| { | |
| "best_metric": 0.9210379123687744, | |
| "best_model_checkpoint": "./wav2vec2-ver2.0/checkpoint-3538", | |
| "epoch": 49.86396181384248, | |
| "global_step": 5200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 4.028111457824707, | |
| "eval_runtime": 62.0842, | |
| "eval_samples_per_second": 13.562, | |
| "eval_steps_per_second": 0.854, | |
| "eval_wer": 1.0, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 3.40583872795105, | |
| "eval_runtime": 58.57, | |
| "eval_samples_per_second": 14.376, | |
| "eval_steps_per_second": 0.905, | |
| "eval_wer": 1.0, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_loss": 3.345716953277588, | |
| "eval_runtime": 62.5527, | |
| "eval_samples_per_second": 13.461, | |
| "eval_steps_per_second": 0.847, | |
| "eval_wer": 1.0, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 3.3383560180664062, | |
| "eval_runtime": 59.2148, | |
| "eval_samples_per_second": 14.219, | |
| "eval_steps_per_second": 0.895, | |
| "eval_wer": 1.0, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 4.7e-05, | |
| "loss": 3.351, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 3.319535970687866, | |
| "eval_runtime": 60.0386, | |
| "eval_samples_per_second": 14.024, | |
| "eval_steps_per_second": 0.883, | |
| "eval_wer": 1.0, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 3.277388334274292, | |
| "eval_runtime": 59.0991, | |
| "eval_samples_per_second": 14.247, | |
| "eval_steps_per_second": 0.897, | |
| "eval_wer": 0.9999866518947635, | |
| "step": 627 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "eval_loss": 2.7498323917388916, | |
| "eval_runtime": 59.3674, | |
| "eval_samples_per_second": 14.183, | |
| "eval_steps_per_second": 0.893, | |
| "eval_wer": 1.018353644700135, | |
| "step": 731 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 2.0694806575775146, | |
| "eval_runtime": 59.1337, | |
| "eval_samples_per_second": 14.239, | |
| "eval_steps_per_second": 0.896, | |
| "eval_wer": 0.9267989908832441, | |
| "step": 836 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 1.666611909866333, | |
| "eval_runtime": 59.1057, | |
| "eval_samples_per_second": 14.246, | |
| "eval_steps_per_second": 0.897, | |
| "eval_wer": 0.8102833802741701, | |
| "step": 941 | |
| }, | |
| { | |
| "epoch": 9.56, | |
| "learning_rate": 4.2e-05, | |
| "loss": 2.5482, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.4118962287902832, | |
| "eval_runtime": 60.2006, | |
| "eval_samples_per_second": 13.987, | |
| "eval_steps_per_second": 0.88, | |
| "eval_wer": 0.7014028858603522, | |
| "step": 1046 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "eval_loss": 1.2479561567306519, | |
| "eval_runtime": 59.1239, | |
| "eval_samples_per_second": 14.241, | |
| "eval_steps_per_second": 0.896, | |
| "eval_wer": 0.6408024880868161, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 1.1396839618682861, | |
| "eval_runtime": 60.2391, | |
| "eval_samples_per_second": 13.978, | |
| "eval_steps_per_second": 0.88, | |
| "eval_wer": 0.5814434641002709, | |
| "step": 1255 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 1.0593441724777222, | |
| "eval_runtime": 59.2221, | |
| "eval_samples_per_second": 14.218, | |
| "eval_steps_per_second": 0.895, | |
| "eval_wer": 0.5381155145027163, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 1.0059597492218018, | |
| "eval_runtime": 59.2878, | |
| "eval_samples_per_second": 14.202, | |
| "eval_steps_per_second": 0.894, | |
| "eval_wer": 0.5098709238223634, | |
| "step": 1465 | |
| }, | |
| { | |
| "epoch": 14.33, | |
| "learning_rate": 3.7e-05, | |
| "loss": 1.1172, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 14.99, | |
| "eval_loss": 0.9677549600601196, | |
| "eval_runtime": 59.2664, | |
| "eval_samples_per_second": 14.207, | |
| "eval_steps_per_second": 0.894, | |
| "eval_wer": 0.4830412322970754, | |
| "step": 1569 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 0.9378706812858582, | |
| "eval_runtime": 59.4564, | |
| "eval_samples_per_second": 14.162, | |
| "eval_steps_per_second": 0.891, | |
| "eval_wer": 0.46923929148257404, | |
| "step": 1674 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 0.9126999378204346, | |
| "eval_runtime": 59.2107, | |
| "eval_samples_per_second": 14.22, | |
| "eval_steps_per_second": 0.895, | |
| "eval_wer": 0.4618310930763378, | |
| "step": 1779 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 0.8923171758651733, | |
| "eval_runtime": 59.2943, | |
| "eval_samples_per_second": 14.2, | |
| "eval_steps_per_second": 0.894, | |
| "eval_wer": 0.43522831934006967, | |
| "step": 1884 | |
| }, | |
| { | |
| "epoch": 18.99, | |
| "eval_loss": 0.8826682567596436, | |
| "eval_runtime": 59.3015, | |
| "eval_samples_per_second": 14.199, | |
| "eval_steps_per_second": 0.894, | |
| "eval_wer": 0.4254041138860339, | |
| "step": 1988 | |
| }, | |
| { | |
| "epoch": 19.11, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 0.7161, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 0.8722440600395203, | |
| "eval_runtime": 59.4161, | |
| "eval_samples_per_second": 14.171, | |
| "eval_steps_per_second": 0.892, | |
| "eval_wer": 0.43042300145494344, | |
| "step": 2093 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_loss": 0.8755246996879578, | |
| "eval_runtime": 59.3074, | |
| "eval_samples_per_second": 14.197, | |
| "eval_steps_per_second": 0.894, | |
| "eval_wer": 0.41415166117169666, | |
| "step": 2198 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 0.8679744601249695, | |
| "eval_runtime": 59.2292, | |
| "eval_samples_per_second": 14.216, | |
| "eval_steps_per_second": 0.895, | |
| "eval_wer": 0.4157400856948356, | |
| "step": 2303 | |
| }, | |
| { | |
| "epoch": 22.99, | |
| "eval_loss": 0.8705059289932251, | |
| "eval_runtime": 59.3713, | |
| "eval_samples_per_second": 14.182, | |
| "eval_steps_per_second": 0.893, | |
| "eval_wer": 0.411588824966296, | |
| "step": 2407 | |
| }, | |
| { | |
| "epoch": 23.88, | |
| "learning_rate": 2.7000000000000002e-05, | |
| "loss": 0.5338, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 0.8610785603523254, | |
| "eval_runtime": 60.2932, | |
| "eval_samples_per_second": 13.965, | |
| "eval_steps_per_second": 0.879, | |
| "eval_wer": 0.40391366445533056, | |
| "step": 2512 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 0.8716456294059753, | |
| "eval_runtime": 59.4195, | |
| "eval_samples_per_second": 14.17, | |
| "eval_steps_per_second": 0.892, | |
| "eval_wer": 0.3995087897272982, | |
| "step": 2617 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_loss": 0.8720651865005493, | |
| "eval_runtime": 60.3407, | |
| "eval_samples_per_second": 13.954, | |
| "eval_steps_per_second": 0.878, | |
| "eval_wer": 0.40370009477154717, | |
| "step": 2722 | |
| }, | |
| { | |
| "epoch": 26.99, | |
| "eval_loss": 0.8809343576431274, | |
| "eval_runtime": 59.2643, | |
| "eval_samples_per_second": 14.208, | |
| "eval_steps_per_second": 0.894, | |
| "eval_wer": 0.39733304857375495, | |
| "step": 2826 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_loss": 0.9036707878112793, | |
| "eval_runtime": 60.3075, | |
| "eval_samples_per_second": 13.962, | |
| "eval_steps_per_second": 0.879, | |
| "eval_wer": 0.393835845001802, | |
| "step": 2931 | |
| }, | |
| { | |
| "epoch": 28.65, | |
| "learning_rate": 2.2000000000000003e-05, | |
| "loss": 0.4299, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_loss": 0.9118879437446594, | |
| "eval_runtime": 59.2709, | |
| "eval_samples_per_second": 14.206, | |
| "eval_steps_per_second": 0.894, | |
| "eval_wer": 0.39029859711413967, | |
| "step": 3036 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_loss": 0.9117182493209839, | |
| "eval_runtime": 59.2026, | |
| "eval_samples_per_second": 14.222, | |
| "eval_steps_per_second": 0.895, | |
| "eval_wer": 0.3911929201649826, | |
| "step": 3141 | |
| }, | |
| { | |
| "epoch": 30.99, | |
| "eval_loss": 0.9027386903762817, | |
| "eval_runtime": 59.2101, | |
| "eval_samples_per_second": 14.221, | |
| "eval_steps_per_second": 0.895, | |
| "eval_wer": 0.39296821816143196, | |
| "step": 3245 | |
| }, | |
| { | |
| "epoch": 31.99, | |
| "eval_loss": 0.923963189125061, | |
| "eval_runtime": 61.8239, | |
| "eval_samples_per_second": 13.619, | |
| "eval_steps_per_second": 0.857, | |
| "eval_wer": 0.38977802100991765, | |
| "step": 3328 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_loss": 0.9336917400360107, | |
| "eval_runtime": 58.5975, | |
| "eval_samples_per_second": 14.369, | |
| "eval_steps_per_second": 0.904, | |
| "eval_wer": 0.3872418810149899, | |
| "step": 3433 | |
| }, | |
| { | |
| "epoch": 33.63, | |
| "learning_rate": 1.7000000000000003e-05, | |
| "loss": 0.3491, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_loss": 0.9210379123687744, | |
| "eval_runtime": 58.5611, | |
| "eval_samples_per_second": 14.378, | |
| "eval_steps_per_second": 0.905, | |
| "eval_wer": 0.3900716793251198, | |
| "step": 3538 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_loss": 0.9308741092681885, | |
| "eval_runtime": 58.496, | |
| "eval_samples_per_second": 14.394, | |
| "eval_steps_per_second": 0.906, | |
| "eval_wer": 0.39053886300839596, | |
| "step": 3643 | |
| }, | |
| { | |
| "epoch": 35.99, | |
| "eval_loss": 0.9527643918991089, | |
| "eval_runtime": 58.33, | |
| "eval_samples_per_second": 14.435, | |
| "eval_steps_per_second": 0.909, | |
| "eval_wer": 0.3906322997450512, | |
| "step": 3747 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_loss": 0.9505965113639832, | |
| "eval_runtime": 58.5212, | |
| "eval_samples_per_second": 14.388, | |
| "eval_steps_per_second": 0.906, | |
| "eval_wer": 0.3880160711187047, | |
| "step": 3852 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_loss": 0.9606704711914062, | |
| "eval_runtime": 58.4358, | |
| "eval_samples_per_second": 14.409, | |
| "eval_steps_per_second": 0.907, | |
| "eval_wer": 0.3853197538609394, | |
| "step": 3957 | |
| }, | |
| { | |
| "epoch": 38.41, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.3195, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_loss": 0.9566919803619385, | |
| "eval_runtime": 58.6525, | |
| "eval_samples_per_second": 14.356, | |
| "eval_steps_per_second": 0.904, | |
| "eval_wer": 0.3905655592188689, | |
| "step": 4062 | |
| }, | |
| { | |
| "epoch": 39.99, | |
| "eval_loss": 0.9631790518760681, | |
| "eval_runtime": 58.5685, | |
| "eval_samples_per_second": 14.376, | |
| "eval_steps_per_second": 0.905, | |
| "eval_wer": 0.38928414111616855, | |
| "step": 4166 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_loss": 0.9797289371490479, | |
| "eval_runtime": 58.522, | |
| "eval_samples_per_second": 14.388, | |
| "eval_steps_per_second": 0.906, | |
| "eval_wer": 0.38385146228492867, | |
| "step": 4271 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_loss": 0.9818938970565796, | |
| "eval_runtime": 58.7742, | |
| "eval_samples_per_second": 14.326, | |
| "eval_steps_per_second": 0.902, | |
| "eval_wer": 0.38535979817664884, | |
| "step": 4376 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_loss": 0.9686055779457092, | |
| "eval_runtime": 58.9453, | |
| "eval_samples_per_second": 14.284, | |
| "eval_steps_per_second": 0.899, | |
| "eval_wer": 0.38696157080502425, | |
| "step": 4481 | |
| }, | |
| { | |
| "epoch": 43.18, | |
| "learning_rate": 7.000000000000001e-06, | |
| "loss": 0.2892, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 43.99, | |
| "eval_loss": 0.9807793498039246, | |
| "eval_runtime": 58.7863, | |
| "eval_samples_per_second": 14.323, | |
| "eval_steps_per_second": 0.902, | |
| "eval_wer": 0.38953775511566135, | |
| "step": 4585 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_loss": 0.9857133626937866, | |
| "eval_runtime": 58.8468, | |
| "eval_samples_per_second": 14.308, | |
| "eval_steps_per_second": 0.901, | |
| "eval_wer": 0.3892440968004592, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_loss": 0.9959315657615662, | |
| "eval_runtime": 58.8414, | |
| "eval_samples_per_second": 14.31, | |
| "eval_steps_per_second": 0.901, | |
| "eval_wer": 0.3831039683916868, | |
| "step": 4795 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_loss": 0.9959281086921692, | |
| "eval_runtime": 58.7339, | |
| "eval_samples_per_second": 14.336, | |
| "eval_steps_per_second": 0.902, | |
| "eval_wer": 0.387041659436443, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 47.95, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.2705, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 47.99, | |
| "eval_loss": 1.0028016567230225, | |
| "eval_runtime": 58.7024, | |
| "eval_samples_per_second": 14.344, | |
| "eval_steps_per_second": 0.903, | |
| "eval_wer": 0.38601385533323546, | |
| "step": 5004 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_loss": 1.001922845840454, | |
| "eval_runtime": 59.7161, | |
| "eval_samples_per_second": 14.1, | |
| "eval_steps_per_second": 0.888, | |
| "eval_wer": 0.386868134068369, | |
| "step": 5109 | |
| }, | |
| { | |
| "epoch": 49.86, | |
| "eval_loss": 1.004983901977539, | |
| "eval_runtime": 58.7107, | |
| "eval_samples_per_second": 14.342, | |
| "eval_steps_per_second": 0.903, | |
| "eval_wer": 0.3856801527023239, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 49.86, | |
| "step": 5200, | |
| "total_flos": 4.179442576708594e+19, | |
| "train_loss": 0.11175713245685284, | |
| "train_runtime": 33540.098, | |
| "train_samples_per_second": 4.994, | |
| "train_steps_per_second": 0.155 | |
| } | |
| ], | |
| "max_steps": 5200, | |
| "num_train_epochs": 50, | |
| "total_flos": 4.179442576708594e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |