| { | |
| "best_metric": 0.9587628865979382, | |
| "best_model_checkpoint": "wav2vec2-base_have_one/checkpoint-187", | |
| "epoch": 20.0, | |
| "global_step": 340, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 8.823529411764707e-06, | |
| "loss": 0.6902, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.4845360824742268, | |
| "eval_loss": 0.6957051157951355, | |
| "eval_runtime": 37.1182, | |
| "eval_samples_per_second": 2.613, | |
| "eval_steps_per_second": 0.189, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 1.7647058823529414e-05, | |
| "loss": 0.6902, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2.647058823529412e-05, | |
| "loss": 0.68, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6907216494845361, | |
| "eval_loss": 0.6642839908599854, | |
| "eval_runtime": 38.6941, | |
| "eval_samples_per_second": 2.507, | |
| "eval_steps_per_second": 0.181, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 2.9411764705882354e-05, | |
| "loss": 0.6778, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 2.8431372549019608e-05, | |
| "loss": 0.6298, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.5360824742268041, | |
| "eval_loss": 0.6741653680801392, | |
| "eval_runtime": 38.2882, | |
| "eval_samples_per_second": 2.533, | |
| "eval_steps_per_second": 0.183, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 2.745098039215686e-05, | |
| "loss": 0.5278, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.6804123711340206, | |
| "eval_loss": 0.6006929278373718, | |
| "eval_runtime": 38.4017, | |
| "eval_samples_per_second": 2.526, | |
| "eval_steps_per_second": 0.182, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 2.656862745098039e-05, | |
| "loss": 0.5259, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "learning_rate": 2.5588235294117648e-05, | |
| "loss": 0.4355, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.7422680412371134, | |
| "eval_loss": 0.517099916934967, | |
| "eval_runtime": 35.8028, | |
| "eval_samples_per_second": 2.709, | |
| "eval_steps_per_second": 0.196, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 5.29, | |
| "learning_rate": 2.4705882352941174e-05, | |
| "loss": 0.3802, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "learning_rate": 2.372549019607843e-05, | |
| "loss": 0.4019, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.865979381443299, | |
| "eval_loss": 0.3196536898612976, | |
| "eval_runtime": 38.286, | |
| "eval_samples_per_second": 2.534, | |
| "eval_steps_per_second": 0.183, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "learning_rate": 2.2745098039215685e-05, | |
| "loss": 0.3744, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.865979381443299, | |
| "eval_loss": 0.3025638461112976, | |
| "eval_runtime": 38.4396, | |
| "eval_samples_per_second": 2.523, | |
| "eval_steps_per_second": 0.182, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 7.06, | |
| "learning_rate": 2.1764705882352943e-05, | |
| "loss": 0.3023, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 7.65, | |
| "learning_rate": 2.0784313725490197e-05, | |
| "loss": 0.2918, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8969072164948454, | |
| "eval_loss": 0.2628060579299927, | |
| "eval_runtime": 38.2434, | |
| "eval_samples_per_second": 2.536, | |
| "eval_steps_per_second": 0.183, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 8.24, | |
| "learning_rate": 1.980392156862745e-05, | |
| "loss": 0.293, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "learning_rate": 1.8823529411764708e-05, | |
| "loss": 0.2183, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9072164948453608, | |
| "eval_loss": 0.24250493943691254, | |
| "eval_runtime": 38.2877, | |
| "eval_samples_per_second": 2.533, | |
| "eval_steps_per_second": 0.183, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 9.41, | |
| "learning_rate": 1.784313725490196e-05, | |
| "loss": 0.282, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 1.6862745098039215e-05, | |
| "loss": 0.279, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.8556701030927835, | |
| "eval_loss": 0.3291594386100769, | |
| "eval_runtime": 38.2272, | |
| "eval_samples_per_second": 2.537, | |
| "eval_steps_per_second": 0.183, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 10.59, | |
| "learning_rate": 1.5882352941176473e-05, | |
| "loss": 0.241, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.9587628865979382, | |
| "eval_loss": 0.15296605229377747, | |
| "eval_runtime": 38.4242, | |
| "eval_samples_per_second": 2.524, | |
| "eval_steps_per_second": 0.182, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 11.18, | |
| "learning_rate": 1.4901960784313726e-05, | |
| "loss": 0.1683, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 11.76, | |
| "learning_rate": 1.3921568627450982e-05, | |
| "loss": 0.1902, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.9381443298969072, | |
| "eval_loss": 0.16121618449687958, | |
| "eval_runtime": 38.3684, | |
| "eval_samples_per_second": 2.528, | |
| "eval_steps_per_second": 0.182, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 12.35, | |
| "learning_rate": 1.2941176470588236e-05, | |
| "loss": 0.1848, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 12.94, | |
| "learning_rate": 1.1960784313725491e-05, | |
| "loss": 0.2008, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.9278350515463918, | |
| "eval_loss": 0.19607779383659363, | |
| "eval_runtime": 38.2401, | |
| "eval_samples_per_second": 2.537, | |
| "eval_steps_per_second": 0.183, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 13.53, | |
| "learning_rate": 1.0980392156862745e-05, | |
| "loss": 0.1522, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.9278350515463918, | |
| "eval_loss": 0.19184765219688416, | |
| "eval_runtime": 38.2777, | |
| "eval_samples_per_second": 2.534, | |
| "eval_steps_per_second": 0.183, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 14.12, | |
| "learning_rate": 9.999999999999999e-06, | |
| "loss": 0.1117, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 14.71, | |
| "learning_rate": 9.019607843137255e-06, | |
| "loss": 0.1758, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.9278350515463918, | |
| "eval_loss": 0.19222897291183472, | |
| "eval_runtime": 38.3475, | |
| "eval_samples_per_second": 2.53, | |
| "eval_steps_per_second": 0.183, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 15.29, | |
| "learning_rate": 8.03921568627451e-06, | |
| "loss": 0.1421, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 15.88, | |
| "learning_rate": 7.058823529411765e-06, | |
| "loss": 0.1571, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.9484536082474226, | |
| "eval_loss": 0.18052217364311218, | |
| "eval_runtime": 38.3194, | |
| "eval_samples_per_second": 2.531, | |
| "eval_steps_per_second": 0.183, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 16.47, | |
| "learning_rate": 6.07843137254902e-06, | |
| "loss": 0.1148, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.9484536082474226, | |
| "eval_loss": 0.15847636759281158, | |
| "eval_runtime": 38.2687, | |
| "eval_samples_per_second": 2.535, | |
| "eval_steps_per_second": 0.183, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 17.06, | |
| "learning_rate": 5.098039215686275e-06, | |
| "loss": 0.1421, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 17.65, | |
| "learning_rate": 4.11764705882353e-06, | |
| "loss": 0.1343, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.9278350515463918, | |
| "eval_loss": 0.157073974609375, | |
| "eval_runtime": 38.2381, | |
| "eval_samples_per_second": 2.537, | |
| "eval_steps_per_second": 0.183, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 18.24, | |
| "learning_rate": 3.1372549019607846e-06, | |
| "loss": 0.1074, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 18.82, | |
| "learning_rate": 2.1568627450980393e-06, | |
| "loss": 0.134, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.9381443298969072, | |
| "eval_loss": 0.15740494430065155, | |
| "eval_runtime": 38.1402, | |
| "eval_samples_per_second": 2.543, | |
| "eval_steps_per_second": 0.184, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 19.41, | |
| "learning_rate": 1.1764705882352942e-06, | |
| "loss": 0.1036, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 1.9607843137254904e-07, | |
| "loss": 0.1029, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.9381443298969072, | |
| "eval_loss": 0.16617804765701294, | |
| "eval_runtime": 38.1011, | |
| "eval_samples_per_second": 2.546, | |
| "eval_steps_per_second": 0.184, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 340, | |
| "total_flos": 9.284582669750386e+16, | |
| "train_loss": 0.30126741142833935, | |
| "train_runtime": 1869.8807, | |
| "train_samples_per_second": 5.722, | |
| "train_steps_per_second": 0.182 | |
| } | |
| ], | |
| "max_steps": 340, | |
| "num_train_epochs": 20, | |
| "total_flos": 9.284582669750386e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |