| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 31.99304865938431, | |
| "global_step": 4000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0392, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 0.23765751719474792, | |
| "eval_runtime": 220.5891, | |
| "eval_samples_per_second": 16.297, | |
| "eval_steps_per_second": 2.04, | |
| "eval_wer": 0.21887876816308827, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 9.991993594875901e-05, | |
| "loss": 0.0336, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 0.26165521144866943, | |
| "eval_runtime": 157.9726, | |
| "eval_samples_per_second": 22.757, | |
| "eval_steps_per_second": 2.849, | |
| "eval_wer": 0.21649316851008457, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 9.983987189751803e-05, | |
| "loss": 0.0293, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_loss": 0.28323182463645935, | |
| "eval_runtime": 169.3448, | |
| "eval_samples_per_second": 21.229, | |
| "eval_steps_per_second": 2.657, | |
| "eval_wer": 0.2197462589459987, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 9.975980784627703e-05, | |
| "loss": 0.0283, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "eval_loss": 0.29311421513557434, | |
| "eval_runtime": 175.6178, | |
| "eval_samples_per_second": 20.471, | |
| "eval_steps_per_second": 2.562, | |
| "eval_wer": 0.21508349598785512, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 9.967974379503603e-05, | |
| "loss": 0.0274, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "eval_loss": 0.30566948652267456, | |
| "eval_runtime": 182.1945, | |
| "eval_samples_per_second": 19.732, | |
| "eval_steps_per_second": 2.47, | |
| "eval_wer": 0.21828236824983735, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 9.959967974379504e-05, | |
| "loss": 0.0264, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "eval_loss": 0.30197781324386597, | |
| "eval_runtime": 174.7969, | |
| "eval_samples_per_second": 20.567, | |
| "eval_steps_per_second": 2.574, | |
| "eval_wer": 0.2171437865972674, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 9.951961569255405e-05, | |
| "loss": 0.0259, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "eval_loss": 0.3002428412437439, | |
| "eval_runtime": 191.2838, | |
| "eval_samples_per_second": 18.794, | |
| "eval_steps_per_second": 2.353, | |
| "eval_wer": 0.21725222294513122, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 9.943955164131305e-05, | |
| "loss": 0.0254, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "eval_loss": 0.3097267746925354, | |
| "eval_runtime": 183.9687, | |
| "eval_samples_per_second": 19.541, | |
| "eval_steps_per_second": 2.446, | |
| "eval_wer": 0.21752331381479073, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 9.936028823058447e-05, | |
| "loss": 0.0252, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "eval_loss": 0.2970833480358124, | |
| "eval_runtime": 182.1563, | |
| "eval_samples_per_second": 19.736, | |
| "eval_steps_per_second": 2.47, | |
| "eval_wer": 0.2170353502494036, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "learning_rate": 9.928022417934349e-05, | |
| "loss": 0.0234, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "eval_loss": 0.31429246068000793, | |
| "eval_runtime": 193.7999, | |
| "eval_samples_per_second": 18.55, | |
| "eval_steps_per_second": 2.322, | |
| "eval_wer": 0.21405335068314899, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 8.79, | |
| "learning_rate": 9.920016012810248e-05, | |
| "loss": 0.0228, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 8.79, | |
| "eval_loss": 0.32985326647758484, | |
| "eval_runtime": 194.3544, | |
| "eval_samples_per_second": 18.497, | |
| "eval_steps_per_second": 2.315, | |
| "eval_wer": 0.2142702233788766, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 9.912009607686149e-05, | |
| "loss": 0.0236, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "eval_loss": 0.3165593147277832, | |
| "eval_runtime": 185.0001, | |
| "eval_samples_per_second": 19.432, | |
| "eval_steps_per_second": 2.432, | |
| "eval_wer": 0.21833658642376924, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 10.4, | |
| "learning_rate": 9.90400320256205e-05, | |
| "loss": 0.0241, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 10.4, | |
| "eval_loss": 0.3285478949546814, | |
| "eval_runtime": 181.9532, | |
| "eval_samples_per_second": 19.758, | |
| "eval_steps_per_second": 2.473, | |
| "eval_wer": 0.2192582953806116, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "learning_rate": 9.895996797437951e-05, | |
| "loss": 0.0243, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "eval_loss": 0.3187803626060486, | |
| "eval_runtime": 200.4409, | |
| "eval_samples_per_second": 17.935, | |
| "eval_steps_per_second": 2.245, | |
| "eval_wer": 0.22099327694643245, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 11.99, | |
| "learning_rate": 9.887990392313852e-05, | |
| "loss": 0.026, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 11.99, | |
| "eval_loss": 0.32988375425338745, | |
| "eval_runtime": 199.5224, | |
| "eval_samples_per_second": 18.018, | |
| "eval_steps_per_second": 2.255, | |
| "eval_wer": 0.22375840381695944, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 12.79, | |
| "learning_rate": 9.879983987189752e-05, | |
| "loss": 0.0259, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 12.79, | |
| "eval_loss": 0.3099309206008911, | |
| "eval_runtime": 198.0592, | |
| "eval_samples_per_second": 18.151, | |
| "eval_steps_per_second": 2.272, | |
| "eval_wer": 0.22045109520711342, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "learning_rate": 9.871977582065654e-05, | |
| "loss": 0.0255, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "eval_loss": 0.30543622374534607, | |
| "eval_runtime": 202.823, | |
| "eval_samples_per_second": 17.725, | |
| "eval_steps_per_second": 2.219, | |
| "eval_wer": 0.22402949468661895, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "learning_rate": 9.863971176941553e-05, | |
| "loss": 0.0253, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "eval_loss": 0.31324318051338196, | |
| "eval_runtime": 199.664, | |
| "eval_samples_per_second": 18.005, | |
| "eval_steps_per_second": 2.254, | |
| "eval_wer": 0.21779440468445022, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 15.2, | |
| "learning_rate": 9.855964771817454e-05, | |
| "loss": 0.0244, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 15.2, | |
| "eval_loss": 0.33187857270240784, | |
| "eval_runtime": 197.0859, | |
| "eval_samples_per_second": 18.241, | |
| "eval_steps_per_second": 2.283, | |
| "eval_wer": 0.22121014964216004, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 15.99, | |
| "learning_rate": 9.847958366693355e-05, | |
| "loss": 0.0231, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 15.99, | |
| "eval_loss": 0.33831512928009033, | |
| "eval_runtime": 200.252, | |
| "eval_samples_per_second": 17.952, | |
| "eval_steps_per_second": 2.247, | |
| "eval_wer": 0.21920407720667967, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 16.79, | |
| "learning_rate": 9.839951961569256e-05, | |
| "loss": 0.0235, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 16.79, | |
| "eval_loss": 0.31389620900154114, | |
| "eval_runtime": 198.2191, | |
| "eval_samples_per_second": 18.136, | |
| "eval_steps_per_second": 2.27, | |
| "eval_wer": 0.21622207764042506, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 17.6, | |
| "learning_rate": 9.831945556445156e-05, | |
| "loss": 0.0227, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 17.6, | |
| "eval_loss": 0.32037118077278137, | |
| "eval_runtime": 202.9198, | |
| "eval_samples_per_second": 17.716, | |
| "eval_steps_per_second": 2.218, | |
| "eval_wer": 0.217360659292995, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 18.4, | |
| "learning_rate": 9.823939151321058e-05, | |
| "loss": 0.0228, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 18.4, | |
| "eval_loss": 0.32169201970100403, | |
| "eval_runtime": 193.9, | |
| "eval_samples_per_second": 18.54, | |
| "eval_steps_per_second": 2.321, | |
| "eval_wer": 0.21757753198872262, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "learning_rate": 9.815932746196959e-05, | |
| "loss": 0.0217, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "eval_loss": 0.3112569749355316, | |
| "eval_runtime": 198.2135, | |
| "eval_samples_per_second": 18.137, | |
| "eval_steps_per_second": 2.27, | |
| "eval_wer": 0.2170895684233355, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 19.99, | |
| "learning_rate": 9.807926341072858e-05, | |
| "loss": 0.0212, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 19.99, | |
| "eval_loss": 0.31596991419792175, | |
| "eval_runtime": 199.2987, | |
| "eval_samples_per_second": 18.038, | |
| "eval_steps_per_second": 2.258, | |
| "eval_wer": 0.21351116894382996, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 20.79, | |
| "learning_rate": 9.79991993594876e-05, | |
| "loss": 0.0216, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 20.79, | |
| "eval_loss": 0.3226161003112793, | |
| "eval_runtime": 199.747, | |
| "eval_samples_per_second": 17.998, | |
| "eval_steps_per_second": 2.253, | |
| "eval_wer": 0.21378225981348947, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 21.6, | |
| "learning_rate": 9.79191353082466e-05, | |
| "loss": 0.0242, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 21.6, | |
| "eval_loss": 0.3281223177909851, | |
| "eval_runtime": 197.1976, | |
| "eval_samples_per_second": 18.23, | |
| "eval_steps_per_second": 2.282, | |
| "eval_wer": 0.2169269139015398, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 22.4, | |
| "learning_rate": 9.783907125700561e-05, | |
| "loss": 0.0245, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 22.4, | |
| "eval_loss": 0.3078162968158722, | |
| "eval_runtime": 198.6659, | |
| "eval_samples_per_second": 18.096, | |
| "eval_steps_per_second": 2.265, | |
| "eval_wer": 0.2176317501626545, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 23.2, | |
| "learning_rate": 9.775900720576461e-05, | |
| "loss": 0.0229, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 23.2, | |
| "eval_loss": 0.31995320320129395, | |
| "eval_runtime": 204.328, | |
| "eval_samples_per_second": 17.594, | |
| "eval_steps_per_second": 2.202, | |
| "eval_wer": 0.22045109520711342, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 23.99, | |
| "learning_rate": 9.767894315452363e-05, | |
| "loss": 0.0226, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 23.99, | |
| "eval_loss": 0.33075791597366333, | |
| "eval_runtime": 205.0698, | |
| "eval_samples_per_second": 17.531, | |
| "eval_steps_per_second": 2.194, | |
| "eval_wer": 0.2171437865972674, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 24.79, | |
| "learning_rate": 9.759887910328262e-05, | |
| "loss": 0.0213, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 24.79, | |
| "eval_loss": 0.3419627845287323, | |
| "eval_runtime": 206.2312, | |
| "eval_samples_per_second": 17.432, | |
| "eval_steps_per_second": 2.182, | |
| "eval_wer": 0.21936673172847537, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 25.6, | |
| "learning_rate": 9.751881505204163e-05, | |
| "loss": 0.0212, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 25.6, | |
| "eval_loss": 0.3389272093772888, | |
| "eval_runtime": 205.5665, | |
| "eval_samples_per_second": 17.488, | |
| "eval_steps_per_second": 2.189, | |
| "eval_wer": 0.21519193233571893, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 26.4, | |
| "learning_rate": 9.743875100080065e-05, | |
| "loss": 0.0208, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 26.4, | |
| "eval_loss": 0.32781022787094116, | |
| "eval_runtime": 208.0862, | |
| "eval_samples_per_second": 17.276, | |
| "eval_steps_per_second": 2.163, | |
| "eval_wer": 0.21275211450878334, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 27.2, | |
| "learning_rate": 9.735868694955965e-05, | |
| "loss": 0.0212, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 27.2, | |
| "eval_loss": 0.3169388771057129, | |
| "eval_runtime": 206.029, | |
| "eval_samples_per_second": 17.449, | |
| "eval_steps_per_second": 2.184, | |
| "eval_wer": 0.21497505963999133, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 27.99, | |
| "learning_rate": 9.727862289831866e-05, | |
| "loss": 0.0213, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 27.99, | |
| "eval_loss": 0.31786179542541504, | |
| "eval_runtime": 198.632, | |
| "eval_samples_per_second": 18.099, | |
| "eval_steps_per_second": 2.265, | |
| "eval_wer": 0.21757753198872262, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 28.79, | |
| "learning_rate": 9.719855884707766e-05, | |
| "loss": 0.0213, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 28.79, | |
| "eval_loss": 0.32053136825561523, | |
| "eval_runtime": 201.1109, | |
| "eval_samples_per_second": 17.876, | |
| "eval_steps_per_second": 2.238, | |
| "eval_wer": 0.2203426588592496, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 29.6, | |
| "learning_rate": 9.711849479583668e-05, | |
| "loss": 0.0217, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 29.6, | |
| "eval_loss": 0.33174052834510803, | |
| "eval_runtime": 191.0157, | |
| "eval_samples_per_second": 18.82, | |
| "eval_steps_per_second": 2.356, | |
| "eval_wer": 0.2168726957276079, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 30.4, | |
| "learning_rate": 9.703843074459567e-05, | |
| "loss": 0.0221, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 30.4, | |
| "eval_loss": 0.3100583255290985, | |
| "eval_runtime": 190.6873, | |
| "eval_samples_per_second": 18.853, | |
| "eval_steps_per_second": 2.36, | |
| "eval_wer": 0.21774018651051832, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 31.2, | |
| "learning_rate": 9.695836669335468e-05, | |
| "loss": 0.021, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 31.2, | |
| "eval_loss": 0.33132240176200867, | |
| "eval_runtime": 187.5625, | |
| "eval_samples_per_second": 19.167, | |
| "eval_steps_per_second": 2.399, | |
| "eval_wer": 0.21741487746692692, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 31.99, | |
| "learning_rate": 9.68783026421137e-05, | |
| "loss": 0.0212, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 31.99, | |
| "eval_loss": 0.32063281536102295, | |
| "eval_runtime": 192.7124, | |
| "eval_samples_per_second": 18.655, | |
| "eval_steps_per_second": 2.335, | |
| "eval_wer": 0.21340273259596618, | |
| "step": 4000 | |
| } | |
| ], | |
| "max_steps": 125000, | |
| "num_train_epochs": 1000, | |
| "total_flos": 9.112861160368682e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |