| { | |
| "best_metric": 0.0011983223487118035, | |
| "best_model_checkpoint": "bert-base-multilingual-uncased-finetuned-keyword/run-3/checkpoint-1075", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 2150, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.46511627906976744, | |
| "grad_norm": 5.422654151916504, | |
| "learning_rate": 3.770844904290478e-05, | |
| "loss": 6.7736, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.9302325581395349, | |
| "grad_norm": 5.474175453186035, | |
| "learning_rate": 3.384091580773506e-05, | |
| "loss": 6.7684, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.0011983223487118035, | |
| "eval_f1": 2.868515496617124e-06, | |
| "eval_loss": 6.748198509216309, | |
| "eval_precision": 1.4359764514221732e-06, | |
| "eval_recall": 0.0011983223487118035, | |
| "eval_runtime": 4.5943, | |
| "eval_samples_per_second": 363.274, | |
| "eval_steps_per_second": 22.854, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 1.3953488372093024, | |
| "grad_norm": 5.854085922241211, | |
| "learning_rate": 2.997338257256534e-05, | |
| "loss": 6.756, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.8604651162790697, | |
| "grad_norm": 4.819112300872803, | |
| "learning_rate": 2.610584933739562e-05, | |
| "loss": 6.7652, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.0011983223487118035, | |
| "eval_f1": 2.868515496617124e-06, | |
| "eval_loss": 6.7370195388793945, | |
| "eval_precision": 1.4359764514221732e-06, | |
| "eval_recall": 0.0011983223487118035, | |
| "eval_runtime": 4.5997, | |
| "eval_samples_per_second": 362.846, | |
| "eval_steps_per_second": 22.827, | |
| "step": 2150 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 5375, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 710050670387424.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 4.157598227807451e-05, | |
| "num_train_epochs": 5, | |
| "per_device_train_batch_size": 4, | |
| "seed": 23 | |
| } | |
| } | |