| { | |
| "best_metric": 0.8181818181818182, | |
| "best_model_checkpoint": "outputs/xlm-roberta-large-twitter-indonesia-sarcastic/checkpoint-708", | |
| "epoch": 15.0, | |
| "eval_steps": 500, | |
| "global_step": 885, | |
| "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": 0.5862, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.75, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.5304240584373474, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 3.3745, | |
| "eval_samples_per_second": 79.42, | |
| "eval_steps_per_second": 1.482, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 9.990951812568578e-06, | |
| "loss": 0.5168, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.75, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.4897027611732483, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 3.3714, | |
| "eval_samples_per_second": 79.491, | |
| "eval_steps_per_second": 1.483, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 9.979044933876465e-06, | |
| "loss": 0.4771, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7947761194029851, | |
| "eval_f1": 0.3373493975903615, | |
| "eval_loss": 0.45346158742904663, | |
| "eval_precision": 0.875, | |
| "eval_recall": 0.208955223880597, | |
| "eval_runtime": 3.3741, | |
| "eval_samples_per_second": 79.428, | |
| "eval_steps_per_second": 1.482, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 9.962224338961997e-06, | |
| "loss": 0.4101, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7910447761194029, | |
| "eval_f1": 0.6585365853658537, | |
| "eval_loss": 0.4235016405582428, | |
| "eval_precision": 0.5567010309278351, | |
| "eval_recall": 0.8059701492537313, | |
| "eval_runtime": 3.3736, | |
| "eval_samples_per_second": 79.44, | |
| "eval_steps_per_second": 1.482, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 9.940506627721576e-06, | |
| "loss": 0.3225, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8507462686567164, | |
| "eval_f1": 0.5918367346938774, | |
| "eval_loss": 0.47333377599716187, | |
| "eval_precision": 0.9354838709677419, | |
| "eval_recall": 0.43283582089552236, | |
| "eval_runtime": 3.3745, | |
| "eval_samples_per_second": 79.419, | |
| "eval_steps_per_second": 1.482, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 9.913913232914188e-06, | |
| "loss": 0.2246, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8694029850746269, | |
| "eval_f1": 0.7008547008547008, | |
| "eval_loss": 0.3362283706665039, | |
| "eval_precision": 0.82, | |
| "eval_recall": 0.6119402985074627, | |
| "eval_runtime": 3.3741, | |
| "eval_samples_per_second": 79.428, | |
| "eval_steps_per_second": 1.482, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 9.882470399009847e-06, | |
| "loss": 0.166, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8768656716417911, | |
| "eval_f1": 0.722689075630252, | |
| "eval_loss": 0.36720752716064453, | |
| "eval_precision": 0.8269230769230769, | |
| "eval_recall": 0.6417910447761194, | |
| "eval_runtime": 3.3726, | |
| "eval_samples_per_second": 79.464, | |
| "eval_steps_per_second": 1.483, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 9.846863705058136e-06, | |
| "loss": 0.0989, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8768656716417911, | |
| "eval_f1": 0.7625899280575541, | |
| "eval_loss": 0.38347017765045166, | |
| "eval_precision": 0.7361111111111112, | |
| "eval_recall": 0.7910447761194029, | |
| "eval_runtime": 3.3739, | |
| "eval_samples_per_second": 79.433, | |
| "eval_steps_per_second": 1.482, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 9.805900576231358e-06, | |
| "loss": 0.0797, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.8992537313432836, | |
| "eval_f1": 0.7938931297709924, | |
| "eval_loss": 0.43790221214294434, | |
| "eval_precision": 0.8125, | |
| "eval_recall": 0.7761194029850746, | |
| "eval_runtime": 3.3735, | |
| "eval_samples_per_second": 79.442, | |
| "eval_steps_per_second": 1.482, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 9.760194603759247e-06, | |
| "loss": 0.08, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.8544776119402985, | |
| "eval_f1": 0.7450980392156863, | |
| "eval_loss": 0.7676528096199036, | |
| "eval_precision": 0.6627906976744186, | |
| "eval_recall": 0.8507462686567164, | |
| "eval_runtime": 3.3728, | |
| "eval_samples_per_second": 79.46, | |
| "eval_steps_per_second": 1.482, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 9.709790893918487e-06, | |
| "loss": 0.0505, | |
| "step": 649 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.8805970149253731, | |
| "eval_f1": 0.7288135593220338, | |
| "eval_loss": 0.7316186428070068, | |
| "eval_precision": 0.8431372549019608, | |
| "eval_recall": 0.6417910447761194, | |
| "eval_runtime": 3.3708, | |
| "eval_samples_per_second": 79.507, | |
| "eval_steps_per_second": 1.483, | |
| "step": 649 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 9.654739189085373e-06, | |
| "loss": 0.073, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.9104477611940298, | |
| "eval_f1": 0.8181818181818182, | |
| "eval_loss": 0.47964057326316833, | |
| "eval_precision": 0.8307692307692308, | |
| "eval_recall": 0.8059701492537313, | |
| "eval_runtime": 3.372, | |
| "eval_samples_per_second": 79.477, | |
| "eval_steps_per_second": 1.483, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 9.595093818646103e-06, | |
| "loss": 0.05, | |
| "step": 767 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.8694029850746269, | |
| "eval_f1": 0.7058823529411765, | |
| "eval_loss": 0.8468834757804871, | |
| "eval_precision": 0.8076923076923077, | |
| "eval_recall": 0.6268656716417911, | |
| "eval_runtime": 3.3726, | |
| "eval_samples_per_second": 79.464, | |
| "eval_steps_per_second": 1.483, | |
| "step": 767 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 9.530913645380233e-06, | |
| "loss": 0.0583, | |
| "step": 826 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.8917910447761194, | |
| "eval_f1": 0.7563025210084034, | |
| "eval_loss": 0.7265912294387817, | |
| "eval_precision": 0.8653846153846154, | |
| "eval_recall": 0.6716417910447762, | |
| "eval_runtime": 3.3727, | |
| "eval_samples_per_second": 79.462, | |
| "eval_steps_per_second": 1.483, | |
| "step": 826 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 9.462262007370205e-06, | |
| "loss": 0.0275, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.8917910447761194, | |
| "eval_f1": 0.7387387387387387, | |
| "eval_loss": 0.897386908531189, | |
| "eval_precision": 0.9318181818181818, | |
| "eval_recall": 0.6119402985074627, | |
| "eval_runtime": 3.3738, | |
| "eval_samples_per_second": 79.437, | |
| "eval_steps_per_second": 1.482, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "step": 885, | |
| "total_flos": 6563126626237440.0, | |
| "train_loss": 0.21473971275286485, | |
| "train_runtime": 1465.663, | |
| "train_samples_per_second": 128.133, | |
| "train_steps_per_second": 4.025 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 5900, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 100, | |
| "save_steps": 500, | |
| "total_flos": 6563126626237440.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |