| { | |
| "best_metric": 0.7445255474452556, | |
| "best_model_checkpoint": "outputs/indobert-base-p1-twitter-indonesia-sarcastic/checkpoint-472", | |
| "epoch": 11.0, | |
| "eval_steps": 500, | |
| "global_step": 649, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.997532801828659e-06, | |
| "loss": 0.5101, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7835820895522388, | |
| "eval_f1": 0.608108108108108, | |
| "eval_loss": 0.4220750629901886, | |
| "eval_precision": 0.5555555555555556, | |
| "eval_recall": 0.6716417910447762, | |
| "eval_runtime": 1.0673, | |
| "eval_samples_per_second": 251.108, | |
| "eval_steps_per_second": 4.685, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 9.990133642141359e-06, | |
| "loss": 0.3508, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8246268656716418, | |
| "eval_f1": 0.6713286713286712, | |
| "eval_loss": 0.34792423248291016, | |
| "eval_precision": 0.631578947368421, | |
| "eval_recall": 0.7164179104477612, | |
| "eval_runtime": 1.0685, | |
| "eval_samples_per_second": 250.816, | |
| "eval_steps_per_second": 4.679, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 9.9778098230154e-06, | |
| "loss": 0.221, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8582089552238806, | |
| "eval_f1": 0.6935483870967741, | |
| "eval_loss": 0.3511403799057007, | |
| "eval_precision": 0.7543859649122807, | |
| "eval_recall": 0.6417910447761194, | |
| "eval_runtime": 1.0653, | |
| "eval_samples_per_second": 251.58, | |
| "eval_steps_per_second": 4.694, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 9.960573506572391e-06, | |
| "loss": 0.1157, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8395522388059702, | |
| "eval_f1": 0.6861313868613139, | |
| "eval_loss": 0.4352029263973236, | |
| "eval_precision": 0.6714285714285714, | |
| "eval_recall": 0.7014925373134329, | |
| "eval_runtime": 1.0649, | |
| "eval_samples_per_second": 251.673, | |
| "eval_steps_per_second": 4.695, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 9.938441702975689e-06, | |
| "loss": 0.0453, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8582089552238806, | |
| "eval_f1": 0.7076923076923077, | |
| "eval_loss": 0.6923192739486694, | |
| "eval_precision": 0.7301587301587301, | |
| "eval_recall": 0.6865671641791045, | |
| "eval_runtime": 1.064, | |
| "eval_samples_per_second": 251.881, | |
| "eval_steps_per_second": 4.699, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 9.911436253643445e-06, | |
| "loss": 0.0192, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8694029850746269, | |
| "eval_f1": 0.7286821705426356, | |
| "eval_loss": 0.7378106117248535, | |
| "eval_precision": 0.7580645161290323, | |
| "eval_recall": 0.7014925373134329, | |
| "eval_runtime": 1.0705, | |
| "eval_samples_per_second": 250.361, | |
| "eval_steps_per_second": 4.671, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 9.880163895209396e-06, | |
| "loss": 0.0159, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8544776119402985, | |
| "eval_f1": 0.6722689075630253, | |
| "eval_loss": 0.8860062956809998, | |
| "eval_precision": 0.7692307692307693, | |
| "eval_recall": 0.5970149253731343, | |
| "eval_runtime": 1.0639, | |
| "eval_samples_per_second": 251.895, | |
| "eval_steps_per_second": 4.7, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 9.843577222724305e-06, | |
| "loss": 0.0165, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8694029850746269, | |
| "eval_f1": 0.7445255474452556, | |
| "eval_loss": 0.8260650634765625, | |
| "eval_precision": 0.7285714285714285, | |
| "eval_recall": 0.7611940298507462, | |
| "eval_runtime": 1.0763, | |
| "eval_samples_per_second": 249.008, | |
| "eval_steps_per_second": 4.646, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 9.80221052429255e-06, | |
| "loss": 0.0175, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.8731343283582089, | |
| "eval_f1": 0.7424242424242424, | |
| "eval_loss": 0.8732029795646667, | |
| "eval_precision": 0.7538461538461538, | |
| "eval_recall": 0.7313432835820896, | |
| "eval_runtime": 1.0644, | |
| "eval_samples_per_second": 251.793, | |
| "eval_steps_per_second": 4.698, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 9.756104623851222e-06, | |
| "loss": 0.0062, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.8656716417910447, | |
| "eval_f1": 0.7272727272727273, | |
| "eval_loss": 0.9647775888442993, | |
| "eval_precision": 0.7384615384615385, | |
| "eval_recall": 0.7164179104477612, | |
| "eval_runtime": 1.0637, | |
| "eval_samples_per_second": 251.945, | |
| "eval_steps_per_second": 4.7, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 9.705305022357621e-06, | |
| "loss": 0.0003, | |
| "step": 649 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.8619402985074627, | |
| "eval_f1": 0.7175572519083969, | |
| "eval_loss": 1.0107759237289429, | |
| "eval_precision": 0.734375, | |
| "eval_recall": 0.7014925373134329, | |
| "eval_runtime": 1.0637, | |
| "eval_samples_per_second": 251.951, | |
| "eval_steps_per_second": 4.701, | |
| "step": 649 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "step": 649, | |
| "total_flos": 1358837045406720.0, | |
| "train_loss": 0.11986877576079226, | |
| "train_runtime": 294.5192, | |
| "train_samples_per_second": 637.649, | |
| "train_steps_per_second": 20.033 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 5900, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 100, | |
| "save_steps": 500, | |
| "total_flos": 1358837045406720.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |