| { | |
| "best_metric": 0.8720870015535992, | |
| "best_model_checkpoint": "swin-base-patch4-window7-224-in22k-MM_Classification_base_V10/checkpoint-61", | |
| "epoch": 6.885245901639344, | |
| "eval_steps": 500, | |
| "global_step": 105, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.6557377049180327, | |
| "grad_norm": 3.5814733505249023, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 0.8498, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.9836065573770492, | |
| "step": 15, | |
| "train_accuracy": 0.8171125759338245, | |
| "train_auc": 0.8967571163903928, | |
| "train_loss": 0.47165462374687195, | |
| "train_runtime": 694.4657, | |
| "train_samples_per_second": 11.141, | |
| "train_steps_per_second": 0.088 | |
| }, | |
| { | |
| "epoch": 0.9836065573770492, | |
| "eval_accuracy": 0.8327291558777835, | |
| "eval_auc": 0.9183935491091096, | |
| "eval_loss": 0.4327956438064575, | |
| "eval_runtime": 205.3728, | |
| "eval_samples_per_second": 9.402, | |
| "eval_steps_per_second": 0.078, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.3114754098360657, | |
| "grad_norm": 2.3799431324005127, | |
| "learning_rate": 4.5212765957446815e-05, | |
| "loss": 0.5123, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.9672131147540983, | |
| "grad_norm": 2.067809581756592, | |
| "learning_rate": 3.9893617021276594e-05, | |
| "loss": 0.4085, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.9672131147540983, | |
| "step": 30, | |
| "train_accuracy": 0.8517513248028952, | |
| "train_auc": 0.9387841345112529, | |
| "train_loss": 0.36320993304252625, | |
| "train_runtime": 684.0745, | |
| "train_samples_per_second": 11.31, | |
| "train_steps_per_second": 0.089 | |
| }, | |
| { | |
| "epoch": 1.9672131147540983, | |
| "eval_accuracy": 0.8518902123252201, | |
| "eval_auc": 0.9423845489697825, | |
| "eval_loss": 0.37112149596214294, | |
| "eval_runtime": 205.1458, | |
| "eval_samples_per_second": 9.413, | |
| "eval_steps_per_second": 0.078, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.6229508196721314, | |
| "grad_norm": 2.11800479888916, | |
| "learning_rate": 3.4574468085106386e-05, | |
| "loss": 0.3717, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.9508196721311473, | |
| "step": 45, | |
| "train_accuracy": 0.864029985782603, | |
| "train_auc": 0.9527023779434378, | |
| "train_loss": 0.3227292597293854, | |
| "train_runtime": 681.4027, | |
| "train_samples_per_second": 11.355, | |
| "train_steps_per_second": 0.09 | |
| }, | |
| { | |
| "epoch": 2.9508196721311473, | |
| "eval_accuracy": 0.8653547384774728, | |
| "eval_auc": 0.9487342167219569, | |
| "eval_loss": 0.3345213234424591, | |
| "eval_runtime": 203.71, | |
| "eval_samples_per_second": 9.479, | |
| "eval_steps_per_second": 0.079, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 3.278688524590164, | |
| "grad_norm": 4.481107711791992, | |
| "learning_rate": 2.925531914893617e-05, | |
| "loss": 0.3301, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.9344262295081966, | |
| "grad_norm": 2.703953981399536, | |
| "learning_rate": 2.393617021276596e-05, | |
| "loss": 0.3196, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "step": 61, | |
| "train_accuracy": 0.8733359183145922, | |
| "train_auc": 0.9563002964315263, | |
| "train_loss": 0.30748647451400757, | |
| "train_runtime": 678.9663, | |
| "train_samples_per_second": 11.395, | |
| "train_steps_per_second": 0.09 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8720870015535992, | |
| "eval_auc": 0.9534343762433686, | |
| "eval_loss": 0.3244781792163849, | |
| "eval_runtime": 204.3133, | |
| "eval_samples_per_second": 9.451, | |
| "eval_steps_per_second": 0.078, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 4.590163934426229, | |
| "grad_norm": 1.967414379119873, | |
| "learning_rate": 1.8617021276595745e-05, | |
| "loss": 0.3279, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 4.983606557377049, | |
| "step": 76, | |
| "train_accuracy": 0.8813493602171384, | |
| "train_auc": 0.9603495718478623, | |
| "train_loss": 0.2974039912223816, | |
| "train_runtime": 680.7385, | |
| "train_samples_per_second": 11.366, | |
| "train_steps_per_second": 0.09 | |
| }, | |
| { | |
| "epoch": 4.983606557377049, | |
| "eval_accuracy": 0.8694976696012429, | |
| "eval_auc": 0.953884522107936, | |
| "eval_loss": 0.3240814805030823, | |
| "eval_runtime": 203.7726, | |
| "eval_samples_per_second": 9.476, | |
| "eval_steps_per_second": 0.079, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 5.245901639344262, | |
| "grad_norm": 1.8759346008300781, | |
| "learning_rate": 1.3297872340425532e-05, | |
| "loss": 0.3042, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 5.901639344262295, | |
| "grad_norm": 2.394904136657715, | |
| "learning_rate": 7.97872340425532e-06, | |
| "loss": 0.2926, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 5.967213114754099, | |
| "step": 91, | |
| "train_accuracy": 0.8858730774201887, | |
| "train_auc": 0.9646418504220758, | |
| "train_loss": 0.28083333373069763, | |
| "train_runtime": 681.28, | |
| "train_samples_per_second": 11.357, | |
| "train_steps_per_second": 0.09 | |
| }, | |
| { | |
| "epoch": 5.967213114754099, | |
| "eval_accuracy": 0.8674262040393579, | |
| "eval_auc": 0.9548863198183253, | |
| "eval_loss": 0.3211652338504791, | |
| "eval_runtime": 205.0822, | |
| "eval_samples_per_second": 9.416, | |
| "eval_steps_per_second": 0.078, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 6.557377049180328, | |
| "grad_norm": 1.7362953424453735, | |
| "learning_rate": 2.6595744680851065e-06, | |
| "loss": 0.2821, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 6.885245901639344, | |
| "step": 105, | |
| "train_accuracy": 0.8937572702597906, | |
| "train_auc": 0.9682688664846578, | |
| "train_loss": 0.26618629693984985, | |
| "train_runtime": 676.8276, | |
| "train_samples_per_second": 11.431, | |
| "train_steps_per_second": 0.09 | |
| }, | |
| { | |
| "epoch": 6.885245901639344, | |
| "eval_accuracy": 0.8705334023821854, | |
| "eval_auc": 0.9549996078144867, | |
| "eval_loss": 0.31725937128067017, | |
| "eval_runtime": 203.7289, | |
| "eval_samples_per_second": 9.478, | |
| "eval_steps_per_second": 0.079, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 6.885245901639344, | |
| "step": 105, | |
| "total_flos": 4.1785312376666235e+18, | |
| "train_loss": 0.3947783969697498, | |
| "train_runtime": 11418.3292, | |
| "train_samples_per_second": 4.743, | |
| "train_steps_per_second": 0.009 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 105, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 7, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.1785312376666235e+18, | |
| "train_batch_size": 128, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |