| { | |
| "best_metric": 0.9230769230769231, | |
| "best_model_checkpoint": "vit-msn-small-corect_cleaned_dataset_lateral_flow_ivalidation/checkpoint-19", | |
| "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": 0.5604395604395604, | |
| "eval_loss": 0.646826446056366, | |
| "eval_runtime": 1.1236, | |
| "eval_samples_per_second": 242.961, | |
| "eval_steps_per_second": 4.45, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.8461538461538463, | |
| "eval_accuracy": 0.8461538461538461, | |
| "eval_loss": 0.4226689040660858, | |
| "eval_runtime": 1.143, | |
| "eval_samples_per_second": 238.855, | |
| "eval_steps_per_second": 4.375, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 2.769230769230769, | |
| "eval_accuracy": 0.8608058608058609, | |
| "eval_loss": 0.33896148204803467, | |
| "eval_runtime": 1.1586, | |
| "eval_samples_per_second": 235.63, | |
| "eval_steps_per_second": 4.316, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 3.076923076923077, | |
| "grad_norm": 4.28239107131958, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.5336, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8864468864468864, | |
| "eval_loss": 0.311496764421463, | |
| "eval_runtime": 1.1462, | |
| "eval_samples_per_second": 238.174, | |
| "eval_steps_per_second": 4.362, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 4.923076923076923, | |
| "eval_accuracy": 0.8937728937728938, | |
| "eval_loss": 0.2986319661140442, | |
| "eval_runtime": 1.1756, | |
| "eval_samples_per_second": 232.213, | |
| "eval_steps_per_second": 4.253, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 5.846153846153846, | |
| "eval_accuracy": 0.9230769230769231, | |
| "eval_loss": 0.2317860871553421, | |
| "eval_runtime": 1.1748, | |
| "eval_samples_per_second": 232.38, | |
| "eval_steps_per_second": 4.256, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 6.153846153846154, | |
| "grad_norm": 13.069446563720703, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.3565, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 6.769230769230769, | |
| "eval_accuracy": 0.9120879120879121, | |
| "eval_loss": 0.27667832374572754, | |
| "eval_runtime": 1.1605, | |
| "eval_samples_per_second": 235.253, | |
| "eval_steps_per_second": 4.309, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9084249084249084, | |
| "eval_loss": 0.248954638838768, | |
| "eval_runtime": 1.1969, | |
| "eval_samples_per_second": 228.096, | |
| "eval_steps_per_second": 4.178, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 8.923076923076923, | |
| "eval_accuracy": 0.8937728937728938, | |
| "eval_loss": 0.31506583094596863, | |
| "eval_runtime": 1.1377, | |
| "eval_samples_per_second": 239.964, | |
| "eval_steps_per_second": 4.395, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 9.23076923076923, | |
| "grad_norm": 23.817771911621094, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.3166, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 9.846153846153847, | |
| "eval_accuracy": 0.9230769230769231, | |
| "eval_loss": 0.24044403433799744, | |
| "eval_runtime": 1.131, | |
| "eval_samples_per_second": 241.388, | |
| "eval_steps_per_second": 4.421, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 10.76923076923077, | |
| "eval_accuracy": 0.9157509157509157, | |
| "eval_loss": 0.25200125575065613, | |
| "eval_runtime": 1.1364, | |
| "eval_samples_per_second": 240.235, | |
| "eval_steps_per_second": 4.4, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.9047619047619048, | |
| "eval_loss": 0.2514563202857971, | |
| "eval_runtime": 1.2769, | |
| "eval_samples_per_second": 213.807, | |
| "eval_steps_per_second": 3.916, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 12.307692307692308, | |
| "grad_norm": 6.21586799621582, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.2657, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 12.923076923076923, | |
| "eval_accuracy": 0.9120879120879121, | |
| "eval_loss": 0.2343965321779251, | |
| "eval_runtime": 1.1708, | |
| "eval_samples_per_second": 233.18, | |
| "eval_steps_per_second": 4.271, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 13.846153846153847, | |
| "eval_accuracy": 0.9194139194139194, | |
| "eval_loss": 0.21868273615837097, | |
| "eval_runtime": 1.1678, | |
| "eval_samples_per_second": 233.777, | |
| "eval_steps_per_second": 4.282, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 14.76923076923077, | |
| "eval_accuracy": 0.9194139194139194, | |
| "eval_loss": 0.22890986502170563, | |
| "eval_runtime": 1.1791, | |
| "eval_samples_per_second": 231.523, | |
| "eval_steps_per_second": 4.24, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 15.384615384615385, | |
| "grad_norm": 9.437164306640625, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.259, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.9194139194139194, | |
| "eval_loss": 0.22513027489185333, | |
| "eval_runtime": 1.1485, | |
| "eval_samples_per_second": 237.698, | |
| "eval_steps_per_second": 4.353, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 16.923076923076923, | |
| "eval_accuracy": 0.9230769230769231, | |
| "eval_loss": 0.2237602174282074, | |
| "eval_runtime": 1.1777, | |
| "eval_samples_per_second": 231.808, | |
| "eval_steps_per_second": 4.246, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 17.846153846153847, | |
| "eval_accuracy": 0.9120879120879121, | |
| "eval_loss": 0.23122061789035797, | |
| "eval_runtime": 1.1714, | |
| "eval_samples_per_second": 233.058, | |
| "eval_steps_per_second": 4.268, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 18.46153846153846, | |
| "grad_norm": 3.8556299209594727, | |
| "learning_rate": 0.0, | |
| "loss": 0.2514, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 18.46153846153846, | |
| "eval_accuracy": 0.9084249084249084, | |
| "eval_loss": 0.23050667345523834, | |
| "eval_runtime": 1.1901, | |
| "eval_samples_per_second": 229.394, | |
| "eval_steps_per_second": 4.201, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 18.46153846153846, | |
| "step": 60, | |
| "total_flos": 2.9493537489380966e+17, | |
| "train_loss": 0.3304726203282674, | |
| "train_runtime": 153.986, | |
| "train_samples_per_second": 105.984, | |
| "train_steps_per_second": 0.39 | |
| } | |
| ], | |
| "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": 2.9493537489380966e+17, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |