| { | |
| "best_metric": 0.46736299991607666, | |
| "best_model_checkpoint": "/scratch/skscla001/speech/results/whisper-medium-swagen-combined-10hrs-model/checkpoint-1600", | |
| "epoch": 2.6247391952309984, | |
| "eval_steps": 200, | |
| "global_step": 2200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.029806259314456036, | |
| "grad_norm": 139.82965087890625, | |
| "learning_rate": 4.0000000000000003e-07, | |
| "loss": 10.6377, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05961251862891207, | |
| "grad_norm": 98.2421646118164, | |
| "learning_rate": 8.8e-07, | |
| "loss": 8.4119, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08941877794336811, | |
| "grad_norm": 64.38908386230469, | |
| "learning_rate": 1.3800000000000001e-06, | |
| "loss": 5.9129, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.11922503725782414, | |
| "grad_norm": 71.607421875, | |
| "learning_rate": 1.8800000000000002e-06, | |
| "loss": 4.4812, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14903129657228018, | |
| "grad_norm": 61.29523468017578, | |
| "learning_rate": 2.38e-06, | |
| "loss": 3.4448, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.17883755588673622, | |
| "grad_norm": 65.6143798828125, | |
| "learning_rate": 2.88e-06, | |
| "loss": 3.1512, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.20864381520119224, | |
| "grad_norm": 64.80217742919922, | |
| "learning_rate": 3.3800000000000007e-06, | |
| "loss": 3.125, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.23845007451564829, | |
| "grad_norm": 57.09419631958008, | |
| "learning_rate": 3.88e-06, | |
| "loss": 2.6418, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.23845007451564829, | |
| "eval_loss": 0.8311507105827332, | |
| "eval_runtime": 571.9983, | |
| "eval_samples_per_second": 1.984, | |
| "eval_steps_per_second": 0.993, | |
| "eval_wer": 0.48349360563101024, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.26825633383010433, | |
| "grad_norm": 53.5373649597168, | |
| "learning_rate": 4.38e-06, | |
| "loss": 2.559, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.29806259314456035, | |
| "grad_norm": 71.17430114746094, | |
| "learning_rate": 4.880000000000001e-06, | |
| "loss": 2.5908, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.32786885245901637, | |
| "grad_norm": 46.32373809814453, | |
| "learning_rate": 5.380000000000001e-06, | |
| "loss": 2.1127, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.35767511177347244, | |
| "grad_norm": 58.01958084106445, | |
| "learning_rate": 5.8800000000000005e-06, | |
| "loss": 2.2759, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.38748137108792846, | |
| "grad_norm": 68.27952575683594, | |
| "learning_rate": 6.380000000000001e-06, | |
| "loss": 2.2239, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.4172876304023845, | |
| "grad_norm": 57.420711517333984, | |
| "learning_rate": 6.88e-06, | |
| "loss": 1.9789, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.44709388971684055, | |
| "grad_norm": 56.379539489746094, | |
| "learning_rate": 7.3800000000000005e-06, | |
| "loss": 2.0375, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.47690014903129657, | |
| "grad_norm": 65.61225128173828, | |
| "learning_rate": 7.88e-06, | |
| "loss": 1.9381, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.47690014903129657, | |
| "eval_loss": 0.6573777794837952, | |
| "eval_runtime": 571.3807, | |
| "eval_samples_per_second": 1.986, | |
| "eval_steps_per_second": 0.994, | |
| "eval_wer": 0.40497670268662633, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.5067064083457526, | |
| "grad_norm": 49.37194061279297, | |
| "learning_rate": 8.380000000000001e-06, | |
| "loss": 2.0002, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.5365126676602087, | |
| "grad_norm": 55.09164810180664, | |
| "learning_rate": 8.880000000000001e-06, | |
| "loss": 1.9199, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.5663189269746647, | |
| "grad_norm": 46.766258239746094, | |
| "learning_rate": 9.38e-06, | |
| "loss": 1.9346, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.5961251862891207, | |
| "grad_norm": 66.73670196533203, | |
| "learning_rate": 9.88e-06, | |
| "loss": 1.8662, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.6259314456035767, | |
| "grad_norm": 64.63770294189453, | |
| "learning_rate": 9.992288961038962e-06, | |
| "loss": 1.8393, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.6557377049180327, | |
| "grad_norm": 59.25200271606445, | |
| "learning_rate": 9.982142857142858e-06, | |
| "loss": 1.6775, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.6855439642324889, | |
| "grad_norm": 43.544105529785156, | |
| "learning_rate": 9.971996753246755e-06, | |
| "loss": 1.6314, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.7153502235469449, | |
| "grad_norm": 37.862571716308594, | |
| "learning_rate": 9.96185064935065e-06, | |
| "loss": 1.7528, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.7153502235469449, | |
| "eval_loss": 0.5705794095993042, | |
| "eval_runtime": 573.4955, | |
| "eval_samples_per_second": 1.979, | |
| "eval_steps_per_second": 0.99, | |
| "eval_wer": 0.35451571329433923, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.7451564828614009, | |
| "grad_norm": 80.73561096191406, | |
| "learning_rate": 9.951704545454546e-06, | |
| "loss": 1.7955, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.7749627421758569, | |
| "grad_norm": 59.763912200927734, | |
| "learning_rate": 9.941558441558441e-06, | |
| "loss": 1.5321, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.8047690014903129, | |
| "grad_norm": 40.65838623046875, | |
| "learning_rate": 9.931412337662338e-06, | |
| "loss": 1.745, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.834575260804769, | |
| "grad_norm": 38.0390625, | |
| "learning_rate": 9.921266233766234e-06, | |
| "loss": 1.5962, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.8643815201192251, | |
| "grad_norm": 65.32721710205078, | |
| "learning_rate": 9.911120129870131e-06, | |
| "loss": 1.8341, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.8941877794336811, | |
| "grad_norm": 59.77840805053711, | |
| "learning_rate": 9.900974025974028e-06, | |
| "loss": 1.7181, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.9239940387481371, | |
| "grad_norm": 53.4656867980957, | |
| "learning_rate": 9.890827922077922e-06, | |
| "loss": 1.568, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.9538002980625931, | |
| "grad_norm": 69.80867767333984, | |
| "learning_rate": 9.880681818181819e-06, | |
| "loss": 1.7421, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.9538002980625931, | |
| "eval_loss": 0.5140205025672913, | |
| "eval_runtime": 584.6629, | |
| "eval_samples_per_second": 1.941, | |
| "eval_steps_per_second": 0.971, | |
| "eval_wer": 0.3503519381381977, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.9836065573770492, | |
| "grad_norm": 58.31004333496094, | |
| "learning_rate": 9.870535714285716e-06, | |
| "loss": 1.4786, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 1.0143070044709388, | |
| "grad_norm": 26.68948745727539, | |
| "learning_rate": 9.86038961038961e-06, | |
| "loss": 1.3642, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.044113263785395, | |
| "grad_norm": 25.357746124267578, | |
| "learning_rate": 9.850243506493507e-06, | |
| "loss": 0.9665, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 1.073919523099851, | |
| "grad_norm": 25.640474319458008, | |
| "learning_rate": 9.840097402597404e-06, | |
| "loss": 0.9145, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.103725782414307, | |
| "grad_norm": 39.184608459472656, | |
| "learning_rate": 9.829951298701298e-06, | |
| "loss": 0.8596, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 1.133532041728763, | |
| "grad_norm": 25.94022560119629, | |
| "learning_rate": 9.819805194805195e-06, | |
| "loss": 0.8788, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.163338301043219, | |
| "grad_norm": 21.88936996459961, | |
| "learning_rate": 9.809659090909092e-06, | |
| "loss": 0.8949, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 1.1931445603576751, | |
| "grad_norm": 34.77507400512695, | |
| "learning_rate": 9.799512987012988e-06, | |
| "loss": 0.9259, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.1931445603576751, | |
| "eval_loss": 0.5174579620361328, | |
| "eval_runtime": 573.7506, | |
| "eval_samples_per_second": 1.978, | |
| "eval_steps_per_second": 0.99, | |
| "eval_wer": 0.32616238723108953, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.222950819672131, | |
| "grad_norm": 32.29697799682617, | |
| "learning_rate": 9.789366883116885e-06, | |
| "loss": 0.776, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 1.2527570789865872, | |
| "grad_norm": 22.945188522338867, | |
| "learning_rate": 9.779220779220781e-06, | |
| "loss": 0.8614, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.2825633383010433, | |
| "grad_norm": 29.45697593688965, | |
| "learning_rate": 9.769074675324676e-06, | |
| "loss": 0.9076, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 1.3123695976154992, | |
| "grad_norm": 21.750009536743164, | |
| "learning_rate": 9.758928571428573e-06, | |
| "loss": 0.8417, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.3421758569299553, | |
| "grad_norm": 23.066518783569336, | |
| "learning_rate": 9.748782467532468e-06, | |
| "loss": 0.8405, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 1.3719821162444115, | |
| "grad_norm": 47.0228157043457, | |
| "learning_rate": 9.738636363636364e-06, | |
| "loss": 0.9124, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.4017883755588674, | |
| "grad_norm": 41.16919708251953, | |
| "learning_rate": 9.72849025974026e-06, | |
| "loss": 0.8915, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 1.4315946348733233, | |
| "grad_norm": 24.697216033935547, | |
| "learning_rate": 9.718344155844157e-06, | |
| "loss": 0.8254, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.4315946348733233, | |
| "eval_loss": 0.4977598488330841, | |
| "eval_runtime": 571.6911, | |
| "eval_samples_per_second": 1.985, | |
| "eval_steps_per_second": 0.994, | |
| "eval_wer": 0.3096064241102409, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.4614008941877794, | |
| "grad_norm": 27.103702545166016, | |
| "learning_rate": 9.708198051948052e-06, | |
| "loss": 0.8325, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 1.4912071535022355, | |
| "grad_norm": 37.062477111816406, | |
| "learning_rate": 9.698051948051949e-06, | |
| "loss": 0.9808, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.5210134128166914, | |
| "grad_norm": 29.10225486755371, | |
| "learning_rate": 9.687905844155845e-06, | |
| "loss": 0.8731, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 1.5508196721311476, | |
| "grad_norm": 33.52768325805664, | |
| "learning_rate": 9.677759740259742e-06, | |
| "loss": 0.8828, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.5806259314456037, | |
| "grad_norm": 27.66816520690918, | |
| "learning_rate": 9.667613636363637e-06, | |
| "loss": 0.9907, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 1.6104321907600596, | |
| "grad_norm": 41.44624710083008, | |
| "learning_rate": 9.657467532467533e-06, | |
| "loss": 0.8091, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.6402384500745155, | |
| "grad_norm": 39.36080551147461, | |
| "learning_rate": 9.64732142857143e-06, | |
| "loss": 0.9308, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 1.6700447093889716, | |
| "grad_norm": 47.41120147705078, | |
| "learning_rate": 9.637175324675325e-06, | |
| "loss": 0.9616, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.6700447093889716, | |
| "eval_loss": 0.4754635989665985, | |
| "eval_runtime": 570.3412, | |
| "eval_samples_per_second": 1.99, | |
| "eval_steps_per_second": 0.996, | |
| "eval_wer": 0.2998909487459106, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.6998509687034278, | |
| "grad_norm": 43.4237174987793, | |
| "learning_rate": 9.627029220779221e-06, | |
| "loss": 0.7285, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 1.7296572280178837, | |
| "grad_norm": 30.96293830871582, | |
| "learning_rate": 9.616883116883118e-06, | |
| "loss": 0.8987, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.7594634873323398, | |
| "grad_norm": 35.58831787109375, | |
| "learning_rate": 9.606737012987014e-06, | |
| "loss": 0.9382, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 1.789269746646796, | |
| "grad_norm": 25.283161163330078, | |
| "learning_rate": 9.596590909090911e-06, | |
| "loss": 0.7889, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.8190760059612519, | |
| "grad_norm": 25.010147094726562, | |
| "learning_rate": 9.586444805194806e-06, | |
| "loss": 0.886, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 1.8488822652757078, | |
| "grad_norm": 37.391361236572266, | |
| "learning_rate": 9.576298701298702e-06, | |
| "loss": 0.7991, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.8786885245901639, | |
| "grad_norm": 41.15829086303711, | |
| "learning_rate": 9.566152597402599e-06, | |
| "loss": 0.7902, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 1.90849478390462, | |
| "grad_norm": 33.89030838012695, | |
| "learning_rate": 9.556006493506494e-06, | |
| "loss": 0.7893, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.90849478390462, | |
| "eval_loss": 0.46736299991607666, | |
| "eval_runtime": 576.0496, | |
| "eval_samples_per_second": 1.97, | |
| "eval_steps_per_second": 0.986, | |
| "eval_wer": 0.3075245365321701, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.938301043219076, | |
| "grad_norm": 35.02192687988281, | |
| "learning_rate": 9.54586038961039e-06, | |
| "loss": 0.94, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 1.968107302533532, | |
| "grad_norm": 21.93513298034668, | |
| "learning_rate": 9.535714285714287e-06, | |
| "loss": 0.8729, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.9979135618479882, | |
| "grad_norm": 30.547515869140625, | |
| "learning_rate": 9.525568181818182e-06, | |
| "loss": 0.7377, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 2.0286140089418776, | |
| "grad_norm": 18.494037628173828, | |
| "learning_rate": 9.515422077922078e-06, | |
| "loss": 0.339, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.058420268256334, | |
| "grad_norm": 27.289072036743164, | |
| "learning_rate": 9.505275974025975e-06, | |
| "loss": 0.393, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 2.08822652757079, | |
| "grad_norm": 20.814571380615234, | |
| "learning_rate": 9.495129870129871e-06, | |
| "loss": 0.3645, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 2.1180327868852458, | |
| "grad_norm": 14.510347366333008, | |
| "learning_rate": 9.484983766233768e-06, | |
| "loss": 0.3043, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 2.147839046199702, | |
| "grad_norm": 30.937259674072266, | |
| "learning_rate": 9.474837662337663e-06, | |
| "loss": 0.3547, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.147839046199702, | |
| "eval_loss": 0.48483970761299133, | |
| "eval_runtime": 577.3872, | |
| "eval_samples_per_second": 1.966, | |
| "eval_steps_per_second": 0.984, | |
| "eval_wer": 0.3157529493407356, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.177645305514158, | |
| "grad_norm": 32.33222579956055, | |
| "learning_rate": 9.46469155844156e-06, | |
| "loss": 0.3615, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 2.207451564828614, | |
| "grad_norm": 19.55378532409668, | |
| "learning_rate": 9.454545454545456e-06, | |
| "loss": 0.4072, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 2.23725782414307, | |
| "grad_norm": 31.809528350830078, | |
| "learning_rate": 9.44439935064935e-06, | |
| "loss": 0.3636, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 2.267064083457526, | |
| "grad_norm": 16.221904754638672, | |
| "learning_rate": 9.434253246753247e-06, | |
| "loss": 0.3927, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.296870342771982, | |
| "grad_norm": 23.400074005126953, | |
| "learning_rate": 9.424107142857144e-06, | |
| "loss": 0.267, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 2.326676602086438, | |
| "grad_norm": 19.966495513916016, | |
| "learning_rate": 9.413961038961039e-06, | |
| "loss": 0.3991, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 2.3564828614008944, | |
| "grad_norm": 23.508337020874023, | |
| "learning_rate": 9.403814935064935e-06, | |
| "loss": 0.3535, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 2.3862891207153503, | |
| "grad_norm": 39.417266845703125, | |
| "learning_rate": 9.393668831168832e-06, | |
| "loss": 0.3568, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.3862891207153503, | |
| "eval_loss": 0.4912998676300049, | |
| "eval_runtime": 564.2324, | |
| "eval_samples_per_second": 2.012, | |
| "eval_steps_per_second": 1.007, | |
| "eval_wer": 0.26162387231089523, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.416095380029806, | |
| "grad_norm": 25.93727684020996, | |
| "learning_rate": 9.383522727272729e-06, | |
| "loss": 0.3906, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 2.445901639344262, | |
| "grad_norm": 22.80946159362793, | |
| "learning_rate": 9.373376623376625e-06, | |
| "loss": 0.3112, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 2.4757078986587184, | |
| "grad_norm": 9.392194747924805, | |
| "learning_rate": 9.36323051948052e-06, | |
| "loss": 0.3682, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 2.5055141579731743, | |
| "grad_norm": 21.888240814208984, | |
| "learning_rate": 9.353084415584416e-06, | |
| "loss": 0.3414, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.5353204172876302, | |
| "grad_norm": 17.335634231567383, | |
| "learning_rate": 9.342938311688311e-06, | |
| "loss": 0.3824, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 2.5651266766020866, | |
| "grad_norm": 37.35403060913086, | |
| "learning_rate": 9.332792207792208e-06, | |
| "loss": 0.3799, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 2.5949329359165425, | |
| "grad_norm": 15.803303718566895, | |
| "learning_rate": 9.322646103896104e-06, | |
| "loss": 0.39, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 2.6247391952309984, | |
| "grad_norm": 21.457035064697266, | |
| "learning_rate": 9.312500000000001e-06, | |
| "loss": 0.3759, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.6247391952309984, | |
| "eval_loss": 0.4685392677783966, | |
| "eval_runtime": 585.3696, | |
| "eval_samples_per_second": 1.939, | |
| "eval_steps_per_second": 0.97, | |
| "eval_wer": 0.3103995241399822, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.6247391952309984, | |
| "step": 2200, | |
| "total_flos": 1.797081121161216e+19, | |
| "train_loss": 1.4413999737392773, | |
| "train_runtime": 10621.5138, | |
| "train_samples_per_second": 18.952, | |
| "train_steps_per_second": 2.367 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 25140, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 3 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.797081121161216e+19, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |