| { | |
| "best_metric": 1.6296087503433228, | |
| "best_model_checkpoint": "facial_age_image_detection/checkpoint-10020", | |
| "epoch": 30.0, | |
| "eval_steps": 500, | |
| "global_step": 10020, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.24297489696515548, | |
| "eval_loss": 2.9744021892547607, | |
| "eval_runtime": 52.2658, | |
| "eval_samples_per_second": 102.132, | |
| "eval_steps_per_second": 3.195, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.864593781344032e-06, | |
| "loss": 2.9888, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.29674035219183215, | |
| "eval_loss": 2.684274673461914, | |
| "eval_runtime": 53.0339, | |
| "eval_samples_per_second": 100.653, | |
| "eval_steps_per_second": 3.149, | |
| "step": 668 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 2.714142427281846e-06, | |
| "loss": 2.5675, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.31997002622705134, | |
| "eval_loss": 2.4912328720092773, | |
| "eval_runtime": 52.2504, | |
| "eval_samples_per_second": 102.162, | |
| "eval_steps_per_second": 3.196, | |
| "step": 1002 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.3405769951292619, | |
| "eval_loss": 2.3644516468048096, | |
| "eval_runtime": 52.2527, | |
| "eval_samples_per_second": 102.157, | |
| "eval_steps_per_second": 3.196, | |
| "step": 1336 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 2.5636910732196588e-06, | |
| "loss": 2.3316, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.3621206444361184, | |
| "eval_loss": 2.266845226287842, | |
| "eval_runtime": 52.3012, | |
| "eval_samples_per_second": 102.063, | |
| "eval_steps_per_second": 3.193, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "learning_rate": 2.4132397191574725e-06, | |
| "loss": 2.185, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.3831022855001873, | |
| "eval_loss": 2.1891231536865234, | |
| "eval_runtime": 53.1986, | |
| "eval_samples_per_second": 100.341, | |
| "eval_steps_per_second": 3.139, | |
| "step": 2004 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.3939677781940802, | |
| "eval_loss": 2.124483346939087, | |
| "eval_runtime": 54.0657, | |
| "eval_samples_per_second": 98.732, | |
| "eval_steps_per_second": 3.089, | |
| "step": 2338 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "learning_rate": 2.262788365095286e-06, | |
| "loss": 2.0759, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.40764331210191085, | |
| "eval_loss": 2.0697174072265625, | |
| "eval_runtime": 52.3282, | |
| "eval_samples_per_second": 102.01, | |
| "eval_steps_per_second": 3.191, | |
| "step": 2672 | |
| }, | |
| { | |
| "epoch": 8.98, | |
| "learning_rate": 2.1123370110330997e-06, | |
| "loss": 1.9878, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.4194454852004496, | |
| "eval_loss": 2.019850015640259, | |
| "eval_runtime": 52.333, | |
| "eval_samples_per_second": 102.001, | |
| "eval_steps_per_second": 3.191, | |
| "step": 3006 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.43368302735106784, | |
| "eval_loss": 1.9797377586364746, | |
| "eval_runtime": 52.4208, | |
| "eval_samples_per_second": 101.83, | |
| "eval_steps_per_second": 3.186, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 10.48, | |
| "learning_rate": 1.9618856569709126e-06, | |
| "loss": 1.9168, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.43349569127013865, | |
| "eval_loss": 1.9416717290878296, | |
| "eval_runtime": 52.2275, | |
| "eval_samples_per_second": 102.207, | |
| "eval_steps_per_second": 3.198, | |
| "step": 3674 | |
| }, | |
| { | |
| "epoch": 11.98, | |
| "learning_rate": 1.8114343029087262e-06, | |
| "loss": 1.8504, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.45185462720119896, | |
| "eval_loss": 1.9020978212356567, | |
| "eval_runtime": 52.0691, | |
| "eval_samples_per_second": 102.518, | |
| "eval_steps_per_second": 3.207, | |
| "step": 4008 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.45766204571000374, | |
| "eval_loss": 1.868658185005188, | |
| "eval_runtime": 52.1907, | |
| "eval_samples_per_second": 102.279, | |
| "eval_steps_per_second": 3.2, | |
| "step": 4342 | |
| }, | |
| { | |
| "epoch": 13.47, | |
| "learning_rate": 1.6609829488465398e-06, | |
| "loss": 1.7952, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.4644061446234545, | |
| "eval_loss": 1.8404171466827393, | |
| "eval_runtime": 52.0362, | |
| "eval_samples_per_second": 102.582, | |
| "eval_steps_per_second": 3.209, | |
| "step": 4676 | |
| }, | |
| { | |
| "epoch": 14.97, | |
| "learning_rate": 1.510531594784353e-06, | |
| "loss": 1.7469, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.4668415136755339, | |
| "eval_loss": 1.814427137374878, | |
| "eval_runtime": 52.0939, | |
| "eval_samples_per_second": 102.469, | |
| "eval_steps_per_second": 3.206, | |
| "step": 5010 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.46796553016110903, | |
| "eval_loss": 1.7911080121994019, | |
| "eval_runtime": 53.1692, | |
| "eval_samples_per_second": 100.396, | |
| "eval_steps_per_second": 3.141, | |
| "step": 5344 | |
| }, | |
| { | |
| "epoch": 16.47, | |
| "learning_rate": 1.3600802407221665e-06, | |
| "loss": 1.7033, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.4795803671787186, | |
| "eval_loss": 1.7677799463272095, | |
| "eval_runtime": 51.8901, | |
| "eval_samples_per_second": 102.871, | |
| "eval_steps_per_second": 3.218, | |
| "step": 5678 | |
| }, | |
| { | |
| "epoch": 17.96, | |
| "learning_rate": 1.20962888665998e-06, | |
| "loss": 1.6621, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.4855751217684526, | |
| "eval_loss": 1.748055338859558, | |
| "eval_runtime": 52.1275, | |
| "eval_samples_per_second": 102.403, | |
| "eval_steps_per_second": 3.204, | |
| "step": 6012 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.48651180217309853, | |
| "eval_loss": 1.7302188873291016, | |
| "eval_runtime": 52.0882, | |
| "eval_samples_per_second": 102.48, | |
| "eval_steps_per_second": 3.206, | |
| "step": 6346 | |
| }, | |
| { | |
| "epoch": 19.46, | |
| "learning_rate": 1.0591775325977935e-06, | |
| "loss": 1.6249, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.4866991382540277, | |
| "eval_loss": 1.7110319137573242, | |
| "eval_runtime": 52.1234, | |
| "eval_samples_per_second": 102.411, | |
| "eval_steps_per_second": 3.204, | |
| "step": 6680 | |
| }, | |
| { | |
| "epoch": 20.96, | |
| "learning_rate": 9.087261785356068e-07, | |
| "loss": 1.6, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.49587860621955787, | |
| "eval_loss": 1.6950350999832153, | |
| "eval_runtime": 52.517, | |
| "eval_samples_per_second": 101.643, | |
| "eval_steps_per_second": 3.18, | |
| "step": 7014 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.4971899587860622, | |
| "eval_loss": 1.683102011680603, | |
| "eval_runtime": 52.8184, | |
| "eval_samples_per_second": 101.063, | |
| "eval_steps_per_second": 3.162, | |
| "step": 7348 | |
| }, | |
| { | |
| "epoch": 22.46, | |
| "learning_rate": 7.582748244734203e-07, | |
| "loss": 1.5698, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.5018733608092919, | |
| "eval_loss": 1.6692556142807007, | |
| "eval_runtime": 52.387, | |
| "eval_samples_per_second": 101.895, | |
| "eval_steps_per_second": 3.188, | |
| "step": 7682 | |
| }, | |
| { | |
| "epoch": 23.95, | |
| "learning_rate": 6.078234704112337e-07, | |
| "loss": 1.5493, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.49625327838141625, | |
| "eval_loss": 1.659037709236145, | |
| "eval_runtime": 52.3852, | |
| "eval_samples_per_second": 101.899, | |
| "eval_steps_per_second": 3.188, | |
| "step": 8016 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.5084301236418134, | |
| "eval_loss": 1.650451421737671, | |
| "eval_runtime": 51.9831, | |
| "eval_samples_per_second": 102.687, | |
| "eval_steps_per_second": 3.213, | |
| "step": 8350 | |
| }, | |
| { | |
| "epoch": 25.45, | |
| "learning_rate": 4.5737211634904716e-07, | |
| "loss": 1.5313, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.5050580741850881, | |
| "eval_loss": 1.6430058479309082, | |
| "eval_runtime": 52.0136, | |
| "eval_samples_per_second": 102.627, | |
| "eval_steps_per_second": 3.211, | |
| "step": 8684 | |
| }, | |
| { | |
| "epoch": 26.95, | |
| "learning_rate": 3.069207622868606e-07, | |
| "loss": 1.5177, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.5063694267515924, | |
| "eval_loss": 1.6367906332015991, | |
| "eval_runtime": 52.2435, | |
| "eval_samples_per_second": 102.175, | |
| "eval_steps_per_second": 3.197, | |
| "step": 9018 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.5076807793180966, | |
| "eval_loss": 1.633717656135559, | |
| "eval_runtime": 52.2304, | |
| "eval_samples_per_second": 102.201, | |
| "eval_steps_per_second": 3.197, | |
| "step": 9352 | |
| }, | |
| { | |
| "epoch": 28.44, | |
| "learning_rate": 1.5646940822467403e-07, | |
| "loss": 1.5101, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.5069314349943799, | |
| "eval_loss": 1.6314198970794678, | |
| "eval_runtime": 52.5904, | |
| "eval_samples_per_second": 101.501, | |
| "eval_steps_per_second": 3.175, | |
| "step": 9686 | |
| }, | |
| { | |
| "epoch": 29.94, | |
| "learning_rate": 6.018054162487462e-09, | |
| "loss": 1.5, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.5050580741850881, | |
| "eval_loss": 1.6296087503433228, | |
| "eval_runtime": 52.2229, | |
| "eval_samples_per_second": 102.216, | |
| "eval_steps_per_second": 3.198, | |
| "step": 10020 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 10020, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "total_flos": 4.964340605762765e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |