| { | |
| "best_metric": 6.12266119021778, | |
| "best_model_checkpoint": "AshtonLKY/Whisper_ASR_ATC_v6/checkpoint-1000", | |
| "epoch": 0.2976190476190476, | |
| "eval_steps": 1000, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00744047619047619, | |
| "grad_norm": 5.413925647735596, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 0.0412, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01488095238095238, | |
| "grad_norm": 3.476644515991211, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.0409, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.022321428571428572, | |
| "grad_norm": 1.9877393245697021, | |
| "learning_rate": 1.5e-06, | |
| "loss": 0.0357, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.02976190476190476, | |
| "grad_norm": 1.821871280670166, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.0297, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03720238095238095, | |
| "grad_norm": 4.649389743804932, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.0284, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.044642857142857144, | |
| "grad_norm": 3.751368999481201, | |
| "learning_rate": 3e-06, | |
| "loss": 0.026, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.052083333333333336, | |
| "grad_norm": 5.829326152801514, | |
| "learning_rate": 3.5e-06, | |
| "loss": 0.0278, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.05952380952380952, | |
| "grad_norm": 2.7991154193878174, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0215, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.06696428571428571, | |
| "grad_norm": 1.027055025100708, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.0131, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.0744047619047619, | |
| "grad_norm": 2.6203041076660156, | |
| "learning_rate": 5e-06, | |
| "loss": 0.0237, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.0818452380952381, | |
| "grad_norm": 0.10589638352394104, | |
| "learning_rate": 5.500000000000001e-06, | |
| "loss": 0.0154, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.08928571428571429, | |
| "grad_norm": 0.6042885184288025, | |
| "learning_rate": 6e-06, | |
| "loss": 0.0138, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.09672619047619048, | |
| "grad_norm": 4.635740280151367, | |
| "learning_rate": 6.5000000000000004e-06, | |
| "loss": 0.012, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.10416666666666667, | |
| "grad_norm": 1.3288782835006714, | |
| "learning_rate": 7e-06, | |
| "loss": 0.0105, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.11160714285714286, | |
| "grad_norm": 0.3894687592983246, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.01, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.11904761904761904, | |
| "grad_norm": 2.7233240604400635, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.0104, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.12648809523809523, | |
| "grad_norm": 1.8257516622543335, | |
| "learning_rate": 8.5e-06, | |
| "loss": 0.0102, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.13392857142857142, | |
| "grad_norm": 20.001121520996094, | |
| "learning_rate": 9e-06, | |
| "loss": 0.0135, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.14136904761904762, | |
| "grad_norm": 1.909671425819397, | |
| "learning_rate": 9.5e-06, | |
| "loss": 0.0058, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.1488095238095238, | |
| "grad_norm": 0.6188738942146301, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0108, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.15625, | |
| "grad_norm": 4.2201385498046875, | |
| "learning_rate": 9.989795918367348e-06, | |
| "loss": 0.01, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.1636904761904762, | |
| "grad_norm": 0.09348121285438538, | |
| "learning_rate": 9.979591836734694e-06, | |
| "loss": 0.0072, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.17113095238095238, | |
| "grad_norm": 0.8602906465530396, | |
| "learning_rate": 9.969387755102042e-06, | |
| "loss": 0.0074, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.17857142857142858, | |
| "grad_norm": 0.9500374794006348, | |
| "learning_rate": 9.959183673469387e-06, | |
| "loss": 0.01, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.18601190476190477, | |
| "grad_norm": 7.845817565917969, | |
| "learning_rate": 9.948979591836737e-06, | |
| "loss": 0.0158, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.19345238095238096, | |
| "grad_norm": 0.8142985701560974, | |
| "learning_rate": 9.938775510204082e-06, | |
| "loss": 0.0098, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.20089285714285715, | |
| "grad_norm": 4.271408557891846, | |
| "learning_rate": 9.92857142857143e-06, | |
| "loss": 0.009, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.20833333333333334, | |
| "grad_norm": 5.065946102142334, | |
| "learning_rate": 9.918367346938776e-06, | |
| "loss": 0.0155, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.21577380952380953, | |
| "grad_norm": 4.185829162597656, | |
| "learning_rate": 9.908163265306123e-06, | |
| "loss": 0.0083, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.22321428571428573, | |
| "grad_norm": 0.18144944310188293, | |
| "learning_rate": 9.89795918367347e-06, | |
| "loss": 0.0095, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.23065476190476192, | |
| "grad_norm": 1.0089025497436523, | |
| "learning_rate": 9.887755102040816e-06, | |
| "loss": 0.0149, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.23809523809523808, | |
| "grad_norm": 0.15361322462558746, | |
| "learning_rate": 9.877551020408164e-06, | |
| "loss": 0.0107, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.24553571428571427, | |
| "grad_norm": 0.5313578248023987, | |
| "learning_rate": 9.867346938775511e-06, | |
| "loss": 0.0151, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.25297619047619047, | |
| "grad_norm": 0.6949892044067383, | |
| "learning_rate": 9.857142857142859e-06, | |
| "loss": 0.0112, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.2604166666666667, | |
| "grad_norm": 3.9174296855926514, | |
| "learning_rate": 9.846938775510205e-06, | |
| "loss": 0.0108, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.26785714285714285, | |
| "grad_norm": 3.3171513080596924, | |
| "learning_rate": 9.836734693877552e-06, | |
| "loss": 0.0106, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.27529761904761907, | |
| "grad_norm": 1.71816086769104, | |
| "learning_rate": 9.8265306122449e-06, | |
| "loss": 0.0144, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.28273809523809523, | |
| "grad_norm": 2.81546688079834, | |
| "learning_rate": 9.816326530612245e-06, | |
| "loss": 0.009, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.29017857142857145, | |
| "grad_norm": 5.431806564331055, | |
| "learning_rate": 9.806122448979593e-06, | |
| "loss": 0.022, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.2976190476190476, | |
| "grad_norm": 4.169656753540039, | |
| "learning_rate": 9.795918367346939e-06, | |
| "loss": 0.0125, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.2976190476190476, | |
| "eval_loss": 0.09145254641771317, | |
| "eval_runtime": 5258.4593, | |
| "eval_samples_per_second": 2.556, | |
| "eval_steps_per_second": 0.16, | |
| "eval_wer": 6.12266119021778, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 25000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 8, | |
| "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": 4.61736640512e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |