| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 39.13027744270205, | |
| "global_step": 8100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0049, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 0.4129045903682709, | |
| "eval_runtime": 227.662, | |
| "eval_samples_per_second": 19.551, | |
| "eval_steps_per_second": 2.447, | |
| "eval_wer": 0.4147929999433652, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 9.940001199976001e-05, | |
| "loss": 0.6812, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 0.34252655506134033, | |
| "eval_runtime": 227.479, | |
| "eval_samples_per_second": 19.567, | |
| "eval_steps_per_second": 2.449, | |
| "eval_wer": 0.3746389533895905, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 9.880002399952003e-05, | |
| "loss": 0.5692, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "eval_loss": 0.3179880976676941, | |
| "eval_runtime": 228.3215, | |
| "eval_samples_per_second": 19.494, | |
| "eval_steps_per_second": 2.44, | |
| "eval_wer": 0.34637820694342186, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 9.820003599928002e-05, | |
| "loss": 0.571, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "eval_loss": 0.2999042272567749, | |
| "eval_runtime": 230.9757, | |
| "eval_samples_per_second": 19.27, | |
| "eval_steps_per_second": 2.412, | |
| "eval_wer": 0.32689584867191485, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 9.760004799904002e-05, | |
| "loss": 0.5005, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "eval_loss": 0.29656580090522766, | |
| "eval_runtime": 233.3067, | |
| "eval_samples_per_second": 19.078, | |
| "eval_steps_per_second": 2.387, | |
| "eval_wer": 0.3163617828623209, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 9.700005999880004e-05, | |
| "loss": 0.4887, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "eval_loss": 0.2906932234764099, | |
| "eval_runtime": 231.4032, | |
| "eval_samples_per_second": 19.235, | |
| "eval_steps_per_second": 2.407, | |
| "eval_wer": 0.30418530894262896, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 9.640007199856004e-05, | |
| "loss": 0.4437, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "eval_loss": 0.3040316700935364, | |
| "eval_runtime": 234.1226, | |
| "eval_samples_per_second": 19.011, | |
| "eval_steps_per_second": 2.379, | |
| "eval_wer": 0.2976156765022371, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 9.580008399832003e-05, | |
| "loss": 0.4448, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "eval_loss": 0.29794958233833313, | |
| "eval_runtime": 233.0536, | |
| "eval_samples_per_second": 19.099, | |
| "eval_steps_per_second": 2.39, | |
| "eval_wer": 0.2977289460270714, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 9.520009599808005e-05, | |
| "loss": 0.4166, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "eval_loss": 0.28735384345054626, | |
| "eval_runtime": 233.1123, | |
| "eval_samples_per_second": 19.094, | |
| "eval_steps_per_second": 2.389, | |
| "eval_wer": 0.28730814974231184, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 9.460010799784005e-05, | |
| "loss": 0.3996, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "eval_loss": 0.28613924980163574, | |
| "eval_runtime": 233.6326, | |
| "eval_samples_per_second": 19.051, | |
| "eval_steps_per_second": 2.384, | |
| "eval_wer": 0.28362689018519566, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "learning_rate": 9.400011999760005e-05, | |
| "loss": 0.3896, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "eval_loss": 0.2923850119113922, | |
| "eval_runtime": 234.9083, | |
| "eval_samples_per_second": 18.948, | |
| "eval_steps_per_second": 2.371, | |
| "eval_wer": 0.27643427535821485, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "learning_rate": 9.340013199736006e-05, | |
| "loss": 0.3749, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "eval_loss": 0.3192364275455475, | |
| "eval_runtime": 236.1058, | |
| "eval_samples_per_second": 18.852, | |
| "eval_steps_per_second": 2.359, | |
| "eval_wer": 0.2773970663193068, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "learning_rate": 9.280014399712006e-05, | |
| "loss": 0.3563, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "eval_loss": 0.2812280058860779, | |
| "eval_runtime": 236.2957, | |
| "eval_samples_per_second": 18.837, | |
| "eval_steps_per_second": 2.357, | |
| "eval_wer": 0.2699779124426573, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 9.220015599688006e-05, | |
| "loss": 0.341, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "eval_loss": 0.287455677986145, | |
| "eval_runtime": 236.5657, | |
| "eval_samples_per_second": 18.815, | |
| "eval_steps_per_second": 2.355, | |
| "eval_wer": 0.27949255252874217, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 7.25, | |
| "learning_rate": 9.160016799664007e-05, | |
| "loss": 0.3581, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 7.25, | |
| "eval_loss": 0.2976861596107483, | |
| "eval_runtime": 238.0057, | |
| "eval_samples_per_second": 18.701, | |
| "eval_steps_per_second": 2.34, | |
| "eval_wer": 0.2733193634252704, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 7.73, | |
| "learning_rate": 9.100017999640008e-05, | |
| "loss": 0.3335, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 7.73, | |
| "eval_loss": 0.3042807877063751, | |
| "eval_runtime": 238.1461, | |
| "eval_samples_per_second": 18.69, | |
| "eval_steps_per_second": 2.339, | |
| "eval_wer": 0.2717902248400068, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 8.21, | |
| "learning_rate": 9.040019199616007e-05, | |
| "loss": 0.3017, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 8.21, | |
| "eval_loss": 0.3114258646965027, | |
| "eval_runtime": 237.5998, | |
| "eval_samples_per_second": 18.733, | |
| "eval_steps_per_second": 2.344, | |
| "eval_wer": 0.26901512148156537, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "learning_rate": 8.980020399592008e-05, | |
| "loss": 0.3119, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "eval_loss": 0.2932363748550415, | |
| "eval_runtime": 237.3835, | |
| "eval_samples_per_second": 18.75, | |
| "eval_steps_per_second": 2.346, | |
| "eval_wer": 0.27280965056351586, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 9.18, | |
| "learning_rate": 8.920621587568248e-05, | |
| "loss": 0.2963, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 9.18, | |
| "eval_loss": 0.3103686273097992, | |
| "eval_runtime": 238.4335, | |
| "eval_samples_per_second": 18.668, | |
| "eval_steps_per_second": 2.336, | |
| "eval_wer": 0.262615393328425, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 9.66, | |
| "learning_rate": 8.86062278754425e-05, | |
| "loss": 0.2916, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 9.66, | |
| "eval_loss": 0.306538462638855, | |
| "eval_runtime": 238.5115, | |
| "eval_samples_per_second": 18.662, | |
| "eval_steps_per_second": 2.335, | |
| "eval_wer": 0.25802797757263407, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 10.14, | |
| "learning_rate": 8.80062398752025e-05, | |
| "loss": 0.2996, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 10.14, | |
| "eval_loss": 0.29877138137817383, | |
| "eval_runtime": 240.2761, | |
| "eval_samples_per_second": 18.525, | |
| "eval_steps_per_second": 2.318, | |
| "eval_wer": 0.25072209322081895, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 10.63, | |
| "learning_rate": 8.74062518749625e-05, | |
| "loss": 0.2754, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 10.63, | |
| "eval_loss": 0.30767822265625, | |
| "eval_runtime": 238.3349, | |
| "eval_samples_per_second": 18.675, | |
| "eval_steps_per_second": 2.337, | |
| "eval_wer": 0.24766381605029167, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 11.11, | |
| "learning_rate": 8.680626387472251e-05, | |
| "loss": 0.2659, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 11.11, | |
| "eval_loss": 0.30970337986946106, | |
| "eval_runtime": 237.7796, | |
| "eval_samples_per_second": 18.719, | |
| "eval_steps_per_second": 2.343, | |
| "eval_wer": 0.2516848841819109, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 11.59, | |
| "learning_rate": 8.620627587448251e-05, | |
| "loss": 0.2662, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 11.59, | |
| "eval_loss": 0.30694690346717834, | |
| "eval_runtime": 238.8654, | |
| "eval_samples_per_second": 18.634, | |
| "eval_steps_per_second": 2.332, | |
| "eval_wer": 0.2517981537067452, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 12.08, | |
| "learning_rate": 8.560628787424252e-05, | |
| "loss": 0.2922, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 12.08, | |
| "eval_loss": 0.2964646518230438, | |
| "eval_runtime": 238.0736, | |
| "eval_samples_per_second": 18.696, | |
| "eval_steps_per_second": 2.34, | |
| "eval_wer": 0.25445998754035226, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 12.56, | |
| "learning_rate": 8.500629987400252e-05, | |
| "loss": 0.2528, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 12.56, | |
| "eval_loss": 0.30119049549102783, | |
| "eval_runtime": 238.9237, | |
| "eval_samples_per_second": 18.629, | |
| "eval_steps_per_second": 2.331, | |
| "eval_wer": 0.25106190179532195, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 13.04, | |
| "learning_rate": 8.440631187376254e-05, | |
| "loss": 0.2655, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 13.04, | |
| "eval_loss": 0.31211164593696594, | |
| "eval_runtime": 238.5153, | |
| "eval_samples_per_second": 18.661, | |
| "eval_steps_per_second": 2.335, | |
| "eval_wer": 0.2524211360933341, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 13.53, | |
| "learning_rate": 8.380632387352253e-05, | |
| "loss": 0.2468, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 13.53, | |
| "eval_loss": 0.31889286637306213, | |
| "eval_runtime": 238.3587, | |
| "eval_samples_per_second": 18.674, | |
| "eval_steps_per_second": 2.337, | |
| "eval_wer": 0.25587585660078155, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 8.320633587328253e-05, | |
| "loss": 0.2584, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "eval_loss": 0.31399527192115784, | |
| "eval_runtime": 238.7233, | |
| "eval_samples_per_second": 18.645, | |
| "eval_steps_per_second": 2.333, | |
| "eval_wer": 0.2527609446678371, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 14.49, | |
| "learning_rate": 8.260634787304255e-05, | |
| "loss": 0.2389, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 14.49, | |
| "eval_loss": 0.32613444328308105, | |
| "eval_runtime": 238.1504, | |
| "eval_samples_per_second": 18.69, | |
| "eval_steps_per_second": 2.339, | |
| "eval_wer": 0.25049555417115027, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 14.97, | |
| "learning_rate": 8.200635987280255e-05, | |
| "loss": 0.2489, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 14.97, | |
| "eval_loss": 0.3339328169822693, | |
| "eval_runtime": 238.2319, | |
| "eval_samples_per_second": 18.683, | |
| "eval_steps_per_second": 2.338, | |
| "eval_wer": 0.2527609446678371, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 15.46, | |
| "learning_rate": 8.140637187256254e-05, | |
| "loss": 0.2231, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 15.46, | |
| "eval_loss": 0.351179838180542, | |
| "eval_runtime": 242.4013, | |
| "eval_samples_per_second": 18.362, | |
| "eval_steps_per_second": 2.298, | |
| "eval_wer": 0.25327065752959166, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 15.94, | |
| "learning_rate": 8.080638387232256e-05, | |
| "loss": 0.2336, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 15.94, | |
| "eval_loss": 0.3061370849609375, | |
| "eval_runtime": 241.0412, | |
| "eval_samples_per_second": 18.466, | |
| "eval_steps_per_second": 2.311, | |
| "eval_wer": 0.25576258707594723, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 16.42, | |
| "learning_rate": 8.020639587208256e-05, | |
| "loss": 0.2236, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 16.42, | |
| "eval_loss": 0.30908501148223877, | |
| "eval_runtime": 242.0206, | |
| "eval_samples_per_second": 18.391, | |
| "eval_steps_per_second": 2.301, | |
| "eval_wer": 0.24817352891204622, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 16.91, | |
| "learning_rate": 7.960640787184257e-05, | |
| "loss": 0.228, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 16.91, | |
| "eval_loss": 0.3035767078399658, | |
| "eval_runtime": 241.4436, | |
| "eval_samples_per_second": 18.435, | |
| "eval_steps_per_second": 2.307, | |
| "eval_wer": 0.24811689414962904, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 17.39, | |
| "learning_rate": 7.900641987160258e-05, | |
| "loss": 0.2185, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 17.39, | |
| "eval_loss": 0.32117584347724915, | |
| "eval_runtime": 241.6265, | |
| "eval_samples_per_second": 18.421, | |
| "eval_steps_per_second": 2.305, | |
| "eval_wer": 0.24698419890128562, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 17.87, | |
| "learning_rate": 7.840643187136257e-05, | |
| "loss": 0.2212, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 17.87, | |
| "eval_loss": 0.32781311869621277, | |
| "eval_runtime": 242.3065, | |
| "eval_samples_per_second": 18.369, | |
| "eval_steps_per_second": 2.299, | |
| "eval_wer": 0.2376394631024523, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 18.36, | |
| "learning_rate": 7.780644387112258e-05, | |
| "loss": 0.2142, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 18.36, | |
| "eval_loss": 0.3259940445423126, | |
| "eval_runtime": 241.5744, | |
| "eval_samples_per_second": 18.425, | |
| "eval_steps_per_second": 2.306, | |
| "eval_wer": 0.23967831454947047, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 18.84, | |
| "learning_rate": 7.72064558708826e-05, | |
| "loss": 0.214, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 18.84, | |
| "eval_loss": 0.31706514954566956, | |
| "eval_runtime": 237.9228, | |
| "eval_samples_per_second": 18.708, | |
| "eval_steps_per_second": 2.341, | |
| "eval_wer": 0.23950841026221895, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 19.32, | |
| "learning_rate": 7.66064678706426e-05, | |
| "loss": 0.2157, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 19.32, | |
| "eval_loss": 0.3263161778450012, | |
| "eval_runtime": 238.133, | |
| "eval_samples_per_second": 18.691, | |
| "eval_steps_per_second": 2.339, | |
| "eval_wer": 0.2429631307696664, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 19.81, | |
| "learning_rate": 7.600647987040259e-05, | |
| "loss": 0.2075, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 19.81, | |
| "eval_loss": 0.3325376510620117, | |
| "eval_runtime": 238.7972, | |
| "eval_samples_per_second": 18.639, | |
| "eval_steps_per_second": 2.333, | |
| "eval_wer": 0.2374129240527836, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 20.29, | |
| "learning_rate": 7.54064918701626e-05, | |
| "loss": 0.2049, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 20.29, | |
| "eval_loss": 0.3318737745285034, | |
| "eval_runtime": 238.8141, | |
| "eval_samples_per_second": 18.638, | |
| "eval_steps_per_second": 2.332, | |
| "eval_wer": 0.24194370504615734, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 20.77, | |
| "learning_rate": 7.480650386992261e-05, | |
| "loss": 0.2049, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 20.77, | |
| "eval_loss": 0.3494427800178528, | |
| "eval_runtime": 237.8921, | |
| "eval_samples_per_second": 18.71, | |
| "eval_steps_per_second": 2.341, | |
| "eval_wer": 0.24251005267032905, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 21.26, | |
| "learning_rate": 7.420651586968261e-05, | |
| "loss": 0.2027, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 21.26, | |
| "eval_loss": 0.3245479166507721, | |
| "eval_runtime": 238.6469, | |
| "eval_samples_per_second": 18.651, | |
| "eval_steps_per_second": 2.334, | |
| "eval_wer": 0.24279322648241491, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 21.74, | |
| "learning_rate": 7.360652786944261e-05, | |
| "loss": 0.1943, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 21.74, | |
| "eval_loss": 0.33962830901145935, | |
| "eval_runtime": 241.874, | |
| "eval_samples_per_second": 18.402, | |
| "eval_steps_per_second": 2.303, | |
| "eval_wer": 0.2394517754998018, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 22.22, | |
| "learning_rate": 7.300653986920262e-05, | |
| "loss": 0.1908, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 22.22, | |
| "eval_loss": 0.336451917886734, | |
| "eval_runtime": 243.387, | |
| "eval_samples_per_second": 18.288, | |
| "eval_steps_per_second": 2.289, | |
| "eval_wer": 0.23718638500311492, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 22.7, | |
| "learning_rate": 7.240655186896262e-05, | |
| "loss": 0.1907, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 22.7, | |
| "eval_loss": 0.32546359300613403, | |
| "eval_runtime": 241.8966, | |
| "eval_samples_per_second": 18.4, | |
| "eval_steps_per_second": 2.303, | |
| "eval_wer": 0.23803590643937247, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 23.19, | |
| "learning_rate": 7.180656386872263e-05, | |
| "loss": 0.1805, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 23.19, | |
| "eval_loss": 0.3294132351875305, | |
| "eval_runtime": 241.6869, | |
| "eval_samples_per_second": 18.416, | |
| "eval_steps_per_second": 2.305, | |
| "eval_wer": 0.2310131958996432, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 23.67, | |
| "learning_rate": 7.120657586848264e-05, | |
| "loss": 0.183, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 23.67, | |
| "eval_loss": 0.3282703459262848, | |
| "eval_runtime": 241.8191, | |
| "eval_samples_per_second": 18.406, | |
| "eval_steps_per_second": 2.303, | |
| "eval_wer": 0.23871552358837855, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 24.15, | |
| "learning_rate": 7.060658786824263e-05, | |
| "loss": 0.1856, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 24.15, | |
| "eval_loss": 0.34477418661117554, | |
| "eval_runtime": 239.7408, | |
| "eval_samples_per_second": 18.566, | |
| "eval_steps_per_second": 2.323, | |
| "eval_wer": 0.2370164807158634, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 24.64, | |
| "learning_rate": 7.000659986800264e-05, | |
| "loss": 0.1883, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 24.64, | |
| "eval_loss": 0.3297135829925537, | |
| "eval_runtime": 239.2028, | |
| "eval_samples_per_second": 18.608, | |
| "eval_steps_per_second": 2.329, | |
| "eval_wer": 0.23123973494931188, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 25.12, | |
| "learning_rate": 6.940661186776265e-05, | |
| "loss": 0.1752, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 25.12, | |
| "eval_loss": 0.32844457030296326, | |
| "eval_runtime": 239.4259, | |
| "eval_samples_per_second": 18.59, | |
| "eval_steps_per_second": 2.326, | |
| "eval_wer": 0.23633686356685735, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 25.6, | |
| "learning_rate": 6.880662386752266e-05, | |
| "loss": 0.1702, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 25.6, | |
| "eval_loss": 0.3195815086364746, | |
| "eval_runtime": 239.8214, | |
| "eval_samples_per_second": 18.56, | |
| "eval_steps_per_second": 2.323, | |
| "eval_wer": 0.23814917596420684, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 26.09, | |
| "learning_rate": 6.820663586728266e-05, | |
| "loss": 0.1815, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 26.09, | |
| "eval_loss": 0.3348907232284546, | |
| "eval_runtime": 239.2339, | |
| "eval_samples_per_second": 18.605, | |
| "eval_steps_per_second": 2.328, | |
| "eval_wer": 0.23418474259500482, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 26.57, | |
| "learning_rate": 6.760664786704266e-05, | |
| "loss": 0.1673, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 26.57, | |
| "eval_loss": 0.33562546968460083, | |
| "eval_runtime": 239.3973, | |
| "eval_samples_per_second": 18.593, | |
| "eval_steps_per_second": 2.327, | |
| "eval_wer": 0.23418474259500482, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 27.05, | |
| "learning_rate": 6.700665986680267e-05, | |
| "loss": 0.1707, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 27.05, | |
| "eval_loss": 0.3253572881221771, | |
| "eval_runtime": 240.5261, | |
| "eval_samples_per_second": 18.505, | |
| "eval_steps_per_second": 2.316, | |
| "eval_wer": 0.2327688735345755, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 27.54, | |
| "learning_rate": 6.640667186656267e-05, | |
| "loss": 0.1676, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 27.54, | |
| "eval_loss": 0.3263373076915741, | |
| "eval_runtime": 240.3409, | |
| "eval_samples_per_second": 18.52, | |
| "eval_steps_per_second": 2.318, | |
| "eval_wer": 0.23214589114798664, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 28.02, | |
| "learning_rate": 6.580668386632267e-05, | |
| "loss": 0.1711, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 28.02, | |
| "eval_loss": 0.3160211145877838, | |
| "eval_runtime": 239.7456, | |
| "eval_samples_per_second": 18.566, | |
| "eval_steps_per_second": 2.323, | |
| "eval_wer": 0.23333522115874725, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 28.5, | |
| "learning_rate": 6.521269574608508e-05, | |
| "loss": 0.1541, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 28.5, | |
| "eval_loss": 0.3510294556617737, | |
| "eval_runtime": 241.2363, | |
| "eval_samples_per_second": 18.451, | |
| "eval_steps_per_second": 2.309, | |
| "eval_wer": 0.22948405731437957, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 28.98, | |
| "learning_rate": 6.46127077458451e-05, | |
| "loss": 0.1588, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 28.98, | |
| "eval_loss": 0.3481566607952118, | |
| "eval_runtime": 239.0227, | |
| "eval_samples_per_second": 18.622, | |
| "eval_steps_per_second": 2.33, | |
| "eval_wer": 0.23667667214136037, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 29.47, | |
| "learning_rate": 6.401271974560509e-05, | |
| "loss": 0.1554, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 29.47, | |
| "eval_loss": 0.3343554735183716, | |
| "eval_runtime": 305.5597, | |
| "eval_samples_per_second": 14.567, | |
| "eval_steps_per_second": 1.823, | |
| "eval_wer": 0.23254233448490683, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 29.95, | |
| "learning_rate": 6.341273174536509e-05, | |
| "loss": 0.1584, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 29.95, | |
| "eval_loss": 0.33723703026771545, | |
| "eval_runtime": 299.7981, | |
| "eval_samples_per_second": 14.847, | |
| "eval_steps_per_second": 1.858, | |
| "eval_wer": 0.23265560400974117, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 30.43, | |
| "learning_rate": 6.281874362512749e-05, | |
| "loss": 0.1563, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 30.43, | |
| "eval_loss": 0.34475767612457275, | |
| "eval_runtime": 302.4221, | |
| "eval_samples_per_second": 14.718, | |
| "eval_steps_per_second": 1.842, | |
| "eval_wer": 0.22925751826471089, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 30.92, | |
| "learning_rate": 6.221875562488751e-05, | |
| "loss": 0.1509, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 30.92, | |
| "eval_loss": 0.34635189175605774, | |
| "eval_runtime": 240.7665, | |
| "eval_samples_per_second": 18.487, | |
| "eval_steps_per_second": 2.313, | |
| "eval_wer": 0.23078665684997451, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 31.4, | |
| "learning_rate": 6.161876762464751e-05, | |
| "loss": 0.1604, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 31.4, | |
| "eval_loss": 0.3334050178527832, | |
| "eval_runtime": 239.9789, | |
| "eval_samples_per_second": 18.547, | |
| "eval_steps_per_second": 2.321, | |
| "eval_wer": 0.22823809254120178, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 31.88, | |
| "learning_rate": 6.101877962440752e-05, | |
| "loss": 0.1487, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 31.88, | |
| "eval_loss": 0.35308021306991577, | |
| "eval_runtime": 239.0592, | |
| "eval_samples_per_second": 18.619, | |
| "eval_steps_per_second": 2.33, | |
| "eval_wer": 0.22948405731437957, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 32.37, | |
| "learning_rate": 6.0418791624167514e-05, | |
| "loss": 0.1492, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 32.37, | |
| "eval_loss": 0.346653014421463, | |
| "eval_runtime": 242.7759, | |
| "eval_samples_per_second": 18.334, | |
| "eval_steps_per_second": 2.294, | |
| "eval_wer": 0.2333918559211644, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 32.85, | |
| "learning_rate": 5.9818803623927524e-05, | |
| "loss": 0.1419, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 32.85, | |
| "eval_loss": 0.3448370397090912, | |
| "eval_runtime": 240.5384, | |
| "eval_samples_per_second": 18.504, | |
| "eval_steps_per_second": 2.316, | |
| "eval_wer": 0.22891770969020786, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "learning_rate": 5.921881562368753e-05, | |
| "loss": 0.1473, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "eval_loss": 0.33699721097946167, | |
| "eval_runtime": 240.2189, | |
| "eval_samples_per_second": 18.529, | |
| "eval_steps_per_second": 2.319, | |
| "eval_wer": 0.22789828396669876, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 33.82, | |
| "learning_rate": 5.861882762344754e-05, | |
| "loss": 0.1421, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 33.82, | |
| "eval_loss": 0.3586665093898773, | |
| "eval_runtime": 240.0237, | |
| "eval_samples_per_second": 18.544, | |
| "eval_steps_per_second": 2.321, | |
| "eval_wer": 0.22733193634252705, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 34.3, | |
| "learning_rate": 5.801883962320754e-05, | |
| "loss": 0.1478, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 34.3, | |
| "eval_loss": 0.34202027320861816, | |
| "eval_runtime": 241.148, | |
| "eval_samples_per_second": 18.458, | |
| "eval_steps_per_second": 2.31, | |
| "eval_wer": 0.22829472730361897, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 34.78, | |
| "learning_rate": 5.741885162296754e-05, | |
| "loss": 0.1417, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 34.78, | |
| "eval_loss": 0.3443390429019928, | |
| "eval_runtime": 240.4384, | |
| "eval_samples_per_second": 18.512, | |
| "eval_steps_per_second": 2.317, | |
| "eval_wer": 0.22971059636404825, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 35.27, | |
| "learning_rate": 5.681886362272755e-05, | |
| "loss": 0.144, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 35.27, | |
| "eval_loss": 0.3634556531906128, | |
| "eval_runtime": 240.4974, | |
| "eval_samples_per_second": 18.507, | |
| "eval_steps_per_second": 2.316, | |
| "eval_wer": 0.2310131958996432, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 35.75, | |
| "learning_rate": 5.621887562248755e-05, | |
| "loss": 0.1389, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 35.75, | |
| "eval_loss": 0.3476064205169678, | |
| "eval_runtime": 242.249, | |
| "eval_samples_per_second": 18.374, | |
| "eval_steps_per_second": 2.299, | |
| "eval_wer": 0.23452455116950785, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 36.23, | |
| "learning_rate": 5.561888762224756e-05, | |
| "loss": 0.1363, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 36.23, | |
| "eval_loss": 0.3405874967575073, | |
| "eval_runtime": 240.8953, | |
| "eval_samples_per_second": 18.477, | |
| "eval_steps_per_second": 2.312, | |
| "eval_wer": 0.23152290876139775, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 36.71, | |
| "learning_rate": 5.501889962200756e-05, | |
| "loss": 0.1354, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 36.71, | |
| "eval_loss": 0.3625139594078064, | |
| "eval_runtime": 240.5012, | |
| "eval_samples_per_second": 18.507, | |
| "eval_steps_per_second": 2.316, | |
| "eval_wer": 0.22886107492779068, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 37.2, | |
| "learning_rate": 5.441891162176756e-05, | |
| "loss": 0.1306, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 37.2, | |
| "eval_loss": 0.3339903652667999, | |
| "eval_runtime": 240.6242, | |
| "eval_samples_per_second": 18.498, | |
| "eval_steps_per_second": 2.315, | |
| "eval_wer": 0.2261992410941836, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 37.68, | |
| "learning_rate": 5.381892362152757e-05, | |
| "loss": 0.1327, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 37.68, | |
| "eval_loss": 0.3558659851551056, | |
| "eval_runtime": 242.3369, | |
| "eval_samples_per_second": 18.367, | |
| "eval_steps_per_second": 2.298, | |
| "eval_wer": 0.22676558871835534, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 38.16, | |
| "learning_rate": 5.321893562128758e-05, | |
| "loss": 0.1291, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 38.16, | |
| "eval_loss": 0.34240660071372986, | |
| "eval_runtime": 237.8177, | |
| "eval_samples_per_second": 18.716, | |
| "eval_steps_per_second": 2.342, | |
| "eval_wer": 0.22580279775726342, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 38.65, | |
| "learning_rate": 5.261894762104757e-05, | |
| "loss": 0.1288, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 38.65, | |
| "eval_loss": 0.33796748518943787, | |
| "eval_runtime": 239.7462, | |
| "eval_samples_per_second": 18.565, | |
| "eval_steps_per_second": 2.323, | |
| "eval_wer": 0.22999377017613412, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 39.13, | |
| "learning_rate": 5.201895962080758e-05, | |
| "loss": 0.1209, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 39.13, | |
| "eval_loss": 0.3304120600223541, | |
| "eval_runtime": 240.8061, | |
| "eval_samples_per_second": 18.484, | |
| "eval_steps_per_second": 2.313, | |
| "eval_wer": 0.228634535878122, | |
| "step": 8100 | |
| } | |
| ], | |
| "max_steps": 16767, | |
| "num_train_epochs": 81, | |
| "total_flos": 3.507453466179225e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |