| { |
| "best_metric": 0.3995174765586853, |
| "best_model_checkpoint": "./speecht5_tts_mabama_es/checkpoint-1200", |
| "epoch": 25.53191489361702, |
| "eval_steps": 1200, |
| "global_step": 1200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.53, |
| "grad_norm": 12.126326560974121, |
| "learning_rate": 2.2e-07, |
| "loss": 1.0931, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.06, |
| "grad_norm": 9.78133487701416, |
| "learning_rate": 4.7000000000000005e-07, |
| "loss": 1.0628, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.6, |
| "grad_norm": 24.999067306518555, |
| "learning_rate": 7.2e-07, |
| "loss": 0.947, |
| "step": 75 |
| }, |
| { |
| "epoch": 2.13, |
| "grad_norm": 5.398886680603027, |
| "learning_rate": 9.7e-07, |
| "loss": 0.898, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.66, |
| "grad_norm": 12.817495346069336, |
| "learning_rate": 1.2200000000000002e-06, |
| "loss": 0.8029, |
| "step": 125 |
| }, |
| { |
| "epoch": 3.19, |
| "grad_norm": 7.071120738983154, |
| "learning_rate": 1.4700000000000001e-06, |
| "loss": 0.7889, |
| "step": 150 |
| }, |
| { |
| "epoch": 3.72, |
| "grad_norm": 4.3572163581848145, |
| "learning_rate": 1.72e-06, |
| "loss": 0.7719, |
| "step": 175 |
| }, |
| { |
| "epoch": 4.26, |
| "grad_norm": 5.61962366104126, |
| "learning_rate": 1.97e-06, |
| "loss": 0.764, |
| "step": 200 |
| }, |
| { |
| "epoch": 4.79, |
| "grad_norm": 6.79171085357666, |
| "learning_rate": 2.2200000000000003e-06, |
| "loss": 0.7441, |
| "step": 225 |
| }, |
| { |
| "epoch": 5.32, |
| "grad_norm": 6.525346755981445, |
| "learning_rate": 2.47e-06, |
| "loss": 0.711, |
| "step": 250 |
| }, |
| { |
| "epoch": 5.85, |
| "grad_norm": 1.7001874446868896, |
| "learning_rate": 2.7200000000000002e-06, |
| "loss": 0.7059, |
| "step": 275 |
| }, |
| { |
| "epoch": 6.38, |
| "grad_norm": 4.468942642211914, |
| "learning_rate": 2.97e-06, |
| "loss": 0.7021, |
| "step": 300 |
| }, |
| { |
| "epoch": 6.91, |
| "grad_norm": 7.033669948577881, |
| "learning_rate": 3.2200000000000005e-06, |
| "loss": 0.6266, |
| "step": 325 |
| }, |
| { |
| "epoch": 7.45, |
| "grad_norm": 3.8984785079956055, |
| "learning_rate": 3.4700000000000002e-06, |
| "loss": 0.6133, |
| "step": 350 |
| }, |
| { |
| "epoch": 7.98, |
| "grad_norm": 3.643061876296997, |
| "learning_rate": 3.7200000000000004e-06, |
| "loss": 0.58, |
| "step": 375 |
| }, |
| { |
| "epoch": 8.51, |
| "grad_norm": 6.500895023345947, |
| "learning_rate": 3.97e-06, |
| "loss": 0.5389, |
| "step": 400 |
| }, |
| { |
| "epoch": 9.04, |
| "grad_norm": 3.851013422012329, |
| "learning_rate": 4.22e-06, |
| "loss": 0.5578, |
| "step": 425 |
| }, |
| { |
| "epoch": 9.57, |
| "grad_norm": 5.976474285125732, |
| "learning_rate": 4.47e-06, |
| "loss": 0.5266, |
| "step": 450 |
| }, |
| { |
| "epoch": 10.11, |
| "grad_norm": 4.052149772644043, |
| "learning_rate": 4.7200000000000005e-06, |
| "loss": 0.5102, |
| "step": 475 |
| }, |
| { |
| "epoch": 10.64, |
| "grad_norm": 6.552683353424072, |
| "learning_rate": 4.970000000000001e-06, |
| "loss": 0.5382, |
| "step": 500 |
| }, |
| { |
| "epoch": 11.17, |
| "grad_norm": 2.714641571044922, |
| "learning_rate": 5.220000000000001e-06, |
| "loss": 0.5167, |
| "step": 525 |
| }, |
| { |
| "epoch": 11.7, |
| "grad_norm": 3.426229953765869, |
| "learning_rate": 5.470000000000001e-06, |
| "loss": 0.5106, |
| "step": 550 |
| }, |
| { |
| "epoch": 12.23, |
| "grad_norm": 5.78665018081665, |
| "learning_rate": 5.72e-06, |
| "loss": 0.5155, |
| "step": 575 |
| }, |
| { |
| "epoch": 12.77, |
| "grad_norm": 1.958343744277954, |
| "learning_rate": 5.9700000000000004e-06, |
| "loss": 0.4872, |
| "step": 600 |
| }, |
| { |
| "epoch": 13.3, |
| "grad_norm": 2.1352875232696533, |
| "learning_rate": 6.220000000000001e-06, |
| "loss": 0.4866, |
| "step": 625 |
| }, |
| { |
| "epoch": 13.83, |
| "grad_norm": 3.6809630393981934, |
| "learning_rate": 6.470000000000001e-06, |
| "loss": 0.5014, |
| "step": 650 |
| }, |
| { |
| "epoch": 14.36, |
| "grad_norm": 2.484553098678589, |
| "learning_rate": 6.720000000000001e-06, |
| "loss": 0.4892, |
| "step": 675 |
| }, |
| { |
| "epoch": 14.89, |
| "grad_norm": 3.656264305114746, |
| "learning_rate": 6.97e-06, |
| "loss": 0.4712, |
| "step": 700 |
| }, |
| { |
| "epoch": 15.43, |
| "grad_norm": 3.709062337875366, |
| "learning_rate": 7.22e-06, |
| "loss": 0.4843, |
| "step": 725 |
| }, |
| { |
| "epoch": 15.96, |
| "grad_norm": 2.776505708694458, |
| "learning_rate": 7.4700000000000005e-06, |
| "loss": 0.4743, |
| "step": 750 |
| }, |
| { |
| "epoch": 16.49, |
| "grad_norm": 3.913029909133911, |
| "learning_rate": 7.72e-06, |
| "loss": 0.4841, |
| "step": 775 |
| }, |
| { |
| "epoch": 17.02, |
| "grad_norm": 3.667405366897583, |
| "learning_rate": 7.970000000000002e-06, |
| "loss": 0.4853, |
| "step": 800 |
| }, |
| { |
| "epoch": 17.55, |
| "grad_norm": 2.917257070541382, |
| "learning_rate": 8.220000000000001e-06, |
| "loss": 0.4773, |
| "step": 825 |
| }, |
| { |
| "epoch": 18.09, |
| "grad_norm": 3.051287889480591, |
| "learning_rate": 8.47e-06, |
| "loss": 0.4772, |
| "step": 850 |
| }, |
| { |
| "epoch": 18.62, |
| "grad_norm": 3.4974617958068848, |
| "learning_rate": 8.720000000000001e-06, |
| "loss": 0.4599, |
| "step": 875 |
| }, |
| { |
| "epoch": 19.15, |
| "grad_norm": 2.259305238723755, |
| "learning_rate": 8.97e-06, |
| "loss": 0.4694, |
| "step": 900 |
| }, |
| { |
| "epoch": 19.68, |
| "grad_norm": 3.4457366466522217, |
| "learning_rate": 9.220000000000002e-06, |
| "loss": 0.4616, |
| "step": 925 |
| }, |
| { |
| "epoch": 20.21, |
| "grad_norm": 7.221055030822754, |
| "learning_rate": 9.47e-06, |
| "loss": 0.4613, |
| "step": 950 |
| }, |
| { |
| "epoch": 20.74, |
| "grad_norm": 9.327741622924805, |
| "learning_rate": 9.72e-06, |
| "loss": 0.4634, |
| "step": 975 |
| }, |
| { |
| "epoch": 21.28, |
| "grad_norm": 3.205131769180298, |
| "learning_rate": 9.970000000000001e-06, |
| "loss": 0.4691, |
| "step": 1000 |
| }, |
| { |
| "epoch": 21.81, |
| "grad_norm": 5.403283596038818, |
| "learning_rate": 8.900000000000001e-06, |
| "loss": 0.46, |
| "step": 1025 |
| }, |
| { |
| "epoch": 22.34, |
| "grad_norm": 2.766523838043213, |
| "learning_rate": 7.650000000000001e-06, |
| "loss": 0.4462, |
| "step": 1050 |
| }, |
| { |
| "epoch": 22.87, |
| "grad_norm": 3.033956289291382, |
| "learning_rate": 6.4000000000000006e-06, |
| "loss": 0.4491, |
| "step": 1075 |
| }, |
| { |
| "epoch": 23.4, |
| "grad_norm": 3.4086856842041016, |
| "learning_rate": 5.150000000000001e-06, |
| "loss": 0.4452, |
| "step": 1100 |
| }, |
| { |
| "epoch": 23.94, |
| "grad_norm": 2.144127607345581, |
| "learning_rate": 3.900000000000001e-06, |
| "loss": 0.4508, |
| "step": 1125 |
| }, |
| { |
| "epoch": 24.47, |
| "grad_norm": 2.2593584060668945, |
| "learning_rate": 2.6500000000000005e-06, |
| "loss": 0.4432, |
| "step": 1150 |
| }, |
| { |
| "epoch": 25.0, |
| "grad_norm": 3.3258821964263916, |
| "learning_rate": 1.4000000000000001e-06, |
| "loss": 0.4526, |
| "step": 1175 |
| }, |
| { |
| "epoch": 25.53, |
| "grad_norm": 1.783236026763916, |
| "learning_rate": 1.5000000000000002e-07, |
| "loss": 0.4516, |
| "step": 1200 |
| }, |
| { |
| "epoch": 25.53, |
| "eval_loss": 0.3995174765586853, |
| "eval_runtime": 4.5311, |
| "eval_samples_per_second": 36.857, |
| "eval_steps_per_second": 4.635, |
| "step": 1200 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 1200, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 26, |
| "save_steps": 1200, |
| "total_flos": 3336935371995456.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
