{ "best_metric": 0.7326732673267327, "best_model_checkpoint": "distilhubert-finetuned-not-a-word2/run-13/checkpoint-48", "epoch": 1.0, "eval_steps": 500, "global_step": 48, "is_hyper_param_search": true, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.1, "grad_norm": 1.2512309551239014, "learning_rate": 1.034188035217011e-05, "loss": 0.7013, "step": 5 }, { "epoch": 0.21, "grad_norm": 1.0938308238983154, "learning_rate": 2.068376070434022e-05, "loss": 0.6709, "step": 10 }, { "epoch": 0.31, "grad_norm": 1.029103398323059, "learning_rate": 3.102564105651033e-05, "loss": 0.676, "step": 15 }, { "epoch": 0.42, "grad_norm": 0.7623715400695801, "learning_rate": 4.136752140868044e-05, "loss": 0.6371, "step": 20 }, { "epoch": 0.52, "grad_norm": 0.6755096912384033, "learning_rate": 5.170940176085055e-05, "loss": 0.6148, "step": 25 }, { "epoch": 0.62, "grad_norm": 0.48364195227622986, "learning_rate": 6.205128211302065e-05, "loss": 0.609, "step": 30 }, { "epoch": 0.73, "grad_norm": 3.724107503890991, "learning_rate": 7.239316246519077e-05, "loss": 0.5257, "step": 35 }, { "epoch": 0.83, "grad_norm": 1.4992948770523071, "learning_rate": 8.273504281736088e-05, "loss": 0.7212, "step": 40 }, { "epoch": 0.94, "grad_norm": 4.220996856689453, "learning_rate": 9.307692316953099e-05, "loss": 0.6503, "step": 45 }, { "epoch": 1.0, "eval_f1": 0.7326732673267327, "eval_loss": 0.7372970581054688, "eval_runtime": 1.384, "eval_samples_per_second": 46.242, "eval_steps_per_second": 5.78, "step": 48 } ], "logging_steps": 5, "max_steps": 480, "num_input_tokens_seen": 0, "num_train_epochs": 10, "save_steps": 500, "total_flos": 670686130935120.0, "train_batch_size": 4, "trial_name": null, "trial_params": { "learning_rate": 9.928205138083305e-05, "per_device_train_batch_size": 4 } }