| { | |
| "best_metric": 0.9535481125844637, | |
| "best_model_checkpoint": "microsoft-swinv2-small-patch4-window16-256-finetuned-xblockm\\checkpoint-160", | |
| "epoch": 7.901234567901234, | |
| "eval_steps": 500, | |
| "global_step": 160, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.49382716049382713, | |
| "grad_norm": 1.6179720163345337, | |
| "learning_rate": 1.5503875968992248e-05, | |
| "loss": 0.6579, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.9876543209876543, | |
| "grad_norm": 2.4816274642944336, | |
| "learning_rate": 3.1007751937984497e-05, | |
| "loss": 0.4357, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.9876543209876543, | |
| "eval_loss": 0.2544282078742981, | |
| "eval_roc_auc": 0.7784430091957527, | |
| "eval_runtime": 57.6433, | |
| "eval_samples_per_second": 5.621, | |
| "eval_steps_per_second": 0.364, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.4814814814814814, | |
| "grad_norm": 1.2008687257766724, | |
| "learning_rate": 4.651162790697675e-05, | |
| "loss": 0.2163, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "grad_norm": 1.6955859661102295, | |
| "learning_rate": 6.201550387596899e-05, | |
| "loss": 0.2027, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "eval_loss": 0.20164352655410767, | |
| "eval_roc_auc": 0.8430768302596149, | |
| "eval_runtime": 62.1569, | |
| "eval_samples_per_second": 5.213, | |
| "eval_steps_per_second": 0.338, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.4691358024691357, | |
| "grad_norm": 0.869544267654419, | |
| "learning_rate": 7.751937984496124e-05, | |
| "loss": 0.1889, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "grad_norm": 0.8159006834030151, | |
| "learning_rate": 9.30232558139535e-05, | |
| "loss": 0.1743, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "eval_loss": 0.17011196911334991, | |
| "eval_roc_auc": 0.8911886208911244, | |
| "eval_runtime": 79.4085, | |
| "eval_samples_per_second": 4.08, | |
| "eval_steps_per_second": 0.264, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.45679012345679, | |
| "grad_norm": 0.8456718921661377, | |
| "learning_rate": 0.00010852713178294573, | |
| "loss": 0.1567, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "grad_norm": 0.9450457692146301, | |
| "learning_rate": 0.00012403100775193799, | |
| "loss": 0.1625, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.16766950488090515, | |
| "eval_roc_auc": 0.9083226959813038, | |
| "eval_runtime": 84.3656, | |
| "eval_samples_per_second": 3.84, | |
| "eval_steps_per_second": 0.249, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 4.444444444444445, | |
| "grad_norm": 0.6654064655303955, | |
| "learning_rate": 0.00013953488372093025, | |
| "loss": 0.1553, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "grad_norm": 0.7665498852729797, | |
| "learning_rate": 0.0001550387596899225, | |
| "loss": 0.1321, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 4.987654320987654, | |
| "eval_loss": 0.144697904586792, | |
| "eval_roc_auc": 0.9246192780572068, | |
| "eval_runtime": 39.0205, | |
| "eval_samples_per_second": 8.303, | |
| "eval_steps_per_second": 0.538, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 5.432098765432099, | |
| "grad_norm": 0.6621432900428772, | |
| "learning_rate": 0.00017054263565891473, | |
| "loss": 0.1232, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 5.925925925925926, | |
| "grad_norm": 0.7424349188804626, | |
| "learning_rate": 0.000186046511627907, | |
| "loss": 0.1155, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 5.9753086419753085, | |
| "eval_loss": 0.14180859923362732, | |
| "eval_roc_auc": 0.9311112381242697, | |
| "eval_runtime": 132.4426, | |
| "eval_samples_per_second": 2.446, | |
| "eval_steps_per_second": 0.159, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 6.419753086419753, | |
| "grad_norm": 0.6604060530662537, | |
| "learning_rate": 0.00019999963640522314, | |
| "loss": 0.1009, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 6.91358024691358, | |
| "grad_norm": 0.7176498174667358, | |
| "learning_rate": 0.0001999560082311786, | |
| "loss": 0.0959, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 6.962962962962963, | |
| "eval_loss": 0.13807977735996246, | |
| "eval_roc_auc": 0.9460352842554489, | |
| "eval_runtime": 148.6943, | |
| "eval_samples_per_second": 2.179, | |
| "eval_steps_per_second": 0.141, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 7.407407407407407, | |
| "grad_norm": 0.7749078869819641, | |
| "learning_rate": 0.0001998396974527365, | |
| "loss": 0.0748, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 7.901234567901234, | |
| "grad_norm": 0.5961336493492126, | |
| "learning_rate": 0.00019965078864480587, | |
| "loss": 0.0788, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 7.901234567901234, | |
| "eval_loss": 0.12518148124217987, | |
| "eval_roc_auc": 0.9535481125844637, | |
| "eval_runtime": 101.3985, | |
| "eval_samples_per_second": 3.195, | |
| "eval_steps_per_second": 0.207, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 7.901234567901234, | |
| "step": 160, | |
| "total_flos": 4.522715256123187e+17, | |
| "train_loss": 0.19196589663624763, | |
| "train_runtime": 9159.5769, | |
| "train_samples_per_second": 1.13, | |
| "train_steps_per_second": 0.017 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 160, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 8, | |
| "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": 4.522715256123187e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |