| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.96969696969697, | |
| "eval_steps": 500, | |
| "global_step": 615, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.9674796747967483e-05, | |
| "loss": 0.6473, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.934959349593496e-05, | |
| "loss": 0.414, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.902439024390244e-05, | |
| "loss": 0.3542, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.869918699186992e-05, | |
| "loss": 0.3396, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.83739837398374e-05, | |
| "loss": 0.3274, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.804878048780488e-05, | |
| "loss": 0.3238, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 1.772357723577236e-05, | |
| "loss": 0.3495, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.739837398373984e-05, | |
| "loss": 0.3068, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.7073170731707317e-05, | |
| "loss": 0.3164, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.6747967479674798e-05, | |
| "loss": 0.2989, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1.642276422764228e-05, | |
| "loss": 0.287, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.6097560975609757e-05, | |
| "loss": 0.2903, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_f1": 0.40107752170008987, | |
| "eval_loss": 0.26861757040023804, | |
| "eval_runtime": 43.0151, | |
| "eval_samples_per_second": 22.992, | |
| "eval_steps_per_second": 1.441, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 1.5772357723577235e-05, | |
| "loss": 0.2869, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 1.5447154471544717e-05, | |
| "loss": 0.2709, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 1.5121951219512196e-05, | |
| "loss": 0.2599, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 1.4796747967479676e-05, | |
| "loss": 0.2565, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 1.4471544715447157e-05, | |
| "loss": 0.2597, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 1.4146341463414635e-05, | |
| "loss": 0.2525, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 1.3821138211382115e-05, | |
| "loss": 0.2519, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 1.3495934959349594e-05, | |
| "loss": 0.2366, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 1.3170731707317076e-05, | |
| "loss": 0.2292, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 1.2845528455284555e-05, | |
| "loss": 0.2214, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 1.2520325203252033e-05, | |
| "loss": 0.2193, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 1.2195121951219513e-05, | |
| "loss": 0.2171, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_f1": 0.6493130874909617, | |
| "eval_loss": 0.2168290913105011, | |
| "eval_runtime": 43.1471, | |
| "eval_samples_per_second": 22.922, | |
| "eval_steps_per_second": 1.437, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1.1869918699186992e-05, | |
| "loss": 0.1994, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 1.1544715447154474e-05, | |
| "loss": 0.204, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 1.1219512195121953e-05, | |
| "loss": 0.1909, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 1.0894308943089431e-05, | |
| "loss": 0.1906, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 1.0569105691056911e-05, | |
| "loss": 0.1919, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 1.024390243902439e-05, | |
| "loss": 0.1825, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 9.91869918699187e-06, | |
| "loss": 0.1839, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 9.59349593495935e-06, | |
| "loss": 0.189, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 9.268292682926831e-06, | |
| "loss": 0.178, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 8.94308943089431e-06, | |
| "loss": 0.1903, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 8.617886178861789e-06, | |
| "loss": 0.1835, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 8.292682926829268e-06, | |
| "loss": 0.1722, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 7.967479674796748e-06, | |
| "loss": 0.1879, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_f1": 0.6612224696857214, | |
| "eval_loss": 0.19899873435497284, | |
| "eval_runtime": 43.1679, | |
| "eval_samples_per_second": 22.911, | |
| "eval_steps_per_second": 1.436, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 7.64227642276423e-06, | |
| "loss": 0.1593, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 7.317073170731707e-06, | |
| "loss": 0.1553, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 6.991869918699188e-06, | |
| "loss": 0.1529, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.1589, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 6.341463414634147e-06, | |
| "loss": 0.1514, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 6.016260162601627e-06, | |
| "loss": 0.1524, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 5.691056910569106e-06, | |
| "loss": 0.1577, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 5.365853658536586e-06, | |
| "loss": 0.1504, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 5.040650406504065e-06, | |
| "loss": 0.151, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 4.715447154471545e-06, | |
| "loss": 0.1539, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 4.390243902439025e-06, | |
| "loss": 0.1575, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 4.0650406504065046e-06, | |
| "loss": 0.1476, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_f1": 0.7060445874511607, | |
| "eval_loss": 0.18790604174137115, | |
| "eval_runtime": 43.1492, | |
| "eval_samples_per_second": 22.92, | |
| "eval_steps_per_second": 1.437, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 3.7398373983739838e-06, | |
| "loss": 0.1412, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 3.414634146341464e-06, | |
| "loss": 0.1274, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 3.0894308943089435e-06, | |
| "loss": 0.1266, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 2.764227642276423e-06, | |
| "loss": 0.1275, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 2.4390243902439027e-06, | |
| "loss": 0.1222, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 2.1138211382113824e-06, | |
| "loss": 0.1275, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 1.788617886178862e-06, | |
| "loss": 0.1248, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "learning_rate": 1.4634146341463414e-06, | |
| "loss": 0.1308, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 1.1382113821138213e-06, | |
| "loss": 0.1272, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 8.130081300813009e-07, | |
| "loss": 0.1261, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 4.878048780487805e-07, | |
| "loss": 0.1289, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "learning_rate": 1.6260162601626018e-07, | |
| "loss": 0.1279, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "eval_f1": 0.7058281501958075, | |
| "eval_loss": 0.1904972940683365, | |
| "eval_runtime": 43.1284, | |
| "eval_samples_per_second": 22.932, | |
| "eval_steps_per_second": 1.438, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "step": 615, | |
| "total_flos": 2.6435427934519296e+16, | |
| "train_loss": 0.2132105562745071, | |
| "train_runtime": 4145.08, | |
| "train_samples_per_second": 9.546, | |
| "train_steps_per_second": 0.148 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 615, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 2.6435427934519296e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |