| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9568377501956837, | |
| "global_step": 105000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5.73025856044724e-06, | |
| "loss": 11.2906, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.1553692056836711e-05, | |
| "loss": 7.0039, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.7377125553226185e-05, | |
| "loss": 6.1153, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.3200559049615657e-05, | |
| "loss": 5.7832, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.9023992546005126e-05, | |
| "loss": 5.6146, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 5.421965599060059, | |
| "eval_runtime": 411.32, | |
| "eval_samples_per_second": 41.389, | |
| "eval_steps_per_second": 5.174, | |
| "eval_wer": 0.9239681855833133, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 3.48474260423946e-05, | |
| "loss": 5.5165, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.067085953878407e-05, | |
| "loss": 5.446, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.649429303517354e-05, | |
| "loss": 5.3865, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 5.2317726531563014e-05, | |
| "loss": 5.3516, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 5.814116002795248e-05, | |
| "loss": 5.3348, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 5.211235046386719, | |
| "eval_runtime": 409.8837, | |
| "eval_samples_per_second": 41.534, | |
| "eval_steps_per_second": 5.192, | |
| "eval_wer": 0.9147464109993301, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 6.396459352434195e-05, | |
| "loss": 5.2944, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 6.978802702073143e-05, | |
| "loss": 5.2642, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 7.56114605171209e-05, | |
| "loss": 5.2581, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 8.143489401351036e-05, | |
| "loss": 5.2314, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 8.725832750989984e-05, | |
| "loss": 5.2119, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 5.13909912109375, | |
| "eval_runtime": 409.6938, | |
| "eval_samples_per_second": 41.553, | |
| "eval_steps_per_second": 5.194, | |
| "eval_wer": 0.9114111424157333, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.308176100628931e-05, | |
| "loss": 5.1866, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.890519450267879e-05, | |
| "loss": 5.1807, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.958877747391876e-05, | |
| "loss": 5.1441, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.908234579155272e-05, | |
| "loss": 5.1273, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.857591410918667e-05, | |
| "loss": 5.1076, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 5.045482158660889, | |
| "eval_runtime": 412.0168, | |
| "eval_samples_per_second": 41.319, | |
| "eval_steps_per_second": 5.165, | |
| "eval_wer": 0.9043837403957815, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.806948242682062e-05, | |
| "loss": 5.0971, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.756305074445458e-05, | |
| "loss": 5.0834, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.705661906208853e-05, | |
| "loss": 5.0678, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.655018737972249e-05, | |
| "loss": 5.0522, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.604375569735643e-05, | |
| "loss": 5.0557, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 4.983465671539307, | |
| "eval_runtime": 410.6819, | |
| "eval_samples_per_second": 41.453, | |
| "eval_steps_per_second": 5.182, | |
| "eval_wer": 0.8979804271846081, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.553732401499038e-05, | |
| "loss": 5.0332, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.503089233262434e-05, | |
| "loss": 5.0225, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.452446065025829e-05, | |
| "loss": 5.0201, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.401802896789223e-05, | |
| "loss": 5.0077, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.35115972855262e-05, | |
| "loss": 4.9969, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 4.943966388702393, | |
| "eval_runtime": 411.257, | |
| "eval_samples_per_second": 41.395, | |
| "eval_steps_per_second": 5.174, | |
| "eval_wer": 0.896159514799699, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 9.300516560316014e-05, | |
| "loss": 4.9911, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 9.249873392079409e-05, | |
| "loss": 4.9935, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 9.199230223842805e-05, | |
| "loss": 4.9755, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 9.1485870556062e-05, | |
| "loss": 4.9771, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 9.097943887369594e-05, | |
| "loss": 4.9577, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 4.906991481781006, | |
| "eval_runtime": 410.7324, | |
| "eval_samples_per_second": 41.448, | |
| "eval_steps_per_second": 5.181, | |
| "eval_wer": 0.8942902538261701, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 9.04730071913299e-05, | |
| "loss": 4.953, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 8.996657550896385e-05, | |
| "loss": 4.9515, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 8.94601438265978e-05, | |
| "loss": 4.9314, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 8.895371214423176e-05, | |
| "loss": 4.9529, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 8.84472804618657e-05, | |
| "loss": 4.9298, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 4.876424312591553, | |
| "eval_runtime": 410.0694, | |
| "eval_samples_per_second": 41.515, | |
| "eval_steps_per_second": 5.189, | |
| "eval_wer": 0.8924795338464294, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 8.794084877949965e-05, | |
| "loss": 4.9117, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 8.743542996049834e-05, | |
| "loss": 4.9273, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 8.693001114149701e-05, | |
| "loss": 4.9357, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 8.642357945913097e-05, | |
| "loss": 4.9211, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 8.591714777676492e-05, | |
| "loss": 4.9096, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 4.8509111404418945, | |
| "eval_runtime": 411.3063, | |
| "eval_samples_per_second": 41.39, | |
| "eval_steps_per_second": 5.174, | |
| "eval_wer": 0.8897156933115739, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 8.541071609439886e-05, | |
| "loss": 4.9029, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 8.490428441203282e-05, | |
| "loss": 4.9012, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 8.439785272966677e-05, | |
| "loss": 4.8984, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 8.389142104730072e-05, | |
| "loss": 4.8971, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 8.338498936493468e-05, | |
| "loss": 4.896, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 4.833607196807861, | |
| "eval_runtime": 411.6309, | |
| "eval_samples_per_second": 41.357, | |
| "eval_steps_per_second": 5.17, | |
| "eval_wer": 0.8886487575654107, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 8.287855768256862e-05, | |
| "loss": 4.8776, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 8.237415172693204e-05, | |
| "loss": 4.8729, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 8.186772004456598e-05, | |
| "loss": 4.8781, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 8.136128836219995e-05, | |
| "loss": 4.8726, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 8.085485667983389e-05, | |
| "loss": 4.8724, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 4.81581449508667, | |
| "eval_runtime": 411.4914, | |
| "eval_samples_per_second": 41.371, | |
| "eval_steps_per_second": 5.171, | |
| "eval_wer": 0.8873070188952817, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 8.034943786083258e-05, | |
| "loss": 4.8579, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 7.984300617846653e-05, | |
| "loss": 4.8618, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 7.933657449610049e-05, | |
| "loss": 4.8674, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 7.883014281373443e-05, | |
| "loss": 4.8535, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 7.832573685809785e-05, | |
| "loss": 4.8488, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 4.8011603355407715, | |
| "eval_runtime": 410.5634, | |
| "eval_samples_per_second": 41.465, | |
| "eval_steps_per_second": 5.183, | |
| "eval_wer": 0.8869696241498325, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 7.78193051757318e-05, | |
| "loss": 4.8533, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 7.731287349336574e-05, | |
| "loss": 4.8563, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 7.68064418109997e-05, | |
| "loss": 4.852, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 7.630001012863365e-05, | |
| "loss": 4.8502, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 7.57935784462676e-05, | |
| "loss": 4.829, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 4.784905910491943, | |
| "eval_runtime": 412.2149, | |
| "eval_samples_per_second": 41.299, | |
| "eval_steps_per_second": 5.162, | |
| "eval_wer": 0.8847121370768731, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 7.528714676390155e-05, | |
| "loss": 4.8315, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 7.478172794490024e-05, | |
| "loss": 4.8269, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 7.427529626253419e-05, | |
| "loss": 4.823, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 7.376886458016814e-05, | |
| "loss": 4.8282, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 7.32624328978021e-05, | |
| "loss": 4.8415, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 4.774867057800293, | |
| "eval_runtime": 411.0732, | |
| "eval_samples_per_second": 41.414, | |
| "eval_steps_per_second": 5.177, | |
| "eval_wer": 0.8846529427237791, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 7.275600121543604e-05, | |
| "loss": 4.827, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 7.225058239643473e-05, | |
| "loss": 4.8117, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 7.174415071406868e-05, | |
| "loss": 4.8178, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 7.123771903170264e-05, | |
| "loss": 4.8036, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 7.073128734933657e-05, | |
| "loss": 4.7941, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 4.765619277954102, | |
| "eval_runtime": 410.9966, | |
| "eval_samples_per_second": 41.421, | |
| "eval_steps_per_second": 5.178, | |
| "eval_wer": 0.8833543257678246, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 7.022586853033526e-05, | |
| "loss": 4.8074, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 6.971943684796922e-05, | |
| "loss": 4.8097, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 6.921401802896789e-05, | |
| "loss": 4.8156, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 6.870758634660185e-05, | |
| "loss": 4.7991, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 6.82011546642358e-05, | |
| "loss": 4.7913, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 4.773669719696045, | |
| "eval_runtime": 410.7775, | |
| "eval_samples_per_second": 41.443, | |
| "eval_steps_per_second": 5.18, | |
| "eval_wer": 0.8835782973378091, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 6.769472298186974e-05, | |
| "loss": 4.7988, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 6.71882912995037e-05, | |
| "loss": 4.7993, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 6.668185961713765e-05, | |
| "loss": 4.8082, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 6.617542793477161e-05, | |
| "loss": 4.797, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 6.566899625240556e-05, | |
| "loss": 4.7943, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 4.763143539428711, | |
| "eval_runtime": 411.3255, | |
| "eval_samples_per_second": 41.388, | |
| "eval_steps_per_second": 5.174, | |
| "eval_wer": 0.8824108749304336, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 6.51625645700395e-05, | |
| "loss": 4.7916, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 6.465613288767347e-05, | |
| "loss": 4.8082, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 6.414970120530741e-05, | |
| "loss": 4.7677, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 6.364326952294136e-05, | |
| "loss": 4.7947, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 6.313683784057532e-05, | |
| "loss": 4.7802, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 4.7554545402526855, | |
| "eval_runtime": 410.6533, | |
| "eval_samples_per_second": 41.456, | |
| "eval_steps_per_second": 5.182, | |
| "eval_wer": 0.8823350852509756, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 6.2631419021574e-05, | |
| "loss": 4.79, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 6.212498733920794e-05, | |
| "loss": 4.7812, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 6.161956852020663e-05, | |
| "loss": 4.7822, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 6.111313683784057e-05, | |
| "loss": 4.7653, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 6.060670515547453e-05, | |
| "loss": 4.7809, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": 4.742018222808838, | |
| "eval_runtime": 411.2108, | |
| "eval_samples_per_second": 41.4, | |
| "eval_steps_per_second": 5.175, | |
| "eval_wer": 0.8812212383066652, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 6.010027347310848e-05, | |
| "loss": 4.78, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 5.9593841790742435e-05, | |
| "loss": 4.7755, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 5.908741010837638e-05, | |
| "loss": 4.7692, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 5.8580978426010335e-05, | |
| "loss": 4.7752, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 5.807454674364429e-05, | |
| "loss": 4.7655, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 4.738577842712402, | |
| "eval_runtime": 410.9533, | |
| "eval_samples_per_second": 41.426, | |
| "eval_steps_per_second": 5.178, | |
| "eval_wer": 0.8806589572882034, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 5.7568115061278236e-05, | |
| "loss": 4.7728, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 5.706168337891219e-05, | |
| "loss": 4.7684, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 5.655525169654614e-05, | |
| "loss": 4.7651, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 5.604882001418009e-05, | |
| "loss": 4.7577, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 5.554238833181404e-05, | |
| "loss": 4.7753, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 4.731768608093262, | |
| "eval_runtime": 411.2946, | |
| "eval_samples_per_second": 41.391, | |
| "eval_steps_per_second": 5.174, | |
| "eval_wer": 0.880302876466612, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 5.5035956649448e-05, | |
| "loss": 4.7567, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5.4529524967081944e-05, | |
| "loss": 4.7649, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 5.40230932847159e-05, | |
| "loss": 4.7431, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 5.351666160234985e-05, | |
| "loss": 4.7517, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 5.3011242783348524e-05, | |
| "loss": 4.7622, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_loss": 4.7267656326293945, | |
| "eval_runtime": 410.5389, | |
| "eval_samples_per_second": 41.467, | |
| "eval_steps_per_second": 5.183, | |
| "eval_wer": 0.8803810182395704, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 5.250481110098248e-05, | |
| "loss": 4.7505, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 5.1998379418616425e-05, | |
| "loss": 4.7562, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 5.149194773625038e-05, | |
| "loss": 4.7565, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 5.0986528917249065e-05, | |
| "loss": 4.7486, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 5.048009723488302e-05, | |
| "loss": 4.7511, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 4.725167751312256, | |
| "eval_runtime": 411.131, | |
| "eval_samples_per_second": 41.408, | |
| "eval_steps_per_second": 5.176, | |
| "eval_wer": 0.8796747368301385, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 4.9973665552516966e-05, | |
| "loss": 4.7501, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 4.946723387015092e-05, | |
| "loss": 4.7481, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 4.896080218778487e-05, | |
| "loss": 4.7376, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.845538336878355e-05, | |
| "loss": 4.7516, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 4.7948951686417507e-05, | |
| "loss": 4.7508, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_loss": 4.714947700500488, | |
| "eval_runtime": 410.7042, | |
| "eval_samples_per_second": 41.451, | |
| "eval_steps_per_second": 5.181, | |
| "eval_wer": 0.878954342859704, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 4.744252000405145e-05, | |
| "loss": 4.7489, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 4.693608832168541e-05, | |
| "loss": 4.7324, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 4.643066950268409e-05, | |
| "loss": 4.7485, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 4.592423782031804e-05, | |
| "loss": 4.7337, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 4.541780613795199e-05, | |
| "loss": 4.7299, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_loss": 4.713499069213867, | |
| "eval_runtime": 410.0852, | |
| "eval_samples_per_second": 41.513, | |
| "eval_steps_per_second": 5.189, | |
| "eval_wer": 0.8791197734359003, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 4.4912387318950675e-05, | |
| "loss": 4.7385, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 4.440595563658463e-05, | |
| "loss": 4.7339, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 4.389952395421858e-05, | |
| "loss": 4.7351, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 4.339309227185253e-05, | |
| "loss": 4.7472, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 4.288666058948648e-05, | |
| "loss": 4.7382, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "eval_loss": 4.706689357757568, | |
| "eval_runtime": 411.4243, | |
| "eval_samples_per_second": 41.378, | |
| "eval_steps_per_second": 5.172, | |
| "eval_wer": 0.8785633726511897, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 4.2380228907120436e-05, | |
| "loss": 4.7372, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 4.187379722475438e-05, | |
| "loss": 4.7344, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 4.136736554238833e-05, | |
| "loss": 4.7225, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 4.086093386002228e-05, | |
| "loss": 4.7339, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 4.0354502177656236e-05, | |
| "loss": 4.723, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "eval_loss": 4.703372001647949, | |
| "eval_runtime": 411.6733, | |
| "eval_samples_per_second": 41.353, | |
| "eval_steps_per_second": 5.169, | |
| "eval_wer": 0.8783083011782551, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 3.984807049529018e-05, | |
| "loss": 4.7498, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.934163881292414e-05, | |
| "loss": 4.7296, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 3.8836219993922824e-05, | |
| "loss": 4.7201, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 3.832978831155678e-05, | |
| "loss": 4.7328, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 3.782436949255546e-05, | |
| "loss": 4.7321, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "eval_loss": 4.700106143951416, | |
| "eval_runtime": 411.0597, | |
| "eval_samples_per_second": 41.415, | |
| "eval_steps_per_second": 5.177, | |
| "eval_wer": 0.8781452226955593, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 3.7317937810189405e-05, | |
| "loss": 4.7226, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 3.681150612782336e-05, | |
| "loss": 4.7271, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 3.630507444545731e-05, | |
| "loss": 4.7245, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 3.579864276309126e-05, | |
| "loss": 4.717, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 3.529221108072521e-05, | |
| "loss": 4.7261, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "eval_loss": 4.695710182189941, | |
| "eval_runtime": 410.4939, | |
| "eval_samples_per_second": 41.472, | |
| "eval_steps_per_second": 5.184, | |
| "eval_wer": 0.8775924807229604, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 3.4785779398359166e-05, | |
| "loss": 4.7225, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 3.427934771599311e-05, | |
| "loss": 4.7112, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 3.3772916033627066e-05, | |
| "loss": 4.7178, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 3.326648435126102e-05, | |
| "loss": 4.7221, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 3.27610655322597e-05, | |
| "loss": 4.6915, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_loss": 4.690956115722656, | |
| "eval_runtime": 411.7522, | |
| "eval_samples_per_second": 41.345, | |
| "eval_steps_per_second": 5.168, | |
| "eval_wer": 0.8773312676725525, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 3.2254633849893653e-05, | |
| "loss": 4.7246, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 3.17482021675276e-05, | |
| "loss": 4.7043, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 3.1241770485161554e-05, | |
| "loss": 4.7311, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 3.073533880279551e-05, | |
| "loss": 4.7179, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 3.0228907120429458e-05, | |
| "loss": 4.7233, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_loss": 4.687117576599121, | |
| "eval_runtime": 411.0114, | |
| "eval_samples_per_second": 41.42, | |
| "eval_steps_per_second": 5.177, | |
| "eval_wer": 0.8769715280388493, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2.9723488301428138e-05, | |
| "loss": 4.7019, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 2.9217056619062088e-05, | |
| "loss": 4.7193, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 2.871062493669604e-05, | |
| "loss": 4.7011, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 2.8204193254329992e-05, | |
| "loss": 4.7246, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 2.769877443532868e-05, | |
| "loss": 4.7245, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "eval_loss": 4.684831619262695, | |
| "eval_runtime": 411.3597, | |
| "eval_samples_per_second": 41.385, | |
| "eval_steps_per_second": 5.173, | |
| "eval_wer": 0.8767522606558656, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.7192342752962626e-05, | |
| "loss": 4.7072, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 2.6685911070596576e-05, | |
| "loss": 4.7038, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.6179479388230526e-05, | |
| "loss": 4.7019, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 2.5674060569229213e-05, | |
| "loss": 4.7023, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2.5167628886863163e-05, | |
| "loss": 4.6995, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "eval_loss": 4.683341979980469, | |
| "eval_runtime": 411.2621, | |
| "eval_samples_per_second": 41.395, | |
| "eval_steps_per_second": 5.174, | |
| "eval_wer": 0.8766509899634863, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 2.4661197204497113e-05, | |
| "loss": 4.7139, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 2.4154765522131064e-05, | |
| "loss": 4.6981, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 2.3648333839765017e-05, | |
| "loss": 4.7053, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 2.31429150207637e-05, | |
| "loss": 4.7152, | |
| "step": 84500 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 2.263648333839765e-05, | |
| "loss": 4.7084, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "eval_loss": 4.678108215332031, | |
| "eval_runtime": 411.2113, | |
| "eval_samples_per_second": 41.4, | |
| "eval_steps_per_second": 5.175, | |
| "eval_wer": 0.8766087829523399, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 2.2130051656031605e-05, | |
| "loss": 4.6985, | |
| "step": 85500 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.1623619973665555e-05, | |
| "loss": 4.7024, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 2.1117188291299505e-05, | |
| "loss": 4.7015, | |
| "step": 86500 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 2.0611769472298185e-05, | |
| "loss": 4.6919, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 2.010533778993214e-05, | |
| "loss": 4.7115, | |
| "step": 87500 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "eval_loss": 4.676379680633545, | |
| "eval_runtime": 410.905, | |
| "eval_samples_per_second": 41.431, | |
| "eval_steps_per_second": 5.179, | |
| "eval_wer": 0.8762864154709211, | |
| "step": 87500 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 1.959890610756609e-05, | |
| "loss": 4.7144, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 1.9092474425200043e-05, | |
| "loss": 4.6893, | |
| "step": 88500 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 1.8587055606198726e-05, | |
| "loss": 4.6977, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 1.808163678719741e-05, | |
| "loss": 4.6987, | |
| "step": 89500 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 1.757520510483136e-05, | |
| "loss": 4.7072, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "eval_loss": 4.674571514129639, | |
| "eval_runtime": 410.8023, | |
| "eval_samples_per_second": 41.441, | |
| "eval_steps_per_second": 5.18, | |
| "eval_wer": 0.8756789219885069, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 1.706877342246531e-05, | |
| "loss": 4.7077, | |
| "step": 90500 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 1.656234174009926e-05, | |
| "loss": 4.7049, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 1.605591005773321e-05, | |
| "loss": 4.7023, | |
| "step": 91500 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 1.5549478375367164e-05, | |
| "loss": 4.695, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 1.5043046693001114e-05, | |
| "loss": 4.7036, | |
| "step": 92500 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "eval_loss": 4.672886848449707, | |
| "eval_runtime": 411.4353, | |
| "eval_samples_per_second": 41.377, | |
| "eval_steps_per_second": 5.172, | |
| "eval_wer": 0.8758804179983762, | |
| "step": 92500 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 1.4536615010635066e-05, | |
| "loss": 4.7079, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 1.4030183328269016e-05, | |
| "loss": 4.7002, | |
| "step": 93500 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 1.3523751645902968e-05, | |
| "loss": 4.6982, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 1.301731996353692e-05, | |
| "loss": 4.6883, | |
| "step": 94500 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 1.2511901144535604e-05, | |
| "loss": 4.6907, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "eval_loss": 4.670739650726318, | |
| "eval_runtime": 410.8726, | |
| "eval_samples_per_second": 41.434, | |
| "eval_steps_per_second": 5.179, | |
| "eval_wer": 0.8756105806051335, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 1.2005469462169554e-05, | |
| "loss": 4.7006, | |
| "step": 95500 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 1.1499037779803506e-05, | |
| "loss": 4.6984, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 1.0992606097437456e-05, | |
| "loss": 4.6942, | |
| "step": 96500 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 1.048718727843614e-05, | |
| "loss": 4.7016, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 9.98075559607009e-06, | |
| "loss": 4.681, | |
| "step": 97500 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "eval_loss": 4.668375492095947, | |
| "eval_runtime": 411.3728, | |
| "eval_samples_per_second": 41.383, | |
| "eval_steps_per_second": 5.173, | |
| "eval_wer": 0.875492453242668, | |
| "step": 97500 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 9.474323913704042e-06, | |
| "loss": 4.6988, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 8.967892231337994e-06, | |
| "loss": 4.7063, | |
| "step": 98500 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 8.462473412336676e-06, | |
| "loss": 4.689, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 7.956041729970628e-06, | |
| "loss": 4.6833, | |
| "step": 99500 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 7.449610047604579e-06, | |
| "loss": 4.6905, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_loss": 4.668146133422852, | |
| "eval_runtime": 410.5824, | |
| "eval_samples_per_second": 41.463, | |
| "eval_steps_per_second": 5.183, | |
| "eval_wer": 0.8755806567489337, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 6.94317836523853e-06, | |
| "loss": 4.6848, | |
| "step": 100500 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 6.4367466828724815e-06, | |
| "loss": 4.6882, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 5.930315000506432e-06, | |
| "loss": 4.6821, | |
| "step": 101500 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 5.4238833181403835e-06, | |
| "loss": 4.6908, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 4.917451635774335e-06, | |
| "loss": 4.6975, | |
| "step": 102500 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "eval_loss": 4.664699554443359, | |
| "eval_runtime": 411.5323, | |
| "eval_samples_per_second": 41.367, | |
| "eval_steps_per_second": 5.171, | |
| "eval_wer": 0.8751601546998029, | |
| "step": 102500 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 4.411019953408286e-06, | |
| "loss": 4.6878, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 3.9056011344069684e-06, | |
| "loss": 4.6829, | |
| "step": 103500 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 3.400182315405652e-06, | |
| "loss": 4.6882, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 2.893750633039603e-06, | |
| "loss": 4.6905, | |
| "step": 104500 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 2.387318950673554e-06, | |
| "loss": 4.6849, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "eval_loss": 4.664451599121094, | |
| "eval_runtime": 411.3214, | |
| "eval_samples_per_second": 41.389, | |
| "eval_steps_per_second": 5.174, | |
| "eval_wer": 0.8751350657024651, | |
| "step": 105000 | |
| } | |
| ], | |
| "max_steps": 107316, | |
| "num_train_epochs": 2, | |
| "total_flos": 1.0233532461203251e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |