| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.8567511994516792, |
| "eval_steps": 100, |
| "global_step": 500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.02, |
| "learning_rate": 8.993468091981983e-06, |
| "loss": 0.6658, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.03, |
| "learning_rate": 8.973891330515647e-06, |
| "loss": 0.4496, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.05, |
| "learning_rate": 8.941326548314408e-06, |
| "loss": 0.3875, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.07, |
| "learning_rate": 8.895868283228027e-06, |
| "loss": 0.3646, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.09, |
| "learning_rate": 8.837648503792598e-06, |
| "loss": 0.3664, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 8.766836226116608e-06, |
| "loss": 0.3676, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 8.683637023215312e-06, |
| "loss": 0.3075, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 8.588292428217834e-06, |
| "loss": 0.2945, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 8.481079233179522e-06, |
| "loss": 0.3539, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 8.362308685535184e-06, |
| "loss": 0.2699, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.17, |
| "eval_accuracy": 0.0, |
| "eval_loss": 0.27337193489074707, |
| "eval_runtime": 53.8814, |
| "eval_samples_per_second": 72.214, |
| "eval_steps_per_second": 12.045, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 8.232325584525908e-06, |
| "loss": 0.2544, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 8.091507280222673e-06, |
| "loss": 0.2776, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 7.940262578052568e-06, |
| "loss": 0.2941, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 7.779030552007946e-06, |
| "loss": 0.2615, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 7.608279269983776e-06, |
| "loss": 0.2673, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.27, |
| "learning_rate": 7.428504434943677e-06, |
| "loss": 0.2524, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 7.240227945859397e-06, |
| "loss": 0.2732, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 7.043996382601448e-06, |
| "loss": 0.2184, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 6.840379419179357e-06, |
| "loss": 0.2578, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 6.629968169938005e-06, |
| "loss": 0.2827, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.34, |
| "eval_accuracy": 0.0, |
| "eval_loss": 0.2310507595539093, |
| "eval_runtime": 54.2245, |
| "eval_samples_per_second": 71.757, |
| "eval_steps_per_second": 11.969, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.36, |
| "learning_rate": 6.41337347351117e-06, |
| "loss": 0.2426, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 6.191224119514071e-06, |
| "loss": 0.2142, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 5.964165023122967e-06, |
| "loss": 0.264, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.41, |
| "learning_rate": 5.73285535284109e-06, |
| "loss": 0.2039, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 5.4979666168862e-06, |
| "loss": 0.2163, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 5.260180713755066e-06, |
| "loss": 0.2363, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.46, |
| "learning_rate": 5.020187952624234e-06, |
| "loss": 0.21, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 4.7786850493340155e-06, |
| "loss": 0.235, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.5, |
| "learning_rate": 4.536373103773464e-06, |
| "loss": 0.2067, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 4.2939555645381675e-06, |
| "loss": 0.2001, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.51, |
| "eval_accuracy": 0.0, |
| "eval_loss": 0.19201719760894775, |
| "eval_runtime": 53.8375, |
| "eval_samples_per_second": 72.273, |
| "eval_steps_per_second": 12.055, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.53, |
| "learning_rate": 4.052136186769563e-06, |
| "loss": 0.1799, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 3.811616989104347e-06, |
| "loss": 0.2202, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.57, |
| "learning_rate": 3.573096215665058e-06, |
| "loss": 0.1974, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.58, |
| "learning_rate": 3.337266309008359e-06, |
| "loss": 0.1872, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.6, |
| "learning_rate": 3.104811899915661e-06, |
| "loss": 0.1746, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.62, |
| "learning_rate": 2.87640781986189e-06, |
| "loss": 0.1728, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.63, |
| "learning_rate": 2.652717141932312e-06, |
| "loss": 0.1656, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.65, |
| "learning_rate": 2.4343892558748025e-06, |
| "loss": 0.1716, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 2.222057982875807e-06, |
| "loss": 0.1698, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.69, |
| "learning_rate": 2.0163397355329136e-06, |
| "loss": 0.1955, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.69, |
| "eval_accuracy": 0.0, |
| "eval_loss": 0.17988212406635284, |
| "eval_runtime": 54.3033, |
| "eval_samples_per_second": 71.653, |
| "eval_steps_per_second": 11.951, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 1.817831728365798e-06, |
| "loss": 0.2, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.72, |
| "learning_rate": 1.6271102440605319e-06, |
| "loss": 0.1686, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.74, |
| "learning_rate": 1.444728960480465e-06, |
| "loss": 0.1618, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.75, |
| "learning_rate": 1.2712173433005088e-06, |
| "loss": 0.1637, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.77, |
| "learning_rate": 1.107079108931101e-06, |
| "loss": 0.1856, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.79, |
| "learning_rate": 9.527907621940788e-07, |
| "loss": 0.1895, |
| "step": 460 |
| }, |
| { |
| "epoch": 0.81, |
| "learning_rate": 8.08800212995727e-07, |
| "loss": 0.1871, |
| "step": 470 |
| }, |
| { |
| "epoch": 0.82, |
| "learning_rate": 6.755254760128572e-07, |
| "loss": 0.1874, |
| "step": 480 |
| }, |
| { |
| "epoch": 0.84, |
| "learning_rate": 5.533534571668463e-07, |
| "loss": 0.1925, |
| "step": 490 |
| }, |
| { |
| "epoch": 0.86, |
| "learning_rate": 4.4263883040857247e-07, |
| "loss": 0.1334, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.86, |
| "eval_accuracy": 0.0, |
| "eval_loss": 0.17077727615833282, |
| "eval_runtime": 54.0155, |
| "eval_samples_per_second": 72.035, |
| "eval_steps_per_second": 12.015, |
| "step": 500 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 583, |
| "num_train_epochs": 1, |
| "save_steps": 100, |
| "total_flos": 0.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
