| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.999924294041941, | |
| "global_step": 33020, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 3.7125e-06, | |
| "loss": 22.2535, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 7.3875e-06, | |
| "loss": 17.5428, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.1137499999999998e-05, | |
| "loss": 9.7898, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.48875e-05, | |
| "loss": 7.271, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.86375e-05, | |
| "loss": 5.6047, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 2.23875e-05, | |
| "loss": 4.2271, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 2.6137499999999995e-05, | |
| "loss": 3.3721, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 2.9887499999999998e-05, | |
| "loss": 3.0444, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 3.36375e-05, | |
| "loss": 2.9811, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 3.7387499999999994e-05, | |
| "loss": 2.953, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 2.952834129333496, | |
| "eval_runtime": 979.2557, | |
| "eval_samples_per_second": 15.663, | |
| "eval_steps_per_second": 1.959, | |
| "eval_wer": 1.0, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.11375e-05, | |
| "loss": 2.9074, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.48875e-05, | |
| "loss": 2.8727, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.8637499999999996e-05, | |
| "loss": 2.8468, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 5.23875e-05, | |
| "loss": 2.8201, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 5.61375e-05, | |
| "loss": 2.3465, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 5.988749999999999e-05, | |
| "loss": 1.6159, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 6.36375e-05, | |
| "loss": 1.3589, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 6.738749999999999e-05, | |
| "loss": 1.2695, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 7.11375e-05, | |
| "loss": 1.2131, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.48875e-05, | |
| "loss": 1.1519, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 0.37347257137298584, | |
| "eval_runtime": 874.3903, | |
| "eval_samples_per_second": 17.541, | |
| "eval_steps_per_second": 2.194, | |
| "eval_wer": 1.0356840848981355, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 7.47654738878143e-05, | |
| "loss": 1.1403, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 7.452369439071565e-05, | |
| "loss": 1.1051, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 7.428191489361702e-05, | |
| "loss": 1.0997, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 7.404013539651837e-05, | |
| "loss": 1.0567, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 7.379835589941972e-05, | |
| "loss": 1.0623, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 7.355657640232107e-05, | |
| "loss": 1.052, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 7.331479690522243e-05, | |
| "loss": 1.0404, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 7.307301740812378e-05, | |
| "loss": 1.0313, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 7.283123791102513e-05, | |
| "loss": 1.0236, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 7.25894584139265e-05, | |
| "loss": 1.0278, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 0.25289738178253174, | |
| "eval_runtime": 871.8162, | |
| "eval_samples_per_second": 17.593, | |
| "eval_steps_per_second": 2.2, | |
| "eval_wer": 1.0390485843313881, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 7.234767891682784e-05, | |
| "loss": 1.0165, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 7.21058994197292e-05, | |
| "loss": 0.9993, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 7.186411992263056e-05, | |
| "loss": 1.0003, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 7.162234042553191e-05, | |
| "loss": 0.9998, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 7.138056092843326e-05, | |
| "loss": 0.9991, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 7.11387814313346e-05, | |
| "loss": 0.996, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 7.089700193423597e-05, | |
| "loss": 0.9827, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 7.065522243713732e-05, | |
| "loss": 0.9728, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 7.041344294003867e-05, | |
| "loss": 0.9853, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 7.017166344294003e-05, | |
| "loss": 0.9922, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 0.22080540657043457, | |
| "eval_runtime": 883.0519, | |
| "eval_samples_per_second": 17.369, | |
| "eval_steps_per_second": 2.172, | |
| "eval_wer": 1.0269999580187237, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 6.992988394584138e-05, | |
| "loss": 0.9785, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 6.969052224371373e-05, | |
| "loss": 0.9838, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 6.945116054158607e-05, | |
| "loss": 0.9724, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 6.920938104448742e-05, | |
| "loss": 0.9681, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 6.896760154738877e-05, | |
