| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.996712689020382, | |
| "global_step": 38000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3405, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1e-05, | |
| "loss": 0.011, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.995500912012546e-06, | |
| "loss": 0.0001, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.982011744767265e-06, | |
| "loss": 0.0065, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 9.959556773844286e-06, | |
| "loss": 0.0124, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 9.928176409999585e-06, | |
| "loss": 0.0, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 9.887927126440367e-06, | |
| "loss": 0.0, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.838881357193897e-06, | |
| "loss": 0.0, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 9.781127366752677e-06, | |
| "loss": 0.0156, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 9.714769091230555e-06, | |
| "loss": 0.0, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 9.639925951315641e-06, | |
| "loss": 0.0, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 9.556732637356626e-06, | |
| "loss": 0.0, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 9.4653388669693e-06, | |
| "loss": 0.0, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 9.365909115599454e-06, | |
| "loss": 0.0, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 9.258622320527083e-06, | |
| "loss": 0.0, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_AUC_Score": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 1.505104364696308e-06, | |
| "eval_runtime": 66.4848, | |
| "eval_samples_per_second": 50.839, | |
| "eval_steps_per_second": 6.362, | |
| "step": 7605 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 9.143671558844552e-06, | |
| "loss": 0.0, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 9.021263699988277e-06, | |
| "loss": 0.0, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 8.891619033449197e-06, | |
| "loss": 0.0, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 8.75497087233206e-06, | |
| "loss": 0.0, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 8.611565133476941e-06, | |
| "loss": 0.0111, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 8.461659894898644e-06, | |
| "loss": 0.0, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 8.30552493134043e-06, | |
| "loss": 0.0, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 8.143441228777884e-06, | |
| "loss": 0.0049, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 7.975700478746671e-06, | |
| "loss": 0.0128, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 7.802604553404178e-06, | |
| "loss": 0.0, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 7.624464962269764e-06, | |
| "loss": 0.0107, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 7.4416022916212495e-06, | |
| "loss": 0.011, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 7.254345627556585e-06, | |
| "loss": 0.0, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 7.063031963758914e-06, | |
| "loss": 0.0, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 6.868005595030889e-06, | |
| "loss": 0.0, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_AUC_Score": 0.9996968629809446, | |
| "eval_f1": 0.9990508354379857, | |
| "eval_loss": 0.01213728729635477, | |
| "eval_runtime": 66.1373, | |
| "eval_samples_per_second": 51.106, | |
| "eval_steps_per_second": 6.396, | |
| "step": 15210 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 6.669617497689624e-06, | |
| "loss": 0.0017, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 6.468224697937357e-06, | |
| "loss": 0.0, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 6.26418962934454e-06, | |
| "loss": 0.0, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 6.057879480601623e-06, | |
| "loss": 0.0, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 5.849665534713365e-06, | |
| "loss": 0.0111, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 5.639922500824873e-06, | |
| "loss": 0.0, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 5.429027839881837e-06, | |
| "loss": 0.0, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 5.217361085338521e-06, | |
| "loss": 0.0, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 5.00530316013601e-06, | |
| "loss": 0.0, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 4.793235691179874e-06, | |
| "loss": 0.0, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 4.581540322550959e-06, | |
| "loss": 0.0, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 4.370598028685259e-06, | |
| "loss": 0.0, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 4.1607884287589305e-06, | |
| "loss": 0.0, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 3.952489103512244e-06, | |
| "loss": 0.0, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 3.746074915742002e-06, | |
| "loss": 0.0, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_AUC_Score": 1.0, | |
| "eval_f1": 0.9996837136583017, | |
| "eval_loss": 0.004720049910247326, | |
| "eval_runtime": 66.7455, | |
| "eval_samples_per_second": 50.64, | |
| "eval_steps_per_second": 6.338, | |
| "step": 22815 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 3.5419173356852643e-06, | |
| "loss": 0.0, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 3.3403837725084208e-06, | |
| "loss": 0.0, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 3.141836913104733e-06, | |
| "loss": 0.0, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 2.9466340693902413e-06, | |
| "loss": 0.0069, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 2.7551265352726518e-06, | |
| "loss": 0.0, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 2.567658954450468e-06, | |
| "loss": 0.0, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 2.3845687001800538e-06, | |
| "loss": 0.0, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 2.206185268126855e-06, | |
| "loss": 0.0, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 2.0328296833933964e-06, | |
| "loss": 0.0, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 1.8648139227912071e-06, | |
| "loss": 0.0, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 1.7024403533963834e-06, | |
| "loss": 0.0, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 1.546001188399141e-06, | |
| "loss": 0.0, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 1.3957779612266815e-06, | |
| "loss": 0.0, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 1.2520410188857307e-06, | |
| "loss": 0.0, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 1.1150490354365434e-06, | |
| "loss": 0.0, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_AUC_Score": 1.0, | |
| "eval_f1": 0.9996837136583017, | |
| "eval_loss": 0.002729017287492752, | |
| "eval_runtime": 66.7534, | |
| "eval_samples_per_second": 50.634, | |
| "eval_steps_per_second": 6.337, | |
| "step": 30420 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 9.850485464739634e-07, | |
| "loss": 0.0, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 8.62273505453296e-07, | |
| "loss": 0.0, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 7.469448626594255e-07, | |
| "loss": 0.0, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 6.392701675769125e-07, | |
| "loss": 0.0, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 5.394431953766388e-07, | |
| "loss": 0.0, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 4.476435981911831e-07, | |
| "loss": 0.0, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 3.6403658180652445e-07, | |
| "loss": 0.0, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 2.887726083518988e-07, | |
| "loss": 0.0, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 2.219871255228473e-07, | |
| "loss": 0.0, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 1.6380032282478364e-07, | |
| "loss": 0.0, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 1.1431691527572675e-07, | |
| "loss": 0.0, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 7.362595495746972e-08, | |
| "loss": 0.0, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 4.1800670754318374e-08, | |
| "loss": 0.0, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 1.889833656781581e-08, | |
| "loss": 0.0, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "learning_rate": 4.96016824461043e-09, | |
| "loss": 0.0, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 1.124940297136945e-11, | |
| "loss": 0.0, | |
| "step": 38000 | |
| } | |
| ], | |
| "max_steps": 38025, | |
| "num_train_epochs": 5, | |
| "total_flos": 3.999288041472e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |