{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "global_step": 1000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.03, "learning_rate": 4.4e-06, "loss": 1.1702, "step": 25 }, { "epoch": 0.05, "learning_rate": 9.4e-06, "loss": 0.5529, "step": 50 }, { "epoch": 0.07, "learning_rate": 1e-05, "loss": 0.4462, "step": 75 }, { "epoch": 0.1, "learning_rate": 1e-05, "loss": 0.4128, "step": 100 }, { "epoch": 0.12, "learning_rate": 1e-05, "loss": 0.3724, "step": 125 }, { "epoch": 0.15, "learning_rate": 1e-05, "loss": 0.3735, "step": 150 }, { "epoch": 0.17, "learning_rate": 1e-05, "loss": 0.3626, "step": 175 }, { "epoch": 0.2, "learning_rate": 1e-05, "loss": 0.3578, "step": 200 }, { "epoch": 0.23, "learning_rate": 1e-05, "loss": 0.3535, "step": 225 }, { "epoch": 0.25, "learning_rate": 1e-05, "loss": 0.3584, "step": 250 }, { "epoch": 0.28, "learning_rate": 1e-05, "loss": 0.3667, "step": 275 }, { "epoch": 0.3, "learning_rate": 1e-05, "loss": 0.3833, "step": 300 }, { "epoch": 0.33, "learning_rate": 1e-05, "loss": 0.3944, "step": 325 }, { "epoch": 0.35, "learning_rate": 1e-05, "loss": 0.3604, "step": 350 }, { "epoch": 0.38, "learning_rate": 1e-05, "loss": 0.3426, "step": 375 }, { "epoch": 0.4, "learning_rate": 1e-05, "loss": 0.3476, "step": 400 }, { "epoch": 0.42, "learning_rate": 1e-05, "loss": 0.3448, "step": 425 }, { "epoch": 0.45, "learning_rate": 1e-05, "loss": 0.3404, "step": 450 }, { "epoch": 0.47, "learning_rate": 1e-05, "loss": 0.3495, "step": 475 }, { "epoch": 0.5, "learning_rate": 1e-05, "loss": 0.366, "step": 500 }, { "epoch": 0.53, "learning_rate": 1e-05, "loss": 0.3964, "step": 525 }, { "epoch": 0.55, "learning_rate": 1e-05, "loss": 0.3662, "step": 550 }, { "epoch": 0.57, "learning_rate": 1e-05, "loss": 0.3409, "step": 575 }, { "epoch": 0.6, "learning_rate": 1e-05, "loss": 0.3348, "step": 600 }, { "epoch": 0.62, "learning_rate": 1e-05, "loss": 0.3461, "step": 625 }, { "epoch": 0.65, "learning_rate": 1e-05, "loss": 0.3255, "step": 650 }, { "epoch": 0.68, "learning_rate": 1e-05, "loss": 0.3415, "step": 675 }, { "epoch": 0.7, "learning_rate": 1e-05, "loss": 0.3136, "step": 700 }, { "epoch": 0.72, "learning_rate": 1e-05, "loss": 0.2972, "step": 725 }, { "epoch": 0.75, "learning_rate": 1e-05, "loss": 0.3137, "step": 750 }, { "epoch": 0.78, "learning_rate": 1e-05, "loss": 0.3074, "step": 775 }, { "epoch": 0.8, "learning_rate": 1e-05, "loss": 0.3585, "step": 800 }, { "epoch": 0.82, "learning_rate": 1e-05, "loss": 0.3482, "step": 825 }, { "epoch": 0.85, "learning_rate": 1e-05, "loss": 0.3624, "step": 850 }, { "epoch": 0.88, "learning_rate": 1e-05, "loss": 0.354, "step": 875 }, { "epoch": 0.9, "learning_rate": 1e-05, "loss": 0.3559, "step": 900 }, { "epoch": 0.93, "learning_rate": 1e-05, "loss": 0.3304, "step": 925 }, { "epoch": 0.95, "learning_rate": 1e-05, "loss": 0.3462, "step": 950 }, { "epoch": 0.97, "learning_rate": 1e-05, "loss": 0.3285, "step": 975 }, { "epoch": 1.0, "learning_rate": 1e-05, "loss": 0.3537, "step": 1000 }, { "epoch": 1.0, "eval_loss": 0.37843355536460876, "eval_runtime": 4480.3594, "eval_samples_per_second": 3.591, "eval_steps_per_second": 0.225, "eval_wer": 16.99780428461219, "step": 1000 }, { "epoch": 1.0, "step": 1000, "total_flos": 9.23473281024e+18, "train_loss": 0.37942890977859495, "train_runtime": 8042.4181, "train_samples_per_second": 3.979, "train_steps_per_second": 0.124 } ], "max_steps": 1000, "num_train_epochs": 9223372036854775807, "total_flos": 9.23473281024e+18, "trial_name": null, "trial_params": null }