| "loss": 0.9702, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 6.872582205029013e-05, | |
| "loss": 0.9697, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 6.848404255319148e-05, | |
| "loss": 0.9667, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 6.824226305609283e-05, | |
| "loss": 0.9594, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 6.80004835589942e-05, | |
| "loss": 0.9708, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 6.775870406189555e-05, | |
| "loss": 0.9618, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 0.2088283896446228, | |
| "eval_runtime": 929.9712, | |
| "eval_samples_per_second": 16.493, | |
| "eval_steps_per_second": 2.062, | |
| "eval_wer": 1.0294408693722599, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 6.75169245647969e-05, | |
| "loss": 0.9612, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 6.727514506769825e-05, | |
| "loss": 0.9555, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 6.703336557059961e-05, | |
| "loss": 0.9627, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 6.679158607350096e-05, | |
| "loss": 0.9436, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 6.654980657640231e-05, | |
| "loss": 0.9513, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 6.630802707930367e-05, | |
| "loss": 0.9369, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 6.606624758220502e-05, | |
| "loss": 0.9416, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 6.582446808510637e-05, | |
| "loss": 0.9395, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 6.558268858800774e-05, | |
| "loss": 0.9404, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 6.534090909090909e-05, | |
| "loss": 0.9364, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_loss": 0.20186825096607208, | |
| "eval_runtime": 905.9024, | |
| "eval_samples_per_second": 16.931, | |
| "eval_steps_per_second": 2.117, | |
| "eval_wer": 1.0214284429144602, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 6.510154738878142e-05, | |
| "loss": 0.9527, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 6.485976789168277e-05, | |
| "loss": 0.9364, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 6.461798839458414e-05, | |
| "loss": 0.9217, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 6.437620889748549e-05, | |
| "loss": 0.932, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 6.413442940038684e-05, | |
| "loss": 0.933, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 6.38926499032882e-05, | |
| "loss": 0.9221, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 6.365087040618955e-05, | |
| "loss": 0.9223, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 6.34090909090909e-05, | |
| "loss": 0.9487, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 6.316731141199225e-05, | |
| "loss": 0.9172, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 6.292553191489361e-05, | |
| "loss": 0.9179, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_loss": 0.1940060555934906, | |
| "eval_runtime": 902.7884, | |
| "eval_samples_per_second": 16.99, | |
| "eval_steps_per_second": 2.125, | |
| "eval_wer": 1.0293808961203303, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 6.268375241779496e-05, | |
| "loss": 0.9202, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 6.244197292069631e-05, | |
| "loss": 0.9169, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 6.220019342359768e-05, | |
| "loss": 0.9228, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 6.195841392649903e-05, | |
| "loss": 0.9258, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 6.171663442940038e-05, | |
| "loss": 0.9149, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 6.147485493230173e-05, | |
| "loss": 0.918, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 6.123307543520309e-05, | |
| "loss": 0.9143, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 6.0991295938104445e-05, | |
| "loss": 0.9113, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 6.0749516441005795e-05, | |
| "loss": 0.9096, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 6.050773694390715e-05, | |
| "loss": 0.9154, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "eval_loss": 0.19150236248970032, | |
| "eval_runtime": 894.343, | |
| "eval_samples_per_second": 17.15, | |
| "eval_steps_per_second": 2.145, | |
| "eval_wer": 1.0289550860316299, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 6.02659574468085e-05, | |
| "loss": 0.9217, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 6.0026595744680845e-05, | |
| "loss": 0.9124, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 5.9784816247582195e-05, | |
| "loss": 0.9141, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 5.954303675048355e-05, | |
| "loss": 0.918, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 5.930125725338491e-05, | |
| "loss": 0.9124, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 5.905947775628626e-05, | |
| "loss": 0.9222, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 5.8817698259187615e-05, | |
| "loss": 0.922, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 5.857591876208897e-05, | |
| "loss": 0.9058, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 5.833413926499032e-05, | |
| "loss": 0.9119, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 5.809235976789167e-05, | |
