| { | |
| "best_metric": 0.9909420289855073, | |
| "best_model_checkpoint": "./fossilBERT_output/checkpoint-5661", | |
| "epoch": 10.0, | |
| "global_step": 6290, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.6025437201907795e-05, | |
| "loss": 0.1219, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9829025844930418, | |
| "eval_f1": 0.980708838043966, | |
| "eval_loss": 0.06422444432973862, | |
| "eval_precision": 0.9741532976827094, | |
| "eval_recall": 0.987353206865402, | |
| "eval_runtime": 2.8563, | |
| "eval_samples_per_second": 880.496, | |
| "eval_steps_per_second": 55.315, | |
| "step": 629 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 4.205087440381558e-05, | |
| "loss": 0.0426, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9864811133200795, | |
| "eval_f1": 0.9845313921747042, | |
| "eval_loss": 0.06980240345001221, | |
| "eval_precision": 0.9917506874427131, | |
| "eval_recall": 0.9774164408310749, | |
| "eval_runtime": 2.8485, | |
| "eval_samples_per_second": 882.932, | |
| "eval_steps_per_second": 55.469, | |
| "step": 1258 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 3.8076311605723374e-05, | |
| "loss": 0.0288, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9876739562624255, | |
| "eval_f1": 0.986054880791723, | |
| "eval_loss": 0.08222242444753647, | |
| "eval_precision": 0.982078853046595, | |
| "eval_recall": 0.990063233965673, | |
| "eval_runtime": 2.8512, | |
| "eval_samples_per_second": 882.071, | |
| "eval_steps_per_second": 55.414, | |
| "step": 1887 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 3.410174880763116e-05, | |
| "loss": 0.0057, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 3.0127186009538953e-05, | |
| "loss": 0.0084, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9880715705765407, | |
| "eval_f1": 0.9864253393665158, | |
| "eval_loss": 0.07759582996368408, | |
| "eval_precision": 0.9882139619220308, | |
| "eval_recall": 0.9846431797651309, | |
| "eval_runtime": 2.839, | |
| "eval_samples_per_second": 885.877, | |
| "eval_steps_per_second": 55.654, | |
| "step": 2516 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 2.6152623211446743e-05, | |
| "loss": 0.0061, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.988469184890656, | |
| "eval_f1": 0.9868599909379248, | |
| "eval_loss": 0.10027419775724411, | |
| "eval_precision": 0.99, | |
| "eval_recall": 0.983739837398374, | |
| "eval_runtime": 2.8617, | |
| "eval_samples_per_second": 878.859, | |
| "eval_steps_per_second": 55.213, | |
| "step": 3145 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "learning_rate": 2.2178060413354532e-05, | |
| "loss": 0.0016, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.989662027833002, | |
| "eval_f1": 0.9882777276825968, | |
| "eval_loss": 0.08881077915430069, | |
| "eval_precision": 0.9864986498649865, | |
| "eval_recall": 0.990063233965673, | |
| "eval_runtime": 2.8662, | |
| "eval_samples_per_second": 877.455, | |
| "eval_steps_per_second": 55.124, | |
| "step": 3774 | |
| }, | |
| { | |
| "epoch": 6.36, | |
| "learning_rate": 1.820349761526232e-05, | |
| "loss": 0.0023, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9904572564612326, | |
| "eval_f1": 0.9891500904159132, | |
| "eval_loss": 0.09042701870203018, | |
| "eval_precision": 0.9900452488687783, | |
| "eval_recall": 0.988256549232159, | |
| "eval_runtime": 2.8476, | |
| "eval_samples_per_second": 883.214, | |
| "eval_steps_per_second": 55.486, | |
| "step": 4403 | |
| }, | |
| { | |
| "epoch": 7.15, | |
| "learning_rate": 1.4228934817170111e-05, | |
| "loss": 0.0037, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "learning_rate": 1.02543720190779e-05, | |
| "loss": 0.0017, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9888667992047714, | |
| "eval_f1": 0.9872611464968153, | |
| "eval_loss": 0.09531795978546143, | |
| "eval_precision": 0.9945004582951421, | |
| "eval_recall": 0.980126467931346, | |
| "eval_runtime": 2.8577, | |
| "eval_samples_per_second": 880.078, | |
| "eval_steps_per_second": 55.289, | |
| "step": 5032 | |
| }, | |
| { | |
| "epoch": 8.74, | |
| "learning_rate": 6.279809220985691e-06, | |
| "loss": 0.0, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9920477137176938, | |
| "eval_f1": 0.9909420289855073, | |
| "eval_loss": 0.0791691467165947, | |
| "eval_precision": 0.9936421435059037, | |
| "eval_recall": 0.988256549232159, | |
| "eval_runtime": 2.8459, | |
| "eval_samples_per_second": 883.726, | |
| "eval_steps_per_second": 55.518, | |
| "step": 5661 | |
| }, | |
| { | |
| "epoch": 9.54, | |
| "learning_rate": 2.3052464228934817e-06, | |
| "loss": 0.0, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9916500994035785, | |
| "eval_f1": 0.990493435943866, | |
| "eval_loss": 0.07801677286624908, | |
| "eval_precision": 0.9927404718693285, | |
| "eval_recall": 0.988256549232159, | |
| "eval_runtime": 2.8772, | |
| "eval_samples_per_second": 874.116, | |
| "eval_steps_per_second": 54.915, | |
| "step": 6290 | |
| } | |
| ], | |
| "max_steps": 6290, | |
| "num_train_epochs": 10, | |
| "total_flos": 3330561570708480.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |