| { |
| "best_global_step": 154, |
| "best_metric": 0.9930795847750865, |
| "best_model_checkpoint": "ast-finetuned-speech-commands-v2-hanzo-fine-tuning/checkpoint-154", |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 154, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.03257328990228013, |
| "grad_norm": 1.1653014421463013, |
| "learning_rate": 2.0000000000000003e-06, |
| "loss": 0.07611768841743469, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.06514657980456026, |
| "grad_norm": 0.3887513279914856, |
| "learning_rate": 4.5e-06, |
| "loss": 0.06761979460716247, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.09771986970684039, |
| "grad_norm": 0.7926945686340332, |
| "learning_rate": 7.000000000000001e-06, |
| "loss": 0.08373377323150635, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.13029315960912052, |
| "grad_norm": 0.4492540955543518, |
| "learning_rate": 9.5e-06, |
| "loss": 0.0332341730594635, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.16286644951140064, |
| "grad_norm": 0.30614861845970154, |
| "learning_rate": 1.2e-05, |
| "loss": 0.05032479763031006, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.19543973941368079, |
| "grad_norm": 0.21970808506011963, |
| "learning_rate": 1.45e-05, |
| "loss": 0.03193366825580597, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.2280130293159609, |
| "grad_norm": 0.5510302186012268, |
| "learning_rate": 1.7000000000000003e-05, |
| "loss": 0.05110905170440674, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.26058631921824105, |
| "grad_norm": 0.2315930873155594, |
| "learning_rate": 1.9500000000000003e-05, |
| "loss": 0.016657236218452453, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.2931596091205212, |
| "grad_norm": 0.2902866303920746, |
| "learning_rate": 2.2000000000000003e-05, |
| "loss": 0.023022058606147765, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.3257328990228013, |
| "grad_norm": 0.5750004649162292, |
| "learning_rate": 2.45e-05, |
| "loss": 0.014302554726600646, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.3583061889250814, |
| "grad_norm": 0.3459576368331909, |
| "learning_rate": 2.7000000000000002e-05, |
| "loss": 0.033040481805801394, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.39087947882736157, |
| "grad_norm": 0.46629878878593445, |
| "learning_rate": 2.95e-05, |
| "loss": 0.019753463566303253, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.4234527687296417, |
| "grad_norm": 1.4239784479141235, |
| "learning_rate": 3.2000000000000005e-05, |
| "loss": 0.03902222216129303, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.4560260586319218, |
| "grad_norm": 0.032012976706027985, |
| "learning_rate": 3.45e-05, |
| "loss": 0.052900946140289305, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.48859934853420195, |
| "grad_norm": 0.07826949656009674, |
| "learning_rate": 3.7e-05, |
| "loss": 0.023861391842365264, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.5211726384364821, |
| "grad_norm": 1.4051694869995117, |
| "learning_rate": 3.9500000000000005e-05, |
| "loss": 0.054276466369628906, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.5537459283387622, |
| "grad_norm": 1.0960911512374878, |
| "learning_rate": 4.2e-05, |
| "loss": 0.05710892677307129, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.5863192182410424, |
| "grad_norm": 0.478943407535553, |
| "learning_rate": 4.4500000000000004e-05, |
| "loss": 0.04267547130584717, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.6188925081433225, |
| "grad_norm": 0.06757480651140213, |
| "learning_rate": 4.7e-05, |
| "loss": 0.017196863889694214, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.6514657980456026, |
| "grad_norm": 0.30626747012138367, |
| "learning_rate": 4.9500000000000004e-05, |
| "loss": 0.031380954384803775, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.6840390879478827, |
| "grad_norm": 0.7386727333068848, |
| "learning_rate": 4.986111111111111e-05, |
| "loss": 0.06237261295318604, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.7166123778501629, |
| "grad_norm": 1.010459303855896, |
| "learning_rate": 4.96875e-05, |
| "loss": 0.050882083177566526, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.749185667752443, |
| "grad_norm": 1.2491978406906128, |
| "learning_rate": 4.951388888888889e-05, |
| "loss": 0.03587841689586639, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.7817589576547231, |
| "grad_norm": 1.2465689182281494, |
| "learning_rate": 4.934027777777778e-05, |
| "loss": 0.04802972674369812, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.8143322475570033, |
| "grad_norm": 0.2289113849401474, |
| "learning_rate": 4.9166666666666665e-05, |
| "loss": 0.04792758822441101, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.8469055374592834, |
| "grad_norm": 0.601269543170929, |
| "learning_rate": 4.8993055555555555e-05, |
| "loss": 0.04989897608757019, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.8794788273615635, |
| "grad_norm": 0.7225825786590576, |
| "learning_rate": 4.8819444444444444e-05, |
| "loss": 0.03563607335090637, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.9120521172638436, |
| "grad_norm": 0.7649105191230774, |
| "learning_rate": 4.8645833333333334e-05, |
| "loss": 0.054471558332443236, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.9446254071661238, |
| "grad_norm": 2.508047103881836, |
| "learning_rate": 4.8472222222222224e-05, |
| "loss": 0.06372030973434448, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.9771986970684039, |
| "grad_norm": 0.08946274220943451, |
| "learning_rate": 4.8298611111111114e-05, |
| "loss": 0.037330257892608645, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.910362920857018, |
| "eval_hanzo_f1": 0.9930795847750865, |
| "eval_hanzo_precision": 0.9862542955326461, |
| "eval_hanzo_recall": 1.0, |
| "eval_loss": 0.44769129157066345, |
| "eval_macro_f1": 0.8652380926401048, |
| "eval_macro_precision": 0.8407417518785465, |
| "eval_macro_recall": 0.9440416294444297, |
| "eval_runtime": 48.3649, |
| "eval_samples_per_second": 94.573, |
| "eval_steps_per_second": 1.489, |
| "step": 154 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 1540, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 2, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.6445549426540544e+17, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