| "loss": 0.8985, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_loss": 0.183705136179924, | |
| "eval_runtime": 937.6258, | |
| "eval_samples_per_second": 16.358, | |
| "eval_steps_per_second": 2.046, | |
| "eval_wer": 1.021140571305198, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 5.7850580270793035e-05, | |
| "loss": 0.9041, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 5.7608800773694385e-05, | |
| "loss": 0.9022, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 5.7367021276595735e-05, | |
| "loss": 0.9014, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 5.71252417794971e-05, | |
| "loss": 0.9027, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 5.688346228239845e-05, | |
| "loss": 0.9067, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 5.66416827852998e-05, | |
| "loss": 0.8946, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 5.639990328820116e-05, | |
| "loss": 0.9072, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 5.615812379110251e-05, | |
| "loss": 0.8864, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 5.591634429400386e-05, | |
| "loss": 0.8944, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 5.5674564796905224e-05, | |
| "loss": 0.9055, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "eval_loss": 0.18378125131130219, | |
| "eval_runtime": 924.9923, | |
| "eval_samples_per_second": 16.582, | |
| "eval_steps_per_second": 2.074, | |
| "eval_wer": 1.0273238135791436, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 5.5432785299806574e-05, | |
| "loss": 0.8932, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 5.5191005802707924e-05, | |
| "loss": 0.8901, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 5.4949226305609274e-05, | |
| "loss": 0.8998, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 5.470744680851064e-05, | |
| "loss": 0.8948, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 5.446566731141199e-05, | |
| "loss": 0.8939, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 5.422630560928433e-05, | |
| "loss": 0.9019, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 5.398452611218568e-05, | |
| "loss": 0.8983, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 5.374274661508704e-05, | |
| "loss": 0.895, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 5.3500967117988394e-05, | |
| "loss": 0.9034, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 5.3259187620889744e-05, | |
| "loss": 0.8861, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "eval_loss": 0.1764763593673706, | |
| "eval_runtime": 887.0032, | |
| "eval_samples_per_second": 17.292, | |
| "eval_steps_per_second": 2.162, | |
| "eval_wer": 1.0139437810736411, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 5.3017408123791094e-05, | |
| "loss": 0.8978, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 5.277562862669245e-05, | |
| "loss": 0.8872, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 5.253384912959381e-05, | |
| "loss": 0.8726, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 5.229206963249516e-05, | |
| "loss": 0.8981, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 5.2050290135396514e-05, | |
| "loss": 0.8895, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 5.180851063829787e-05, | |
| "loss": 0.8889, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 5.156914893617021e-05, | |
| "loss": 0.8842, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 5.1327369439071564e-05, | |
| "loss": 0.9052, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 5.1085589941972914e-05, | |
| "loss": 0.8766, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 5.084381044487427e-05, | |
| "loss": 0.892, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "eval_loss": 0.1722782850265503, | |
| "eval_runtime": 927.8575, | |
| "eval_samples_per_second": 16.531, | |
| "eval_steps_per_second": 2.067, | |
| "eval_wer": 1.0188016144799419, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 5.060203094777562e-05, | |
| "loss": 0.8642, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 5.036025145067698e-05, | |
| "loss": 0.8778, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 5.0118471953578334e-05, | |
| "loss": 0.8669, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 4.9876692456479684e-05, | |
| "loss": 0.8754, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 4.963491295938104e-05, | |
| "loss": 0.877, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 4.93931334622824e-05, | |
| "loss": 0.8669, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 4.915135396518375e-05, | |
| "loss": 0.8775, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 4.891199226305609e-05, | |
| "loss": 0.8587, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 4.867021276595744e-05, | |
| "loss": 0.8669, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 4.842843326885879e-05, | |
| "loss": 0.8778, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_loss": 0.17346103489398956, | |
| "eval_runtime": 930.0275, | |
| "eval_samples_per_second": 16.492, | |
| "eval_steps_per_second": 2.062, | |
| "eval_wer": 1.009175907545235, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 4.8186653771760154e-05, | |
| "loss": 0.8637, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 4.7944874274661503e-05, | |
| "loss": 0.8678, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 4.770309477756285e-05, | |
| "loss": 0.8722, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 4.746131528046422e-05, | |
| "loss": 0.8751, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 4.7219535783365567e-05, | |
| "loss": 0.869, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 4.6977756286266916e-05, | |
| "loss": 0.8599, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 4.673597678916828e-05, | |
| "loss": 0.8378, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 4.649419729206963e-05, | |
| "loss": 0.8585, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 4.625241779497098e-05, | |
| "loss": 0.8586, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 4.601063829787234e-05, | |
| "loss": 0.8645, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "eval_loss": 0.1707320660352707, | |
| "eval_runtime": 915.8262, | |
| "eval_samples_per_second": 16.748, | |
| "eval_steps_per_second": 2.094, | |
| "eval_wer": 1.0106152655915461, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 4.576885880077369e-05, | |
| "loss": 0.8641, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 4.552707930367504e-05, | |
| "loss": 0.8644, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 4.528529980657639e-05, | |
| "loss": 0.8576, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 4.5043520309477756e-05, | |
| "loss": 0.8666, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 4.4801740812379106e-05, | |
| "loss": 0.8572, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 4.4559961315280456e-05, | |
| "loss": 0.8563, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 4.431818181818182e-05, | |
| "loss": 0.8619, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 4.407640232108317e-05, | |
| "loss": 0.8558, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 4.383462282398452e-05, | |
| "loss": 0.8464, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 4.3592843326885876e-05, | |
| "loss": 0.8595, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_loss": 0.17129956185817719, | |
| "eval_runtime": 921.8678, | |
| "eval_samples_per_second": 16.638, | |
| "eval_steps_per_second": 2.081, | |
| "eval_wer": 1.0186396866997318, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 4.335106382978723e-05, | |
| "loss": 0.8532, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 4.310928433268858e-05, | |
| "loss": 0.8375, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 4.286750483558994e-05, | |
| "loss": 0.8668, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 4.2625725338491295e-05, | |
| "loss": 0.8432, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 4.2383945841392645e-05, | |
| "loss": 0.8558, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 4.2142166344294e-05, | |
| "loss": 0.8537, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 4.190038684719536e-05, | |
| "loss": 0.8513, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 4.165860735009671e-05, | |
| "loss": 0.8463, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 4.1416827852998065e-05, | |
| "loss": 0.8581, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 4.1175048355899415e-05, | |
| "loss": 0.8392, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "eval_loss": 0.16857005655765533, | |
| "eval_runtime": 943.014, | |
| "eval_samples_per_second": 16.265, | |
| "eval_steps_per_second": 2.034, | |
| "eval_wer": 1.0052896408201941, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 4.093326885880077e-05, | |
| "loss": 0.8484, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 4.069148936170212e-05, | |
| "loss": 0.8396, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 4.044970986460348e-05, | |
| "loss": 0.8434, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 4.0207930367504835e-05, | |
| "loss": 0.8524, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 3.9966150870406185e-05, | |
| "loss": 0.8504, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 3.972437137330754e-05, | |
| "loss": 0.8341, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 3.948259187620889e-05, | |
| "loss": 0.8543, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 3.924081237911025e-05, | |
| "loss": 0.8576, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 3.8999032882011604e-05, | |
| "loss": 0.858, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 3.8757253384912954e-05, | |
| "loss": 0.8436, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "eval_loss": 0.16531197726726532, | |
| "eval_runtime": 883.362, | |
| "eval_samples_per_second": 17.363, | |
| "eval_steps_per_second": 2.171, | |
| "eval_wer": 1.0095837256583564, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 3.851547388781431e-05, | |
| "loss": 0.8625, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 3.827369439071567e-05, | |
| "loss": 0.8464, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 3.803191489361702e-05, | |
| "loss": 0.862, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 3.779013539651837e-05, | |
| "loss": 0.8395, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 3.754835589941973e-05, | |
| "loss": 0.8468, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 3.730657640232108e-05, | |
| "loss": 0.8414, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 3.706479690522243e-05, | |
| "loss": 0.8306, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 3.682301740812379e-05, | |
| "loss": 0.8468, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 3.6581237911025144e-05, | |
| "loss": 0.8343, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 3.6339458413926494e-05, | |
| "loss": 0.8405, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "eval_loss": 0.16894429922103882, | |
| "eval_runtime": 898.2427, | |
| "eval_samples_per_second": 17.076, | |
| "eval_steps_per_second": 2.135, | |
| "eval_wer": 1.0077125601981516, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 3.609767891682785e-05, | |
| "loss": 0.8311, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 3.58558994197292e-05, | |
| "loss": 0.8378, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 3.561411992263056e-05, | |
| "loss": 0.8445, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 3.5372340425531914e-05, | |
| "loss": 0.8414, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 3.5130560928433263e-05, | |
| "loss": 0.8286, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 3.488878143133462e-05, | |
| "loss": 0.8359, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 3.464700193423598e-05, | |
| "loss": 0.8449, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 3.4405222437137327e-05, | |
| "loss": 0.8496, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 3.416344294003868e-05, | |
| "loss": 0.8487, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 3.392166344294004e-05, | |
| "loss": 0.8382, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "eval_loss": 0.1644931435585022, | |
| "eval_runtime": 913.1462, | |
| "eval_samples_per_second": 16.797, | |
| "eval_steps_per_second": 2.1, | |
| "eval_wer": 1.0113829232162455, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 3.367988394584139e-05, | |
| "loss": 0.8346, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 3.3438104448742746e-05, | |
| "loss": 0.8342, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 3.3196324951644096e-05, | |
| "loss": 0.8291, | |
| "step": 19300 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 3.295454545454545e-05, | |
| "loss": 0.8401, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 3.2715183752417797e-05, | |
| "loss": 0.8304, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 3.2473404255319146e-05, | |
| "loss": 0.8141, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 3.22316247582205e-05, | |
| "loss": 0.8296, | |
| "step": 19700 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.198984526112185e-05, | |
| "loss": 0.841, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 3.174806576402321e-05, | |
| "loss": 0.8328, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 3.1506286266924566e-05, | |
| "loss": 0.8247, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "eval_loss": 0.16470365226268768, | |
| "eval_runtime": 939.1383, | |
| "eval_samples_per_second": 16.332, | |
| "eval_steps_per_second": 2.042, | |
| "eval_wer": 1.007808517401239, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 3.1264506769825916e-05, | |
| "loss": 0.8196, | |
| "step": 20100 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 3.102272727272727e-05, | |
| "loss": 0.827, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 3.078094777562862e-05, | |
| "loss": 0.8342, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 3.053916827852998e-05, | |
| "loss": 0.8155, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 3.0297388781431333e-05, | |
| "loss": 0.8178, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 3.005560928433269e-05, | |
| "loss": 0.8289, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 2.981382978723404e-05, | |
| "loss": 0.8288, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 2.9572050290135396e-05, | |
| "loss": 0.8285, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 2.9330270793036746e-05, | |
| "loss": 0.822, | |
| "step": 20900 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 2.9088491295938102e-05, | |
| "loss": 0.8219, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "eval_loss": 0.16108199954032898, | |
| "eval_runtime": 895.1463, | |
| "eval_samples_per_second": 17.135, | |
| "eval_steps_per_second": 2.143, | |
| "eval_wer": 1.0025548605322026, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 2.884671179883946e-05, | |
| "loss": 0.8173, | |
| "step": 21100 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 2.860493230174081e-05, | |
| "loss": 0.8187, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 2.8363152804642165e-05, | |
| "loss": 0.8305, | |
| "step": 21300 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 2.812137330754352e-05, | |
| "loss": 0.819, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 2.7879593810444872e-05, | |
| "loss": 0.8219, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 2.7640232108317212e-05, | |
| "loss": 0.8269, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 2.7398452611218565e-05, | |
| "loss": 0.8022, | |
| "step": 21700 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 2.715667311411992e-05, | |
| "loss": 0.8262, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 2.6914893617021275e-05, | |
| "loss": 0.8039, | |
| "step": 21900 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 2.667311411992263e-05, | |
| "loss": 0.8024, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "eval_loss": 0.15802350640296936, | |
| "eval_runtime": 867.7109, | |
| "eval_samples_per_second": 17.676, | |
| "eval_steps_per_second": 2.21, | |
| "eval_wer": 1.0062072315747177, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 2.6431334622823982e-05, | |
| "loss": 0.8231, | |
| "step": 22100 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 2.618955512572534e-05, | |
| "loss": 0.8089, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 2.594777562862669e-05, | |
| "loss": 0.8201, | |
| "step": 22300 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 2.5705996131528045e-05, | |
| "loss": 0.8044, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 2.5466634429400382e-05, | |
| "loss": 0.8036, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 2.522485493230174e-05, | |
| "loss": 0.817, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 2.4983075435203095e-05, | |
| "loss": 0.8174, | |
| "step": 22700 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 2.4741295938104445e-05, | |
| "loss": 0.8198, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 2.4499516441005802e-05, | |
| "loss": 0.8195, | |
| "step": 22900 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 2.4257736943907155e-05, | |
| "loss": 0.8087, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "eval_loss": 0.1578305959701538, | |
| "eval_runtime": 904.3081, | |
| "eval_samples_per_second": 16.961, | |
| "eval_steps_per_second": 2.121, | |
| "eval_wer": 1.0037783148715673, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 2.401595744680851e-05, | |
| "loss": 0.8126, | |
| "step": 23100 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 2.3774177949709865e-05, | |
| "loss": 0.8227, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 2.3532398452611215e-05, | |
| "loss": 0.7986, | |
| "step": 23300 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 2.329061895551257e-05, | |
| "loss": 0.8122, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 2.3048839458413925e-05, | |
| "loss": 0.8076, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 2.2807059961315278e-05, | |
| "loss": 0.8073, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 2.256528046421663e-05, | |
| "loss": 0.8166, | |
| "step": 23700 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 2.2323500967117988e-05, | |
| "loss": 0.8102, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 2.208172147001934e-05, | |
| "loss": 0.7968, | |
| "step": 23900 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 2.1839941972920694e-05, | |
| "loss": 0.8097, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "eval_loss": 0.15561607480049133, | |
| "eval_runtime": 885.7009, | |
| "eval_samples_per_second": 17.317, | |
| "eval_steps_per_second": 2.166, | |
| "eval_wer": 1.0056854642829298, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 2.1598162475822048e-05, | |
| "loss": 0.8142, | |
| "step": 24100 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 2.13563829787234e-05, | |
| "loss": 0.8124, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 2.1114603481624758e-05, | |
| "loss": 0.7959, | |
| "step": 24300 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 2.0872823984526107e-05, | |
| "loss": 0.7978, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 2.0631044487427464e-05, | |
| "loss": 0.7976, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 2.038926499032882e-05, | |
| "loss": 0.8037, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 2.014748549323017e-05, | |
| "loss": 0.7937, | |
| "step": 24700 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 1.9905705996131527e-05, | |
| "loss": 0.8103, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 1.9663926499032884e-05, | |
| "loss": 0.8081, | |
| "step": 24900 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 1.9422147001934234e-05, | |
| "loss": 0.8094, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "eval_loss": 0.1551727056503296, | |
| "eval_runtime": 901.9892, | |
| "eval_samples_per_second": 17.005, | |
| "eval_steps_per_second": 2.126, | |
| "eval_wer": 1.0035084352378838, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 1.9182785299806577e-05, | |
| "loss": 0.795, | |
| "step": 25100 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 1.8941005802707927e-05, | |
| "loss": 0.8121, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 1.8699226305609284e-05, | |
| "loss": 0.8036, | |
| "step": 25300 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 1.8457446808510637e-05, | |
| "loss": 0.8006, | |
| "step": 25400 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 1.821566731141199e-05, | |
| "loss": 0.8095, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 1.7973887814313344e-05, | |
| "loss": 0.7927, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 1.7732108317214697e-05, | |
| "loss": 0.8054, | |
| "step": 25700 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 1.7490328820116054e-05, | |
| "loss": 0.7775, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 1.7248549323017407e-05, | |
| "loss": 0.7962, | |
| "step": 25900 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 1.700676982591876e-05, | |
| "loss": 0.7836, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "eval_loss": 0.15161673724651337, | |
| "eval_runtime": 868.8581, | |
| "eval_samples_per_second": 17.653, | |
| "eval_steps_per_second": 2.207, | |
| "eval_wer": 1.0051876862919138, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 1.6764990328820113e-05, | |
| "loss": 0.793, | |
| "step": 26100 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 1.6523210831721467e-05, | |
| "loss": 0.8035, | |
| "step": 26200 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 1.6281431334622823e-05, | |
| "loss": 0.7855, | |
| "step": 26300 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 1.6039651837524177e-05, | |
| "loss": 0.7937, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 1.579787234042553e-05, | |
| "loss": 0.8005, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 1.5556092843326883e-05, | |
| "loss": 0.8062, | |
| "step": 26600 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 1.531431334622824e-05, | |
| "loss": 0.7946, | |
| "step": 26700 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 1.5072533849129593e-05, | |
| "loss": 0.7994, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 1.4830754352030946e-05, | |
| "loss": 0.7915, | |
| "step": 26900 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 1.45889748549323e-05, | |
| "loss": 0.8042, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "eval_loss": 0.1515103131532669, | |
| "eval_runtime": 873.3263, | |
| "eval_samples_per_second": 17.563, | |
| "eval_steps_per_second": 2.196, | |
| "eval_wer": 1.0053556113973168, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 1.4347195357833655e-05, | |
| "loss": 0.7784, | |
| "step": 27100 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 1.410541586073501e-05, | |
| "loss": 0.7937, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 1.3863636363636363e-05, | |
| "loss": 0.7871, | |
| "step": 27300 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 1.3621856866537716e-05, | |
| "loss": 0.7819, | |
| "step": 27400 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 1.3380077369439071e-05, | |
| "loss": 0.7794, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 1.3138297872340424e-05, | |
| "loss": 0.7875, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 1.2896518375241777e-05, | |
| "loss": 0.7862, | |
| "step": 27700 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 1.265473887814313e-05, | |
| "loss": 0.8009, | |
| "step": 27800 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 1.2412959381044487e-05, | |
| "loss": 0.7958, | |
| "step": 27900 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 1.217117988394584e-05, | |
| "loss": 0.7925, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "eval_loss": 0.14987634122371674, | |
| "eval_runtime": 917.3137, | |
| "eval_samples_per_second": 16.721, | |
| "eval_steps_per_second": 2.091, | |
| "eval_wer": 1.0031066144499554, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 1.1929400386847194e-05, | |
| "loss": 0.787, | |
| "step": 28100 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 1.1690038684719534e-05, | |
| "loss": 0.7846, | |
| "step": 28200 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 1.1448259187620889e-05, | |
| "loss": 0.7775, | |
| "step": 28300 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 1.1206479690522242e-05, | |
| "loss": 0.7925, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 1.0964700193423596e-05, | |
| "loss": 0.7919, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 1.072292069632495e-05, | |
| "loss": 0.7778, | |
| "step": 28600 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 1.0481141199226306e-05, | |
| "loss": 0.7841, | |
| "step": 28700 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 1.0239361702127659e-05, | |
| "loss": 0.7833, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 9.997582205029012e-06, | |
| "loss": 0.7735, | |
| "step": 28900 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 9.755802707930365e-06, | |
| "loss": 0.7855, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "eval_loss": 0.14901261031627655, | |
| "eval_runtime": 914.5847, | |
| "eval_samples_per_second": 16.77, | |
| "eval_steps_per_second": 2.097, | |
| "eval_wer": 1.0041201624075662, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 9.514023210831722e-06, | |
| "loss": 0.7916, | |
| "step": 29100 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "learning_rate": 9.272243713733075e-06, | |
| "loss": 0.7928, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 9.030464216634429e-06, | |
| "loss": 0.7872, | |
| "step": 29300 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 8.788684719535783e-06, | |
| "loss": 0.7894, | |
| "step": 29400 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 8.546905222437137e-06, | |
| "loss": 0.7863, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 8.30512572533849e-06, | |
| "loss": 0.7854, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 8.063346228239843e-06, | |
| "loss": 0.7866, | |
| "step": 29700 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 7.821566731141198e-06, | |
| "loss": 0.7844, | |
| "step": 29800 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 7.579787234042552e-06, | |
| "loss": 0.7825, | |
| "step": 29900 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 7.338007736943906e-06, | |
| "loss": 0.7814, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "eval_loss": 0.14820893108844757, | |
| "eval_runtime": 892.0957, | |
| "eval_samples_per_second": 17.193, | |
| "eval_steps_per_second": 2.15, | |
| "eval_wer": 1.006842948045172, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "learning_rate": 7.096228239845261e-06, | |
| "loss": 0.7724, | |
| "step": 30100 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 6.854448742746615e-06, | |
| "loss": 0.7775, | |
| "step": 30200 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "learning_rate": 6.615087040618955e-06, | |
| "loss": 0.7781, | |
| "step": 30300 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 6.373307543520309e-06, | |
| "loss": 0.7726, | |
| "step": 30400 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 6.131528046421662e-06, | |
| "loss": 0.777, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 5.889748549323017e-06, | |
| "loss": 0.781, | |
| "step": 30600 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 5.6479690522243705e-06, | |
| "loss": 0.7646, | |
| "step": 30700 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 5.406189555125725e-06, | |
| "loss": 0.7773, | |
| "step": 30800 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 5.164410058027079e-06, | |
| "loss": 0.7621, | |
| "step": 30900 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 4.922630560928433e-06, | |
| "loss": 0.7859, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "eval_loss": 0.14604978263378143, | |
| "eval_runtime": 869.7135, | |
| "eval_samples_per_second": 17.636, | |
| "eval_steps_per_second": 2.205, | |
| "eval_wer": 1.0065970577122603, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "learning_rate": 4.680851063829787e-06, | |
| "loss": 0.7915, | |
| "step": 31100 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 4.439071566731141e-06, | |
| "loss": 0.7725, | |
| "step": 31200 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 4.197292069632495e-06, | |
| "loss": 0.7818, | |
| "step": 31300 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 3.955512572533848e-06, | |
| "loss": 0.7781, | |
| "step": 31400 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 3.7137330754352025e-06, | |
| "loss": 0.7761, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 3.4719535783365566e-06, | |
| "loss": 0.7777, | |
| "step": 31600 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 3.2301740812379107e-06, | |
| "loss": 0.7803, | |
| "step": 31700 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "learning_rate": 2.9883945841392644e-06, | |
| "loss": 0.7795, | |
| "step": 31800 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 2.7466150870406185e-06, | |
| "loss": 0.7733, | |
| "step": 31900 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 2.5048355899419726e-06, | |
| "loss": 0.7819, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "eval_loss": 0.14636215567588806, | |
| "eval_runtime": 874.2952, | |
| "eval_samples_per_second": 17.543, | |
| "eval_steps_per_second": 2.194, | |
| "eval_wer": 1.006159252973174, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 2.2630560928433267e-06, | |
| "loss": 0.7621, | |
| "step": 32100 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "learning_rate": 2.021276595744681e-06, | |
| "loss": 0.7757, | |
| "step": 32200 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 1.7794970986460347e-06, | |
| "loss": 0.7777, | |
| "step": 32300 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 1.5377176015473886e-06, | |
| "loss": 0.7706, | |
| "step": 32400 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 1.2983558994197291e-06, | |
| "loss": 0.7789, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 1.0565764023210832e-06, | |
| "loss": 0.7748, | |
| "step": 32600 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 8.147969052224371e-07, | |
| "loss": 0.7691, | |
| "step": 32700 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "learning_rate": 5.730174081237911e-07, | |
| "loss": 0.7874, | |
| "step": 32800 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "learning_rate": 3.31237911025145e-07, | |
| "loss": 0.7824, | |
| "step": 32900 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 8.945841392649903e-08, | |
| "loss": 0.7784, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.14604903757572174, | |
| "eval_runtime": 897.5045, | |
| "eval_samples_per_second": 17.09, | |
| "eval_steps_per_second": 2.137, | |
| "eval_wer": 1.0063391727289628, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 33020, | |
| "total_flos": 1.7278096619727022e+20, | |
| "train_loss": 1.1067264282508449, | |
| "train_runtime": 104618.9402, | |
| "train_samples_per_second": 10.101, | |
| "train_steps_per_second": 0.316 | |
| } | |
| ], | |
| "max_steps": 33020, | |
| "num_train_epochs": 5, | |
| "total_flos": 1.7278096619727022e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |