| { | |
| "best_metric": 0.28394800424575806, | |
| "best_model_checkpoint": "/kaggle/working/wav2vec2-speech-emotion/checkpoint-1100", | |
| "epoch": 12.64367816091954, | |
| "eval_steps": 100, | |
| "global_step": 1100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.28735632183908044, | |
| "grad_norm": 81616.25, | |
| "learning_rate": 2.5e-06, | |
| "loss": 1.9364, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5747126436781609, | |
| "grad_norm": 113624.453125, | |
| "learning_rate": 5e-06, | |
| "loss": 1.9286, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8620689655172413, | |
| "grad_norm": 74490.7890625, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 1.9194, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.1494252873563218, | |
| "grad_norm": 94447.8125, | |
| "learning_rate": 1e-05, | |
| "loss": 1.9086, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.1494252873563218, | |
| "eval_accuracy": 0.2261904761904762, | |
| "eval_loss": 1.9561063051223755, | |
| "eval_runtime": 10.2339, | |
| "eval_samples_per_second": 16.416, | |
| "eval_steps_per_second": 1.075, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.4367816091954024, | |
| "grad_norm": 60535.6171875, | |
| "learning_rate": 1.25e-05, | |
| "loss": 1.8885, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.7241379310344827, | |
| "grad_norm": 118006.9765625, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 1.8847, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.0114942528735633, | |
| "grad_norm": 109447.6953125, | |
| "learning_rate": 1.7500000000000002e-05, | |
| "loss": 1.8595, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 2.2988505747126435, | |
| "grad_norm": 131271.265625, | |
| "learning_rate": 2e-05, | |
| "loss": 1.7796, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.2988505747126435, | |
| "eval_accuracy": 0.42857142857142855, | |
| "eval_loss": 1.737054705619812, | |
| "eval_runtime": 10.3261, | |
| "eval_samples_per_second": 16.269, | |
| "eval_steps_per_second": 1.065, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.586206896551724, | |
| "grad_norm": 222429.421875, | |
| "learning_rate": 1.9974751105436266e-05, | |
| "loss": 1.6504, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 2.873563218390805, | |
| "grad_norm": 482113.40625, | |
| "learning_rate": 1.98991319230804e-05, | |
| "loss": 1.4559, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.160919540229885, | |
| "grad_norm": 375893.84375, | |
| "learning_rate": 1.9773524313084857e-05, | |
| "loss": 1.2633, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 3.4482758620689653, | |
| "grad_norm": 542423.5625, | |
| "learning_rate": 1.959856256610988e-05, | |
| "loss": 1.1442, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.4482758620689653, | |
| "eval_accuracy": 0.6726190476190477, | |
| "eval_loss": 1.0434563159942627, | |
| "eval_runtime": 10.2866, | |
| "eval_samples_per_second": 16.332, | |
| "eval_steps_per_second": 1.069, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.735632183908046, | |
| "grad_norm": 321237.03125, | |
| "learning_rate": 1.937513020029588e-05, | |
| "loss": 1.0287, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 4.022988505747127, | |
| "grad_norm": 494109.96875, | |
| "learning_rate": 1.9104355499692166e-05, | |
| "loss": 0.929, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.310344827586207, | |
| "grad_norm": 399620.6875, | |
| "learning_rate": 1.8787605816671956e-05, | |
| "loss": 0.809, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 4.597701149425287, | |
| "grad_norm": 320774.09375, | |
| "learning_rate": 1.8426480667105178e-05, | |
| "loss": 0.7284, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.597701149425287, | |
| "eval_accuracy": 0.7857142857142857, | |
| "eval_loss": 0.8009253144264221, | |
| "eval_runtime": 10.0989, | |
| "eval_samples_per_second": 16.635, | |
| "eval_steps_per_second": 1.089, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.885057471264368, | |
| "grad_norm": 316548.5625, | |
| "learning_rate": 1.8022803653156983e-05, | |
| "loss": 0.7361, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 5.172413793103448, | |
| "grad_norm": 592323.0, | |
| "learning_rate": 1.757861325449997e-05, | |
| "loss": 0.6226, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 5.459770114942529, | |
| "grad_norm": 686948.0625, | |
| "learning_rate": 1.7096152534442515e-05, | |
| "loss": 0.5987, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 5.747126436781609, | |
| "grad_norm": 314310.65625, | |
| "learning_rate": 1.6577857812954994e-05, | |
| "loss": 0.5259, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.747126436781609, | |
| "eval_accuracy": 0.8511904761904762, | |
| "eval_loss": 0.5674353837966919, | |
| "eval_runtime": 10.2098, | |
| "eval_samples_per_second": 16.455, | |
| "eval_steps_per_second": 1.077, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.0344827586206895, | |
| "grad_norm": 747515.625, | |
| "learning_rate": 1.6026346363792565e-05, | |
| "loss": 0.534, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 6.32183908045977, | |
| "grad_norm": 308987.9375, | |
| "learning_rate": 1.5444403197841345e-05, | |
| "loss": 0.448, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 6.609195402298851, | |
| "grad_norm": 1300700.75, | |
| "learning_rate": 1.4834966999429179e-05, | |
| "loss": 0.439, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 6.896551724137931, | |
| "grad_norm": 359445.15625, | |
| "learning_rate": 1.4201115286619464e-05, | |
| "loss": 0.3734, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 6.896551724137931, | |
| "eval_accuracy": 0.8273809523809523, | |
| "eval_loss": 0.6119872331619263, | |
| "eval_runtime": 10.1904, | |
| "eval_samples_per_second": 16.486, | |
| "eval_steps_per_second": 1.079, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 7.183908045977011, | |
| "grad_norm": 156436.734375, | |
| "learning_rate": 1.3546048870425356e-05, | |
| "loss": 0.331, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 7.471264367816092, | |
| "grad_norm": 920202.625, | |
| "learning_rate": 1.2873075691421808e-05, | |
| "loss": 0.3074, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 7.758620689655173, | |
| "grad_norm": 501704.25, | |
| "learning_rate": 1.2185594115376991e-05, | |
| "loss": 0.2982, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 8.045977011494253, | |
| "grad_norm": 210118.0625, | |
| "learning_rate": 1.1487075772256517e-05, | |
| "loss": 0.2702, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 8.045977011494253, | |
| "eval_accuracy": 0.9464285714285714, | |
| "eval_loss": 0.2987803518772125, | |
| "eval_runtime": 10.1874, | |
| "eval_samples_per_second": 16.491, | |
| "eval_steps_per_second": 1.08, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 8.333333333333334, | |
| "grad_norm": 529805.875, | |
| "learning_rate": 1.0781048025259648e-05, | |
| "loss": 0.2609, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 8.620689655172415, | |
| "grad_norm": 280091.625, | |
| "learning_rate": 1.0071076158414977e-05, | |
| "loss": 0.2612, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 8.908045977011493, | |
| "grad_norm": 457920.8125, | |
| "learning_rate": 9.360745372684346e-06, | |
| "loss": 0.2353, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 9.195402298850574, | |
| "grad_norm": 791098.25, | |
| "learning_rate": 8.653642681490608e-06, | |
| "loss": 0.2171, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 9.195402298850574, | |
| "eval_accuracy": 0.8928571428571429, | |
| "eval_loss": 0.34595435857772827, | |
| "eval_runtime": 10.2959, | |
| "eval_samples_per_second": 16.317, | |
| "eval_steps_per_second": 1.068, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 9.482758620689655, | |
| "grad_norm": 490233.0, | |
| "learning_rate": 7.953338797092902e-06, | |
| "loss": 0.1884, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 9.770114942528735, | |
| "grad_norm": 605037.8125, | |
| "learning_rate": 7.263370099279173e-06, | |
| "loss": 0.1573, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 10.057471264367816, | |
| "grad_norm": 504736.34375, | |
| "learning_rate": 6.587220777430097e-06, | |
| "loss": 0.1424, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 10.344827586206897, | |
| "grad_norm": 559532.25, | |
| "learning_rate": 5.928305236133016e-06, | |
| "loss": 0.1634, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 10.344827586206897, | |
| "eval_accuracy": 0.9345238095238095, | |
| "eval_loss": 0.29700732231140137, | |
| "eval_runtime": 10.0813, | |
| "eval_samples_per_second": 16.665, | |
| "eval_steps_per_second": 1.091, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 10.632183908045977, | |
| "grad_norm": 426639.75, | |
| "learning_rate": 5.2899508531936526e-06, | |
| "loss": 0.1735, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 10.919540229885058, | |
| "grad_norm": 421293.25, | |
| "learning_rate": 4.675381177113837e-06, | |
| "loss": 0.2091, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 11.206896551724139, | |
| "grad_norm": 1287860.25, | |
| "learning_rate": 4.087699648884248e-06, | |
| "loss": 0.1832, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 11.494252873563218, | |
| "grad_norm": 596496.875, | |
| "learning_rate": 3.529873930293546e-06, | |
| "loss": 0.1483, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 11.494252873563218, | |
| "eval_accuracy": 0.9226190476190477, | |
| "eval_loss": 0.3032456934452057, | |
| "eval_runtime": 10.027, | |
| "eval_samples_per_second": 16.755, | |
| "eval_steps_per_second": 1.097, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 11.781609195402298, | |
| "grad_norm": 223663.953125, | |
| "learning_rate": 3.004720917892464e-06, | |
| "loss": 0.1588, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 12.068965517241379, | |
| "grad_norm": 55755.37109375, | |
| "learning_rate": 2.514892518288988e-06, | |
| "loss": 0.1392, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 12.35632183908046, | |
| "grad_norm": 260650.140625, | |
| "learning_rate": 2.0628622566063063e-06, | |
| "loss": 0.1493, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 12.64367816091954, | |
| "grad_norm": 60438.0390625, | |
| "learning_rate": 1.6509127857277784e-06, | |
| "loss": 0.1077, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 12.64367816091954, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.28394800424575806, | |
| "eval_runtime": 10.0833, | |
| "eval_samples_per_second": 16.661, | |
| "eval_steps_per_second": 1.091, | |
| "step": 1100 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 1305, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 15, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "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": 4.682951691910107e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |