| { | |
| "best_metric": 15.072300680807968, | |
| "best_model_checkpoint": "./checkpoint-30000", | |
| "epoch": 16.029333333333334, | |
| "global_step": 30000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.94e-06, | |
| "loss": 2.2038, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 3.94e-06, | |
| "loss": 0.7125, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5.94e-06, | |
| "loss": 0.4459, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 7.94e-06, | |
| "loss": 0.3765, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.940000000000001e-06, | |
| "loss": 0.3301, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.967118644067797e-06, | |
| "loss": 0.3847, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.933220338983051e-06, | |
| "loss": 0.3367, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.899322033898305e-06, | |
| "loss": 0.303, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.86542372881356e-06, | |
| "loss": 0.2564, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.831525423728815e-06, | |
| "loss": 0.2271, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.797627118644069e-06, | |
| "loss": 0.2222, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.763728813559323e-06, | |
| "loss": 0.2269, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.729830508474576e-06, | |
| "loss": 0.196, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.695932203389831e-06, | |
| "loss": 0.2159, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.662033898305085e-06, | |
| "loss": 0.2502, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.62813559322034e-06, | |
| "loss": 0.2134, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.594237288135594e-06, | |
| "loss": 0.1912, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.56033898305085e-06, | |
| "loss": 0.2222, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.526440677966103e-06, | |
| "loss": 0.2021, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 9.492542372881357e-06, | |
| "loss": 0.1637, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 0.25550365447998047, | |
| "eval_runtime": 7151.6815, | |
| "eval_samples_per_second": 2.033, | |
| "eval_steps_per_second": 0.254, | |
| "eval_wer": 26.468238339053617, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 9.45864406779661e-06, | |
| "loss": 0.1463, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 9.424745762711865e-06, | |
| "loss": 0.1564, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 9.390847457627119e-06, | |
| "loss": 0.1364, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 9.356949152542374e-06, | |
| "loss": 0.1658, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 9.323050847457628e-06, | |
| "loss": 0.1629, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 9.289152542372882e-06, | |
| "loss": 0.152, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 9.255254237288135e-06, | |
| "loss": 0.1301, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 9.22135593220339e-06, | |
| "loss": 0.1091, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 9.187457627118644e-06, | |
| "loss": 0.1064, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 9.1535593220339e-06, | |
| "loss": 0.1137, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 9.119661016949153e-06, | |
| "loss": 0.1096, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 9.085762711864408e-06, | |
| "loss": 0.1067, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 9.051864406779662e-06, | |
| "loss": 0.1277, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 9.017966101694916e-06, | |
| "loss": 0.1131, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 8.98406779661017e-06, | |
| "loss": 0.1024, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 8.950169491525425e-06, | |
| "loss": 0.107, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 8.91627118644068e-06, | |
| "loss": 0.1422, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 8.882372881355933e-06, | |
| "loss": 0.1602, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 8.848474576271187e-06, | |
| "loss": 0.1187, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 8.81457627118644e-06, | |
| "loss": 0.1375, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "eval_loss": 0.22229675948619843, | |
| "eval_runtime": 7004.2343, | |
| "eval_samples_per_second": 2.076, | |
| "eval_steps_per_second": 0.26, | |
| "eval_wer": 21.539413717436563, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 8.780677966101696e-06, | |
| "loss": 0.1246, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 8.74677966101695e-06, | |
| "loss": 0.1577, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 8.712881355932205e-06, | |
| "loss": 0.1267, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 8.678983050847459e-06, | |
| "loss": 0.1178, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 8.645084745762712e-06, | |
| "loss": 0.1335, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 8.611186440677966e-06, | |
| "loss": 0.1288, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 8.577288135593221e-06, | |
| "loss": 0.1592, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 8.543389830508475e-06, | |
| "loss": 0.161, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 8.509830508474578e-06, | |
| "loss": 0.1658, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 8.475932203389831e-06, | |
| "loss": 0.12, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 8.442033898305085e-06, | |
| "loss": 0.1518, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 8.40813559322034e-06, | |
| "loss": 0.1806, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 8.374237288135594e-06, | |
| "loss": 0.1206, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 8.340338983050849e-06, | |
| "loss": 0.1254, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 8.306440677966103e-06, | |
| "loss": 0.1198, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 8.272542372881356e-06, | |
| "loss": 0.0787, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 8.23864406779661e-06, | |
| "loss": 0.0666, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 8.204745762711865e-06, | |
| "loss": 0.0742, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 8.170847457627119e-06, | |
| "loss": 0.0668, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 8.136949152542374e-06, | |
| "loss": 0.0851, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "eval_loss": 0.2086436152458191, | |
| "eval_runtime": 7023.6759, | |
| "eval_samples_per_second": 2.07, | |
| "eval_steps_per_second": 0.259, | |
| "eval_wer": 19.672536994317223, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 8.103050847457628e-06, | |
| "loss": 0.0861, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 8.069152542372881e-06, | |
| "loss": 0.0815, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 8.035254237288137e-06, | |
| "loss": 0.0715, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 8.00135593220339e-06, | |
| "loss": 0.0582, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 7.967457627118644e-06, | |
| "loss": 0.056, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 7.9335593220339e-06, | |
| "loss": 0.0497, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 7.899661016949153e-06, | |
| "loss": 0.061, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 7.865762711864408e-06, | |
| "loss": 0.0557, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 7.831864406779662e-06, | |
| "loss": 0.0545, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 7.797966101694915e-06, | |
| "loss": 0.0581, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 7.765762711864407e-06, | |
| "loss": 0.4649, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 7.731864406779661e-06, | |
| "loss": 1.2438, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 7.697966101694916e-06, | |
| "loss": 0.1309, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 7.66406779661017e-06, | |
| "loss": 0.0762, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 7.630169491525424e-06, | |
| "loss": 0.0604, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 7.596271186440679e-06, | |
| "loss": 0.0653, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 7.5623728813559326e-06, | |
| "loss": 0.0609, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 7.528474576271188e-06, | |
| "loss": 0.0755, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 7.4945762711864415e-06, | |
| "loss": 0.0663, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 7.460677966101696e-06, | |
| "loss": 0.0573, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "eval_loss": 0.2178211659193039, | |
| "eval_runtime": 7037.8839, | |
| "eval_samples_per_second": 2.066, | |
| "eval_steps_per_second": 0.258, | |
| "eval_wer": 18.427952512237663, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 7.4267796610169496e-06, | |
| "loss": 0.073, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 7.392881355932204e-06, | |
| "loss": 0.0633, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 7.358983050847458e-06, | |
| "loss": 0.077, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 7.325084745762713e-06, | |
| "loss": 0.0701, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 7.2911864406779666e-06, | |
| "loss": 0.0867, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 7.257288135593221e-06, | |
| "loss": 0.0637, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 7.223389830508475e-06, | |
| "loss": 0.0649, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 7.18949152542373e-06, | |
| "loss": 0.0945, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 7.1555932203389836e-06, | |
| "loss": 0.0719, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 7.121694915254238e-06, | |
| "loss": 0.0608, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 7.087796610169492e-06, | |
| "loss": 0.0669, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 7.053898305084746e-06, | |
| "loss": 0.0429, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 7.0200000000000006e-06, | |
| "loss": 0.0346, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 6.986101694915255e-06, | |
| "loss": 0.0314, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 6.952203389830509e-06, | |
| "loss": 0.0351, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 6.918305084745763e-06, | |
| "loss": 0.0372, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 6.884406779661017e-06, | |
| "loss": 0.0367, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 6.850508474576272e-06, | |
| "loss": 0.0297, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 6.816610169491526e-06, | |
| "loss": 0.0372, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 6.78271186440678e-06, | |
| "loss": 0.036, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "eval_loss": 0.23119649291038513, | |
| "eval_runtime": 6929.3454, | |
| "eval_samples_per_second": 2.099, | |
| "eval_steps_per_second": 0.262, | |
| "eval_wer": 17.82479041242334, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 6.7488135593220345e-06, | |
| "loss": 0.0407, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 6.714915254237289e-06, | |
| "loss": 0.0337, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 6.6810169491525435e-06, | |
| "loss": 0.0412, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 6.647118644067797e-06, | |
| "loss": 0.035, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 6.6132203389830515e-06, | |
| "loss": 0.0355, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 6.579322033898305e-06, | |
| "loss": 0.0443, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 6.5454237288135605e-06, | |
| "loss": 0.0384, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 6.511525423728814e-06, | |
| "loss": 0.0321, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 6.4776271186440685e-06, | |
| "loss": 0.034, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 6.443728813559322e-06, | |
| "loss": 0.04, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 6.4098305084745775e-06, | |
| "loss": 0.0329, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 6.375932203389831e-06, | |
| "loss": 0.0292, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 6.3420338983050855e-06, | |
| "loss": 0.0359, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 6.308135593220339e-06, | |
| "loss": 0.0335, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 6.274237288135594e-06, | |
| "loss": 0.0392, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 6.240338983050847e-06, | |
| "loss": 0.0374, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "learning_rate": 6.2064406779661025e-06, | |
| "loss": 0.0387, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "learning_rate": 6.172542372881356e-06, | |
| "loss": 0.0274, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "learning_rate": 6.138644067796611e-06, | |
| "loss": 0.0244, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 6.104745762711864e-06, | |
| "loss": 0.0238, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "eval_loss": 0.26207804679870605, | |
| "eval_runtime": 6973.9359, | |
| "eval_samples_per_second": 2.085, | |
| "eval_steps_per_second": 0.261, | |
| "eval_wer": 17.409553817588478, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 6.0708474576271195e-06, | |
| "loss": 0.0276, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 6.036949152542373e-06, | |
| "loss": 0.0277, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 6.003050847457628e-06, | |
| "loss": 0.0253, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 5.969152542372881e-06, | |
| "loss": 0.0248, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 5.935254237288136e-06, | |
| "loss": 0.0262, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "learning_rate": 5.90135593220339e-06, | |
| "loss": 0.0324, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "learning_rate": 5.867457627118645e-06, | |
| "loss": 0.0357, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 5.833559322033899e-06, | |
| "loss": 0.0642, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 5.799661016949153e-06, | |
| "loss": 0.0973, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 5.765762711864408e-06, | |
| "loss": 0.0925, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 5.731864406779662e-06, | |
| "loss": 0.1244, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 5.697966101694916e-06, | |
| "loss": 0.0937, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 5.66406779661017e-06, | |
| "loss": 0.1086, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 5.630169491525425e-06, | |
| "loss": 0.0851, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 5.596271186440679e-06, | |
| "loss": 0.0796, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 5.562372881355933e-06, | |
| "loss": 0.0684, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 5.528474576271187e-06, | |
| "loss": 0.0711, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 5.494576271186441e-06, | |
| "loss": 0.0679, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 5.460677966101695e-06, | |
| "loss": 0.0669, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 5.42677966101695e-06, | |
| "loss": 0.0733, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "eval_loss": 0.21199654042720795, | |
| "eval_runtime": 6989.399, | |
| "eval_samples_per_second": 2.081, | |
| "eval_steps_per_second": 0.26, | |
| "eval_wer": 16.565576998818432, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 5.392881355932204e-06, | |
| "loss": 0.073, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 5.358983050847458e-06, | |
| "loss": 0.076, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 5.325084745762712e-06, | |
| "loss": 0.0898, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 7.06, | |
| "learning_rate": 5.291186440677967e-06, | |
| "loss": 0.0829, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 7.06, | |
| "learning_rate": 5.257288135593221e-06, | |
| "loss": 0.0896, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 5.223389830508475e-06, | |
| "loss": 0.06, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 5.189491525423729e-06, | |
| "loss": 0.0192, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 5.155593220338983e-06, | |
| "loss": 0.0161, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 5.121694915254237e-06, | |
| "loss": 0.0175, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 5.087796610169492e-06, | |
| "loss": 0.0167, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 5.053898305084746e-06, | |
| "loss": 0.0186, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 5.02e-06, | |
| "loss": 0.0198, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 4.986101694915255e-06, | |
| "loss": 0.0181, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "learning_rate": 4.952203389830509e-06, | |
| "loss": 0.0156, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "learning_rate": 4.918305084745763e-06, | |
| "loss": 0.0103, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "learning_rate": 4.884406779661017e-06, | |
| "loss": 0.0114, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "learning_rate": 4.850508474576272e-06, | |
| "loss": 0.0109, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "learning_rate": 4.816610169491525e-06, | |
| "loss": 0.015, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "learning_rate": 4.78271186440678e-06, | |
| "loss": 0.0114, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "learning_rate": 4.748813559322034e-06, | |
| "loss": 0.0111, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "eval_loss": 0.2681731879711151, | |
| "eval_runtime": 6987.2917, | |
| "eval_samples_per_second": 2.081, | |
| "eval_steps_per_second": 0.26, | |
| "eval_wer": 16.22911157373544, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "learning_rate": 4.714915254237289e-06, | |
| "loss": 0.011, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "learning_rate": 4.681016949152542e-06, | |
| "loss": 0.0133, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "learning_rate": 4.647118644067797e-06, | |
| "loss": 0.0162, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 4.613220338983051e-06, | |
| "loss": 0.0147, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 4.579322033898305e-06, | |
| "loss": 0.0173, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 4.545423728813559e-06, | |
| "loss": 0.0135, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 4.511525423728815e-06, | |
| "loss": 0.0146, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 4.477627118644068e-06, | |
| "loss": 0.0152, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 4.443728813559323e-06, | |
| "loss": 0.0166, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 4.409830508474577e-06, | |
| "loss": 0.0138, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 4.375932203389831e-06, | |
| "loss": 0.0128, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 4.342033898305085e-06, | |
| "loss": 0.0195, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 4.30813559322034e-06, | |
| "loss": 0.0147, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 4.274237288135593e-06, | |
| "loss": 0.0177, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "learning_rate": 4.240338983050848e-06, | |
| "loss": 0.0155, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "learning_rate": 4.206440677966102e-06, | |
| "loss": 0.019, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "learning_rate": 4.172542372881357e-06, | |
| "loss": 0.0157, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 9.05, | |
| "learning_rate": 4.13864406779661e-06, | |
| "loss": 0.0149, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 9.05, | |
| "learning_rate": 4.104745762711865e-06, | |
| "loss": 0.0228, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 9.05, | |
| "learning_rate": 4.070847457627119e-06, | |
| "loss": 0.0155, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 9.05, | |
| "eval_loss": 0.2676936686038971, | |
| "eval_runtime": 7019.5973, | |
| "eval_samples_per_second": 2.072, | |
| "eval_steps_per_second": 0.259, | |
| "eval_wer": 15.9241546165532, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 9.06, | |
| "learning_rate": 4.036949152542373e-06, | |
| "loss": 0.0117, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 9.06, | |
| "learning_rate": 4.003050847457627e-06, | |
| "loss": 0.0131, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 3.969152542372882e-06, | |
| "loss": 0.0072, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 3.935254237288136e-06, | |
| "loss": 0.0051, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 3.90135593220339e-06, | |
| "loss": 0.0055, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 3.867457627118644e-06, | |
| "loss": 0.0054, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 10.02, | |
| "learning_rate": 3.833559322033899e-06, | |
| "loss": 0.0056, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 10.02, | |
| "learning_rate": 3.7996610169491528e-06, | |
| "loss": 0.0054, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 10.02, | |
| "learning_rate": 3.765762711864407e-06, | |
| "loss": 0.0031, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 10.03, | |
| "learning_rate": 3.7318644067796613e-06, | |
| "loss": 0.0061, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 10.03, | |
| "learning_rate": 3.6979661016949153e-06, | |
| "loss": 0.0059, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 10.03, | |
| "learning_rate": 3.6640677966101694e-06, | |
| "loss": 0.0053, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 10.04, | |
| "learning_rate": 3.630169491525424e-06, | |
| "loss": 0.0051, | |
| "step": 19300 | |
| }, | |
| { | |
| "epoch": 10.04, | |
| "learning_rate": 3.5962711864406787e-06, | |
| "loss": 0.007, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 10.04, | |
| "learning_rate": 3.5623728813559327e-06, | |
| "loss": 0.0046, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 10.05, | |
| "learning_rate": 3.528813559322034e-06, | |
| "loss": 0.0057, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 10.05, | |
| "learning_rate": 3.494915254237288e-06, | |
| "loss": 0.0069, | |
| "step": 19700 | |
| }, | |
| { | |
| "epoch": 10.05, | |
| "learning_rate": 3.4610169491525425e-06, | |
| "loss": 0.0057, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 10.06, | |
| "learning_rate": 3.4271186440677966e-06, | |
| "loss": 0.0038, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 10.06, | |
| "learning_rate": 3.393220338983051e-06, | |
| "loss": 0.0041, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 10.06, | |
| "eval_loss": 0.3177700340747833, | |
| "eval_runtime": 7017.5255, | |
| "eval_samples_per_second": 2.072, | |
| "eval_steps_per_second": 0.259, | |
| "eval_wer": 15.953412479603893, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 3.359322033898305e-06, | |
| "loss": 0.0071, | |
| "step": 20100 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 3.3254237288135595e-06, | |
| "loss": 0.0053, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 3.2915254237288136e-06, | |
| "loss": 0.0055, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 3.2576271186440685e-06, | |
| "loss": 0.007, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 3.2237288135593225e-06, | |
| "loss": 0.0055, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 3.189830508474577e-06, | |
| "loss": 0.0078, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 3.155932203389831e-06, | |
| "loss": 0.0062, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "learning_rate": 3.122033898305085e-06, | |
| "loss": 0.0064, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "learning_rate": 3.0881355932203395e-06, | |
| "loss": 0.0038, | |
| "step": 20900 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "learning_rate": 3.0542372881355935e-06, | |
| "loss": 0.0036, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 11.04, | |
| "learning_rate": 3.020338983050848e-06, | |
| "loss": 0.0041, | |
| "step": 21100 | |
| }, | |
| { | |
| "epoch": 11.04, | |
| "learning_rate": 2.986440677966102e-06, | |
| "loss": 0.0039, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 11.04, | |
| "learning_rate": 2.952542372881356e-06, | |
| "loss": 0.0056, | |
| "step": 21300 | |
| }, | |
| { | |
| "epoch": 11.05, | |
| "learning_rate": 2.9186440677966105e-06, | |
| "loss": 0.0036, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 11.05, | |
| "learning_rate": 2.8847457627118646e-06, | |
| "loss": 0.0044, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 11.05, | |
| "learning_rate": 2.850847457627119e-06, | |
| "loss": 0.0036, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 11.06, | |
| "learning_rate": 2.816949152542373e-06, | |
| "loss": 0.0051, | |
| "step": 21700 | |
| }, | |
| { | |
| "epoch": 11.06, | |
| "learning_rate": 2.7830508474576275e-06, | |
| "loss": 0.0053, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 2.7491525423728816e-06, | |
| "loss": 0.0027, | |
| "step": 21900 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 2.7152542372881356e-06, | |
| "loss": 0.0023, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "eval_loss": 0.3218221366405487, | |
| "eval_runtime": 7009.1784, | |
| "eval_samples_per_second": 2.075, | |
| "eval_steps_per_second": 0.259, | |
| "eval_wer": 16.053564395431273, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 2.68135593220339e-06, | |
| "loss": 0.0017, | |
| "step": 22100 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 2.647457627118644e-06, | |
| "loss": 0.0022, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 12.02, | |
| "learning_rate": 2.6135593220338986e-06, | |
| "loss": 0.002, | |
| "step": 22300 | |
| }, | |
| { | |
| "epoch": 12.02, | |
| "learning_rate": 2.5796610169491526e-06, | |
| "loss": 0.0023, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 12.02, | |
| "learning_rate": 2.5457627118644066e-06, | |
| "loss": 0.0016, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 12.03, | |
| "learning_rate": 2.511864406779661e-06, | |
| "loss": 0.002, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 12.03, | |
| "learning_rate": 2.4779661016949156e-06, | |
| "loss": 0.0027, | |
| "step": 22700 | |
| }, | |
| { | |
| "epoch": 12.03, | |
| "learning_rate": 2.4440677966101696e-06, | |
| "loss": 0.0022, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 12.04, | |
| "learning_rate": 2.410169491525424e-06, | |
| "loss": 0.0022, | |
| "step": 22900 | |
| }, | |
| { | |
| "epoch": 12.04, | |
| "learning_rate": 2.376271186440678e-06, | |
| "loss": 0.0023, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 12.04, | |
| "learning_rate": 2.3423728813559326e-06, | |
| "loss": 0.0026, | |
| "step": 23100 | |
| }, | |
| { | |
| "epoch": 12.05, | |
| "learning_rate": 2.3084745762711866e-06, | |
| "loss": 0.0018, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 12.05, | |
| "learning_rate": 2.2745762711864406e-06, | |
| "loss": 0.0028, | |
| "step": 23300 | |
| }, | |
| { | |
| "epoch": 12.05, | |
| "learning_rate": 2.240677966101695e-06, | |
| "loss": 0.0029, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 12.06, | |
| "learning_rate": 2.206779661016949e-06, | |
| "loss": 0.0016, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 12.06, | |
| "learning_rate": 2.1728813559322036e-06, | |
| "loss": 0.0014, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 2.1393220338983053e-06, | |
| "loss": 0.0245, | |
| "step": 23700 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 2.1054237288135594e-06, | |
| "loss": 0.0488, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 2.071525423728814e-06, | |
| "loss": 0.0468, | |
| "step": 23900 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 2.0379661016949155e-06, | |
| "loss": 0.0621, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "eval_loss": 0.23132386803627014, | |
| "eval_runtime": 7011.068, | |
| "eval_samples_per_second": 2.074, | |
| "eval_steps_per_second": 0.259, | |
| "eval_wer": 15.616947054520903, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 2.0040677966101696e-06, | |
| "loss": 0.0542, | |
| "step": 24100 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "learning_rate": 1.9701694915254236e-06, | |
| "loss": 0.0534, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "learning_rate": 1.936271186440678e-06, | |
| "loss": 0.0409, | |
| "step": 24300 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "learning_rate": 1.9023728813559323e-06, | |
| "loss": 0.0431, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 13.03, | |
| "learning_rate": 1.8684745762711868e-06, | |
| "loss": 0.0341, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 13.03, | |
| "learning_rate": 1.834576271186441e-06, | |
| "loss": 0.0348, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 13.03, | |
| "learning_rate": 1.800677966101695e-06, | |
| "loss": 0.0332, | |
| "step": 24700 | |
| }, | |
| { | |
| "epoch": 13.04, | |
| "learning_rate": 1.7667796610169493e-06, | |
| "loss": 0.0308, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 13.04, | |
| "learning_rate": 1.7328813559322036e-06, | |
| "loss": 0.0336, | |
| "step": 24900 | |
| }, | |
| { | |
| "epoch": 13.04, | |
| "learning_rate": 1.6989830508474578e-06, | |
| "loss": 0.0334, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 13.05, | |
| "learning_rate": 1.665084745762712e-06, | |
| "loss": 0.034, | |
| "step": 25100 | |
| }, | |
| { | |
| "epoch": 13.05, | |
| "learning_rate": 1.6311864406779663e-06, | |
| "loss": 0.0433, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 13.05, | |
| "learning_rate": 1.5972881355932204e-06, | |
| "loss": 0.0401, | |
| "step": 25300 | |
| }, | |
| { | |
| "epoch": 13.06, | |
| "learning_rate": 1.5633898305084746e-06, | |
| "loss": 0.0404, | |
| "step": 25400 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 1.5294915254237289e-06, | |
| "loss": 0.0328, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 1.4955932203389831e-06, | |
| "loss": 0.0033, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 1.4616949152542374e-06, | |
| "loss": 0.0021, | |
| "step": 25700 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 1.4277966101694916e-06, | |
| "loss": 0.0023, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 1.393898305084746e-06, | |
| "loss": 0.0021, | |
| "step": 25900 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "learning_rate": 1.3600000000000001e-06, | |
| "loss": 0.0022, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "eval_loss": 0.28866246342658997, | |
| "eval_runtime": 6982.432, | |
| "eval_samples_per_second": 2.083, | |
| "eval_steps_per_second": 0.26, | |
| "eval_wer": 15.108310358408822, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "learning_rate": 1.3261016949152544e-06, | |
| "loss": 0.0025, | |
| "step": 26100 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "learning_rate": 1.2922033898305086e-06, | |
| "loss": 0.002, | |
| "step": 26200 | |
| }, | |
| { | |
| "epoch": 14.03, | |
| "learning_rate": 1.2583050847457629e-06, | |
| "loss": 0.0016, | |
| "step": 26300 | |
| }, | |
| { | |
| "epoch": 14.03, | |
| "learning_rate": 1.2244067796610171e-06, | |
| "loss": 0.001, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 14.03, | |
| "learning_rate": 1.1905084745762714e-06, | |
| "loss": 0.0014, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 14.04, | |
| "learning_rate": 1.1566101694915254e-06, | |
| "loss": 0.0013, | |
| "step": 26600 | |
| }, | |
| { | |
| "epoch": 14.04, | |
| "learning_rate": 1.1227118644067796e-06, | |
| "loss": 0.0015, | |
| "step": 26700 | |
| }, | |
| { | |
| "epoch": 14.04, | |
| "learning_rate": 1.0888135593220339e-06, | |
| "loss": 0.0014, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 14.05, | |
| "learning_rate": 1.0549152542372884e-06, | |
| "loss": 0.0014, | |
| "step": 26900 | |
| }, | |
| { | |
| "epoch": 14.05, | |
| "learning_rate": 1.0210169491525424e-06, | |
| "loss": 0.0013, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 14.05, | |
| "learning_rate": 9.871186440677966e-07, | |
| "loss": 0.0012, | |
| "step": 27100 | |
| }, | |
| { | |
| "epoch": 14.06, | |
| "learning_rate": 9.532203389830509e-07, | |
| "loss": 0.0015, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 14.06, | |
| "learning_rate": 9.193220338983051e-07, | |
| "loss": 0.0012, | |
| "step": 27300 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 8.854237288135594e-07, | |
| "loss": 0.0197, | |
| "step": 27400 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "learning_rate": 8.515254237288137e-07, | |
| "loss": 0.0192, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "learning_rate": 8.176271186440679e-07, | |
| "loss": 0.0242, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "learning_rate": 7.837288135593221e-07, | |
| "loss": 0.0281, | |
| "step": 27700 | |
| }, | |
| { | |
| "epoch": 15.02, | |
| "learning_rate": 7.498305084745763e-07, | |
| "loss": 0.0274, | |
| "step": 27800 | |
| }, | |
| { | |
| "epoch": 15.02, | |
| "learning_rate": 7.159322033898305e-07, | |
| "loss": 0.0212, | |
| "step": 27900 | |
| }, | |
| { | |
| "epoch": 15.02, | |
| "learning_rate": 6.820338983050848e-07, | |
| "loss": 0.0199, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 15.02, | |
| "eval_loss": 0.25532078742980957, | |
| "eval_runtime": 7006.3593, | |
| "eval_samples_per_second": 2.076, | |
| "eval_steps_per_second": 0.259, | |
| "eval_wer": 15.18483092331064, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 15.03, | |
| "learning_rate": 6.484745762711865e-07, | |
| "loss": 0.0197, | |
| "step": 28100 | |
| }, | |
| { | |
| "epoch": 15.03, | |
| "learning_rate": 6.145762711864408e-07, | |
| "loss": 0.0137, | |
| "step": 28200 | |
| }, | |
| { | |
| "epoch": 15.03, | |
| "learning_rate": 5.806779661016949e-07, | |
| "loss": 0.0167, | |
| "step": 28300 | |
| }, | |
| { | |
| "epoch": 15.04, | |
| "learning_rate": 5.467796610169493e-07, | |
| "loss": 0.0165, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 15.04, | |
| "learning_rate": 5.128813559322034e-07, | |
| "loss": 0.0161, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 15.04, | |
| "learning_rate": 4.789830508474576e-07, | |
| "loss": 0.0147, | |
| "step": 28600 | |
| }, | |
| { | |
| "epoch": 15.05, | |
| "learning_rate": 4.4508474576271195e-07, | |
| "loss": 0.0186, | |
| "step": 28700 | |
| }, | |
| { | |
| "epoch": 15.05, | |
| "learning_rate": 4.1118644067796615e-07, | |
| "loss": 0.0228, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 15.05, | |
| "learning_rate": 3.7728813559322034e-07, | |
| "loss": 0.0228, | |
| "step": 28900 | |
| }, | |
| { | |
| "epoch": 15.06, | |
| "learning_rate": 3.433898305084746e-07, | |
| "loss": 0.0195, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 15.06, | |
| "learning_rate": 3.0949152542372884e-07, | |
| "loss": 0.0233, | |
| "step": 29100 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 2.755932203389831e-07, | |
| "loss": 0.0118, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 16.01, | |
| "learning_rate": 2.4169491525423734e-07, | |
| "loss": 0.0103, | |
| "step": 29300 | |
| }, | |
| { | |
| "epoch": 16.01, | |
| "learning_rate": 2.0779661016949154e-07, | |
| "loss": 0.0118, | |
| "step": 29400 | |
| }, | |
| { | |
| "epoch": 16.01, | |
| "learning_rate": 1.7389830508474579e-07, | |
| "loss": 0.0161, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 16.02, | |
| "learning_rate": 1.4e-07, | |
| "loss": 0.016, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 16.02, | |
| "learning_rate": 1.0610169491525425e-07, | |
| "loss": 0.0138, | |
| "step": 29700 | |
| }, | |
| { | |
| "epoch": 16.02, | |
| "learning_rate": 7.220338983050848e-08, | |
| "loss": 0.0125, | |
| "step": 29800 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 3.830508474576272e-08, | |
| "loss": 0.0129, | |
| "step": 29900 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 4.406779661016949e-09, | |
| "loss": 0.0083, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "eval_loss": 0.2589367628097534, | |
| "eval_runtime": 7159.0133, | |
| "eval_samples_per_second": 2.031, | |
| "eval_steps_per_second": 0.254, | |
| "eval_wer": 15.072300680807968, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "step": 30000, | |
| "total_flos": 1.3849328795516928e+20, | |
| "train_loss": 0.07104161073341966, | |
| "train_runtime": 196903.7961, | |
| "train_samples_per_second": 2.438, | |
| "train_steps_per_second": 0.152 | |
| } | |
| ], | |
| "max_steps": 30000, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 1.3849328795516928e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |