| { | |
| "best_global_step": 1000, | |
| "best_metric": 168.64974807007812, | |
| "best_model_checkpoint": "./whisper-small-finetuned-multilingual-on-kaggle-v2/checkpoint-1000", | |
| "epoch": 1.1273957158962795, | |
| "eval_steps": 1000, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02818489289740699, | |
| "grad_norm": 0.6385474801063538, | |
| "learning_rate": 4.800000000000001e-07, | |
| "loss": 0.436, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05636978579481398, | |
| "grad_norm": 0.364500492811203, | |
| "learning_rate": 9.800000000000001e-07, | |
| "loss": 0.4351, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08455467869222097, | |
| "grad_norm": 0.249020516872406, | |
| "learning_rate": 1.48e-06, | |
| "loss": 0.4622, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.11273957158962795, | |
| "grad_norm": 0.6031928062438965, | |
| "learning_rate": 1.98e-06, | |
| "loss": 0.4681, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14092446448703494, | |
| "grad_norm": 0.3203608989715576, | |
| "learning_rate": 2.4800000000000004e-06, | |
| "loss": 0.4639, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.16910935738444194, | |
| "grad_norm": 0.6545065641403198, | |
| "learning_rate": 2.9800000000000003e-06, | |
| "loss": 0.4419, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.19729425028184894, | |
| "grad_norm": 0.2052975744009018, | |
| "learning_rate": 3.48e-06, | |
| "loss": 0.4438, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.2254791431792559, | |
| "grad_norm": 0.6051822304725647, | |
| "learning_rate": 3.980000000000001e-06, | |
| "loss": 0.4034, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.25366403607666294, | |
| "grad_norm": 0.6141038537025452, | |
| "learning_rate": 4.48e-06, | |
| "loss": 0.4104, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.2818489289740699, | |
| "grad_norm": 0.534954845905304, | |
| "learning_rate": 4.980000000000001e-06, | |
| "loss": 0.4167, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.3100338218714769, | |
| "grad_norm": 0.6292374730110168, | |
| "learning_rate": 5.480000000000001e-06, | |
| "loss": 0.387, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.3382187147688839, | |
| "grad_norm": 0.5661519765853882, | |
| "learning_rate": 5.98e-06, | |
| "loss": 0.4088, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.3664036076662909, | |
| "grad_norm": 0.3687807321548462, | |
| "learning_rate": 6.480000000000001e-06, | |
| "loss": 0.3419, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.3945885005636979, | |
| "grad_norm": 0.5748394131660461, | |
| "learning_rate": 6.98e-06, | |
| "loss": 0.3881, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.4227733934611049, | |
| "grad_norm": 0.40532639622688293, | |
| "learning_rate": 7.48e-06, | |
| "loss": 0.3589, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.4509582863585118, | |
| "grad_norm": 0.2873406410217285, | |
| "learning_rate": 7.980000000000002e-06, | |
| "loss": 0.3263, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.4791431792559188, | |
| "grad_norm": 0.3314521908760071, | |
| "learning_rate": 8.48e-06, | |
| "loss": 0.3614, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.5073280721533259, | |
| "grad_norm": 0.1603882908821106, | |
| "learning_rate": 8.98e-06, | |
| "loss": 0.2867, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.5355129650507328, | |
| "grad_norm": 0.2617914378643036, | |
| "learning_rate": 9.48e-06, | |
| "loss": 0.3226, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.5636978579481398, | |
| "grad_norm": 0.16243544220924377, | |
| "learning_rate": 9.980000000000001e-06, | |
| "loss": 0.2966, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.5918827508455468, | |
| "grad_norm": 0.21829640865325928, | |
| "learning_rate": 9.946666666666667e-06, | |
| "loss": 0.2815, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.6200676437429538, | |
| "grad_norm": 0.30274373292922974, | |
| "learning_rate": 9.891111111111113e-06, | |
| "loss": 0.2956, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.6482525366403608, | |
| "grad_norm": 0.5401255488395691, | |
| "learning_rate": 9.835555555555556e-06, | |
| "loss": 0.2772, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.6764374295377678, | |
| "grad_norm": 0.596587061882019, | |
| "learning_rate": 9.780000000000001e-06, | |
| "loss": 0.2943, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.7046223224351748, | |
| "grad_norm": 0.2570999562740326, | |
| "learning_rate": 9.724444444444445e-06, | |
| "loss": 0.2749, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.7328072153325818, | |
| "grad_norm": 0.18179918825626373, | |
| "learning_rate": 9.66888888888889e-06, | |
| "loss": 0.2767, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.7609921082299888, | |
| "grad_norm": 0.13621068000793457, | |
| "learning_rate": 9.613333333333335e-06, | |
| "loss": 0.2697, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.7891770011273957, | |
| "grad_norm": 0.2660331130027771, | |
| "learning_rate": 9.557777777777777e-06, | |
| "loss": 0.2742, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.8173618940248027, | |
| "grad_norm": 0.11947935819625854, | |
| "learning_rate": 9.502222222222223e-06, | |
| "loss": 0.2753, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.8455467869222097, | |
| "grad_norm": 0.2724321484565735, | |
| "learning_rate": 9.446666666666667e-06, | |
| "loss": 0.2494, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.8737316798196166, | |
| "grad_norm": 0.11410418152809143, | |
| "learning_rate": 9.391111111111111e-06, | |
| "loss": 0.264, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.9019165727170236, | |
| "grad_norm": 0.13550838828086853, | |
| "learning_rate": 9.335555555555557e-06, | |
| "loss": 0.2611, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.9301014656144306, | |
| "grad_norm": 1.507051706314087, | |
| "learning_rate": 9.280000000000001e-06, | |
| "loss": 0.2748, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.9582863585118376, | |
| "grad_norm": 0.11221399158239365, | |
| "learning_rate": 9.224444444444445e-06, | |
| "loss": 0.2972, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.9864712514092446, | |
| "grad_norm": 0.705410361289978, | |
| "learning_rate": 9.168888888888889e-06, | |
| "loss": 0.2527, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 1.0146561443066517, | |
| "grad_norm": 0.13268794119358063, | |
| "learning_rate": 9.113333333333335e-06, | |
| "loss": 0.2646, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.0428410372040586, | |
| "grad_norm": 1.25346839427948, | |
| "learning_rate": 9.057777777777779e-06, | |
| "loss": 0.265, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 1.0710259301014655, | |
| "grad_norm": 1.471956491470337, | |
| "learning_rate": 9.002222222222223e-06, | |
| "loss": 0.2856, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.0992108229988726, | |
| "grad_norm": 0.13319148123264313, | |
| "learning_rate": 8.946666666666669e-06, | |
| "loss": 0.2552, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 1.1273957158962795, | |
| "grad_norm": 0.7707216143608093, | |
| "learning_rate": 8.891111111111111e-06, | |
| "loss": 0.2825, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.1273957158962795, | |
| "eval_loss": 1.5161501169204712, | |
| "eval_runtime": 3096.2186, | |
| "eval_samples_per_second": 0.541, | |
| "eval_steps_per_second": 0.017, | |
| "eval_wer": 168.64974807007812, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 5000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "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": 4.63717100371968e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |