| { | |
| "best_metric": 0.706896551724138, | |
| "best_model_checkpoint": "outputs/bert-base-multilingual-cased-twitter-indonesia-sarcastic/checkpoint-354", | |
| "epoch": 9.0, | |
| "eval_steps": 500, | |
| "global_step": 531, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.99761572031246e-06, | |
| "loss": 0.5333, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.75, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.47915688157081604, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 1.0725, | |
| "eval_samples_per_second": 249.878, | |
| "eval_steps_per_second": 4.662, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 9.990465155165683e-06, | |
| "loss": 0.4642, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7910447761194029, | |
| "eval_f1": 0.3, | |
| "eval_loss": 0.4418473243713379, | |
| "eval_precision": 0.9230769230769231, | |
| "eval_recall": 0.1791044776119403, | |
| "eval_runtime": 1.0651, | |
| "eval_samples_per_second": 251.625, | |
| "eval_steps_per_second": 4.694, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 9.978555124138569e-06, | |
| "loss": 0.3961, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8134328358208955, | |
| "eval_f1": 0.5192307692307693, | |
| "eval_loss": 0.4319072365760803, | |
| "eval_precision": 0.7297297297297297, | |
| "eval_recall": 0.40298507462686567, | |
| "eval_runtime": 1.0672, | |
| "eval_samples_per_second": 251.127, | |
| "eval_steps_per_second": 4.685, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 9.961568226140335e-06, | |
| "loss": 0.325, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.746268656716418, | |
| "eval_f1": 0.6179775280898877, | |
| "eval_loss": 0.5264418721199036, | |
| "eval_precision": 0.4954954954954955, | |
| "eval_recall": 0.8208955223880597, | |
| "eval_runtime": 1.0669, | |
| "eval_samples_per_second": 251.206, | |
| "eval_steps_per_second": 4.687, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 9.93968485932029e-06, | |
| "loss": 0.2432, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8246268656716418, | |
| "eval_f1": 0.6299212598425197, | |
| "eval_loss": 0.4624307453632355, | |
| "eval_precision": 0.6666666666666666, | |
| "eval_recall": 0.5970149253731343, | |
| "eval_runtime": 1.064, | |
| "eval_samples_per_second": 251.884, | |
| "eval_steps_per_second": 4.699, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 9.912926619919478e-06, | |
| "loss": 0.1819, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8731343283582089, | |
| "eval_f1": 0.706896551724138, | |
| "eval_loss": 0.42611974477767944, | |
| "eval_precision": 0.8367346938775511, | |
| "eval_recall": 0.6119402985074627, | |
| "eval_runtime": 1.0705, | |
| "eval_samples_per_second": 250.352, | |
| "eval_steps_per_second": 4.671, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 9.881319915089625e-06, | |
| "loss": 0.148, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8544776119402985, | |
| "eval_f1": 0.6776859504132231, | |
| "eval_loss": 0.5371143817901611, | |
| "eval_precision": 0.7592592592592593, | |
| "eval_recall": 0.6119402985074627, | |
| "eval_runtime": 1.0641, | |
| "eval_samples_per_second": 251.866, | |
| "eval_steps_per_second": 4.699, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 9.844895936832474e-06, | |
| "loss": 0.0995, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8395522388059702, | |
| "eval_f1": 0.6766917293233083, | |
| "eval_loss": 0.6810328364372253, | |
| "eval_precision": 0.6818181818181818, | |
| "eval_recall": 0.6716417910447762, | |
| "eval_runtime": 1.0652, | |
| "eval_samples_per_second": 251.603, | |
| "eval_steps_per_second": 4.694, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 9.803690631217043e-06, | |
| "loss": 0.0843, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.8208955223880597, | |
| "eval_f1": 0.5384615384615384, | |
| "eval_loss": 0.8350497484207153, | |
| "eval_precision": 0.7567567567567568, | |
| "eval_recall": 0.417910447761194, | |
| "eval_runtime": 1.0631, | |
| "eval_samples_per_second": 252.096, | |
| "eval_steps_per_second": 4.703, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "step": 531, | |
| "total_flos": 1111775764423680.0, | |
| "train_loss": 0.2750625179312323, | |
| "train_runtime": 261.0331, | |
| "train_samples_per_second": 719.449, | |
| "train_steps_per_second": 22.602 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 5900, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 100, | |
| "save_steps": 500, | |
| "total_flos": 1111775764423680.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |