588279000650135e-05, | |
| "loss": 1.8362, | |
| "step": 30400 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.583635181573326e-05, | |
| "loss": 1.8361, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.578991362496517e-05, | |
| "loss": 1.8711, | |
| "step": 30600 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 3.574347543419709e-05, | |
| "loss": 1.8515, | |
| "step": 30700 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 3.5697037243429e-05, | |
| "loss": 1.8456, | |
| "step": 30800 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 3.565059905266091e-05, | |
| "loss": 1.8257, | |
| "step": 30900 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 3.560416086189282e-05, | |
| "loss": 1.8386, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_gen_len": 18.999102333931777, | |
| "eval_loss": 1.667382836341858, | |
| "eval_rouge1": 24.5155, | |
| "eval_rouge2": 11.7333, | |
| "eval_rougeL": 20.2529, | |
| "eval_rougeLsum": 23.145, | |
| "eval_runtime": 1035.863, | |
| "eval_samples_per_second": 12.905, | |
| "eval_steps_per_second": 1.613, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 3.555772267112473e-05, | |
| "loss": 1.8316, | |
| "step": 31100 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 3.551128448035665e-05, | |
| "loss": 1.8511, | |
| "step": 31200 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 3.546484628958856e-05, | |
| "loss": 1.8526, | |
| "step": 31300 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 3.541840809882047e-05, | |
| "loss": 1.8468, | |
| "step": 31400 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.537196990805238e-05, | |
| "loss": 1.8796, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.5325531717284295e-05, | |
| "loss": 1.8526, | |
| "step": 31600 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.527909352651621e-05, | |
| "loss": 1.8418, | |
| "step": 31700 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.523265533574812e-05, | |
| "loss": 1.8185, | |
| "step": 31800 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.5186217144980035e-05, | |
| "loss": 1.8886, | |
| "step": 31900 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.513977895421194e-05, | |
| "loss": 1.82, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_gen_len": 18.998803111909037, | |
| "eval_loss": 1.66925048828125, | |
| "eval_rouge1": 24.4498, | |
| "eval_rouge2": 11.7118, | |
| "eval_rougeL": 20.2183, | |
| "eval_rougeLsum": 23.0767, | |
| "eval_runtime": 1043.8464, | |
| "eval_samples_per_second": 12.806, | |
| "eval_steps_per_second": 1.601, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.509334076344386e-05, | |
| "loss": 1.8643, | |
| "step": 32100 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.5046902572675774e-05, | |
| "loss": 1.7943, | |
| "step": 32200 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.500046438190768e-05, | |
| "loss": 1.8089, | |
| "step": 32300 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.4954026191139594e-05, | |
| "loss": 1.7881, | |
| "step": 32400 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.490758800037151e-05, | |
| "loss": 1.8543, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.486114980960342e-05, | |
| "loss": 1.8068, | |
| "step": 32600 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.481471161883533e-05, | |
| "loss": 1.8266, | |
| "step": 32700 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.4768273428067246e-05, | |
| "loss": 1.8328, | |
| "step": 32800 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.472183523729915e-05, | |
| "loss": 1.8644, | |
| "step": 32900 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.4675397046531066e-05, | |
| "loss": 1.8475, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_gen_len": 18.999251944943147, | |
| "eval_loss": 1.6676273345947266, | |
| "eval_rouge1": 24.442, | |
| "eval_rouge2": 11.676, | |
| "eval_rougeL": 20.168, | |
| "eval_rougeLsum": 23.0409, | |
| "eval_runtime": 1028.9174, | |
| "eval_samples_per_second": 12.992, | |
| "eval_steps_per_second": 1.624, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.4628958855762986e-05, | |
| "loss": 1.8232, | |
| "step": 33100 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.458252066499489e-05, | |
| "loss": 1.8512, | |
| "step": 33200 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.4536082474226805e-05, | |
| "loss": 1.8338, | |
| "step": 33300 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.448964428345872e-05, | |
| "loss": 1.8103, | |
| "step": 33400 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.444320609269063e-05, | |
| "loss": 1.8454, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.4396767901922544e-05, | |
| "loss": 1.8433, | |
| "step": 33600 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.435032971115446e-05, | |
| "loss": 1.868, | |
| "step": 33700 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.4303891520386364e-05, | |
| "loss": 1.794, | |
| "step": 33800 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.425745332961828e-05, | |
| "loss": 1.7941, | |
| "step": 33900 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 3.42110151388502e-05, | |
| "loss": 1.7948, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_gen_len": 18.999027528426094, | |
| "eval_loss": 1.6689342260360718, | |
| "eval_rouge1": 24.4561, | |
| "eval_rouge2": 11.7865, | |
| "eval_rougeL": 20.2446, | |
| "eval_rougeLsum": 23.0707, | |
| "eval_runtime": 1028.9964, | |
| "eval_samples_per_second": 12.991, | |
| "eval_steps_per_second": 1.624, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 3.41645769480821e-05, | |
| "loss": 1.8232, | |
| "step": 34100 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 3.4118138757314017e-05, | |
| "loss": 1.8209, | |
| "step": 34200 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.407170056654593e-05, | |
| "loss": 1.8718, | |
| "step": 34300 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.4025262375777836e-05, | |
| "loss": 1.8139, | |
| "step": 34400 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.3978824185009756e-05, | |
| "loss": 1.8332, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.393238599424167e-05, | |
| "loss": 1.8244, | |
| "step": 34600 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.3885947803473575e-05, | |
| "loss": 1.7957, | |
| "step": 34700 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.383950961270549e-05, | |
| "loss": 1.8466, | |
| "step": 34800 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.379307142193741e-05, | |
| "loss": 1.8225, | |
| "step": 34900 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.3746633231169315e-05, | |
| "loss": 1.8357, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_gen_len": 18.999401555954517, | |
| "eval_loss": 1.6757416725158691, | |
| "eval_rouge1": 24.4005, | |
| "eval_rouge2": 11.7299, | |
| "eval_rougeL": 20.1999, | |
| "eval_rougeLsum": 23.0093, | |
| "eval_runtime": 1030.4474, | |
| "eval_samples_per_second": 12.973, | |
| "eval_steps_per_second": 1.622, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.370019504040123e-05, | |
| "loss": 1.8064, | |
| "step": 35100 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.365375684963314e-05, | |
| "loss": 1.8333, | |
| "step": 35200 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.360731865886505e-05, | |
| "loss": 1.8368, | |
| "step": 35300 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.356088046809697e-05, | |
| "loss": 1.8732, | |
| "step": 35400 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.351444227732888e-05, | |
| "loss": 1.8425, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.346800408656079e-05, | |
| "loss": 1.7983, | |
| "step": 35600 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.34215658957927e-05, | |
| "loss": 1.8615, | |
| "step": 35700 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.337512770502461e-05, | |
| "loss": 1.8414, | |
| "step": 35800 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.3328689514256526e-05, | |
| "loss": 1.8695, | |
| "step": 35900 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.328225132348844e-05, | |
| "loss": 1.8624, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_gen_len": 18.998803111909037, | |
| "eval_loss": 1.674521803855896, | |
| "eval_rouge1": 24.3371, | |
| "eval_rouge2": 11.6749, | |
| "eval_rougeL": 20.1257, | |
| "eval_rougeLsum": 22.9428, | |
| "eval_runtime": 1027.0502, | |
| "eval_samples_per_second": 13.016, | |
| "eval_steps_per_second": 1.627, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.323581313272035e-05, | |
| "loss": 1.8208, | |
| "step": 36100 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.318937494195226e-05, | |
| "loss": 1.8022, | |
| "step": 36200 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.314293675118418e-05, | |
| "loss": 1.8168, | |
| "step": 36300 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.309649856041609e-05, | |
| "loss": 1.8046, | |
| "step": 36400 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 3.3050060369648e-05, | |
| "loss": 1.8199, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 3.300362217887991e-05, | |
| "loss": 1.8291, | |
| "step": 36600 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 3.2957183988111825e-05, | |
| "loss": 1.7895, | |
| "step": 36700 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.291074579734374e-05, | |
| "loss": 1.8152, | |
| "step": 36800 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.286430760657565e-05, | |
| "loss": 1.8328, | |
| "step": 36900 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.2817869415807564e-05, | |
| "loss": 1.8309, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_gen_len": 18.999476361460204, | |
| "eval_loss": 1.6674766540527344, | |
| "eval_rouge1": 24.5108, | |
| "eval_rouge2": 11.8038, | |
| "eval_rougeL": 20.2691, | |
| "eval_rougeLsum": 23.117, | |
| "eval_runtime": 1029.1013, | |
| "eval_samples_per_second": 12.99, | |
| "eval_steps_per_second": 1.624, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.277143122503947e-05, | |
| "loss": 1.7957, | |
| "step": 37100 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 3.2724993034271383e-05, | |
| "loss": 1.8033, | |
| "step": 37200 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 3.26785548435033e-05, | |
| "loss": 1.8517, | |
| "step": 37300 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 3.263211665273521e-05, | |
| "loss": 1.804, | |
| "step": 37400 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 3.258567846196712e-05, | |
| "loss": 1.7834, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.2539240271199036e-05, | |
| "loss": 1.819, | |
| "step": 37600 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.249280208043094e-05, | |
| "loss": 1.8737, | |
| "step": 37700 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.244636388966286e-05, | |
| "loss": 1.7807, | |
| "step": 37800 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 3.2399925698894775e-05, | |
| "loss": 1.8099, | |
| "step": 37900 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 3.235348750812668e-05, | |
| "loss": 1.8237, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_gen_len": 18.99955116696589, | |
| "eval_loss": 1.6654016971588135, | |
| "eval_rouge1": 24.482, | |
| "eval_rouge2": 11.7485, | |
| "eval_rougeL": 20.2225, | |
| "eval_rougeLsum": 23.0917, | |
| "eval_runtime": 1033.6425, | |
| "eval_samples_per_second": 12.933, | |
| "eval_steps_per_second": 1.617, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 3.2307049317358595e-05, | |
| "loss": 1.7796, | |
| "step": 38100 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 3.2260611126590515e-05, | |
| "loss": 1.8055, | |
| "step": 38200 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 3.221417293582242e-05, | |
| "loss": 1.8558, | |
| "step": 38300 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 3.2167734745054334e-05, | |
| "loss": 1.8292, | |
| "step": 38400 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 3.212129655428625e-05, | |
| "loss": 1.8351, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.2074858363518154e-05, | |
| "loss": 1.8071, | |
| "step": 38600 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.2028420172750074e-05, | |
| "loss": 1.7892, | |
| "step": 38700 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.198198198198199e-05, | |
| "loss": 1.864, | |
| "step": 38800 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.193554379121389e-05, | |
| "loss": 1.8289, | |
| "step": 38900 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.1889105600445806e-05, | |
| "loss": 1.7743, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "eval_gen_len": 18.999251944943147, | |
| "eval_loss": 1.6681499481201172, | |
| "eval_rouge1": 24.5106, | |
| "eval_rouge2": 11.7511, | |
| "eval_rougeL": 20.2583, | |
| "eval_rougeLsum": 23.123, | |
| "eval_runtime": 1040.1281, | |
| "eval_samples_per_second": 12.852, | |
| "eval_steps_per_second": 1.607, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.184266740967772e-05, | |
| "loss": 1.77, | |
| "step": 39100 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.179622921890963e-05, | |
| "loss": 1.7844, | |
| "step": 39200 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 3.1749791028141546e-05, | |
| "loss": 1.791, | |
| "step": 39300 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 3.170335283737346e-05, | |
| "loss": 1.8038, | |
| "step": 39400 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 3.1656914646605365e-05, | |
| "loss": 1.8211, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 3.1610476455837285e-05, | |
| "loss": 1.8608, | |
| "step": 39600 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.15640382650692e-05, | |
| "loss": 1.8124, | |
| "step": 39700 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.1517600074301105e-05, | |
| "loss": 1.8327, | |
| "step": 39800 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.147116188353302e-05, | |
| "loss": 1.7969, | |
| "step": 39900 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.142472369276493e-05, | |
| "loss": 1.7811, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "eval_gen_len": 18.999102333931777, | |
| "eval_loss": 1.6636024713516235, | |
| "eval_rouge1": 24.6194, | |
| "eval_rouge2": 11.843, | |
| "eval_rougeL": 20.3375, | |
| "eval_rougeLsum": 23.2259, | |
| "eval_runtime": 1032.055, | |
| "eval_samples_per_second": 12.953, | |
| "eval_steps_per_second": 1.619, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 3.1378285501996844e-05, | |
| "loss": 1.8392, | |
| "step": 40100 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 3.133184731122876e-05, | |
| "loss": 1.7993, | |
| "step": 40200 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 3.128540912046067e-05, | |
| "loss": 1.7919, | |
| "step": 40300 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.123897092969258e-05, | |
| "loss": 1.7836, | |
| "step": 40400 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.119253273892449e-05, | |
| "loss": 1.815, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.114609454815641e-05, | |
| "loss": 1.8078, | |
| "step": 40600 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.1099656357388316e-05, | |
| "loss": 1.8451, | |
| "step": 40700 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 3.105321816662023e-05, | |
| "loss": 1.8362, | |
| "step": 40800 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 3.100677997585214e-05, | |
| "loss": 1.7685, | |
| "step": 40900 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 3.0960341785084055e-05, | |
| "loss": 1.7973, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.666628360748291, | |
| "eval_rouge1": 24.5434, | |
| "eval_rouge2": 11.8133, | |
| "eval_rougeL": 20.3033, | |
| "eval_rougeLsum": 23.165, | |
| "eval_runtime": 1027.5741, | |
| "eval_samples_per_second": 13.009, | |
| "eval_steps_per_second": 1.626, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3.091390359431597e-05, | |
| "loss": 1.8079, | |
| "step": 41100 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3.086746540354788e-05, | |
| "loss": 1.8149, | |
| "step": 41200 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3.082102721277979e-05, | |
| "loss": 1.8236, | |
| "step": 41300 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3.07745890220117e-05, | |
| "loss": 1.8512, | |
| "step": 41400 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 3.072815083124362e-05, | |
| "loss": 1.7871, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 3.068171264047553e-05, | |
| "loss": 1.763, | |
| "step": 41600 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 3.063527444970744e-05, | |
| "loss": 1.7681, | |
| "step": 41700 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 3.0588836258939354e-05, | |
| "loss": 1.7997, | |
| "step": 41800 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.054239806817126e-05, | |
| "loss": 1.7942, | |
| "step": 41900 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.049595987740318e-05, | |
| "loss": 1.8156, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "eval_gen_len": 18.999326750448834, | |
| "eval_loss": 1.6660268306732178, | |
| "eval_rouge1": 24.4857, | |
| "eval_rouge2": 11.7526, | |
| "eval_rougeL": 20.2406, | |
| "eval_rougeLsum": 23.1081, | |
| "eval_runtime": 1032.3479, | |
| "eval_samples_per_second": 12.949, | |
| "eval_steps_per_second": 1.619, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.044952168663509e-05, | |
| "loss": 1.8213, | |
| "step": 42100 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 3.0403083495867003e-05, | |
| "loss": 1.8291, | |
| "step": 42200 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 3.0356645305098913e-05, | |
| "loss": 1.8549, | |
| "step": 42300 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 3.031020711433083e-05, | |
| "loss": 1.8268, | |
| "step": 42400 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 3.0263768923562742e-05, | |
| "loss": 1.819, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 3.0217330732794652e-05, | |
| "loss": 1.8526, | |
| "step": 42600 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 3.0170892542026562e-05, | |
| "loss": 1.8245, | |
| "step": 42700 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 3.0124454351258475e-05, | |
| "loss": 1.786, | |
| "step": 42800 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.007801616049039e-05, | |
| "loss": 1.8223, | |
| "step": 42900 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.00315779697223e-05, | |
| "loss": 1.8403, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_gen_len": 18.999775583482943, | |
| "eval_loss": 1.6620622873306274, | |
| "eval_rouge1": 24.4632, | |
| "eval_rouge2": 11.7525, | |
| "eval_rougeL": 20.2459, | |
| "eval_rougeLsum": 23.0692, | |
| "eval_runtime": 1022.9465, | |
| "eval_samples_per_second": 13.068, | |
| "eval_steps_per_second": 1.634, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 2.9985139778954214e-05, | |
| "loss": 1.7771, | |
| "step": 43100 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 2.9938701588186124e-05, | |
| "loss": 1.7898, | |
| "step": 43200 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 2.9892263397418034e-05, | |
| "loss": 1.8423, | |
| "step": 43300 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 2.9845825206649954e-05, | |
| "loss": 1.8072, | |
| "step": 43400 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 2.9799387015881863e-05, | |
| "loss": 1.7805, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 2.9752948825113773e-05, | |
| "loss": 1.8016, | |
| "step": 43600 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 2.9706510634345686e-05, | |
| "loss": 1.8198, | |
| "step": 43700 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 2.9660072443577603e-05, | |
| "loss": 1.845, | |
| "step": 43800 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 2.9613634252809513e-05, | |
| "loss": 1.8332, | |
| "step": 43900 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 2.9567196062041426e-05, | |
| "loss": 1.8129, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "eval_gen_len": 18.99985038898863, | |
| "eval_loss": 1.66425359249115, | |
| "eval_rouge1": 24.6032, | |
| "eval_rouge2": 11.8251, | |
| "eval_rougeL": 20.3368, | |
| "eval_rougeLsum": 23.1806, | |
| "eval_runtime": 1020.3885, | |
| "eval_samples_per_second": 13.101, | |
| "eval_steps_per_second": 1.638, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 2.9520757871273335e-05, | |
| "loss": 1.8524, | |
| "step": 44100 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 2.9474319680505245e-05, | |
| "loss": 1.8298, | |
| "step": 44200 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 2.9427881489737165e-05, | |
| "loss": 1.8446, | |
| "step": 44300 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 2.9381443298969075e-05, | |
| "loss": 1.8012, | |
| "step": 44400 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 2.9335005108200985e-05, | |
| "loss": 1.8111, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 2.9288566917432898e-05, | |
| "loss": 1.7765, | |
| "step": 44600 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 2.9242128726664808e-05, | |
| "loss": 1.8229, | |
| "step": 44700 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 2.9195690535896724e-05, | |
| "loss": 1.8203, | |
| "step": 44800 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 2.9149252345128637e-05, | |
| "loss": 1.7998, | |
| "step": 44900 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 2.9102814154360547e-05, | |
| "loss": 1.7896, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_gen_len": 18.999251944943147, | |
| "eval_loss": 1.6622380018234253, | |
| "eval_rouge1": 24.4619, | |
| "eval_rouge2": 11.7769, | |
| "eval_rougeL": 20.2516, | |
| "eval_rougeLsum": 23.0647, | |
| "eval_runtime": 1031.3113, | |
| "eval_samples_per_second": 12.962, | |
| "eval_steps_per_second": 1.62, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 2.9056375963592457e-05, | |
| "loss": 1.8123, | |
| "step": 45100 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 2.9009937772824373e-05, | |
| "loss": 1.8106, | |
| "step": 45200 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 2.8963499582056286e-05, | |
| "loss": 1.8164, | |
| "step": 45300 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 2.8917061391288196e-05, | |
| "loss": 1.7791, | |
| "step": 45400 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 2.887062320052011e-05, | |
| "loss": 1.7977, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 2.882418500975202e-05, | |
| "loss": 1.749, | |
| "step": 45600 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 2.8777746818983935e-05, | |
| "loss": 1.827, | |
| "step": 45700 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 2.873130862821585e-05, | |
| "loss": 1.8235, | |
| "step": 45800 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 2.868487043744776e-05, | |
| "loss": 1.7922, | |
| "step": 45900 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 2.8638432246679668e-05, | |
| "loss": 1.7948, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_gen_len": 18.999177139437464, | |
| "eval_loss": 1.6607564687728882, | |
| "eval_rouge1": 24.5468, | |
| "eval_rouge2": 11.8041, | |
| "eval_rougeL": 20.2941, | |
| "eval_rougeLsum": 23.1551, | |
| "eval_runtime": 1037.8425, | |
| "eval_samples_per_second": 12.881, | |
| "eval_steps_per_second": 1.61, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 2.859199405591158e-05, | |
| "loss": 1.7752, | |
| "step": 46100 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 2.8545555865143498e-05, | |
| "loss": 1.8504, | |
| "step": 46200 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 2.8499117674375408e-05, | |
| "loss": 1.8319, | |
| "step": 46300 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 2.845267948360732e-05, | |
| "loss": 1.7981, | |
| "step": 46400 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 2.840624129283923e-05, | |
| "loss": 1.8179, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 2.8359803102071147e-05, | |
| "loss": 1.7838, | |
| "step": 46600 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 2.831336491130306e-05, | |
| "loss": 1.799, | |
| "step": 46700 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 2.826692672053497e-05, | |
| "loss": 1.812, | |
| "step": 46800 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 2.822048852976688e-05, | |
| "loss": 1.8216, | |
| "step": 46900 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 2.8174050338998793e-05, | |
| "loss": 1.8043, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_gen_len": 18.999326750448834, | |
| "eval_loss": 1.6613510847091675, | |
| "eval_rouge1": 24.5774, | |
| "eval_rouge2": 11.8246, | |
| "eval_rougeL": 20.3189, | |
| "eval_rougeLsum": 23.1836, | |
| "eval_runtime": 1024.3233, | |
| "eval_samples_per_second": 13.051, | |
| "eval_steps_per_second": 1.631, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 2.812761214823071e-05, | |
| "loss": 1.8114, | |
| "step": 47100 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.808117395746262e-05, | |
| "loss": 1.7885, | |
| "step": 47200 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.8034735766694532e-05, | |
| "loss": 1.7741, | |
| "step": 47300 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.7988297575926442e-05, | |
| "loss": 1.8216, | |
| "step": 47400 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.794185938515835e-05, | |
| "loss": 1.8408, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2.789542119439027e-05, | |
| "loss": 1.7825, | |
| "step": 47600 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2.784898300362218e-05, | |
| "loss": 1.8244, | |
| "step": 47700 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2.780254481285409e-05, | |
| "loss": 1.8074, | |
| "step": 47800 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2.7756106622086004e-05, | |
| "loss": 1.8102, | |
| "step": 47900 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2.7709668431317914e-05, | |
| "loss": 1.7884, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "eval_gen_len": 18.999326750448834, | |
| "eval_loss": 1.658116340637207, | |
| "eval_rouge1": 24.5688, | |
| "eval_rouge2": 11.843, | |
| "eval_rougeL": 20.2993, | |
| "eval_rougeLsum": 23.1756, | |
| "eval_runtime": 1026.94, | |
| "eval_samples_per_second": 13.017, | |
| "eval_steps_per_second": 1.627, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2.766323024054983e-05, | |
| "loss": 1.8173, | |
| "step": 48100 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2.7616792049781744e-05, | |
| "loss": 1.7631, | |
| "step": 48200 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.7570353859013653e-05, | |
| "loss": 1.7902, | |
| "step": 48300 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.7523915668245563e-05, | |
| "loss": 1.8197, | |
| "step": 48400 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.7477477477477483e-05, | |
| "loss": 1.8447, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.7431039286709393e-05, | |
| "loss": 1.7617, | |
| "step": 48600 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.7384601095941302e-05, | |
| "loss": 1.8125, | |
| "step": 48700 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.7338162905173216e-05, | |
| "loss": 1.8059, | |
| "step": 48800 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.7291724714405125e-05, | |
| "loss": 1.8517, | |
| "step": 48900 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2.7245286523637042e-05, | |
| "loss": 1.8041, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "eval_gen_len": 18.99955116696589, | |
| "eval_loss": 1.6614130735397339, | |
| "eval_rouge1": 24.5454, | |
| "eval_rouge2": 11.8346, | |
| "eval_rougeL": 20.3179, | |
| "eval_rougeLsum": 23.1605, | |
| "eval_runtime": 1026.6117, | |
| "eval_samples_per_second": 13.021, | |
| "eval_steps_per_second": 1.628, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2.7198848332868955e-05, | |
| "loss": 1.7901, | |
| "step": 49100 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2.7152410142100865e-05, | |
| "loss": 1.8027, | |
| "step": 49200 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2.7105971951332774e-05, | |
| "loss": 1.7979, | |
| "step": 49300 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.7059533760564688e-05, | |
| "loss": 1.7853, | |
| "step": 49400 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.7013095569796604e-05, | |
| "loss": 1.7663, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.6966657379028514e-05, | |
| "loss": 1.7904, | |
| "step": 49600 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.6920219188260427e-05, | |
| "loss": 1.8164, | |
| "step": 49700 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.6873780997492337e-05, | |
| "loss": 1.8056, | |
| "step": 49800 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.6827342806724253e-05, | |
| "loss": 1.7842, | |
| "step": 49900 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.6780904615956166e-05, | |
| "loss": 1.8192, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_gen_len": 18.999775583482943, | |
| "eval_loss": 1.6596847772598267, | |
| "eval_rouge1": 24.5017, | |
| "eval_rouge2": 11.7755, | |
| "eval_rougeL": 20.2439, | |
| "eval_rougeLsum": 23.1148, | |
| "eval_runtime": 1036.17, | |
| "eval_samples_per_second": 12.901, | |
| "eval_steps_per_second": 1.613, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2.6734466425188076e-05, | |
| "loss": 1.7418, | |
| "step": 50100 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2.6688028234419986e-05, | |
| "loss": 1.7761, | |
| "step": 50200 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2.66415900436519e-05, | |
| "loss": 1.7924, | |
| "step": 50300 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2.6595151852883816e-05, | |
| "loss": 1.8212, | |
| "step": 50400 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 2.6548713662115725e-05, | |
| "loss": 1.7813, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 2.650227547134764e-05, | |
| "loss": 1.8258, | |
| "step": 50600 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 2.6455837280579548e-05, | |
| "loss": 1.8491, | |
| "step": 50700 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2.640939908981146e-05, | |
| "loss": 1.8285, | |
| "step": 50800 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2.6362960899043378e-05, | |
| "loss": 1.8399, | |
| "step": 50900 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2.6316522708275288e-05, | |
| "loss": 1.8679, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "eval_gen_len": 18.999476361460204, | |
| "eval_loss": 1.6554793119430542, | |
| "eval_rouge1": 24.5302, | |
| "eval_rouge2": 11.7638, | |
| "eval_rougeL": 20.2592, | |
| "eval_rougeLsum": 23.1395, | |
| "eval_runtime": 1033.7739, | |
| "eval_samples_per_second": 12.931, | |
| "eval_steps_per_second": 1.616, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2.6270084517507197e-05, | |
| "loss": 1.7982, | |
| "step": 51100 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 2.622364632673911e-05, | |
| "loss": 1.8176, | |
| "step": 51200 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 2.6177208135971027e-05, | |
| "loss": 1.8155, | |
| "step": 51300 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 2.6130769945202937e-05, | |
| "loss": 1.8084, | |
| "step": 51400 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 2.608433175443485e-05, | |
| "loss": 1.824, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 2.603789356366676e-05, | |
| "loss": 1.7652, | |
| "step": 51600 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 2.599145537289867e-05, | |
| "loss": 1.7971, | |
| "step": 51700 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 2.594501718213059e-05, | |
| "loss": 1.8167, | |
| "step": 51800 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2.58985789913625e-05, | |
| "loss": 1.789, | |
| "step": 51900 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2.585214080059441e-05, | |
| "loss": 1.82, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "eval_gen_len": 18.999775583482943, | |
| "eval_loss": 1.6571003198623657, | |
| "eval_rouge1": 24.546, | |
| "eval_rouge2": 11.7798, | |
| "eval_rougeL": 20.265, | |
| "eval_rougeLsum": 23.1408, | |
| "eval_runtime": 1022.2185, | |
| "eval_samples_per_second": 13.077, | |
| "eval_steps_per_second": 1.635, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2.5805702609826322e-05, | |
| "loss": 1.8416, | |
| "step": 52100 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2.575926441905823e-05, | |
| "loss": 1.851, | |
| "step": 52200 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 2.5712826228290148e-05, | |
| "loss": 1.8012, | |
| "step": 52300 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 2.566638803752206e-05, | |
| "loss": 1.8015, | |
| "step": 52400 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 2.561994984675397e-05, | |
| "loss": 1.7634, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 2.557351165598588e-05, | |
| "loss": 1.8303, | |
| "step": 52600 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 2.5527073465217797e-05, | |
| "loss": 1.8022, | |
| "step": 52700 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 2.548063527444971e-05, | |
| "loss": 1.8292, | |
| "step": 52800 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 2.543419708368162e-05, | |
| "loss": 1.7705, | |
| "step": 52900 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 2.5387758892913533e-05, | |
| "loss": 1.8267, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_gen_len": 18.99955116696589, | |
| "eval_loss": 1.655230164527893, | |
| "eval_rouge1": 24.5214, | |
| "eval_rouge2": 11.7368, | |
| "eval_rougeL": 20.2276, | |
| "eval_rougeLsum": 23.1504, | |
| "eval_runtime": 1027.6634, | |
| "eval_samples_per_second": 13.008, | |
| "eval_steps_per_second": 1.626, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 2.5341320702145443e-05, | |
| "loss": 1.8101, | |
| "step": 53100 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 2.529488251137736e-05, | |
| "loss": 1.7931, | |
| "step": 53200 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 2.5248444320609273e-05, | |
| "loss": 1.8394, | |
| "step": 53300 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 2.5202006129841182e-05, | |
| "loss": 1.8143, | |
| "step": 53400 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 2.5155567939073092e-05, | |
| "loss": 1.8197, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 2.5109129748305005e-05, | |
| "loss": 1.8011, | |
| "step": 53600 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.5062691557536922e-05, | |
| "loss": 1.8094, | |
| "step": 53700 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.501625336676883e-05, | |
| "loss": 1.816, | |
| "step": 53800 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.4969815176000745e-05, | |
| "loss": 1.8274, | |
| "step": 53900 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.4923376985232658e-05, | |
| "loss": 1.8063, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_gen_len": 18.999177139437464, | |
| "eval_loss": 1.6588006019592285, | |
| "eval_rouge1": 24.5222, | |
| "eval_rouge2": 11.8209, | |
| "eval_rougeL": 20.2941, | |
| "eval_rougeLsum": 23.1551, | |
| "eval_runtime": 1031.4983, | |
| "eval_samples_per_second": 12.96, | |
| "eval_steps_per_second": 1.62, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 2.4876938794464568e-05, | |
| "loss": 1.8088, | |
| "step": 54100 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 2.483050060369648e-05, | |
| "loss": 1.8148, | |
| "step": 54200 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 2.4784062412928394e-05, | |
| "loss": 1.8075, | |
| "step": 54300 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.4737624222160304e-05, | |
| "loss": 1.8276, | |
| "step": 54400 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.469118603139222e-05, | |
| "loss": 1.7834, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.464474784062413e-05, | |
| "loss": 1.7928, | |
| "step": 54600 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.4598309649856043e-05, | |
| "loss": 1.7802, | |
| "step": 54700 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 2.4551871459087956e-05, | |
| "loss": 1.8131, | |
| "step": 54800 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 2.4505433268319866e-05, | |
| "loss": 1.7951, | |
| "step": 54900 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 2.445899507755178e-05, | |
| "loss": 1.8171, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "eval_gen_len": 18.999625972471573, | |
| "eval_loss": 1.656943440437317, | |
| "eval_rouge1": 24.5845, | |
| "eval_rouge2": 11.8182, | |
| "eval_rougeL": 20.3147, | |
| "eval_rougeLsum": 23.1812, | |
| "eval_runtime": 1034.3258, | |
| "eval_samples_per_second": 12.924, | |
| "eval_steps_per_second": 1.616, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2.4412556886783692e-05, | |
| "loss": 1.8054, | |
| "step": 55100 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2.4366118696015605e-05, | |
| "loss": 1.8182, | |
| "step": 55200 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2.4319680505247515e-05, | |
| "loss": 1.8019, | |
| "step": 55300 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2.427324231447943e-05, | |
| "loss": 1.7822, | |
| "step": 55400 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 2.422680412371134e-05, | |
| "loss": 1.7951, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 2.418036593294325e-05, | |
| "loss": 1.8077, | |
| "step": 55600 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 2.4133927742175168e-05, | |
| "loss": 1.7961, | |
| "step": 55700 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 2.4087489551407077e-05, | |
| "loss": 1.7619, | |
| "step": 55800 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 2.404105136063899e-05, | |
| "loss": 1.7999, | |
| "step": 55900 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 2.3994613169870904e-05, | |
| "loss": 1.7884, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "eval_gen_len": 18.999775583482943, | |
| "eval_loss": 1.6596565246582031, | |
| "eval_rouge1": 24.532, | |
| "eval_rouge2": 11.8057, | |
| "eval_rougeL": 20.2622, | |
| "eval_rougeLsum": 23.1459, | |
| "eval_runtime": 1029.0813, | |
| "eval_samples_per_second": 12.99, | |
| "eval_steps_per_second": 1.624, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 2.3948174979102817e-05, | |
| "loss": 1.8125, | |
| "step": 56100 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 2.3901736788334726e-05, | |
| "loss": 1.7802, | |
| "step": 56200 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 2.385529859756664e-05, | |
| "loss": 1.7974, | |
| "step": 56300 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 2.3808860406798553e-05, | |
| "loss": 1.8124, | |
| "step": 56400 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 2.3762422216030463e-05, | |
| "loss": 1.8032, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 2.371598402526238e-05, | |
| "loss": 1.7827, | |
| "step": 56600 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 2.366954583449429e-05, | |
| "loss": 1.7876, | |
| "step": 56700 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 2.3623107643726202e-05, | |
| "loss": 1.7645, | |
| "step": 56800 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 2.3576669452958115e-05, | |
| "loss": 1.8223, | |
| "step": 56900 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 2.3530231262190025e-05, | |
| "loss": 1.7588, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "eval_gen_len": 18.999401555954517, | |
| "eval_loss": 1.657245397567749, | |
| "eval_rouge1": 24.6532, | |
| "eval_rouge2": 11.8958, | |
| "eval_rougeL": 20.3877, | |
| "eval_rougeLsum": 23.2776, | |
| "eval_runtime": 1034.2975, | |
| "eval_samples_per_second": 12.925, | |
| "eval_steps_per_second": 1.616, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 2.3483793071421938e-05, | |
| "loss": 1.8284, | |
| "step": 57100 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 2.343735488065385e-05, | |
| "loss": 1.7801, | |
| "step": 57200 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.3390916689885764e-05, | |
| "loss": 1.8094, | |
| "step": 57300 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.3344478499117674e-05, | |
| "loss": 1.7872, | |
| "step": 57400 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.329804030834959e-05, | |
| "loss": 1.8076, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.32516021175815e-05, | |
| "loss": 1.7796, | |
| "step": 57600 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 2.320516392681341e-05, | |
| "loss": 1.7982, | |
| "step": 57700 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 2.3158725736045326e-05, | |
| "loss": 1.7809, | |
| "step": 57800 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 2.3112287545277236e-05, | |
| "loss": 1.8185, | |
| "step": 57900 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 2.306584935450915e-05, | |
| "loss": 1.7847, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "eval_gen_len": 18.99955116696589, | |
| "eval_loss": 1.6560837030410767, | |
| "eval_rouge1": 24.5483, | |
| "eval_rouge2": 11.856, | |
| "eval_rougeL": 20.3188, | |
| "eval_rougeLsum": 23.1852, | |
| "eval_runtime": 1032.6185, | |
| "eval_samples_per_second": 12.946, | |
| "eval_steps_per_second": 1.618, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 2.3019411163741062e-05, | |
| "loss": 1.8374, | |
| "step": 58100 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 2.2972972972972976e-05, | |
| "loss": 1.7944, | |
| "step": 58200 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 2.2926534782204885e-05, | |
| "loss": 1.826, | |
| "step": 58300 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 2.28800965914368e-05, | |
| "loss": 1.8044, | |
| "step": 58400 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 2.283365840066871e-05, | |
| "loss": 1.8192, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 2.278722020990062e-05, | |
| "loss": 1.812, | |
| "step": 58600 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 2.2740782019132538e-05, | |
| "loss": 1.79, | |
| "step": 58700 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 2.2694343828364448e-05, | |
| "loss": 1.7627, | |
| "step": 58800 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 2.264790563759636e-05, | |
| "loss": 1.7941, | |
| "step": 58900 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 2.2601467446828274e-05, | |
| "loss": 1.8523, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_gen_len": 18.99955116696589, | |
| "eval_loss": 1.6583877801895142, | |
| "eval_rouge1": 24.5501, | |
| "eval_rouge2": 11.8666, | |
| "eval_rougeL": 20.3197, | |
| "eval_rougeLsum": 23.1683, | |
| "eval_runtime": 1024.679, | |
| "eval_samples_per_second": 13.046, | |
| "eval_steps_per_second": 1.631, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 2.2555029256060184e-05, | |
| "loss": 1.7878, | |
| "step": 59100 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 2.2508591065292097e-05, | |
| "loss": 1.8199, | |
| "step": 59200 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 2.246215287452401e-05, | |
| "loss": 1.8112, | |
| "step": 59300 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 2.2415714683755923e-05, | |
| "loss": 1.808, | |
| "step": 59400 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 2.2369276492987833e-05, | |
| "loss": 1.8271, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 2.232283830221975e-05, | |
| "loss": 1.8064, | |
| "step": 59600 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 2.227640011145166e-05, | |
| "loss": 1.8218, | |
| "step": 59700 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 2.222996192068357e-05, | |
| "loss": 1.7955, | |
| "step": 59800 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 2.2183523729915485e-05, | |
| "loss": 1.822, | |
| "step": 59900 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 2.2137085539147395e-05, | |
| "loss": 1.7955, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "eval_gen_len": 18.999925194494313, | |
| "eval_loss": 1.6546396017074585, | |
| "eval_rouge1": 24.5126, | |
| "eval_rouge2": 11.8043, | |
| "eval_rougeL": 20.2603, | |
| "eval_rougeLsum": 23.1175, | |
| "eval_runtime": 1034.7782, | |
| "eval_samples_per_second": 12.919, | |
| "eval_steps_per_second": 1.615, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 2.2090647348379308e-05, | |
| "loss": 1.8306, | |
| "step": 60100 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 2.204420915761122e-05, | |
| "loss": 1.8132, | |
| "step": 60200 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 2.1997770966843135e-05, | |
| "loss": 1.8131, | |
| "step": 60300 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 2.1951332776075044e-05, | |
| "loss": 1.7976, | |
| "step": 60400 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 2.1904894585306957e-05, | |
| "loss": 1.7933, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 2.185845639453887e-05, | |
| "loss": 1.8118, | |
| "step": 60600 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 2.181201820377078e-05, | |
| "loss": 1.8073, | |
| "step": 60700 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 2.1765580013002697e-05, | |
| "loss": 1.7865, | |
| "step": 60800 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 2.1719141822234607e-05, | |
| "loss": 1.7636, | |
| "step": 60900 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 2.1672703631466516e-05, | |
| "loss": 1.8215, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "eval_gen_len": 18.999625972471573, | |
| "eval_loss": 1.654118299484253, | |
| "eval_rouge1": 24.5884, | |
| "eval_rouge2": 11.8003, | |
| "eval_rougeL": 20.2887, | |
| "eval_rougeLsum": 23.1866, | |
| "eval_runtime": 1027.8853, | |
| "eval_samples_per_second": 13.005, | |
| "eval_steps_per_second": 1.626, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 2.1626265440698433e-05, | |
| "loss": 1.8436, | |
| "step": 61100 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 2.1579827249930343e-05, | |
| "loss": 1.7967, | |
| "step": 61200 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 2.1533389059162256e-05, | |
| "loss": 1.7764, | |
| "step": 61300 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 2.148695086839417e-05, | |
| "loss": 1.8181, | |
| "step": 61400 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 2.1440512677626082e-05, | |
| "loss": 1.7699, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 2.1394074486857992e-05, | |
| "loss": 1.8442, | |
| "step": 61600 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 2.1347636296089905e-05, | |
| "loss": 1.7805, | |
| "step": 61700 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 2.1301198105321818e-05, | |
| "loss": 1.8129, | |
| "step": 61800 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 2.1254759914553728e-05, | |
| "loss": 1.7628, | |
| "step": 61900 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 2.1208321723785644e-05, | |
| "loss": 1.7917, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_gen_len": 18.99970077797726, | |
| "eval_loss": 1.6567963361740112, | |
| "eval_rouge1": 24.619, | |
| "eval_rouge2": 11.8868, | |
| "eval_rougeL": 20.3496, | |
| "eval_rougeLsum": 23.2304, | |
| "eval_runtime": 1035.7478, | |
| "eval_samples_per_second": 12.907, | |
| "eval_steps_per_second": 1.613, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 2.1161883533017554e-05, | |
| "loss": 1.7878, | |
| "step": 62100 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 2.1115445342249467e-05, | |
| "loss": 1.7953, | |
| "step": 62200 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 2.106900715148138e-05, | |
| "loss": 1.826, | |
| "step": 62300 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 2.102256896071329e-05, | |
| "loss": 1.8013, | |
| "step": 62400 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 2.0976130769945203e-05, | |
| "loss": 1.8322, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 2.0929692579177116e-05, | |
| "loss": 1.7874, | |
| "step": 62600 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 2.088325438840903e-05, | |
| "loss": 1.8104, | |
| "step": 62700 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 2.083681619764094e-05, | |
| "loss": 1.7578, | |
| "step": 62800 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 2.0790378006872856e-05, | |
| "loss": 1.8312, | |
| "step": 62900 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2.0743939816104765e-05, | |
| "loss": 1.7543, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_gen_len": 18.99955116696589, | |
| "eval_loss": 1.6570059061050415, | |
| "eval_rouge1": 24.5378, | |
| "eval_rouge2": 11.8192, | |
| "eval_rougeL": 20.2681, | |
| "eval_rougeLsum": 23.1454, | |
| "eval_runtime": 1031.5618, | |
| "eval_samples_per_second": 12.959, | |
| "eval_steps_per_second": 1.62, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2.0697501625336675e-05, | |
| "loss": 1.8303, | |
| "step": 63100 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2.065106343456859e-05, | |
| "loss": 1.7995, | |
| "step": 63200 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2.06046252438005e-05, | |
| "loss": 1.814, | |
| "step": 63300 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 2.0558187053032415e-05, | |
| "loss": 1.8235, | |
| "step": 63400 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 2.0511748862264328e-05, | |
| "loss": 1.8151, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 2.046531067149624e-05, | |
| "loss": 1.8041, | |
| "step": 63600 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 2.041887248072815e-05, | |
| "loss": 1.8169, | |
| "step": 63700 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 2.0372434289960064e-05, | |
| "loss": 1.7921, | |
| "step": 63800 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 2.0325996099191977e-05, | |
| "loss": 1.8136, | |
| "step": 63900 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 2.0279557908423887e-05, | |
| "loss": 1.7978, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "eval_gen_len": 18.99985038898863, | |
| "eval_loss": 1.6541448831558228, | |
| "eval_rouge1": 24.5719, | |
| "eval_rouge2": 11.8446, | |
| "eval_rougeL": 20.2873, | |
| "eval_rougeLsum": 23.1855, | |
| "eval_runtime": 1033.6446, | |
| "eval_samples_per_second": 12.933, | |
| "eval_steps_per_second": 1.617, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 2.0233119717655803e-05, | |
| "loss": 1.799, | |
| "step": 64100 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 2.0186681526887713e-05, | |
| "loss": 1.8007, | |
| "step": 64200 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 2.0140243336119626e-05, | |
| "loss": 1.7989, | |
| "step": 64300 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 2.009380514535154e-05, | |
| "loss": 1.8069, | |
| "step": 64400 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 2.004736695458345e-05, | |
| "loss": 1.7949, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 2.0000928763815362e-05, | |
| "loss": 1.8045, | |
| "step": 64600 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 1.9954490573047275e-05, | |
| "loss": 1.8275, | |
| "step": 64700 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 1.9908052382279188e-05, | |
| "loss": 1.8041, | |
| "step": 64800 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 1.9861614191511098e-05, | |
| "loss": 1.7827, | |
| "step": 64900 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 1.9815176000743015e-05, | |
| "loss": 1.8228, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "eval_gen_len": 18.999775583482943, | |
| "eval_loss": 1.6561096906661987, | |
| "eval_rouge1": 24.5193, | |
| "eval_rouge2": 11.8527, | |
| "eval_rougeL": 20.3185, | |
| "eval_rougeLsum": 23.1395, | |
| "eval_runtime": 1033.2498, | |
| "eval_samples_per_second": 12.938, | |
| "eval_steps_per_second": 1.617, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 1.9768737809974924e-05, | |
| "loss": 1.8076, | |
| "step": 65100 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 1.9722299619206834e-05, | |
| "loss": 1.7672, | |
| "step": 65200 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 1.967586142843875e-05, | |
| "loss": 1.8212, | |
| "step": 65300 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 1.962942323767066e-05, | |
| "loss": 1.8367, | |
| "step": 65400 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 1.9582985046902573e-05, | |
| "loss": 1.8581, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 1.9536546856134487e-05, | |
| "loss": 1.7974, | |
| "step": 65600 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 1.94901086653664e-05, | |
| "loss": 1.7626, | |
| "step": 65700 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 1.944367047459831e-05, | |
| "loss": 1.7704, | |
| "step": 65800 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 1.9397232283830223e-05, | |
| "loss": 1.8347, | |
| "step": 65900 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 1.9350794093062136e-05, | |
| "loss": 1.8163, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "eval_gen_len": 18.999775583482943, | |
| "eval_loss": 1.6537002325057983, | |
| "eval_rouge1": 24.4385, | |
| "eval_rouge2": 11.7625, | |
| "eval_rougeL": 20.2042, | |
| "eval_rougeLsum": 23.0671, | |
| "eval_runtime": 1036.124, | |
| "eval_samples_per_second": 12.902, | |
| "eval_steps_per_second": 1.613, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 1.9304355902294045e-05, | |
| "loss": 1.7862, | |
| "step": 66100 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 1.9257917711525962e-05, | |
| "loss": 1.7817, | |
| "step": 66200 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 1.9211479520757872e-05, | |
| "loss": 1.8224, | |
| "step": 66300 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 1.9165041329989785e-05, | |
| "loss": 1.808, | |
| "step": 66400 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 1.9118603139221698e-05, | |
| "loss": 1.7908, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 1.9072164948453608e-05, | |
| "loss": 1.8254, | |
| "step": 66600 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 1.902572675768552e-05, | |
| "loss": 1.7312, | |
| "step": 66700 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 1.8979288566917434e-05, | |
| "loss": 1.7895, | |
| "step": 66800 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 1.8932850376149347e-05, | |
| "loss": 1.7815, | |
| "step": 66900 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 1.8886412185381257e-05, | |
| "loss": 1.7868, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_gen_len": 18.999775583482943, | |
| "eval_loss": 1.653245210647583, | |
| "eval_rouge1": 24.4985, | |
| "eval_rouge2": 11.8187, | |
| "eval_rougeL": 20.2775, | |
| "eval_rougeLsum": 23.1426, | |
| "eval_runtime": 1028.3624, | |
| "eval_samples_per_second": 12.999, | |
| "eval_steps_per_second": 1.625, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 1.8839973994613173e-05, | |
| "loss": 1.8127, | |
| "step": 67100 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 1.8793535803845083e-05, | |
| "loss": 1.8062, | |
| "step": 67200 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 1.8747097613076993e-05, | |
| "loss": 1.809, | |
| "step": 67300 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 1.870065942230891e-05, | |
| "loss": 1.7546, | |
| "step": 67400 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 1.865422123154082e-05, | |
| "loss": 1.7803, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 1.8607783040772732e-05, | |
| "loss": 1.8209, | |
| "step": 67600 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 1.8561344850004645e-05, | |
| "loss": 1.8339, | |
| "step": 67700 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 1.851490665923656e-05, | |
| "loss": 1.8038, | |
| "step": 67800 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 1.846846846846847e-05, | |
| "loss": 1.806, | |
| "step": 67900 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 1.842203027770038e-05, | |
| "loss": 1.8345, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "eval_gen_len": 18.99985038898863, | |
| "eval_loss": 1.6522008180618286, | |
| "eval_rouge1": 24.5375, | |
| "eval_rouge2": 11.8398, | |
| "eval_rougeL": 20.285, | |
| "eval_rougeLsum": 23.1643, | |
| "eval_runtime": 1032.6207, | |
| "eval_samples_per_second": 12.946, | |
| "eval_steps_per_second": 1.618, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 1.8375592086932295e-05, | |
| "loss": 1.7729, | |
| "step": 68100 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 1.8329153896164204e-05, | |
| "loss": 1.7864, | |
| "step": 68200 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 1.828271570539612e-05, | |
| "loss": 1.8057, | |
| "step": 68300 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 1.823627751462803e-05, | |
| "loss": 1.7886, | |
| "step": 68400 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 1.8189839323859944e-05, | |
| "loss": 1.7784, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 1.8143401133091857e-05, | |
| "loss": 1.7989, | |
| "step": 68600 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 1.8096962942323767e-05, | |
| "loss": 1.7866, | |
| "step": 68700 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 1.805052475155568e-05, | |
| "loss": 1.8348, | |
| "step": 68800 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 1.8004086560787593e-05, | |
| "loss": 1.7391, | |
| "step": 68900 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 1.7957648370019506e-05, | |
| "loss": 1.7773, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_gen_len": 18.99985038898863, | |
| "eval_loss": 1.6528586149215698, | |
| "eval_rouge1": 24.4722, | |
| "eval_rouge2": 11.7979, | |
| "eval_rougeL": 20.2636, | |
| "eval_rougeLsum": 23.106, | |
| "eval_runtime": 1032.709, | |
| "eval_samples_per_second": 12.945, | |
| "eval_steps_per_second": 1.618, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.7911210179251416e-05, | |
| "loss": 1.8172, | |
| "step": 69100 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.7864771988483332e-05, | |
| "loss": 1.7618, | |
| "step": 69200 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.7818333797715242e-05, | |
| "loss": 1.7885, | |
| "step": 69300 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.7771895606947152e-05, | |
| "loss": 1.7803, | |
| "step": 69400 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 1.772545741617907e-05, | |
| "loss": 1.8239, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 1.7679019225410978e-05, | |
| "loss": 1.8412, | |
| "step": 69600 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 1.763258103464289e-05, | |
| "loss": 1.8328, | |
| "step": 69700 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 1.7586142843874804e-05, | |
| "loss": 1.8049, | |
| "step": 69800 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 1.7539704653106717e-05, | |
| "loss": 1.8353, | |
| "step": 69900 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 1.7493266462338627e-05, | |
| "loss": 1.8409, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "eval_gen_len": 18.99985038898863, | |
| "eval_loss": 1.6521377563476562, | |
| "eval_rouge1": 24.4845, | |
| "eval_rouge2": 11.8136, | |
| "eval_rougeL": 20.2557, | |
| "eval_rougeLsum": 23.1089, | |
| "eval_runtime": 1028.0193, | |
| "eval_samples_per_second": 13.004, | |
| "eval_steps_per_second": 1.625, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 1.744682827157054e-05, | |
| "loss": 1.7909, | |
| "step": 70100 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 1.7400390080802453e-05, | |
| "loss": 1.8121, | |
| "step": 70200 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 1.7353951890034363e-05, | |
| "loss": 1.814, | |
| "step": 70300 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 1.730751369926628e-05, | |
| "loss": 1.7987, | |
| "step": 70400 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 1.726107550849819e-05, | |
| "loss": 1.7947, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 1.72146373177301e-05, | |
| "loss": 1.7807, | |
| "step": 70600 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 1.7168199126962016e-05, | |
| "loss": 1.8074, | |
| "step": 70700 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 1.7121760936193926e-05, | |
| "loss": 1.7884, | |
| "step": 70800 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 1.707532274542584e-05, | |
| "loss": 1.7609, | |
| "step": 70900 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 1.7028884554657752e-05, | |
| "loss": 1.8146, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "eval_gen_len": 18.99985038898863, | |
| "eval_loss": 1.6515237092971802, | |
| "eval_rouge1": 24.4923, | |
| "eval_rouge2": 11.7965, | |
| "eval_rougeL": 20.2521, | |
| "eval_rougeLsum": 23.1247, | |
| "eval_runtime": 1024.8513, | |
| "eval_samples_per_second": 13.044, | |
| "eval_steps_per_second": 1.63, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 1.6982446363889665e-05, | |
| "loss": 1.7835, | |
| "step": 71100 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 1.6936008173121575e-05, | |
| "loss": 1.8227, | |
| "step": 71200 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 1.6889569982353488e-05, | |
| "loss": 1.8015, | |
| "step": 71300 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 1.68431317915854e-05, | |
| "loss": 1.79, | |
| "step": 71400 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 1.679669360081731e-05, | |
| "loss": 1.7974, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 1.6750255410049227e-05, | |
| "loss": 1.8084, | |
| "step": 71600 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.6703817219281137e-05, | |
| "loss": 1.8178, | |
| "step": 71700 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.665737902851305e-05, | |
| "loss": 1.7481, | |
| "step": 71800 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.6610940837744963e-05, | |
| "loss": 1.7653, | |
| "step": 71900 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1.6564502646976873e-05, | |
| "loss": 1.7466, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.6526038646697998, | |
| "eval_rouge1": 24.4913, | |
| "eval_rouge2": 11.8254, | |
| "eval_rougeL": 20.2562, | |
| "eval_rougeLsum": 23.1266, | |
| "eval_runtime": 1034.5967, | |
| "eval_samples_per_second": 12.921, | |
| "eval_steps_per_second": 1.615, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1.6518064456208786e-05, | |
| "loss": 1.7975, | |
| "step": 72100 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1.64716262654407e-05, | |
| "loss": 1.7617, | |
| "step": 72200 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1.6425188074672612e-05, | |
| "loss": 1.7838, | |
| "step": 72300 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1.6378749883904522e-05, | |
| "loss": 1.8457, | |
| "step": 72400 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1.633231169313644e-05, | |
| "loss": 1.7611, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1.628587350236835e-05, | |
| "loss": 1.788, | |
| "step": 72600 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1.6239435311600258e-05, | |
| "loss": 1.785, | |
| "step": 72700 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1.6192997120832175e-05, | |
| "loss": 1.8231, | |
| "step": 72800 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1.6146558930064084e-05, | |
| "loss": 1.7751, | |
| "step": 72900 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1.6100120739295998e-05, | |
| "loss": 1.8009, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.6505471467971802, | |
| "eval_rouge1": 24.5231, | |
| "eval_rouge2": 11.8414, | |
| "eval_rougeL": 20.2842, | |
| "eval_rougeLsum": 23.1654, | |
| "eval_runtime": 1023.213, | |
| "eval_samples_per_second": 13.065, | |
| "eval_steps_per_second": 1.633, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.605368254852791e-05, | |
| "loss": 1.8207, | |
| "step": 73100 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.6007244357759824e-05, | |
| "loss": 1.7569, | |
| "step": 73200 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.5960806166991734e-05, | |
| "loss": 1.7819, | |
| "step": 73300 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.5914367976223647e-05, | |
| "loss": 1.7628, | |
| "step": 73400 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.586792978545556e-05, | |
| "loss": 1.8075, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.582149159468747e-05, | |
| "loss": 1.7719, | |
| "step": 73600 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.5775053403919386e-05, | |
| "loss": 1.8057, | |
| "step": 73700 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1.5728615213151296e-05, | |
| "loss": 1.7819, | |
| "step": 73800 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1.568217702238321e-05, | |
| "loss": 1.7737, | |
| "step": 73900 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1.5635738831615122e-05, | |
| "loss": 1.7768, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.6516097784042358, | |
| "eval_rouge1": 24.5192, | |
| "eval_rouge2": 11.8206, | |
| "eval_rougeL": 20.2884, | |
| "eval_rougeLsum": 23.1493, | |
| "eval_runtime": 1036.5849, | |
| "eval_samples_per_second": 12.896, | |
| "eval_steps_per_second": 1.612, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1.5589300640847032e-05, | |
| "loss": 1.8128, | |
| "step": 74100 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.5542862450078945e-05, | |
| "loss": 1.8214, | |
| "step": 74200 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.5496424259310858e-05, | |
| "loss": 1.8027, | |
| "step": 74300 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.544998606854277e-05, | |
| "loss": 1.7881, | |
| "step": 74400 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1.540354787777468e-05, | |
| "loss": 1.8071, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1.5357109687006598e-05, | |
| "loss": 1.7745, | |
| "step": 74600 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1.5310671496238507e-05, | |
| "loss": 1.7855, | |
| "step": 74700 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1.5264233305470417e-05, | |
| "loss": 1.7824, | |
| "step": 74800 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 1.5217795114702332e-05, | |
| "loss": 1.8059, | |
| "step": 74900 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 1.5171356923934243e-05, | |
| "loss": 1.7569, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.6540724039077759, | |
| "eval_rouge1": 24.6135, | |
| "eval_rouge2": 11.9135, | |
| "eval_rougeL": 20.3513, | |
| "eval_rougeLsum": 23.2279, | |
| "eval_runtime": 1023.1896, | |
| "eval_samples_per_second": 13.065, | |
| "eval_steps_per_second": 1.633, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 1.5124918733166158e-05, | |
| "loss": 1.8309, | |
| "step": 75100 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 1.5078480542398068e-05, | |
| "loss": 1.8047, | |
| "step": 75200 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 1.5032042351629983e-05, | |
| "loss": 1.7746, | |
| "step": 75300 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 1.4985604160861894e-05, | |
| "loss": 1.8134, | |
| "step": 75400 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 1.4939165970093804e-05, | |
| "loss": 1.7825, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 1.4892727779325719e-05, | |
| "loss": 1.7939, | |
| "step": 75600 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 1.484628958855763e-05, | |
| "loss": 1.7539, | |
| "step": 75700 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 1.4799851397789543e-05, | |
| "loss": 1.7659, | |
| "step": 75800 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 1.4753413207021455e-05, | |
| "loss": 1.7926, | |
| "step": 75900 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 1.470697501625337e-05, | |
| "loss": 1.7893, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "eval_gen_len": 18.99970077797726, | |
| "eval_loss": 1.6507411003112793, | |
| "eval_rouge1": 24.5934, | |
| "eval_rouge2": 11.8727, | |
| "eval_rougeL": 20.3305, | |
| "eval_rougeLsum": 23.2106, | |
| "eval_runtime": 1030.6978, | |
| "eval_samples_per_second": 12.97, | |
| "eval_steps_per_second": 1.621, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 1.466053682548528e-05, | |
| "loss": 1.7752, | |
| "step": 76100 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 1.461409863471719e-05, | |
| "loss": 1.8088, | |
| "step": 76200 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 1.4567660443949106e-05, | |
| "loss": 1.8084, | |
| "step": 76300 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 1.4521222253181015e-05, | |
| "loss": 1.7934, | |
| "step": 76400 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 1.447478406241293e-05, | |
| "loss": 1.7928, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 1.4428345871644842e-05, | |
| "loss": 1.783, | |
| "step": 76600 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1.4381907680876755e-05, | |
| "loss": 1.806, | |
| "step": 76700 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1.4335469490108666e-05, | |
| "loss": 1.7723, | |
| "step": 76800 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1.4289031299340578e-05, | |
| "loss": 1.7634, | |
| "step": 76900 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 1.424259310857249e-05, | |
| "loss": 1.763, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "eval_gen_len": 18.999925194494313, | |
| "eval_loss": 1.6511585712432861, | |
| "eval_rouge1": 24.5829, | |
| "eval_rouge2": 11.8543, | |
| "eval_rougeL": 20.3142, | |
| "eval_rougeLsum": 23.2049, | |
| "eval_runtime": 1026.6075, | |
| "eval_samples_per_second": 13.022, | |
| "eval_steps_per_second": 1.628, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 1.4196154917804402e-05, | |
| "loss": 1.7742, | |
| "step": 77100 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 1.4149716727036317e-05, | |
| "loss": 1.7836, | |
| "step": 77200 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 1.4103278536268227e-05, | |
| "loss": 1.8182, | |
| "step": 77300 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 1.4056840345500142e-05, | |
| "loss": 1.7747, | |
| "step": 77400 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 1.4010402154732053e-05, | |
| "loss": 1.7785, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 1.3963963963963963e-05, | |
| "loss": 1.8223, | |
| "step": 77600 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 1.3917525773195878e-05, | |
| "loss": 1.7769, | |
| "step": 77700 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.3871087582427789e-05, | |
| "loss": 1.772, | |
| "step": 77800 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.3824649391659702e-05, | |
| "loss": 1.8052, | |
| "step": 77900 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.3778211200891614e-05, | |
| "loss": 1.7552, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "eval_gen_len": 18.999775583482943, | |
| "eval_loss": 1.6506332159042358, | |
| "eval_rouge1": 24.5332, | |
| "eval_rouge2": 11.8309, | |
| "eval_rougeL": 20.2795, | |
| "eval_rougeLsum": 23.1654, | |
| "eval_runtime": 1034.7013, | |
| "eval_samples_per_second": 12.92, | |
| "eval_steps_per_second": 1.615, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 1.3731773010123527e-05, | |
| "loss": 1.8099, | |
| "step": 78100 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 1.3685334819355438e-05, | |
| "loss": 1.8016, | |
| "step": 78200 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 1.363889662858735e-05, | |
| "loss": 1.8055, | |
| "step": 78300 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 1.3592458437819264e-05, | |
| "loss": 1.7729, | |
| "step": 78400 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1.3546020247051174e-05, | |
| "loss": 1.7733, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1.3499582056283089e-05, | |
| "loss": 1.8059, | |
| "step": 78600 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1.3453143865515e-05, | |
| "loss": 1.7685, | |
| "step": 78700 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 1.3406705674746914e-05, | |
| "loss": 1.7758, | |
| "step": 78800 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 1.3360267483978825e-05, | |
| "loss": 1.8085, | |
| "step": 78900 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 1.3313829293210736e-05, | |
| "loss": 1.7632, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "eval_gen_len": 18.999476361460204, | |
| "eval_loss": 1.6498222351074219, | |
| "eval_rouge1": 24.5569, | |
| "eval_rouge2": 11.8313, | |
| "eval_rougeL": 20.3158, | |
| "eval_rougeLsum": 23.1808, | |
| "eval_runtime": 1034.8948, | |
| "eval_samples_per_second": 12.917, | |
| "eval_steps_per_second": 1.615, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 1.326739110244265e-05, | |
| "loss": 1.7951, | |
| "step": 79100 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 1.3220952911674561e-05, | |
| "loss": 1.8045, | |
| "step": 79200 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 1.3174514720906476e-05, | |
| "loss": 1.8099, | |
| "step": 79300 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 1.3128076530138386e-05, | |
| "loss": 1.7945, | |
| "step": 79400 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 1.30816383393703e-05, | |
| "loss": 1.7755, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 1.3035200148602212e-05, | |
| "loss": 1.8063, | |
| "step": 79600 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 1.2988761957834122e-05, | |
| "loss": 1.805, | |
| "step": 79700 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 1.2942323767066036e-05, | |
| "loss": 1.7553, | |
| "step": 79800 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 1.2895885576297948e-05, | |
| "loss": 1.7999, | |
| "step": 79900 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 1.2849447385529861e-05, | |
| "loss": 1.8056, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "eval_gen_len": 18.99955116696589, | |
| "eval_loss": 1.648803949356079, | |
| "eval_rouge1": 24.6217, | |
| "eval_rouge2": 11.8877, | |
| "eval_rougeL": 20.3555, | |
| "eval_rougeLsum": 23.2514, | |
| "eval_runtime": 1025.8108, | |
| "eval_samples_per_second": 13.032, | |
| "eval_steps_per_second": 1.629, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 1.2803009194761772e-05, | |
| "loss": 1.8237, | |
| "step": 80100 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 1.2756571003993684e-05, | |
| "loss": 1.7823, | |
| "step": 80200 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 1.2710132813225597e-05, | |
| "loss": 1.7627, | |
| "step": 80300 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 1.2663694622457508e-05, | |
| "loss": 1.8085, | |
| "step": 80400 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 1.2617256431689423e-05, | |
| "loss": 1.802, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 1.2570818240921333e-05, | |
| "loss": 1.7549, | |
| "step": 80600 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 1.2524380050153248e-05, | |
| "loss": 1.8025, | |
| "step": 80700 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 1.247794185938516e-05, | |
| "loss": 1.7366, | |
| "step": 80800 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 1.243150366861707e-05, | |
| "loss": 1.7989, | |
| "step": 80900 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 1.2385065477848984e-05, | |
| "loss": 1.8066, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "eval_gen_len": 18.99955116696589, | |
| "eval_loss": 1.6494295597076416, | |
| "eval_rouge1": 24.5799, | |
| "eval_rouge2": 11.8515, | |
| "eval_rougeL": 20.3307, | |
| "eval_rougeLsum": 23.2059, | |
| "eval_runtime": 1033.346, | |
| "eval_samples_per_second": 12.937, | |
| "eval_steps_per_second": 1.617, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 1.2338627287080897e-05, | |
| "loss": 1.7608, | |
| "step": 81100 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 1.2292189096312808e-05, | |
| "loss": 1.7725, | |
| "step": 81200 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 1.224575090554472e-05, | |
| "loss": 1.8072, | |
| "step": 81300 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 1.2199312714776633e-05, | |
| "loss": 1.8053, | |
| "step": 81400 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 1.2152874524008545e-05, | |
| "loss": 1.7835, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 1.2106436333240458e-05, | |
| "loss": 1.7689, | |
| "step": 81600 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 1.205999814247237e-05, | |
| "loss": 1.7674, | |
| "step": 81700 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 1.2013559951704282e-05, | |
| "loss": 1.7972, | |
| "step": 81800 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 1.1967121760936195e-05, | |
| "loss": 1.7737, | |
| "step": 81900 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 1.1920683570168107e-05, | |
| "loss": 1.7903, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "eval_gen_len": 18.999775583482943, | |
| "eval_loss": 1.64866042137146, | |
| "eval_rouge1": 24.6151, | |
| "eval_rouge2": 11.889, | |
| "eval_rougeL": 20.3739, | |
| "eval_rougeLsum": 23.2226, | |
| "eval_runtime": 1030.2163, | |
| "eval_samples_per_second": 12.976, | |
| "eval_steps_per_second": 1.622, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 1.1874245379400018e-05, | |
| "loss": 1.8065, | |
| "step": 82100 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 1.1827807188631931e-05, | |
| "loss": 1.7835, | |
| "step": 82200 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 1.1781368997863844e-05, | |
| "loss": 1.8129, | |
| "step": 82300 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 1.1734930807095756e-05, | |
| "loss": 1.7741, | |
| "step": 82400 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 1.1688492616327669e-05, | |
| "loss": 1.7969, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 1.164205442555958e-05, | |
| "loss": 1.8015, | |
| "step": 82600 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 1.1595616234791492e-05, | |
| "loss": 1.8278, | |
| "step": 82700 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 1.1549178044023405e-05, | |
| "loss": 1.7772, | |
| "step": 82800 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 1.1502739853255318e-05, | |
| "loss": 1.7987, | |
| "step": 82900 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 1.145630166248723e-05, | |
| "loss": 1.805, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "eval_gen_len": 18.999625972471573, | |
| "eval_loss": 1.6492658853530884, | |
| "eval_rouge1": 24.5739, | |
| "eval_rouge2": 11.8659, | |
| "eval_rougeL": 20.3354, | |
| "eval_rougeLsum": 23.1884, | |
| "eval_runtime": 1027.6519, | |
| "eval_samples_per_second": 13.008, | |
| "eval_steps_per_second": 1.626, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 1.1409863471719143e-05, | |
| "loss": 1.7888, | |
| "step": 83100 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 1.1363425280951056e-05, | |
| "loss": 1.7929, | |
| "step": 83200 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 1.1316987090182966e-05, | |
| "loss": 1.7597, | |
| "step": 83300 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 1.1270548899414879e-05, | |
| "loss": 1.7312, | |
| "step": 83400 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 1.1224110708646792e-05, | |
| "loss": 1.8046, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 1.1177672517878703e-05, | |
| "loss": 1.7843, | |
| "step": 83600 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 1.1131234327110617e-05, | |
| "loss": 1.7888, | |
| "step": 83700 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 1.108479613634253e-05, | |
| "loss": 1.788, | |
| "step": 83800 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 1.1038357945574441e-05, | |
| "loss": 1.7549, | |
| "step": 83900 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 1.0991919754806353e-05, | |
| "loss": 1.7843, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "eval_gen_len": 18.999625972471573, | |
| "eval_loss": 1.6487183570861816, | |
| "eval_rouge1": 24.6125, | |
| "eval_rouge2": 11.8879, | |
| "eval_rougeL": 20.3648, | |
| "eval_rougeLsum": 23.2274, | |
| "eval_runtime": 1035.6996, | |
| "eval_samples_per_second": 12.907, | |
| "eval_steps_per_second": 1.613, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 1.0945481564038266e-05, | |
| "loss": 1.804, | |
| "step": 84100 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 1.0899043373270177e-05, | |
| "loss": 1.7363, | |
| "step": 84200 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 1.085260518250209e-05, | |
| "loss": 1.766, | |
| "step": 84300 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 1.0806166991734003e-05, | |
| "loss": 1.7654, | |
| "step": 84400 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 1.0759728800965915e-05, | |
| "loss": 1.7047, | |
| "step": 84500 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 1.0713290610197828e-05, | |
| "loss": 1.8477, | |
| "step": 84600 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 1.066685241942974e-05, | |
| "loss": 1.8153, | |
| "step": 84700 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 1.062041422866165e-05, | |
| "loss": 1.7948, | |
| "step": 84800 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 1.0573976037893564e-05, | |
| "loss": 1.7346, | |
| "step": 84900 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 1.0527537847125477e-05, | |
| "loss": 1.8153, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "eval_gen_len": 18.99955116696589, | |
| "eval_loss": 1.6492679119110107, | |
| "eval_rouge1": 24.5638, | |
| "eval_rouge2": 11.8392, | |
| "eval_rougeL": 20.3084, | |
| "eval_rougeLsum": 23.165, | |
| "eval_runtime": 1016.7714, | |
| "eval_samples_per_second": 13.147, | |
| "eval_steps_per_second": 1.643, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 1.0481099656357389e-05, | |
| "loss": 1.7736, | |
| "step": 85100 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 1.0434661465589302e-05, | |
| "loss": 1.789, | |
| "step": 85200 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 1.0388223274821215e-05, | |
| "loss": 1.7885, | |
| "step": 85300 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 1.0341785084053125e-05, | |
| "loss": 1.8059, | |
| "step": 85400 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 1.0295346893285038e-05, | |
| "loss": 1.7775, | |
| "step": 85500 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 1.024890870251695e-05, | |
| "loss": 1.7642, | |
| "step": 85600 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 1.0202470511748862e-05, | |
| "loss": 1.8427, | |
| "step": 85700 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 1.0156032320980775e-05, | |
| "loss": 1.8049, | |
| "step": 85800 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 1.0109594130212689e-05, | |
| "loss": 1.8209, | |
| "step": 85900 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 1.00631559394446e-05, | |
| "loss": 1.7581, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_gen_len": 18.99955116696589, | |
| "eval_loss": 1.649044156074524, | |
| "eval_rouge1": 24.6121, | |
| "eval_rouge2": 11.8876, | |
| "eval_rougeL": 20.36, | |
| "eval_rougeLsum": 23.2163, | |
| "eval_runtime": 1017.7889, | |
| "eval_samples_per_second": 13.134, | |
| "eval_steps_per_second": 1.642, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 1.0016717748676511e-05, | |
| "loss": 1.755, | |
| "step": 86100 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 9.970279557908425e-06, | |
| "loss": 1.7848, | |
| "step": 86200 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 9.923841367140336e-06, | |
| "loss": 1.755, | |
| "step": 86300 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 9.877403176372249e-06, | |
| "loss": 1.7571, | |
| "step": 86400 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 9.830964985604162e-06, | |
| "loss": 1.7997, | |
| "step": 86500 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 9.784526794836074e-06, | |
| "loss": 1.7845, | |
| "step": 86600 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 9.738088604067985e-06, | |
| "loss": 1.7804, | |
| "step": 86700 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 9.691650413299898e-06, | |
| "loss": 1.8016, | |
| "step": 86800 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 9.64521222253181e-06, | |
| "loss": 1.8139, | |
| "step": 86900 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 9.598774031763723e-06, | |
| "loss": 1.6925, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "eval_gen_len": 18.999775583482943, | |
| "eval_loss": 1.6501575708389282, | |
| "eval_rouge1": 24.6192, | |
| "eval_rouge2": 11.8992, | |
| "eval_rougeL": 20.3786, | |
| "eval_rougeLsum": 23.2421, | |
| "eval_runtime": 1018.5996, | |
| "eval_samples_per_second": 13.124, | |
| "eval_steps_per_second": 1.64, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 9.552335840995636e-06, | |
| "loss": 1.7919, | |
| "step": 87100 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 9.505897650227547e-06, | |
| "loss": 1.7798, | |
| "step": 87200 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 9.45945945945946e-06, | |
| "loss": 1.7735, | |
| "step": 87300 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 9.413021268691372e-06, | |
| "loss": 1.7761, | |
| "step": 87400 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 9.366583077923283e-06, | |
| "loss": 1.7919, | |
| "step": 87500 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 9.320144887155197e-06, | |
| "loss": 1.7737, | |
| "step": 87600 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 9.27370669638711e-06, | |
| "loss": 1.776, | |
| "step": 87700 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 9.227268505619021e-06, | |
| "loss": 1.7919, | |
| "step": 87800 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 9.180830314850934e-06, | |
| "loss": 1.7506, | |
| "step": 87900 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 9.134392124082847e-06, | |
| "loss": 1.7535, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "eval_gen_len": 18.999625972471573, | |
| "eval_loss": 1.6472678184509277, | |
| "eval_rouge1": 24.6134, | |
| "eval_rouge2": 11.8877, | |
| "eval_rougeL": 20.3663, | |
| "eval_rougeLsum": 23.2262, | |
| "eval_runtime": 1017.7072, | |
| "eval_samples_per_second": 13.135, | |
| "eval_steps_per_second": 1.642, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 9.087953933314757e-06, | |
| "loss": 1.8082, | |
| "step": 88100 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 9.04151574254667e-06, | |
| "loss": 1.763, | |
| "step": 88200 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 8.995077551778583e-06, | |
| "loss": 1.7831, | |
| "step": 88300 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 8.948639361010495e-06, | |
| "loss": 1.7592, | |
| "step": 88400 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 8.902201170242408e-06, | |
| "loss": 1.7907, | |
| "step": 88500 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 8.855762979474321e-06, | |
| "loss": 1.7634, | |
| "step": 88600 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 8.809324788706233e-06, | |
| "loss": 1.7956, | |
| "step": 88700 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 8.762886597938144e-06, | |
| "loss": 1.7781, | |
| "step": 88800 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 8.716448407170057e-06, | |
| "loss": 1.7713, | |
| "step": 88900 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 8.670010216401969e-06, | |
| "loss": 1.751, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "eval_gen_len": 18.999625972471573, | |
| "eval_loss": 1.6496267318725586, | |
| "eval_rouge1": 24.5728, | |
| "eval_rouge2": 11.8886, | |
| "eval_rougeL": 20.3411, | |
| "eval_rougeLsum": 23.1906, | |
| "eval_runtime": 1018.4137, | |
| "eval_samples_per_second": 13.126, | |
| "eval_steps_per_second": 1.641, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 8.623572025633882e-06, | |
| "loss": 1.7497, | |
| "step": 89100 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 8.577133834865795e-06, | |
| "loss": 1.7948, | |
| "step": 89200 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 8.530695644097706e-06, | |
| "loss": 1.7926, | |
| "step": 89300 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 8.48425745332962e-06, | |
| "loss": 1.7706, | |
| "step": 89400 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 8.437819262561531e-06, | |
| "loss": 1.7496, | |
| "step": 89500 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 8.391381071793442e-06, | |
| "loss": 1.8102, | |
| "step": 89600 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 8.344942881025355e-06, | |
| "loss": 1.7853, | |
| "step": 89700 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 8.298504690257269e-06, | |
| "loss": 1.8141, | |
| "step": 89800 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 8.25206649948918e-06, | |
| "loss": 1.8381, | |
| "step": 89900 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 8.205628308721093e-06, | |
| "loss": 1.7577, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "eval_gen_len": 18.999625972471573, | |
| "eval_loss": 1.6477200984954834, | |
| "eval_rouge1": 24.5616, | |
| "eval_rouge2": 11.8489, | |
| "eval_rougeL": 20.3021, | |
| "eval_rougeLsum": 23.1754, | |
| "eval_runtime": 1017.6231, | |
| "eval_samples_per_second": 13.136, | |
| "eval_steps_per_second": 1.642, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 8.159190117953006e-06, | |
| "loss": 1.8061, | |
| "step": 90100 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 8.112751927184916e-06, | |
| "loss": 1.7683, | |
| "step": 90200 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 8.06631373641683e-06, | |
| "loss": 1.8018, | |
| "step": 90300 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 8.019875545648742e-06, | |
| "loss": 1.7921, | |
| "step": 90400 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 7.973437354880654e-06, | |
| "loss": 1.7881, | |
| "step": 90500 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 7.926999164112567e-06, | |
| "loss": 1.7732, | |
| "step": 90600 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 7.88056097334448e-06, | |
| "loss": 1.811, | |
| "step": 90700 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 7.834122782576391e-06, | |
| "loss": 1.7783, | |
| "step": 90800 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 7.787684591808303e-06, | |
| "loss": 1.7847, | |
| "step": 90900 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 7.741246401040216e-06, | |
| "loss": 1.8, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "eval_gen_len": 18.999625972471573, | |
| "eval_loss": 1.6473010778427124, | |
| "eval_rouge1": 24.5614, | |
| "eval_rouge2": 11.8663, | |
| "eval_rougeL": 20.3282, | |
| "eval_rougeLsum": 23.1868, | |
| "eval_runtime": 1018.187, | |
| "eval_samples_per_second": 13.129, | |
| "eval_steps_per_second": 1.641, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 7.694808210272127e-06, | |
| "loss": 1.8041, | |
| "step": 91100 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 7.64837001950404e-06, | |
| "loss": 1.8265, | |
| "step": 91200 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 7.601931828735953e-06, | |
| "loss": 1.782, | |
| "step": 91300 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 7.555493637967866e-06, | |
| "loss": 1.7359, | |
| "step": 91400 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 7.509055447199777e-06, | |
| "loss": 1.7759, | |
| "step": 91500 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 7.462617256431689e-06, | |
| "loss": 1.8017, | |
| "step": 91600 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 7.416179065663602e-06, | |
| "loss": 1.7952, | |
| "step": 91700 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 7.369740874895514e-06, | |
| "loss": 1.8326, | |
| "step": 91800 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 7.323302684127427e-06, | |
| "loss": 1.7451, | |
| "step": 91900 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 7.27686449335934e-06, | |
| "loss": 1.7859, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "eval_gen_len": 18.999775583482943, | |
| "eval_loss": 1.64827299118042, | |
| "eval_rouge1": 24.5594, | |
| "eval_rouge2": 11.8426, | |
| "eval_rougeL": 20.3197, | |
| "eval_rougeLsum": 23.191, | |
| "eval_runtime": 1017.4363, | |
| "eval_samples_per_second": 13.139, | |
| "eval_steps_per_second": 1.642, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 7.230426302591252e-06, | |
| "loss": 1.7739, | |
| "step": 92100 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 7.1839881118231635e-06, | |
| "loss": 1.7942, | |
| "step": 92200 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 7.137549921055076e-06, | |
| "loss": 1.7971, | |
| "step": 92300 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 7.091111730286988e-06, | |
| "loss": 1.8096, | |
| "step": 92400 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 7.0446735395189e-06, | |
| "loss": 1.7967, | |
| "step": 92500 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 6.9982353487508135e-06, | |
| "loss": 1.7789, | |
| "step": 92600 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 6.951797157982726e-06, | |
| "loss": 1.8053, | |
| "step": 92700 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 6.905358967214638e-06, | |
| "loss": 1.7866, | |
| "step": 92800 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 6.8589207764465495e-06, | |
| "loss": 1.7849, | |
| "step": 92900 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 6.812482585678462e-06, | |
| "loss": 1.7984, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "eval_gen_len": 18.999775583482943, | |
| "eval_loss": 1.6468589305877686, | |
| "eval_rouge1": 24.5732, | |
| "eval_rouge2": 11.8258, | |
| "eval_rougeL": 20.3204, | |
| "eval_rougeLsum": 23.1958, | |
| "eval_runtime": 1017.2834, | |
| "eval_samples_per_second": 13.141, | |
| "eval_steps_per_second": 1.643, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 6.766044394910374e-06, | |
| "loss": 1.7749, | |
| "step": 93100 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 6.719606204142287e-06, | |
| "loss": 1.7922, | |
| "step": 93200 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 6.6731680133741995e-06, | |
| "loss": 1.7375, | |
| "step": 93300 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 6.626729822606112e-06, | |
| "loss": 1.7701, | |
| "step": 93400 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 6.580291631838025e-06, | |
| "loss": 1.7792, | |
| "step": 93500 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 6.5338534410699355e-06, | |
| "loss": 1.7739, | |
| "step": 93600 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 6.487415250301848e-06, | |
| "loss": 1.7358, | |
| "step": 93700 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 6.440977059533761e-06, | |
| "loss": 1.7957, | |
| "step": 93800 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 6.394538868765673e-06, | |
| "loss": 1.8148, | |
| "step": 93900 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 6.3481006779975855e-06, | |
| "loss": 1.7943, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "eval_gen_len": 18.999625972471573, | |
| "eval_loss": 1.6477123498916626, | |
| "eval_rouge1": 24.5888, | |
| "eval_rouge2": 11.8602, | |
| "eval_rougeL": 20.3352, | |
| "eval_rougeLsum": 23.2181, | |
| "eval_runtime": 1018.432, | |
| "eval_samples_per_second": 13.126, | |
| "eval_steps_per_second": 1.641, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 6.301662487229499e-06, | |
| "loss": 1.7667, | |
| "step": 94100 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 6.255224296461411e-06, | |
| "loss": 1.8027, | |
| "step": 94200 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 6.208786105693322e-06, | |
| "loss": 1.7746, | |
| "step": 94300 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 6.1623479149252355e-06, | |
| "loss": 1.7585, | |
| "step": 94400 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 6.115909724157147e-06, | |
| "loss": 1.7668, | |
| "step": 94500 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 6.069471533389059e-06, | |
| "loss": 1.7702, | |
| "step": 94600 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 6.023033342620972e-06, | |
| "loss": 1.7837, | |
| "step": 94700 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 5.976595151852884e-06, | |
| "loss": 1.8103, | |
| "step": 94800 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 5.930156961084796e-06, | |
| "loss": 1.7929, | |
| "step": 94900 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 5.883718770316709e-06, | |
| "loss": 1.7888, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "eval_gen_len": 18.999625972471573, | |
| "eval_loss": 1.647167682647705, | |
| "eval_rouge1": 24.5781, | |
| "eval_rouge2": 11.844, | |
| "eval_rougeL": 20.3272, | |
| "eval_rougeLsum": 23.216, | |
| "eval_runtime": 1019.3426, | |
| "eval_samples_per_second": 13.114, | |
| "eval_steps_per_second": 1.639, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 5.837280579548621e-06, | |
| "loss": 1.7946, | |
| "step": 95100 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 5.790842388780533e-06, | |
| "loss": 1.8053, | |
| "step": 95200 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 5.744404198012446e-06, | |
| "loss": 1.7827, | |
| "step": 95300 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 5.697966007244358e-06, | |
| "loss": 1.7985, | |
| "step": 95400 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 5.65152781647627e-06, | |
| "loss": 1.7939, | |
| "step": 95500 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 5.605089625708183e-06, | |
| "loss": 1.7877, | |
| "step": 95600 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 5.558651434940095e-06, | |
| "loss": 1.7493, | |
| "step": 95700 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 5.512213244172007e-06, | |
| "loss": 1.7465, | |
| "step": 95800 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 5.46577505340392e-06, | |
| "loss": 1.7958, | |
| "step": 95900 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 5.419336862635832e-06, | |
| "loss": 1.7803, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "eval_gen_len": 18.99955116696589, | |
| "eval_loss": 1.6482892036437988, | |
| "eval_rouge1": 24.5454, | |
| "eval_rouge2": 11.8245, | |
| "eval_rougeL": 20.2917, | |
| "eval_rougeLsum": 23.1727, | |
| "eval_runtime": 1025.0182, | |
| "eval_samples_per_second": 13.042, | |
| "eval_steps_per_second": 1.63, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 5.372898671867744e-06, | |
| "loss": 1.7544, | |
| "step": 96100 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 5.326460481099657e-06, | |
| "loss": 1.8355, | |
| "step": 96200 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 5.280022290331569e-06, | |
| "loss": 1.7922, | |
| "step": 96300 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 5.233584099563481e-06, | |
| "loss": 1.7703, | |
| "step": 96400 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 5.1871459087953935e-06, | |
| "loss": 1.7628, | |
| "step": 96500 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 5.140707718027306e-06, | |
| "loss": 1.8141, | |
| "step": 96600 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 5.094269527259218e-06, | |
| "loss": 1.7856, | |
| "step": 96700 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 5.047831336491131e-06, | |
| "loss": 1.8083, | |
| "step": 96800 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 5.001393145723043e-06, | |
| "loss": 1.773, | |
| "step": 96900 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 4.954954954954955e-06, | |
| "loss": 1.8106, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "eval_gen_len": 18.999625972471573, | |
| "eval_loss": 1.6460872888565063, | |
| "eval_rouge1": 24.5694, | |
| "eval_rouge2": 11.8344, | |
| "eval_rougeL": 20.3123, | |
| "eval_rougeLsum": 23.1934, | |
| "eval_runtime": 1025.7089, | |
| "eval_samples_per_second": 13.033, | |
| "eval_steps_per_second": 1.629, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 4.908516764186868e-06, | |
| "loss": 1.7935, | |
| "step": 97100 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 4.8620785734187795e-06, | |
| "loss": 1.8337, | |
| "step": 97200 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 4.815640382650692e-06, | |
| "loss": 1.83, | |
| "step": 97300 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 4.769202191882605e-06, | |
| "loss": 1.8323, | |
| "step": 97400 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 4.722764001114516e-06, | |
| "loss": 1.7592, | |
| "step": 97500 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 4.676325810346429e-06, | |
| "loss": 1.8037, | |
| "step": 97600 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 4.629887619578342e-06, | |
| "loss": 1.765, | |
| "step": 97700 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 4.583449428810254e-06, | |
| "loss": 1.7744, | |
| "step": 97800 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 4.5370112380421655e-06, | |
| "loss": 1.8041, | |
| "step": 97900 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 4.490573047274079e-06, | |
| "loss": 1.8713, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "eval_gen_len": 18.999625972471573, | |
| "eval_loss": 1.6453874111175537, | |
| "eval_rouge1": 24.5906, | |
| "eval_rouge2": 11.8573, | |
| "eval_rougeL": 20.3447, | |
| "eval_rougeLsum": 23.2181, | |
| "eval_runtime": 1023.9699, | |
| "eval_samples_per_second": 13.055, | |
| "eval_steps_per_second": 1.632, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 4.444134856505991e-06, | |
| "loss": 1.7536, | |
| "step": 98100 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 4.397696665737902e-06, | |
| "loss": 1.8293, | |
| "step": 98200 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 4.3512584749698155e-06, | |
| "loss": 1.7953, | |
| "step": 98300 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 4.304820284201728e-06, | |
| "loss": 1.7937, | |
| "step": 98400 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 4.25838209343364e-06, | |
| "loss": 1.7473, | |
| "step": 98500 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 4.211943902665552e-06, | |
| "loss": 1.7745, | |
| "step": 98600 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 4.165505711897465e-06, | |
| "loss": 1.815, | |
| "step": 98700 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 4.119067521129377e-06, | |
| "loss": 1.7747, | |
| "step": 98800 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 4.072629330361289e-06, | |
| "loss": 1.7989, | |
| "step": 98900 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 4.0261911395932016e-06, | |
| "loss": 1.7655, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "eval_gen_len": 18.99955116696589, | |
| "eval_loss": 1.6468464136123657, | |
| "eval_rouge1": 24.5709, | |
| "eval_rouge2": 11.8573, | |
| "eval_rougeL": 20.3139, | |
| "eval_rougeLsum": 23.1994, | |
| "eval_runtime": 1022.5566, | |
| "eval_samples_per_second": 13.073, | |
| "eval_steps_per_second": 1.634, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 3.979752948825114e-06, | |
| "loss": 1.7739, | |
| "step": 99100 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 3.933314758057027e-06, | |
| "loss": 1.7992, | |
| "step": 99200 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 3.886876567288938e-06, | |
| "loss": 1.7752, | |
| "step": 99300 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 3.840438376520851e-06, | |
| "loss": 1.7836, | |
| "step": 99400 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 3.7940001857527634e-06, | |
| "loss": 1.7634, | |
| "step": 99500 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 3.7475619949846753e-06, | |
| "loss": 1.7795, | |
| "step": 99600 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 3.701123804216588e-06, | |
| "loss": 1.7955, | |
| "step": 99700 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 3.6546856134485003e-06, | |
| "loss": 1.7791, | |
| "step": 99800 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 3.608247422680412e-06, | |
| "loss": 1.8135, | |
| "step": 99900 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 3.561809231912325e-06, | |
| "loss": 1.7616, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "eval_gen_len": 18.999775583482943, | |
| "eval_loss": 1.6464020013809204, | |
| "eval_rouge1": 24.5852, | |
| "eval_rouge2": 11.8531, | |
| "eval_rougeL": 20.3172, | |
| "eval_rougeLsum": 23.2089, | |
| "eval_runtime": 1032.8825, | |
| "eval_samples_per_second": 12.942, | |
| "eval_steps_per_second": 1.618, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 3.515371041144237e-06, | |
| "loss": 1.7835, | |
| "step": 100100 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 3.46893285037615e-06, | |
| "loss": 1.8031, | |
| "step": 100200 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 3.4224946596080617e-06, | |
| "loss": 1.8073, | |
| "step": 100300 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 3.376056468839974e-06, | |
| "loss": 1.8209, | |
| "step": 100400 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 3.3296182780718867e-06, | |
| "loss": 1.763, | |
| "step": 100500 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 3.2831800873037986e-06, | |
| "loss": 1.7552, | |
| "step": 100600 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 3.236741896535711e-06, | |
| "loss": 1.7884, | |
| "step": 100700 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 3.1903037057676236e-06, | |
| "loss": 1.7717, | |
| "step": 100800 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 3.1438655149995363e-06, | |
| "loss": 1.7844, | |
| "step": 100900 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 3.097427324231448e-06, | |
| "loss": 1.7581, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "eval_gen_len": 18.99970077797726, | |
| "eval_loss": 1.6467525959014893, | |
| "eval_rouge1": 24.5748, | |
| "eval_rouge2": 11.8452, | |
| "eval_rougeL": 20.3043, | |
| "eval_rougeLsum": 23.1849, | |
| "eval_runtime": 1030.0572, | |
| "eval_samples_per_second": 12.978, | |
| "eval_steps_per_second": 1.622, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 3.0509891334633604e-06, | |
| "loss": 1.7973, | |
| "step": 101100 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 3.0045509426952727e-06, | |
| "loss": 1.7992, | |
| "step": 101200 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 2.958112751927185e-06, | |
| "loss": 1.7591, | |
| "step": 101300 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 2.9116745611590973e-06, | |
| "loss": 1.7999, | |
| "step": 101400 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 2.86523637039101e-06, | |
| "loss": 1.8001, | |
| "step": 101500 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 2.818798179622922e-06, | |
| "loss": 1.8029, | |
| "step": 101600 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 2.772359988854834e-06, | |
| "loss": 1.7549, | |
| "step": 101700 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 2.725921798086747e-06, | |
| "loss": 1.7741, | |
| "step": 101800 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 2.6794836073186587e-06, | |
| "loss": 1.7553, | |
| "step": 101900 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 2.6330454165505714e-06, | |
| "loss": 1.7743, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "eval_gen_len": 18.99955116696589, | |
| "eval_loss": 1.6462187767028809, | |
| "eval_rouge1": 24.5665, | |
| "eval_rouge2": 11.8328, | |
| "eval_rougeL": 20.2992, | |
| "eval_rougeLsum": 23.1896, | |
| "eval_runtime": 1029.3539, | |
| "eval_samples_per_second": 12.987, | |
| "eval_steps_per_second": 1.623, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 2.5866072257824837e-06, | |
| "loss": 1.7841, | |
| "step": 102100 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 2.540169035014396e-06, | |
| "loss": 1.7552, | |
| "step": 102200 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 2.4937308442463083e-06, | |
| "loss": 1.7752, | |
| "step": 102300 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 2.4472926534782206e-06, | |
| "loss": 1.799, | |
| "step": 102400 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 2.400854462710133e-06, | |
| "loss": 1.7874, | |
| "step": 102500 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 2.354416271942045e-06, | |
| "loss": 1.7632, | |
| "step": 102600 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 2.307978081173958e-06, | |
| "loss": 1.7783, | |
| "step": 102700 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 2.2615398904058697e-06, | |
| "loss": 1.7644, | |
| "step": 102800 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 2.215101699637782e-06, | |
| "loss": 1.8257, | |
| "step": 102900 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 2.1686635088696947e-06, | |
| "loss": 1.78, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "eval_gen_len": 18.99955116696589, | |
| "eval_loss": 1.6458466053009033, | |
| "eval_rouge1": 24.5716, | |
| "eval_rouge2": 11.8399, | |
| "eval_rougeL": 20.31, | |
| "eval_rougeLsum": 23.1943, | |
| "eval_runtime": 1026.5447, | |
| "eval_samples_per_second": 13.022, | |
| "eval_steps_per_second": 1.628, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 2.1222253181016066e-06, | |
| "loss": 1.7643, | |
| "step": 103100 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 2.0757871273335193e-06, | |
| "loss": 1.7706, | |
| "step": 103200 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 2.0293489365654316e-06, | |
| "loss": 1.8195, | |
| "step": 103300 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 1.982910745797344e-06, | |
| "loss": 1.8257, | |
| "step": 103400 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 1.936472555029256e-06, | |
| "loss": 1.8226, | |
| "step": 103500 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 1.8900343642611683e-06, | |
| "loss": 1.7884, | |
| "step": 103600 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 1.843596173493081e-06, | |
| "loss": 1.8019, | |
| "step": 103700 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 1.797157982724993e-06, | |
| "loss": 1.767, | |
| "step": 103800 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 1.7507197919569055e-06, | |
| "loss": 1.8028, | |
| "step": 103900 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 1.7042816011888178e-06, | |
| "loss": 1.8162, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "eval_gen_len": 18.999625972471573, | |
| "eval_loss": 1.6455563306808472, | |
| "eval_rouge1": 24.5719, | |
| "eval_rouge2": 11.8358, | |
| "eval_rougeL": 20.3132, | |
| "eval_rougeLsum": 23.1921, | |
| "eval_runtime": 1021.2047, | |
| "eval_samples_per_second": 13.09, | |
| "eval_steps_per_second": 1.636, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 1.65784341042073e-06, | |
| "loss": 1.8019, | |
| "step": 104100 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 1.6114052196526424e-06, | |
| "loss": 1.7694, | |
| "step": 104200 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 1.5649670288845547e-06, | |
| "loss": 1.7769, | |
| "step": 104300 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 1.518528838116467e-06, | |
| "loss": 1.7884, | |
| "step": 104400 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 1.4720906473483793e-06, | |
| "loss": 1.8234, | |
| "step": 104500 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 1.4256524565802918e-06, | |
| "loss": 1.7983, | |
| "step": 104600 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 1.379214265812204e-06, | |
| "loss": 1.7418, | |
| "step": 104700 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 1.3327760750441163e-06, | |
| "loss": 1.7558, | |
| "step": 104800 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 1.2863378842760288e-06, | |
| "loss": 1.7995, | |
| "step": 104900 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 1.239899693507941e-06, | |
| "loss": 1.7862, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "eval_gen_len": 18.999625972471573, | |
| "eval_loss": 1.6462281942367554, | |
| "eval_rouge1": 24.5938, | |
| "eval_rouge2": 11.8624, | |
| "eval_rougeL": 20.337, | |
| "eval_rougeLsum": 23.2131, | |
| "eval_runtime": 1018.9945, | |
| "eval_samples_per_second": 13.119, | |
| "eval_steps_per_second": 1.64, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 1.1934615027398532e-06, | |
| "loss": 1.7785, | |
| "step": 105100 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 1.1470233119717657e-06, | |
| "loss": 1.7551, | |
| "step": 105200 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 1.100585121203678e-06, | |
| "loss": 1.7387, | |
| "step": 105300 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 1.0541469304355903e-06, | |
| "loss": 1.7499, | |
| "step": 105400 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 1.0077087396675028e-06, | |
| "loss": 1.7999, | |
| "step": 105500 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 9.612705488994148e-07, | |
| "loss": 1.7999, | |
| "step": 105600 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 9.148323581313272e-07, | |
| "loss": 1.7517, | |
| "step": 105700 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 8.683941673632395e-07, | |
| "loss": 1.788, | |
| "step": 105800 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 8.219559765951519e-07, | |
| "loss": 1.7931, | |
| "step": 105900 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 7.755177858270642e-07, | |
| "loss": 1.7995, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "eval_gen_len": 18.999625972471573, | |
| "eval_loss": 1.6458855867385864, | |
| "eval_rouge1": 24.5885, | |
| "eval_rouge2": 11.8606, | |
| "eval_rougeL": 20.3325, | |
| "eval_rougeLsum": 23.2137, | |
| "eval_runtime": 1019.094, | |
| "eval_samples_per_second": 13.118, | |
| "eval_steps_per_second": 1.64, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 7.290795950589765e-07, | |
| "loss": 1.7883, | |
| "step": 106100 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 6.826414042908889e-07, | |
| "loss": 1.8355, | |
| "step": 106200 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 6.362032135228012e-07, | |
| "loss": 1.7487, | |
| "step": 106300 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 5.897650227547135e-07, | |
| "loss": 1.7886, | |
| "step": 106400 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 5.433268319866259e-07, | |
| "loss": 1.8009, | |
| "step": 106500 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 4.968886412185381e-07, | |
| "loss": 1.7814, | |
| "step": 106600 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 4.504504504504505e-07, | |
| "loss": 1.7931, | |
| "step": 106700 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 4.040122596823628e-07, | |
| "loss": 1.7789, | |
| "step": 106800 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 3.575740689142751e-07, | |
| "loss": 1.7562, | |
| "step": 106900 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 3.1113587814618745e-07, | |
| "loss": 1.7559, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "eval_gen_len": 18.999625972471573, | |
| "eval_loss": 1.6453537940979004, | |
| "eval_rouge1": 24.593, | |
| "eval_rouge2": 11.861, | |
| "eval_rougeL": 20.3401, | |
| "eval_rougeLsum": 23.2188, | |
| "eval_runtime": 1019.1949, | |
| "eval_samples_per_second": 13.116, | |
| "eval_steps_per_second": 1.64, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 2.6469768737809974e-07, | |
| "loss": 1.7975, | |
| "step": 107100 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 2.182594966100121e-07, | |
| "loss": 1.7641, | |
| "step": 107200 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 1.718213058419244e-07, | |
| "loss": 1.7987, | |
| "step": 107300 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 1.2538311507383673e-07, | |
| "loss": 1.7663, | |
| "step": 107400 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 7.894492430574905e-08, | |
| "loss": 1.8012, | |
| "step": 107500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.2506733537661375e-08, | |
| "loss": 1.7603, | |
| "step": 107600 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 107670, | |
| "total_flos": 2.3279391489785856e+17, | |
| "train_loss": 0.2034699499612622, | |
| "train_runtime": 19944.6617, | |
| "train_samples_per_second": 43.186, | |
| "train_steps_per_second": 5.398 | |
| } | |
| ], | |
| "max_steps": 107670, | |
| "num_train_epochs": 3, | |
| "total_flos": 2.3279391489785856e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |