| { | |
| "best_metric": 0.7184367179870605, | |
| "best_model_checkpoint": "./croupier-creature-classifier/checkpoint-500", | |
| "epoch": 6.0, | |
| "global_step": 546, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00019633699633699633, | |
| "loss": 1.3778, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00019267399267399268, | |
| "loss": 1.3655, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00018901098901098903, | |
| "loss": 1.4055, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00018534798534798537, | |
| "loss": 1.3073, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0001816849816849817, | |
| "loss": 1.1786, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00017802197802197802, | |
| "loss": 1.1462, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00017435897435897436, | |
| "loss": 1.171, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00017069597069597068, | |
| "loss": 1.1439, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.00016703296703296706, | |
| "loss": 1.1168, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.00016336996336996338, | |
| "loss": 0.8932, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_accuracy": 0.6058823529411764, | |
| "eval_loss": 0.9914249181747437, | |
| "eval_runtime": 1.5014, | |
| "eval_samples_per_second": 113.229, | |
| "eval_steps_per_second": 14.653, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00015970695970695973, | |
| "loss": 0.9693, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.00015604395604395605, | |
| "loss": 0.8965, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.00015238095238095237, | |
| "loss": 0.8848, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.00014871794871794872, | |
| "loss": 0.8311, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.00014505494505494506, | |
| "loss": 0.8909, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.0001413919413919414, | |
| "loss": 0.8739, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.00013772893772893773, | |
| "loss": 0.9564, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.00013406593406593405, | |
| "loss": 0.9058, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 0.0001304029304029304, | |
| "loss": 0.6668, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 0.00012673992673992675, | |
| "loss": 0.6608, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "eval_accuracy": 0.6588235294117647, | |
| "eval_loss": 0.8645371198654175, | |
| "eval_runtime": 1.6411, | |
| "eval_samples_per_second": 103.586, | |
| "eval_steps_per_second": 13.405, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 0.0001230769230769231, | |
| "loss": 0.6599, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 0.00011941391941391942, | |
| "loss": 0.6528, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 0.00011575091575091577, | |
| "loss": 0.79, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 0.0001120879120879121, | |
| "loss": 0.633, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 0.00010842490842490842, | |
| "loss": 0.7036, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 0.00010476190476190477, | |
| "loss": 0.693, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 0.0001010989010989011, | |
| "loss": 0.6463, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 9.743589743589744e-05, | |
| "loss": 0.6102, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 9.377289377289377e-05, | |
| "loss": 0.4745, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 9.010989010989012e-05, | |
| "loss": 0.6084, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "eval_accuracy": 0.7294117647058823, | |
| "eval_loss": 0.7325618863105774, | |
| "eval_runtime": 2.0857, | |
| "eval_samples_per_second": 81.509, | |
| "eval_steps_per_second": 10.548, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 8.644688644688645e-05, | |
| "loss": 0.5139, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 8.278388278388279e-05, | |
| "loss": 0.4558, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 7.912087912087912e-05, | |
| "loss": 0.6333, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 7.545787545787546e-05, | |
| "loss": 0.4555, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 7.17948717948718e-05, | |
| "loss": 0.5633, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 6.813186813186814e-05, | |
| "loss": 0.6345, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 6.446886446886447e-05, | |
| "loss": 0.4467, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 6.08058608058608e-05, | |
| "loss": 0.4054, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 5.714285714285714e-05, | |
| "loss": 0.3802, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 5.347985347985348e-05, | |
| "loss": 0.5261, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "eval_accuracy": 0.6941176470588235, | |
| "eval_loss": 0.7683902382850647, | |
| "eval_runtime": 1.6322, | |
| "eval_samples_per_second": 104.156, | |
| "eval_steps_per_second": 13.479, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 4.981684981684982e-05, | |
| "loss": 0.3335, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 4.615384615384616e-05, | |
| "loss": 0.3908, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 4.249084249084249e-05, | |
| "loss": 0.3603, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 3.8827838827838833e-05, | |
| "loss": 0.3774, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 3.516483516483517e-05, | |
| "loss": 0.3759, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 3.15018315018315e-05, | |
| "loss": 0.3021, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 2.783882783882784e-05, | |
| "loss": 0.3494, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 2.4175824175824177e-05, | |
| "loss": 0.33, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 2.0512820512820512e-05, | |
| "loss": 0.3074, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "learning_rate": 1.6849816849816853e-05, | |
| "loss": 0.2511, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "eval_accuracy": 0.7058823529411765, | |
| "eval_loss": 0.7184367179870605, | |
| "eval_runtime": 1.6349, | |
| "eval_samples_per_second": 103.983, | |
| "eval_steps_per_second": 13.457, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 1.3186813186813187e-05, | |
| "loss": 0.2773, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 9.523809523809523e-06, | |
| "loss": 0.3286, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "learning_rate": 5.860805860805861e-06, | |
| "loss": 0.2832, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 2.197802197802198e-06, | |
| "loss": 0.2439, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "step": 546, | |
| "total_flos": 6.74657354848813e+17, | |
| "train_loss": 0.6752170354892046, | |
| "train_runtime": 241.286, | |
| "train_samples_per_second": 36.082, | |
| "train_steps_per_second": 2.263 | |
| } | |
| ], | |
| "max_steps": 546, | |
| "num_train_epochs": 6, | |
| "total_flos": 6.74657354848813e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |