| { | |
| "best_metric": 0.7894736842105264, | |
| "best_model_checkpoint": "outputs/xlm-roberta-base-twitter-indonesia-sarcastic/checkpoint-590", | |
| "epoch": 13.0, | |
| "eval_steps": 500, | |
| "global_step": 767, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.997697221833061e-06, | |
| "loss": 0.5641, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.75, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.5259643793106079, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 1.0571, | |
| "eval_samples_per_second": 253.522, | |
| "eval_steps_per_second": 4.73, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 9.990465155165683e-06, | |
| "loss": 0.5317, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.75, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.5029988288879395, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 1.053, | |
| "eval_samples_per_second": 254.519, | |
| "eval_steps_per_second": 4.748, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 9.978555124138569e-06, | |
| "loss": 0.4995, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.75, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.4655507504940033, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 1.0523, | |
| "eval_samples_per_second": 254.669, | |
| "eval_steps_per_second": 4.751, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 9.961568226140335e-06, | |
| "loss": 0.4599, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7686567164179104, | |
| "eval_f1": 0.6025641025641025, | |
| "eval_loss": 0.4502911865711212, | |
| "eval_precision": 0.5280898876404494, | |
| "eval_recall": 0.7014925373134329, | |
| "eval_runtime": 1.057, | |
| "eval_samples_per_second": 253.552, | |
| "eval_steps_per_second": 4.73, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 9.93968485932029e-06, | |
| "loss": 0.4082, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8470149253731343, | |
| "eval_f1": 0.6434782608695653, | |
| "eval_loss": 0.378521591424942, | |
| "eval_precision": 0.7708333333333334, | |
| "eval_recall": 0.5522388059701493, | |
| "eval_runtime": 1.0544, | |
| "eval_samples_per_second": 254.183, | |
| "eval_steps_per_second": 4.742, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 9.912926619919478e-06, | |
| "loss": 0.3274, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8619402985074627, | |
| "eval_f1": 0.6991869918699187, | |
| "eval_loss": 0.3604646623134613, | |
| "eval_precision": 0.7678571428571429, | |
| "eval_recall": 0.6417910447761194, | |
| "eval_runtime": 1.0555, | |
| "eval_samples_per_second": 253.908, | |
| "eval_steps_per_second": 4.737, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 9.881895849126432e-06, | |
| "loss": 0.2621, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8619402985074627, | |
| "eval_f1": 0.6837606837606838, | |
| "eval_loss": 0.3764938712120056, | |
| "eval_precision": 0.8, | |
| "eval_recall": 0.5970149253731343, | |
| "eval_runtime": 1.0562, | |
| "eval_samples_per_second": 253.732, | |
| "eval_steps_per_second": 4.734, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 9.845553233485602e-06, | |
| "loss": 0.2332, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8768656716417911, | |
| "eval_f1": 0.759124087591241, | |
| "eval_loss": 0.34082189202308655, | |
| "eval_precision": 0.7428571428571429, | |
| "eval_recall": 0.7761194029850746, | |
| "eval_runtime": 1.0525, | |
| "eval_samples_per_second": 254.642, | |
| "eval_steps_per_second": 4.751, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 9.804428641814051e-06, | |
| "loss": 0.1579, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.8731343283582089, | |
| "eval_f1": 0.7213114754098361, | |
| "eval_loss": 0.43820273876190186, | |
| "eval_precision": 0.8, | |
| "eval_recall": 0.6567164179104478, | |
| "eval_runtime": 1.055, | |
| "eval_samples_per_second": 254.04, | |
| "eval_steps_per_second": 4.74, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 9.75856265911873e-06, | |
| "loss": 0.1467, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.8805970149253731, | |
| "eval_f1": 0.7894736842105264, | |
| "eval_loss": 0.38548171520233154, | |
| "eval_precision": 0.7058823529411765, | |
| "eval_recall": 0.8955223880597015, | |
| "eval_runtime": 1.053, | |
| "eval_samples_per_second": 254.501, | |
| "eval_steps_per_second": 4.748, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 9.708000549587091e-06, | |
| "loss": 0.098, | |
| "step": 649 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.8805970149253731, | |
| "eval_f1": 0.7500000000000001, | |
| "eval_loss": 0.46932676434516907, | |
| "eval_precision": 0.7868852459016393, | |
| "eval_recall": 0.7164179104477612, | |
| "eval_runtime": 1.058, | |
| "eval_samples_per_second": 253.305, | |
| "eval_steps_per_second": 4.726, | |
| "step": 649 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 9.653766360237254e-06, | |
| "loss": 0.0929, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.8805970149253731, | |
| "eval_f1": 0.7333333333333334, | |
| "eval_loss": 0.6206381916999817, | |
| "eval_precision": 0.8301886792452831, | |
| "eval_recall": 0.6567164179104478, | |
| "eval_runtime": 1.0526, | |
| "eval_samples_per_second": 254.603, | |
| "eval_steps_per_second": 4.75, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 9.594043625628571e-06, | |
| "loss": 0.0555, | |
| "step": 767 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.8843283582089553, | |
| "eval_f1": 0.7633587786259542, | |
| "eval_loss": 0.7134280800819397, | |
| "eval_precision": 0.78125, | |
| "eval_recall": 0.746268656716418, | |
| "eval_runtime": 1.054, | |
| "eval_samples_per_second": 254.279, | |
| "eval_steps_per_second": 4.744, | |
| "step": 767 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "step": 767, | |
| "total_flos": 1605898326389760.0, | |
| "train_loss": 0.2951739639471221, | |
| "train_runtime": 432.0494, | |
| "train_samples_per_second": 434.673, | |
| "train_steps_per_second": 13.656 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 5900, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 100, | |
| "save_steps": 500, | |
| "total_flos": 1605898326389760.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |