| { | |
| "best_metric": 0.9373634377276038, | |
| "best_model_checkpoint": "./weather-base/checkpoint-342", | |
| "epoch": 2.995633187772926, | |
| "global_step": 513, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.615384615384616e-06, | |
| "loss": 2.5162, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.923076923076923e-05, | |
| "loss": 2.2089, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 2.8846153846153845e-05, | |
| "loss": 1.744, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 1.1145, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.8076923076923084e-05, | |
| "loss": 0.7667, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.9132321041214754e-05, | |
| "loss": 0.6373, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.804772234273319e-05, | |
| "loss": 0.4996, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.696312364425163e-05, | |
| "loss": 0.429, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.587852494577007e-05, | |
| "loss": 0.4243, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.47939262472885e-05, | |
| "loss": 0.3769, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 4.370932754880694e-05, | |
| "loss": 0.4072, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 4.262472885032538e-05, | |
| "loss": 0.3406, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.154013015184382e-05, | |
| "loss": 0.3224, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 4.045553145336225e-05, | |
| "loss": 0.4434, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 3.9370932754880696e-05, | |
| "loss": 0.3797, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.828633405639914e-05, | |
| "loss": 0.316, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.720173535791757e-05, | |
| "loss": 0.3277, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9002184996358339, | |
| "eval_loss": 0.29298296570777893, | |
| "eval_runtime": 34.0636, | |
| "eval_samples_per_second": 40.307, | |
| "eval_steps_per_second": 5.049, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.611713665943601e-05, | |
| "loss": 0.3201, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.503253796095445e-05, | |
| "loss": 0.3002, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.394793926247289e-05, | |
| "loss": 0.2141, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 3.286334056399132e-05, | |
| "loss": 0.2718, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 3.1778741865509765e-05, | |
| "loss": 0.2551, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 3.06941431670282e-05, | |
| "loss": 0.2694, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2.960954446854664e-05, | |
| "loss": 0.3507, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 2.8524945770065074e-05, | |
| "loss": 0.2558, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.7440347071583517e-05, | |
| "loss": 0.185, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 2.635574837310195e-05, | |
| "loss": 0.2202, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 2.5271149674620394e-05, | |
| "loss": 0.2468, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 2.418655097613883e-05, | |
| "loss": 0.2374, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 2.3101952277657267e-05, | |
| "loss": 0.2063, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 2.2017353579175707e-05, | |
| "loss": 0.1711, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 2.0932754880694143e-05, | |
| "loss": 0.2644, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.9848156182212583e-05, | |
| "loss": 0.2194, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 1.876355748373102e-05, | |
| "loss": 0.2401, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9373634377276038, | |
| "eval_loss": 0.19143207371234894, | |
| "eval_runtime": 72.116, | |
| "eval_samples_per_second": 19.039, | |
| "eval_steps_per_second": 2.385, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.767895878524946e-05, | |
| "loss": 0.1665, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 1.6594360086767896e-05, | |
| "loss": 0.1463, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 1.5509761388286336e-05, | |
| "loss": 0.1939, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 1.4425162689804772e-05, | |
| "loss": 0.2001, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 1.334056399132321e-05, | |
| "loss": 0.2046, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 1.225596529284165e-05, | |
| "loss": 0.172, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 1.1171366594360088e-05, | |
| "loss": 0.1597, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 1.0086767895878525e-05, | |
| "loss": 0.1624, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 9.002169197396963e-06, | |
| "loss": 0.1609, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 7.917570498915401e-06, | |
| "loss": 0.1972, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 6.832971800433839e-06, | |
| "loss": 0.1007, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 5.748373101952278e-06, | |
| "loss": 0.0885, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 4.663774403470715e-06, | |
| "loss": 0.1321, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 3.5791757049891544e-06, | |
| "loss": 0.1699, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 2.4945770065075926e-06, | |
| "loss": 0.1647, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 1.4099783080260303e-06, | |
| "loss": 0.1175, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 3.2537960954446857e-07, | |
| "loss": 0.1036, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9359067734887109, | |
| "eval_loss": 0.18145906925201416, | |
| "eval_runtime": 29.9478, | |
| "eval_samples_per_second": 45.846, | |
| "eval_steps_per_second": 5.743, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 513, | |
| "total_flos": 1.2743012151733248e+18, | |
| "train_loss": 0.393069394557332, | |
| "train_runtime": 1296.2409, | |
| "train_samples_per_second": 12.704, | |
| "train_steps_per_second": 0.396 | |
| } | |
| ], | |
| "max_steps": 513, | |
| "num_train_epochs": 3, | |
| "total_flos": 1.2743012151733248e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |