| { | |
| "best_metric": 0.697825193570947, | |
| "best_model_checkpoint": "trained/hebban-reviews5/bert-base-multilingual-cased/checkpoint-4500", | |
| "epoch": 4.382997370727432, | |
| "global_step": 5001, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.502099580083983e-05, | |
| "loss": 1.3159, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_accuracy": 0.4912475345167653, | |
| "eval_f1": 0.48070042281702435, | |
| "eval_loss": 1.1863828897476196, | |
| "eval_precision": 0.5054226630223979, | |
| "eval_qwk": 0.6104106009981652, | |
| "eval_recall": 0.4912475345167653, | |
| "eval_runtime": 23.5101, | |
| "eval_samples_per_second": 690.086, | |
| "eval_steps_per_second": 5.402, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.003199360127974e-05, | |
| "loss": 1.092, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_accuracy": 0.5488165680473372, | |
| "eval_f1": 0.5517553489817303, | |
| "eval_loss": 1.0387530326843262, | |
| "eval_precision": 0.5678859988610889, | |
| "eval_qwk": 0.6346615351470672, | |
| "eval_recall": 0.5488165680473372, | |
| "eval_runtime": 23.5201, | |
| "eval_samples_per_second": 689.794, | |
| "eval_steps_per_second": 5.4, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 3.5032993401319734e-05, | |
| "loss": 0.9709, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_accuracy": 0.5436390532544378, | |
| "eval_f1": 0.5408623179767048, | |
| "eval_loss": 1.0117485523223877, | |
| "eval_precision": 0.5642348913139151, | |
| "eval_qwk": 0.6678503252600388, | |
| "eval_recall": 0.5436390532544378, | |
| "eval_runtime": 23.6496, | |
| "eval_samples_per_second": 686.015, | |
| "eval_steps_per_second": 5.37, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.0033993201359727e-05, | |
| "loss": 0.9404, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_accuracy": 0.5279215976331361, | |
| "eval_f1": 0.5218328433667149, | |
| "eval_loss": 1.0087615251541138, | |
| "eval_precision": 0.5543969942392576, | |
| "eval_qwk": 0.6748096376745845, | |
| "eval_recall": 0.5279215976331361, | |
| "eval_runtime": 23.476, | |
| "eval_samples_per_second": 691.088, | |
| "eval_steps_per_second": 5.41, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 2.503499300139972e-05, | |
| "loss": 0.8657, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "eval_accuracy": 0.5708826429980276, | |
| "eval_f1": 0.5692427852436814, | |
| "eval_loss": 1.0947091579437256, | |
| "eval_precision": 0.5827881052454773, | |
| "eval_qwk": 0.6863988830193634, | |
| "eval_recall": 0.5708826429980276, | |
| "eval_runtime": 23.3841, | |
| "eval_samples_per_second": 693.805, | |
| "eval_steps_per_second": 5.431, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 2.0035992801439712e-05, | |
| "loss": 0.8004, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "eval_accuracy": 0.5539940828402367, | |
| "eval_f1": 0.5591418616361084, | |
| "eval_loss": 1.0360697507858276, | |
| "eval_precision": 0.5772334772150153, | |
| "eval_qwk": 0.6712182177231302, | |
| "eval_recall": 0.5539940828402367, | |
| "eval_runtime": 23.5321, | |
| "eval_samples_per_second": 689.441, | |
| "eval_steps_per_second": 5.397, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 1.5046990601879624e-05, | |
| "loss": 0.7687, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "eval_accuracy": 0.5808678500986193, | |
| "eval_f1": 0.5832607549463982, | |
| "eval_loss": 1.2274583578109741, | |
| "eval_precision": 0.5914789641012546, | |
| "eval_qwk": 0.689381177306146, | |
| "eval_recall": 0.5808678500986193, | |
| "eval_runtime": 23.7912, | |
| "eval_samples_per_second": 681.932, | |
| "eval_steps_per_second": 5.338, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 1.0047990401919617e-05, | |
| "loss": 0.6773, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "eval_accuracy": 0.5830251479289941, | |
| "eval_f1": 0.5826927994622666, | |
| "eval_loss": 1.222939133644104, | |
| "eval_precision": 0.5930910696407776, | |
| "eval_qwk": 0.6959801434105679, | |
| "eval_recall": 0.5830251479289941, | |
| "eval_runtime": 23.6989, | |
| "eval_samples_per_second": 684.589, | |
| "eval_steps_per_second": 5.359, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 5.048990201959608e-06, | |
| "loss": 0.6584, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "eval_accuracy": 0.5886341222879684, | |
| "eval_f1": 0.5886427250282493, | |
| "eval_loss": 1.281541347503662, | |
| "eval_precision": 0.5969768120377853, | |
| "eval_qwk": 0.697825193570947, | |
| "eval_recall": 0.5886341222879684, | |
| "eval_runtime": 23.7004, | |
| "eval_samples_per_second": 684.544, | |
| "eval_steps_per_second": 5.359, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 4.999000199960008e-08, | |
| "loss": 0.5961, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "eval_accuracy": 0.5894354043392505, | |
| "eval_f1": 0.5909264551740898, | |
| "eval_loss": 1.359961748123169, | |
| "eval_precision": 0.5997451050742093, | |
| "eval_qwk": 0.6969542849451541, | |
| "eval_recall": 0.5894354043392505, | |
| "eval_runtime": 23.5424, | |
| "eval_samples_per_second": 689.138, | |
| "eval_steps_per_second": 5.395, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "step": 5001, | |
| "total_flos": 1.6839139993111757e+17, | |
| "train_loss": 0.8685172849525287, | |
| "train_runtime": 2653.5735, | |
| "train_samples_per_second": 241.232, | |
| "train_steps_per_second": 1.885 | |
| } | |
| ], | |
| "max_steps": 5001, | |
| "num_train_epochs": 5, | |
| "total_flos": 1.6839139993111757e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |