| { | |
| "best_metric": 0.9447983014861996, | |
| "best_model_checkpoint": "./weather-mod/checkpoint-472", | |
| "epoch": 6.0, | |
| "global_step": 708, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.5492957746478872e-05, | |
| "loss": 0.179, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 2.2535211267605634e-05, | |
| "loss": 0.1308, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 2.9577464788732395e-05, | |
| "loss": 0.1013, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.661971830985916e-05, | |
| "loss": 0.1276, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.366197183098591e-05, | |
| "loss": 0.1344, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.992150706436421e-05, | |
| "loss": 0.1502, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.913657770800628e-05, | |
| "loss": 0.1448, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.8351648351648355e-05, | |
| "loss": 0.1864, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.756671899529043e-05, | |
| "loss": 0.2092, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 4.67817896389325e-05, | |
| "loss": 0.2008, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 4.599686028257457e-05, | |
| "loss": 0.1517, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9150743099787686, | |
| "eval_loss": 0.26539650559425354, | |
| "eval_runtime": 14.9714, | |
| "eval_samples_per_second": 31.46, | |
| "eval_steps_per_second": 3.941, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 4.5211930926216645e-05, | |
| "loss": 0.145, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 4.442700156985872e-05, | |
| "loss": 0.1558, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 4.364207221350079e-05, | |
| "loss": 0.1556, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 0.1194, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 4.207221350078493e-05, | |
| "loss": 0.1738, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 4.1287284144427e-05, | |
| "loss": 0.1495, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 4.0502354788069074e-05, | |
| "loss": 0.1603, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 3.971742543171115e-05, | |
| "loss": 0.1494, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 3.893249607535322e-05, | |
| "loss": 0.1469, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 3.814756671899529e-05, | |
| "loss": 0.1922, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 3.7362637362637365e-05, | |
| "loss": 0.1371, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 3.657770800627944e-05, | |
| "loss": 0.1627, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9320594479830149, | |
| "eval_loss": 0.2255283147096634, | |
| "eval_runtime": 34.5035, | |
| "eval_samples_per_second": 13.651, | |
| "eval_steps_per_second": 1.71, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 3.579277864992151e-05, | |
| "loss": 0.2128, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 3.500784929356358e-05, | |
| "loss": 0.0869, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 3.4222919937205655e-05, | |
| "loss": 0.1261, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 3.343799058084773e-05, | |
| "loss": 0.1104, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 3.265306122448979e-05, | |
| "loss": 0.1111, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 3.1868131868131866e-05, | |
| "loss": 0.0662, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 3.108320251177394e-05, | |
| "loss": 0.1436, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 3.029827315541601e-05, | |
| "loss": 0.1594, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 2.9513343799058084e-05, | |
| "loss": 0.105, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 2.8728414442700156e-05, | |
| "loss": 0.063, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 2.794348508634223e-05, | |
| "loss": 0.104, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 2.71585557299843e-05, | |
| "loss": 0.1071, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9341825902335457, | |
| "eval_loss": 0.2734454274177551, | |
| "eval_runtime": 34.3105, | |
| "eval_samples_per_second": 13.728, | |
| "eval_steps_per_second": 1.72, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 2.6373626373626374e-05, | |
| "loss": 0.0874, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 2.5588697017268447e-05, | |
| "loss": 0.1084, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 2.480376766091052e-05, | |
| "loss": 0.0758, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 2.4018838304552592e-05, | |
| "loss": 0.0895, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 2.3233908948194665e-05, | |
| "loss": 0.0998, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 2.2448979591836737e-05, | |
| "loss": 0.0797, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 2.166405023547881e-05, | |
| "loss": 0.0318, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 2.0879120879120882e-05, | |
| "loss": 0.0744, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 2.0094191522762955e-05, | |
| "loss": 0.0453, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 1.9309262166405024e-05, | |
| "loss": 0.1569, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 1.8524332810047097e-05, | |
| "loss": 0.0866, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 1.773940345368917e-05, | |
| "loss": 0.0757, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9447983014861996, | |
| "eval_loss": 0.23432743549346924, | |
| "eval_runtime": 35.6046, | |
| "eval_samples_per_second": 13.229, | |
| "eval_steps_per_second": 1.657, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 1.6954474097331242e-05, | |
| "loss": 0.0881, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 1.6169544740973315e-05, | |
| "loss": 0.0385, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 0.0238, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 1.4599686028257458e-05, | |
| "loss": 0.0733, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 1.3814756671899529e-05, | |
| "loss": 0.1086, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 1.3029827315541602e-05, | |
| "loss": 0.0896, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 1.2244897959183674e-05, | |
| "loss": 0.0461, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 1.1459968602825747e-05, | |
| "loss": 0.0427, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 1.067503924646782e-05, | |
| "loss": 0.0634, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 9.89010989010989e-06, | |
| "loss": 0.0591, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 9.105180533751963e-06, | |
| "loss": 0.0816, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 8.320251177394036e-06, | |
| "loss": 0.059, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9384288747346072, | |
| "eval_loss": 0.2577723562717438, | |
| "eval_runtime": 13.3966, | |
| "eval_samples_per_second": 35.158, | |
| "eval_steps_per_second": 4.404, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "learning_rate": 7.535321821036106e-06, | |
| "loss": 0.0398, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "learning_rate": 6.750392464678179e-06, | |
| "loss": 0.0226, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 5.25, | |
| "learning_rate": 5.965463108320252e-06, | |
| "loss": 0.0777, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 5.34, | |
| "learning_rate": 5.180533751962323e-06, | |
| "loss": 0.1017, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 5.42, | |
| "learning_rate": 4.395604395604396e-06, | |
| "loss": 0.0144, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 5.51, | |
| "learning_rate": 3.610675039246468e-06, | |
| "loss": 0.0738, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "learning_rate": 2.8257456828885403e-06, | |
| "loss": 0.0168, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 5.68, | |
| "learning_rate": 2.040816326530612e-06, | |
| "loss": 0.029, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "learning_rate": 1.2558869701726847e-06, | |
| "loss": 0.0407, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 5.85, | |
| "learning_rate": 4.7095761381475665e-07, | |
| "loss": 0.1009, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 0.0, | |
| "loss": 0.0266, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9426751592356688, | |
| "eval_loss": 0.23305891454219818, | |
| "eval_runtime": 33.4701, | |
| "eval_samples_per_second": 14.072, | |
| "eval_steps_per_second": 1.763, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "step": 708, | |
| "total_flos": 1.7589230025365053e+18, | |
| "train_loss": 0.10344488720941004, | |
| "train_runtime": 2153.5363, | |
| "train_samples_per_second": 10.506, | |
| "train_steps_per_second": 0.329 | |
| } | |
| ], | |
| "max_steps": 708, | |
| "num_train_epochs": 6, | |
| "total_flos": 1.7589230025365053e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |