| { | |
| "best_metric": 0.9194139194139194, | |
| "best_model_checkpoint": "vit-msn-small-corect_deepcleaned_dataset_lateral_flow_ivalidation/checkpoint-39", | |
| "epoch": 18.46153846153846, | |
| "eval_steps": 500, | |
| "global_step": 60, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9230769230769231, | |
| "eval_accuracy": 0.7216117216117216, | |
| "eval_loss": 0.6175123453140259, | |
| "eval_runtime": 1.1447, | |
| "eval_samples_per_second": 238.5, | |
| "eval_steps_per_second": 4.368, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.8461538461538463, | |
| "eval_accuracy": 0.8351648351648352, | |
| "eval_loss": 0.4141041934490204, | |
| "eval_runtime": 1.1326, | |
| "eval_samples_per_second": 241.031, | |
| "eval_steps_per_second": 4.414, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 2.769230769230769, | |
| "eval_accuracy": 0.5787545787545788, | |
| "eval_loss": 0.7407873868942261, | |
| "eval_runtime": 1.1747, | |
| "eval_samples_per_second": 232.409, | |
| "eval_steps_per_second": 4.257, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 3.076923076923077, | |
| "grad_norm": 70.46142578125, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.5817, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9157509157509157, | |
| "eval_loss": 0.27566295862197876, | |
| "eval_runtime": 1.1638, | |
| "eval_samples_per_second": 234.573, | |
| "eval_steps_per_second": 4.296, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 4.923076923076923, | |
| "eval_accuracy": 0.8791208791208791, | |
| "eval_loss": 0.28472262620925903, | |
| "eval_runtime": 1.1571, | |
| "eval_samples_per_second": 235.942, | |
| "eval_steps_per_second": 4.321, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 5.846153846153846, | |
| "eval_accuracy": 0.9010989010989011, | |
| "eval_loss": 0.2455928921699524, | |
| "eval_runtime": 1.2196, | |
| "eval_samples_per_second": 223.848, | |
| "eval_steps_per_second": 4.1, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 6.153846153846154, | |
| "grad_norm": 8.08311653137207, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.3724, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 6.769230769230769, | |
| "eval_accuracy": 0.9120879120879121, | |
| "eval_loss": 0.25474727153778076, | |
| "eval_runtime": 1.1827, | |
| "eval_samples_per_second": 230.827, | |
| "eval_steps_per_second": 4.228, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8827838827838828, | |
| "eval_loss": 0.3007383942604065, | |
| "eval_runtime": 1.2369, | |
| "eval_samples_per_second": 220.714, | |
| "eval_steps_per_second": 4.042, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 8.923076923076923, | |
| "eval_accuracy": 0.9010989010989011, | |
| "eval_loss": 0.3042505383491516, | |
| "eval_runtime": 1.1883, | |
| "eval_samples_per_second": 229.74, | |
| "eval_steps_per_second": 4.208, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 9.23076923076923, | |
| "grad_norm": 12.493155479431152, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.3155, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 9.846153846153847, | |
| "eval_accuracy": 0.9047619047619048, | |
| "eval_loss": 0.2603397071361542, | |
| "eval_runtime": 1.1963, | |
| "eval_samples_per_second": 228.207, | |
| "eval_steps_per_second": 4.18, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 10.76923076923077, | |
| "eval_accuracy": 0.9157509157509157, | |
| "eval_loss": 0.24810168147087097, | |
| "eval_runtime": 1.1361, | |
| "eval_samples_per_second": 240.289, | |
| "eval_steps_per_second": 4.401, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.9194139194139194, | |
| "eval_loss": 0.22294031083583832, | |
| "eval_runtime": 1.1914, | |
| "eval_samples_per_second": 229.149, | |
| "eval_steps_per_second": 4.197, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 12.307692307692308, | |
| "grad_norm": 8.086904525756836, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.2844, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 12.923076923076923, | |
| "eval_accuracy": 0.8791208791208791, | |
| "eval_loss": 0.3036467432975769, | |
| "eval_runtime": 1.1286, | |
| "eval_samples_per_second": 241.895, | |
| "eval_steps_per_second": 4.43, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 13.846153846153847, | |
| "eval_accuracy": 0.9084249084249084, | |
| "eval_loss": 0.2578851580619812, | |
| "eval_runtime": 1.1539, | |
| "eval_samples_per_second": 236.595, | |
| "eval_steps_per_second": 4.333, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 14.76923076923077, | |
| "eval_accuracy": 0.9157509157509157, | |
| "eval_loss": 0.2433992624282837, | |
| "eval_runtime": 1.2067, | |
| "eval_samples_per_second": 226.24, | |
| "eval_steps_per_second": 4.144, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 15.384615384615385, | |
| "grad_norm": 3.2125346660614014, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.2517, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.9047619047619048, | |
| "eval_loss": 0.27184122800827026, | |
| "eval_runtime": 1.1306, | |
| "eval_samples_per_second": 241.471, | |
| "eval_steps_per_second": 4.423, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 16.923076923076923, | |
| "eval_accuracy": 0.9120879120879121, | |
| "eval_loss": 0.25126636028289795, | |
| "eval_runtime": 1.1542, | |
| "eval_samples_per_second": 236.531, | |
| "eval_steps_per_second": 4.332, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 17.846153846153847, | |
| "eval_accuracy": 0.9120879120879121, | |
| "eval_loss": 0.25034624338150024, | |
| "eval_runtime": 1.2382, | |
| "eval_samples_per_second": 220.484, | |
| "eval_steps_per_second": 4.038, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 18.46153846153846, | |
| "grad_norm": 4.7955803871154785, | |
| "learning_rate": 0.0, | |
| "loss": 0.2468, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 18.46153846153846, | |
| "eval_accuracy": 0.9120879120879121, | |
| "eval_loss": 0.24911320209503174, | |
| "eval_runtime": 1.1404, | |
| "eval_samples_per_second": 239.4, | |
| "eval_steps_per_second": 4.385, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 18.46153846153846, | |
| "step": 60, | |
| "total_flos": 2.9458314315627725e+17, | |
| "train_loss": 0.342086935043335, | |
| "train_runtime": 153.4118, | |
| "train_samples_per_second": 106.25, | |
| "train_steps_per_second": 0.391 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 60, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "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": 2.9458314315627725e+17, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |