{ "best_metric": 0.46117448806762695, "best_model_checkpoint": "speecht5_finetuned_voxpopuli_pl/checkpoint-1000", "epoch": 5.025125628140704, "eval_steps": 1000, "global_step": 1000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.12562814070351758, "grad_norm": 34.14754104614258, "learning_rate": 4.6000000000000004e-07, "loss": 6.2754, "step": 25 }, { "epoch": 0.25125628140703515, "grad_norm": 25.906333923339844, "learning_rate": 9.400000000000001e-07, "loss": 6.1497, "step": 50 }, { "epoch": 0.3768844221105528, "grad_norm": 29.097463607788086, "learning_rate": 1.44e-06, "loss": 6.0335, "step": 75 }, { "epoch": 0.5025125628140703, "grad_norm": 18.543378829956055, "learning_rate": 1.94e-06, "loss": 5.8815, "step": 100 }, { "epoch": 0.628140703517588, "grad_norm": 24.147188186645508, "learning_rate": 2.4400000000000004e-06, "loss": 5.5659, "step": 125 }, { "epoch": 0.7537688442211056, "grad_norm": 15.634539604187012, "learning_rate": 2.9400000000000002e-06, "loss": 5.3573, "step": 150 }, { "epoch": 0.8793969849246231, "grad_norm": 14.31460189819336, "learning_rate": 3.44e-06, "loss": 5.2616, "step": 175 }, { "epoch": 1.0050251256281406, "grad_norm": 19.75978660583496, "learning_rate": 3.94e-06, "loss": 5.1787, "step": 200 }, { "epoch": 1.1306532663316582, "grad_norm": 12.639854431152344, "learning_rate": 4.440000000000001e-06, "loss": 5.1214, "step": 225 }, { "epoch": 1.2562814070351758, "grad_norm": 17.792396545410156, "learning_rate": 4.94e-06, "loss": 5.0703, "step": 250 }, { "epoch": 1.3819095477386933, "grad_norm": 22.859201431274414, "learning_rate": 5.4400000000000004e-06, "loss": 4.9714, "step": 275 }, { "epoch": 1.507537688442211, "grad_norm": 16.62458610534668, "learning_rate": 5.94e-06, "loss": 4.8681, "step": 300 }, { "epoch": 1.6331658291457285, "grad_norm": 17.881174087524414, "learning_rate": 6.440000000000001e-06, "loss": 4.8252, "step": 325 }, { "epoch": 1.758793969849246, "grad_norm": 14.765595436096191, "learning_rate": 6.9400000000000005e-06, "loss": 4.5588, "step": 350 }, { "epoch": 1.8844221105527639, "grad_norm": 13.808978080749512, "learning_rate": 7.440000000000001e-06, "loss": 4.5211, "step": 375 }, { "epoch": 2.0100502512562812, "grad_norm": 10.674385070800781, "learning_rate": 7.94e-06, "loss": 4.4888, "step": 400 }, { "epoch": 2.135678391959799, "grad_norm": 15.555588722229004, "learning_rate": 8.44e-06, "loss": 4.4513, "step": 425 }, { "epoch": 2.2613065326633164, "grad_norm": 13.092530250549316, "learning_rate": 8.94e-06, "loss": 4.3646, "step": 450 }, { "epoch": 2.3869346733668344, "grad_norm": 12.971352577209473, "learning_rate": 9.440000000000001e-06, "loss": 4.3459, "step": 475 }, { "epoch": 2.5125628140703515, "grad_norm": 10.348517417907715, "learning_rate": 9.940000000000001e-06, "loss": 4.2915, "step": 500 }, { "epoch": 2.6381909547738696, "grad_norm": 13.625853538513184, "learning_rate": 9.937142857142858e-06, "loss": 4.3095, "step": 525 }, { "epoch": 2.7638190954773867, "grad_norm": 11.426923751831055, "learning_rate": 9.865714285714285e-06, "loss": 4.1899, "step": 550 }, { "epoch": 2.8894472361809047, "grad_norm": 11.516312599182129, "learning_rate": 9.794285714285714e-06, "loss": 4.2233, "step": 575 }, { "epoch": 3.0150753768844223, "grad_norm": 16.141698837280273, "learning_rate": 9.722857142857143e-06, "loss": 4.1831, "step": 600 }, { "epoch": 3.14070351758794, "grad_norm": 14.935202598571777, "learning_rate": 9.651428571428572e-06, "loss": 4.1739, "step": 625 }, { "epoch": 3.2663316582914574, "grad_norm": 10.119762420654297, "learning_rate": 9.58e-06, "loss": 4.1649, "step": 650 }, { "epoch": 3.391959798994975, "grad_norm": 16.50948143005371, "learning_rate": 9.508571428571429e-06, "loss": 4.1627, "step": 675 }, { "epoch": 3.5175879396984926, "grad_norm": 10.08300495147705, "learning_rate": 9.437142857142858e-06, "loss": 4.1915, "step": 700 }, { "epoch": 3.64321608040201, "grad_norm": 9.375288963317871, "learning_rate": 9.365714285714287e-06, "loss": 4.1279, "step": 725 }, { "epoch": 3.7688442211055277, "grad_norm": 13.562234878540039, "learning_rate": 9.294285714285714e-06, "loss": 4.1083, "step": 750 }, { "epoch": 3.8944723618090453, "grad_norm": 15.115653991699219, "learning_rate": 9.222857142857143e-06, "loss": 4.1236, "step": 775 }, { "epoch": 4.0201005025125625, "grad_norm": 9.049237251281738, "learning_rate": 9.151428571428572e-06, "loss": 4.0964, "step": 800 }, { "epoch": 4.1457286432160805, "grad_norm": 9.250771522521973, "learning_rate": 9.080000000000001e-06, "loss": 4.0669, "step": 825 }, { "epoch": 4.271356783919598, "grad_norm": 12.07302474975586, "learning_rate": 9.00857142857143e-06, "loss": 4.0587, "step": 850 }, { "epoch": 4.396984924623116, "grad_norm": 9.538933753967285, "learning_rate": 8.937142857142857e-06, "loss": 4.0837, "step": 875 }, { "epoch": 4.522613065326633, "grad_norm": 14.347626686096191, "learning_rate": 8.865714285714287e-06, "loss": 4.0086, "step": 900 }, { "epoch": 4.648241206030151, "grad_norm": 10.831369400024414, "learning_rate": 8.794285714285716e-06, "loss": 4.0563, "step": 925 }, { "epoch": 4.773869346733669, "grad_norm": 9.891343116760254, "learning_rate": 8.722857142857145e-06, "loss": 4.0057, "step": 950 }, { "epoch": 4.899497487437186, "grad_norm": 9.572471618652344, "learning_rate": 8.651428571428572e-06, "loss": 4.0557, "step": 975 }, { "epoch": 5.025125628140704, "grad_norm": 9.745298385620117, "learning_rate": 8.580000000000001e-06, "loss": 3.9902, "step": 1000 }, { "epoch": 5.025125628140704, "eval_loss": 0.46117448806762695, "eval_runtime": 75.4681, "eval_samples_per_second": 9.381, "eval_steps_per_second": 4.691, "step": 1000 } ], "logging_steps": 25, "max_steps": 4000, "num_input_tokens_seen": 0, "num_train_epochs": 21, "save_steps": 1000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 4502414650961304.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }