| { | |
| "best_global_step": 13000, | |
| "best_metric": 0.44776962168266515, | |
| "best_model_checkpoint": "/home/cluster-dgxa100/slp01/bagas-fine-tune-whisper/whisper-tiny-javanese-openslr-v7/checkpoint-13000", | |
| "epoch": 400.0, | |
| "eval_steps": 1000, | |
| "global_step": 50000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 28.316560745239258, | |
| "learning_rate": 7.88e-07, | |
| "loss": 3.6257, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 19.273317337036133, | |
| "learning_rate": 1.588e-06, | |
| "loss": 2.0745, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "grad_norm": 20.253143310546875, | |
| "learning_rate": 2.3880000000000003e-06, | |
| "loss": 1.5564, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "grad_norm": 18.321447372436523, | |
| "learning_rate": 3.188e-06, | |
| "loss": 1.2332, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 15.124577522277832, | |
| "learning_rate": 3.988000000000001e-06, | |
| "loss": 0.9973, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.0427539348602295, | |
| "eval_runtime": 42.8057, | |
| "eval_samples_per_second": 5.84, | |
| "eval_steps_per_second": 1.472, | |
| "eval_wer": 0.6821005081874647, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "grad_norm": 17.642391204833984, | |
| "learning_rate": 4.7880000000000006e-06, | |
| "loss": 0.7932, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "grad_norm": 12.182209014892578, | |
| "learning_rate": 5.588e-06, | |
| "loss": 0.6471, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "grad_norm": 14.519808769226074, | |
| "learning_rate": 6.3880000000000005e-06, | |
| "loss": 0.5151, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "grad_norm": 13.092401504516602, | |
| "learning_rate": 7.1880000000000005e-06, | |
| "loss": 0.3948, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "grad_norm": 11.094600677490234, | |
| "learning_rate": 7.988e-06, | |
| "loss": 0.3139, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 0.8733022212982178, | |
| "eval_runtime": 46.221, | |
| "eval_samples_per_second": 5.409, | |
| "eval_steps_per_second": 1.363, | |
| "eval_wer": 0.6233766233766234, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 17.6, | |
| "grad_norm": 13.814520835876465, | |
| "learning_rate": 8.788000000000001e-06, | |
| "loss": 0.2389, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "grad_norm": 10.147465705871582, | |
| "learning_rate": 9.588e-06, | |
| "loss": 0.1868, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 20.8, | |
| "grad_norm": 6.512983798980713, | |
| "learning_rate": 1.0388e-05, | |
| "loss": 0.1454, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 22.4, | |
| "grad_norm": 7.759674549102783, | |
| "learning_rate": 1.1188e-05, | |
| "loss": 0.1186, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "grad_norm": 8.339158058166504, | |
| "learning_rate": 1.1988000000000001e-05, | |
| "loss": 0.0988, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 0.8925266861915588, | |
| "eval_runtime": 44.0477, | |
| "eval_samples_per_second": 5.676, | |
| "eval_steps_per_second": 1.43, | |
| "eval_wer": 0.6346696781479391, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 25.6, | |
| "grad_norm": 4.570150375366211, | |
| "learning_rate": 1.2788e-05, | |
| "loss": 0.0821, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 27.2, | |
| "grad_norm": 6.510232925415039, | |
| "learning_rate": 1.3588000000000001e-05, | |
| "loss": 0.0745, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 28.8, | |
| "grad_norm": 6.720197677612305, | |
| "learning_rate": 1.4388000000000002e-05, | |
| "loss": 0.0664, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 30.4, | |
| "grad_norm": 6.113977432250977, | |
| "learning_rate": 1.5188000000000001e-05, | |
| "loss": 0.0579, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "grad_norm": 4.528390884399414, | |
| "learning_rate": 1.5988e-05, | |
| "loss": 0.0499, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_loss": 0.9389314651489258, | |
| "eval_runtime": 43.1155, | |
| "eval_samples_per_second": 5.798, | |
| "eval_steps_per_second": 1.461, | |
| "eval_wer": 0.6149068322981367, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 33.6, | |
| "grad_norm": 8.023102760314941, | |
| "learning_rate": 1.6784e-05, | |
| "loss": 0.0488, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 35.2, | |
| "grad_norm": 5.378859043121338, | |
| "learning_rate": 1.7584e-05, | |
| "loss": 0.0443, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 36.8, | |
| "grad_norm": 6.565428256988525, | |
| "learning_rate": 1.8380000000000004e-05, | |
| "loss": 0.0415, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 38.4, | |
| "grad_norm": 3.81632137298584, | |
| "learning_rate": 1.918e-05, | |
| "loss": 0.0387, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 1.75031316280365, | |
| "learning_rate": 1.9980000000000002e-05, | |
| "loss": 0.0349, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_loss": 0.9878742098808289, | |
| "eval_runtime": 41.8583, | |
| "eval_samples_per_second": 5.973, | |
| "eval_steps_per_second": 1.505, | |
| "eval_wer": 0.6205533596837944, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 41.6, | |
| "grad_norm": 1.5769927501678467, | |
| "learning_rate": 1.9913333333333335e-05, | |
| "loss": 0.0335, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 43.2, | |
| "grad_norm": 4.837329387664795, | |
| "learning_rate": 1.9824444444444445e-05, | |
| "loss": 0.0303, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 44.8, | |
| "grad_norm": 4.526083469390869, | |
| "learning_rate": 1.9735555555555556e-05, | |
| "loss": 0.0282, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 46.4, | |
| "grad_norm": 4.3648176193237305, | |
| "learning_rate": 1.9646666666666666e-05, | |
| "loss": 0.0285, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "grad_norm": 4.617649078369141, | |
| "learning_rate": 1.955777777777778e-05, | |
| "loss": 0.0246, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_loss": 1.02446711063385, | |
| "eval_runtime": 41.3069, | |
| "eval_samples_per_second": 6.052, | |
| "eval_steps_per_second": 1.525, | |
| "eval_wer": 0.46809712027103334, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 49.6, | |
| "grad_norm": 1.5408967733383179, | |
| "learning_rate": 1.946888888888889e-05, | |
| "loss": 0.0235, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 51.2, | |
| "grad_norm": 4.78511381149292, | |
| "learning_rate": 1.938e-05, | |
| "loss": 0.0212, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 52.8, | |
| "grad_norm": 0.8843356370925903, | |
| "learning_rate": 1.9291111111111115e-05, | |
| "loss": 0.0193, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 54.4, | |
| "grad_norm": 2.4114930629730225, | |
| "learning_rate": 1.9202222222222225e-05, | |
| "loss": 0.0193, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "grad_norm": 3.1046841144561768, | |
| "learning_rate": 1.9113333333333336e-05, | |
| "loss": 0.0164, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_loss": 1.103171706199646, | |
| "eval_runtime": 41.2052, | |
| "eval_samples_per_second": 6.067, | |
| "eval_steps_per_second": 1.529, | |
| "eval_wer": 0.47148503670242803, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 57.6, | |
| "grad_norm": 2.163294792175293, | |
| "learning_rate": 1.902488888888889e-05, | |
| "loss": 0.0157, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 59.2, | |
| "grad_norm": 4.016397953033447, | |
| "learning_rate": 1.8936e-05, | |
| "loss": 0.015, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 60.8, | |
| "grad_norm": 3.4655325412750244, | |
| "learning_rate": 1.884711111111111e-05, | |
| "loss": 0.0124, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 62.4, | |
| "grad_norm": 2.6923351287841797, | |
| "learning_rate": 1.8758222222222224e-05, | |
| "loss": 0.0121, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "grad_norm": 3.1834566593170166, | |
| "learning_rate": 1.8669333333333334e-05, | |
| "loss": 0.0118, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_loss": 1.1389034986495972, | |
| "eval_runtime": 42.003, | |
| "eval_samples_per_second": 5.952, | |
| "eval_steps_per_second": 1.5, | |
| "eval_wer": 0.598531902879729, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 65.6, | |
| "grad_norm": 1.3980759382247925, | |
| "learning_rate": 1.8580444444444445e-05, | |
| "loss": 0.0126, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 67.2, | |
| "grad_norm": 3.1268885135650635, | |
| "learning_rate": 1.849155555555556e-05, | |
| "loss": 0.0109, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 68.8, | |
| "grad_norm": 2.908175468444824, | |
| "learning_rate": 1.840266666666667e-05, | |
| "loss": 0.0126, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 70.4, | |
| "grad_norm": 3.613409996032715, | |
| "learning_rate": 1.831377777777778e-05, | |
| "loss": 0.0105, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "grad_norm": 2.127668619155884, | |
| "learning_rate": 1.822488888888889e-05, | |
| "loss": 0.0094, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_loss": 1.145694375038147, | |
| "eval_runtime": 41.9604, | |
| "eval_samples_per_second": 5.958, | |
| "eval_steps_per_second": 1.501, | |
| "eval_wer": 0.5793337097684924, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 73.6, | |
| "grad_norm": 3.8510990142822266, | |
| "learning_rate": 1.8136000000000004e-05, | |
| "loss": 0.0106, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 75.2, | |
| "grad_norm": 0.6357870697975159, | |
| "learning_rate": 1.8047111111111114e-05, | |
| "loss": 0.0077, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 76.8, | |
| "grad_norm": 0.7974900603294373, | |
| "learning_rate": 1.7958222222222225e-05, | |
| "loss": 0.0092, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 78.4, | |
| "grad_norm": 3.332366943359375, | |
| "learning_rate": 1.7869333333333335e-05, | |
| "loss": 0.0097, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "grad_norm": 3.0786008834838867, | |
| "learning_rate": 1.7780444444444446e-05, | |
| "loss": 0.0086, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_loss": 1.1853593587875366, | |
| "eval_runtime": 42.1314, | |
| "eval_samples_per_second": 5.934, | |
| "eval_steps_per_second": 1.495, | |
| "eval_wer": 0.5375494071146245, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 81.6, | |
| "grad_norm": 1.0725177526474, | |
| "learning_rate": 1.7691555555555556e-05, | |
| "loss": 0.0072, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 83.2, | |
| "grad_norm": 0.27933818101882935, | |
| "learning_rate": 1.7602666666666667e-05, | |
| "loss": 0.0074, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 84.8, | |
| "grad_norm": 1.2738243341445923, | |
| "learning_rate": 1.7513777777777777e-05, | |
| "loss": 0.0061, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 86.4, | |
| "grad_norm": 6.480189323425293, | |
| "learning_rate": 1.742488888888889e-05, | |
| "loss": 0.0065, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "grad_norm": 0.33281826972961426, | |
| "learning_rate": 1.7336e-05, | |
| "loss": 0.0067, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_loss": 1.237168788909912, | |
| "eval_runtime": 40.9166, | |
| "eval_samples_per_second": 6.11, | |
| "eval_steps_per_second": 1.54, | |
| "eval_wer": 0.466403162055336, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 89.6, | |
| "grad_norm": 0.395781934261322, | |
| "learning_rate": 1.7247111111111112e-05, | |
| "loss": 0.0055, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 91.2, | |
| "grad_norm": 2.044802188873291, | |
| "learning_rate": 1.7158222222222222e-05, | |
| "loss": 0.0071, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 92.8, | |
| "grad_norm": 0.7053709030151367, | |
| "learning_rate": 1.7069333333333336e-05, | |
| "loss": 0.0069, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 94.4, | |
| "grad_norm": 2.6809892654418945, | |
| "learning_rate": 1.6980444444444447e-05, | |
| "loss": 0.0059, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "grad_norm": 0.43073830008506775, | |
| "learning_rate": 1.6891555555555557e-05, | |
| "loss": 0.005, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_loss": 1.2564021348953247, | |
| "eval_runtime": 43.0999, | |
| "eval_samples_per_second": 5.8, | |
| "eval_steps_per_second": 1.462, | |
| "eval_wer": 0.4991530208921513, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 97.6, | |
| "grad_norm": 0.7439399361610413, | |
| "learning_rate": 1.6802666666666668e-05, | |
| "loss": 0.0052, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 99.2, | |
| "grad_norm": 0.18939250707626343, | |
| "learning_rate": 1.671377777777778e-05, | |
| "loss": 0.005, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 100.8, | |
| "grad_norm": 2.827566385269165, | |
| "learning_rate": 1.6624888888888892e-05, | |
| "loss": 0.0052, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 102.4, | |
| "grad_norm": 3.124176502227783, | |
| "learning_rate": 1.6536000000000002e-05, | |
| "loss": 0.0041, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 104.0, | |
| "grad_norm": 1.91826593875885, | |
| "learning_rate": 1.6447111111111113e-05, | |
| "loss": 0.0043, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 104.0, | |
| "eval_loss": 1.27247154712677, | |
| "eval_runtime": 41.9766, | |
| "eval_samples_per_second": 5.956, | |
| "eval_steps_per_second": 1.501, | |
| "eval_wer": 0.44776962168266515, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 105.6, | |
| "grad_norm": 0.8713739514350891, | |
| "learning_rate": 1.6358222222222223e-05, | |
| "loss": 0.0032, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 107.2, | |
| "grad_norm": 0.05066121742129326, | |
| "learning_rate": 1.6269333333333334e-05, | |
| "loss": 0.0042, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 108.8, | |
| "grad_norm": 1.1562632322311401, | |
| "learning_rate": 1.6180444444444444e-05, | |
| "loss": 0.0032, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 110.4, | |
| "grad_norm": 0.07406218349933624, | |
| "learning_rate": 1.6091555555555555e-05, | |
| "loss": 0.0037, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 112.0, | |
| "grad_norm": 0.997751772403717, | |
| "learning_rate": 1.600266666666667e-05, | |
| "loss": 0.0039, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 112.0, | |
| "eval_loss": 1.3331384658813477, | |
| "eval_runtime": 43.8205, | |
| "eval_samples_per_second": 5.705, | |
| "eval_steps_per_second": 1.438, | |
| "eval_wer": 0.5307735742518351, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 113.6, | |
| "grad_norm": 0.19617311656475067, | |
| "learning_rate": 1.591377777777778e-05, | |
| "loss": 0.0043, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 115.2, | |
| "grad_norm": 3.2143056392669678, | |
| "learning_rate": 1.5825333333333336e-05, | |
| "loss": 0.0051, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 116.8, | |
| "grad_norm": 0.6758298873901367, | |
| "learning_rate": 1.5736444444444446e-05, | |
| "loss": 0.0033, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 118.4, | |
| "grad_norm": 2.0771877765655518, | |
| "learning_rate": 1.5647555555555557e-05, | |
| "loss": 0.0037, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 120.0, | |
| "grad_norm": 2.100074529647827, | |
| "learning_rate": 1.5558666666666667e-05, | |
| "loss": 0.0036, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 120.0, | |
| "eval_loss": 1.3492019176483154, | |
| "eval_runtime": 43.5776, | |
| "eval_samples_per_second": 5.737, | |
| "eval_steps_per_second": 1.446, | |
| "eval_wer": 0.603613777526821, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 121.6, | |
| "grad_norm": 0.3508625030517578, | |
| "learning_rate": 1.5469777777777778e-05, | |
| "loss": 0.0026, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 123.2, | |
| "grad_norm": 0.0235364381223917, | |
| "learning_rate": 1.5380888888888888e-05, | |
| "loss": 0.0033, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 124.8, | |
| "grad_norm": 1.745226263999939, | |
| "learning_rate": 1.5292e-05, | |
| "loss": 0.0024, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 126.4, | |
| "grad_norm": 1.7244856357574463, | |
| "learning_rate": 1.5203111111111112e-05, | |
| "loss": 0.0027, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 128.0, | |
| "grad_norm": 2.978816509246826, | |
| "learning_rate": 1.5114222222222223e-05, | |
| "loss": 0.0028, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 128.0, | |
| "eval_loss": 1.3909789323806763, | |
| "eval_runtime": 41.3413, | |
| "eval_samples_per_second": 6.047, | |
| "eval_steps_per_second": 1.524, | |
| "eval_wer": 0.45511010728402035, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 129.6, | |
| "grad_norm": 0.11152245104312897, | |
| "learning_rate": 1.5025333333333333e-05, | |
| "loss": 0.0023, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 131.2, | |
| "grad_norm": 0.12898045778274536, | |
| "learning_rate": 1.4936444444444447e-05, | |
| "loss": 0.0029, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 132.8, | |
| "grad_norm": 0.8840957880020142, | |
| "learning_rate": 1.4847555555555558e-05, | |
| "loss": 0.0026, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 134.4, | |
| "grad_norm": 0.07675749063491821, | |
| "learning_rate": 1.4758666666666668e-05, | |
| "loss": 0.0027, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 136.0, | |
| "grad_norm": 0.5362949371337891, | |
| "learning_rate": 1.4669777777777779e-05, | |
| "loss": 0.0034, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 136.0, | |
| "eval_loss": 1.436603307723999, | |
| "eval_runtime": 41.9502, | |
| "eval_samples_per_second": 5.959, | |
| "eval_steps_per_second": 1.502, | |
| "eval_wer": 0.4906832298136646, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 137.6, | |
| "grad_norm": 1.4152299165725708, | |
| "learning_rate": 1.458088888888889e-05, | |
| "loss": 0.0024, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 139.2, | |
| "grad_norm": 0.1923665702342987, | |
| "learning_rate": 1.4492000000000001e-05, | |
| "loss": 0.0023, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 140.8, | |
| "grad_norm": 0.9098421931266785, | |
| "learning_rate": 1.4403111111111112e-05, | |
| "loss": 0.0018, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 142.4, | |
| "grad_norm": 0.06011312082409859, | |
| "learning_rate": 1.4314222222222222e-05, | |
| "loss": 0.0023, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 144.0, | |
| "grad_norm": 0.4919435381889343, | |
| "learning_rate": 1.4225333333333336e-05, | |
| "loss": 0.0024, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 144.0, | |
| "eval_loss": 1.3797271251678467, | |
| "eval_runtime": 46.4998, | |
| "eval_samples_per_second": 5.376, | |
| "eval_steps_per_second": 1.355, | |
| "eval_wer": 0.6126482213438735, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 145.6, | |
| "grad_norm": 1.19382905960083, | |
| "learning_rate": 1.4136444444444446e-05, | |
| "loss": 0.0026, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 147.2, | |
| "grad_norm": 0.1949184685945511, | |
| "learning_rate": 1.4047555555555557e-05, | |
| "loss": 0.0017, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 148.8, | |
| "grad_norm": 0.030353059992194176, | |
| "learning_rate": 1.3959111111111112e-05, | |
| "loss": 0.002, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 150.4, | |
| "grad_norm": 0.8148756623268127, | |
| "learning_rate": 1.3870222222222223e-05, | |
| "loss": 0.0016, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 152.0, | |
| "grad_norm": 0.1468518227338791, | |
| "learning_rate": 1.3781333333333335e-05, | |
| "loss": 0.0019, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 152.0, | |
| "eval_loss": 1.4368208646774292, | |
| "eval_runtime": 42.0557, | |
| "eval_samples_per_second": 5.945, | |
| "eval_steps_per_second": 1.498, | |
| "eval_wer": 0.5228684359119141, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 153.6, | |
| "grad_norm": 3.330853223800659, | |
| "learning_rate": 1.3692888888888892e-05, | |
| "loss": 0.0024, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 155.2, | |
| "grad_norm": 2.411620616912842, | |
| "learning_rate": 1.3604000000000002e-05, | |
| "loss": 0.0018, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 156.8, | |
| "grad_norm": 1.7824522256851196, | |
| "learning_rate": 1.3515111111111113e-05, | |
| "loss": 0.0019, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 158.4, | |
| "grad_norm": 0.05631573125720024, | |
| "learning_rate": 1.3426222222222223e-05, | |
| "loss": 0.0018, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 160.0, | |
| "grad_norm": 0.20461511611938477, | |
| "learning_rate": 1.3337333333333335e-05, | |
| "loss": 0.0017, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 160.0, | |
| "eval_loss": 1.4499236345291138, | |
| "eval_runtime": 43.1323, | |
| "eval_samples_per_second": 5.796, | |
| "eval_steps_per_second": 1.461, | |
| "eval_wer": 0.5979672501411631, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 161.6, | |
| "grad_norm": 0.01897699199616909, | |
| "learning_rate": 1.3248444444444446e-05, | |
| "loss": 0.0028, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 163.2, | |
| "grad_norm": 0.9474685192108154, | |
| "learning_rate": 1.3160000000000001e-05, | |
| "loss": 0.0027, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 164.8, | |
| "grad_norm": 0.10914404690265656, | |
| "learning_rate": 1.3071111111111112e-05, | |
| "loss": 0.0026, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 166.4, | |
| "grad_norm": 0.6951639652252197, | |
| "learning_rate": 1.2982222222222222e-05, | |
| "loss": 0.0015, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 168.0, | |
| "grad_norm": 0.591296911239624, | |
| "learning_rate": 1.2893333333333336e-05, | |
| "loss": 0.0014, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 168.0, | |
| "eval_loss": 1.4369308948516846, | |
| "eval_runtime": 43.7269, | |
| "eval_samples_per_second": 5.717, | |
| "eval_steps_per_second": 1.441, | |
| "eval_wer": 0.5940146809712027, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 169.6, | |
| "grad_norm": 0.07852908968925476, | |
| "learning_rate": 1.2804444444444446e-05, | |
| "loss": 0.0018, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 171.2, | |
| "grad_norm": 0.4466964304447174, | |
| "learning_rate": 1.2715555555555557e-05, | |
| "loss": 0.0016, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 172.8, | |
| "grad_norm": 0.6805703043937683, | |
| "learning_rate": 1.2626666666666667e-05, | |
| "loss": 0.001, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 174.4, | |
| "grad_norm": 0.14335931837558746, | |
| "learning_rate": 1.253777777777778e-05, | |
| "loss": 0.001, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 176.0, | |
| "grad_norm": 1.0165632963180542, | |
| "learning_rate": 1.244888888888889e-05, | |
| "loss": 0.0015, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 176.0, | |
| "eval_loss": 1.4614824056625366, | |
| "eval_runtime": 42.489, | |
| "eval_samples_per_second": 5.884, | |
| "eval_steps_per_second": 1.483, | |
| "eval_wer": 0.5307735742518351, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 177.6, | |
| "grad_norm": 0.4234725832939148, | |
| "learning_rate": 1.236e-05, | |
| "loss": 0.0019, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 179.2, | |
| "grad_norm": 4.320431232452393, | |
| "learning_rate": 1.227111111111111e-05, | |
| "loss": 0.0027, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 180.8, | |
| "grad_norm": 0.04678142070770264, | |
| "learning_rate": 1.2182222222222225e-05, | |
| "loss": 0.0018, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 182.4, | |
| "grad_norm": 0.19874203205108643, | |
| "learning_rate": 1.2093333333333335e-05, | |
| "loss": 0.0013, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 184.0, | |
| "grad_norm": 0.636381208896637, | |
| "learning_rate": 1.2004444444444445e-05, | |
| "loss": 0.001, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 184.0, | |
| "eval_loss": 1.445263147354126, | |
| "eval_runtime": 41.9644, | |
| "eval_samples_per_second": 5.957, | |
| "eval_steps_per_second": 1.501, | |
| "eval_wer": 0.49858836815358554, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 185.6, | |
| "grad_norm": 0.021843163296580315, | |
| "learning_rate": 1.1915555555555556e-05, | |
| "loss": 0.0017, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 187.2, | |
| "grad_norm": 0.0671222060918808, | |
| "learning_rate": 1.1826666666666668e-05, | |
| "loss": 0.0012, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 188.8, | |
| "grad_norm": 0.04560863971710205, | |
| "learning_rate": 1.1737777777777779e-05, | |
| "loss": 0.0019, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 190.4, | |
| "grad_norm": 0.17737437784671783, | |
| "learning_rate": 1.1648888888888889e-05, | |
| "loss": 0.0008, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 192.0, | |
| "grad_norm": 0.05606027692556381, | |
| "learning_rate": 1.156e-05, | |
| "loss": 0.0009, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 192.0, | |
| "eval_loss": 1.4906095266342163, | |
| "eval_runtime": 43.2268, | |
| "eval_samples_per_second": 5.783, | |
| "eval_steps_per_second": 1.457, | |
| "eval_wer": 0.5471485036702428, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 193.6, | |
| "grad_norm": 2.6839418411254883, | |
| "learning_rate": 1.1471111111111113e-05, | |
| "loss": 0.0016, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 195.2, | |
| "grad_norm": 0.05472835153341293, | |
| "learning_rate": 1.1382222222222224e-05, | |
| "loss": 0.0014, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 196.8, | |
| "grad_norm": 0.4221028685569763, | |
| "learning_rate": 1.1293333333333334e-05, | |
| "loss": 0.001, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 198.4, | |
| "grad_norm": 0.025390515103936195, | |
| "learning_rate": 1.120488888888889e-05, | |
| "loss": 0.0017, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 200.0, | |
| "grad_norm": 0.02648915909230709, | |
| "learning_rate": 1.1116e-05, | |
| "loss": 0.0007, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 200.0, | |
| "eval_loss": 1.4574248790740967, | |
| "eval_runtime": 42.0773, | |
| "eval_samples_per_second": 5.941, | |
| "eval_steps_per_second": 1.497, | |
| "eval_wer": 0.49407114624505927, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 201.6, | |
| "grad_norm": 0.05941193923354149, | |
| "learning_rate": 1.1027111111111112e-05, | |
| "loss": 0.0011, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 203.2, | |
| "grad_norm": 0.02862560749053955, | |
| "learning_rate": 1.0938222222222223e-05, | |
| "loss": 0.0012, | |
| "step": 25400 | |
| }, | |
| { | |
| "epoch": 204.8, | |
| "grad_norm": 0.024127991870045662, | |
| "learning_rate": 1.0849333333333335e-05, | |
| "loss": 0.0011, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 206.4, | |
| "grad_norm": 0.08150752633810043, | |
| "learning_rate": 1.0760444444444445e-05, | |
| "loss": 0.0008, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 208.0, | |
| "grad_norm": 0.05071726813912392, | |
| "learning_rate": 1.0671555555555557e-05, | |
| "loss": 0.0011, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 208.0, | |
| "eval_loss": 1.4995194673538208, | |
| "eval_runtime": 41.3368, | |
| "eval_samples_per_second": 6.048, | |
| "eval_steps_per_second": 1.524, | |
| "eval_wer": 0.4647092038396386, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 209.6, | |
| "grad_norm": 8.064842224121094, | |
| "learning_rate": 1.0582666666666668e-05, | |
| "loss": 0.001, | |
| "step": 26200 | |
| }, | |
| { | |
| "epoch": 211.2, | |
| "grad_norm": 0.02605404146015644, | |
| "learning_rate": 1.0493777777777778e-05, | |
| "loss": 0.001, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 212.8, | |
| "grad_norm": 0.06135524809360504, | |
| "learning_rate": 1.0404888888888889e-05, | |
| "loss": 0.0011, | |
| "step": 26600 | |
| }, | |
| { | |
| "epoch": 214.4, | |
| "grad_norm": 0.014893967658281326, | |
| "learning_rate": 1.0316e-05, | |
| "loss": 0.0008, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 216.0, | |
| "grad_norm": 0.009221619926393032, | |
| "learning_rate": 1.0227111111111111e-05, | |
| "loss": 0.0007, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 216.0, | |
| "eval_loss": 1.5195382833480835, | |
| "eval_runtime": 42.2229, | |
| "eval_samples_per_second": 5.921, | |
| "eval_steps_per_second": 1.492, | |
| "eval_wer": 0.515527950310559, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 217.6, | |
| "grad_norm": 0.3534085154533386, | |
| "learning_rate": 1.0138222222222223e-05, | |
| "loss": 0.0012, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 219.2, | |
| "grad_norm": 0.09608615189790726, | |
| "learning_rate": 1.0049333333333334e-05, | |
| "loss": 0.0007, | |
| "step": 27400 | |
| }, | |
| { | |
| "epoch": 220.8, | |
| "grad_norm": 0.03040822595357895, | |
| "learning_rate": 9.960444444444444e-06, | |
| "loss": 0.0008, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 222.4, | |
| "grad_norm": 0.030991466715931892, | |
| "learning_rate": 9.871555555555557e-06, | |
| "loss": 0.0008, | |
| "step": 27800 | |
| }, | |
| { | |
| "epoch": 224.0, | |
| "grad_norm": 0.270130455493927, | |
| "learning_rate": 9.783111111111112e-06, | |
| "loss": 0.0011, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 224.0, | |
| "eval_loss": 1.4928404092788696, | |
| "eval_runtime": 42.9045, | |
| "eval_samples_per_second": 5.827, | |
| "eval_steps_per_second": 1.468, | |
| "eval_wer": 0.5482778091473743, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 225.6, | |
| "grad_norm": 0.059342194348573685, | |
| "learning_rate": 9.694222222222222e-06, | |
| "loss": 0.0008, | |
| "step": 28200 | |
| }, | |
| { | |
| "epoch": 227.2, | |
| "grad_norm": 0.09850233793258667, | |
| "learning_rate": 9.605333333333334e-06, | |
| "loss": 0.001, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 228.8, | |
| "grad_norm": 0.012932940386235714, | |
| "learning_rate": 9.516444444444445e-06, | |
| "loss": 0.0007, | |
| "step": 28600 | |
| }, | |
| { | |
| "epoch": 230.4, | |
| "grad_norm": 0.4113960862159729, | |
| "learning_rate": 9.427555555555557e-06, | |
| "loss": 0.0008, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 232.0, | |
| "grad_norm": 11.596172332763672, | |
| "learning_rate": 9.338666666666667e-06, | |
| "loss": 0.0011, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 232.0, | |
| "eval_loss": 1.5243357419967651, | |
| "eval_runtime": 42.099, | |
| "eval_samples_per_second": 5.938, | |
| "eval_steps_per_second": 1.496, | |
| "eval_wer": 0.5143986448334275, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 233.6, | |
| "grad_norm": 0.14402435719966888, | |
| "learning_rate": 9.249777777777778e-06, | |
| "loss": 0.0005, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 235.2, | |
| "grad_norm": 0.037319615483284, | |
| "learning_rate": 9.160888888888888e-06, | |
| "loss": 0.0006, | |
| "step": 29400 | |
| }, | |
| { | |
| "epoch": 236.8, | |
| "grad_norm": 0.05602966248989105, | |
| "learning_rate": 9.072e-06, | |
| "loss": 0.0009, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 238.4, | |
| "grad_norm": 0.018490877002477646, | |
| "learning_rate": 8.983111111111111e-06, | |
| "loss": 0.0007, | |
| "step": 29800 | |
| }, | |
| { | |
| "epoch": 240.0, | |
| "grad_norm": 3.7446510791778564, | |
| "learning_rate": 8.894222222222223e-06, | |
| "loss": 0.0007, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 240.0, | |
| "eval_loss": 1.5804709196090698, | |
| "eval_runtime": 41.044, | |
| "eval_samples_per_second": 6.091, | |
| "eval_steps_per_second": 1.535, | |
| "eval_wer": 0.48842461885940147, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 241.6, | |
| "grad_norm": 0.09505221247673035, | |
| "learning_rate": 8.805333333333334e-06, | |
| "loss": 0.0005, | |
| "step": 30200 | |
| }, | |
| { | |
| "epoch": 243.2, | |
| "grad_norm": 0.031215248629450798, | |
| "learning_rate": 8.716444444444446e-06, | |
| "loss": 0.0007, | |
| "step": 30400 | |
| }, | |
| { | |
| "epoch": 244.8, | |
| "grad_norm": 0.3624882996082306, | |
| "learning_rate": 8.627555555555556e-06, | |
| "loss": 0.0004, | |
| "step": 30600 | |
| }, | |
| { | |
| "epoch": 246.4, | |
| "grad_norm": 0.025587618350982666, | |
| "learning_rate": 8.538666666666667e-06, | |
| "loss": 0.0007, | |
| "step": 30800 | |
| }, | |
| { | |
| "epoch": 248.0, | |
| "grad_norm": 0.8972709774971008, | |
| "learning_rate": 8.450222222222224e-06, | |
| "loss": 0.0005, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 248.0, | |
| "eval_loss": 1.5293784141540527, | |
| "eval_runtime": 42.2688, | |
| "eval_samples_per_second": 5.915, | |
| "eval_steps_per_second": 1.49, | |
| "eval_wer": 0.5115753811405985, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 249.6, | |
| "grad_norm": 0.02251521684229374, | |
| "learning_rate": 8.361333333333334e-06, | |
| "loss": 0.0007, | |
| "step": 31200 | |
| }, | |
| { | |
| "epoch": 251.2, | |
| "grad_norm": 0.007881904020905495, | |
| "learning_rate": 8.272444444444445e-06, | |
| "loss": 0.0004, | |
| "step": 31400 | |
| }, | |
| { | |
| "epoch": 252.8, | |
| "grad_norm": 0.0084000863134861, | |
| "learning_rate": 8.183555555555555e-06, | |
| "loss": 0.0005, | |
| "step": 31600 | |
| }, | |
| { | |
| "epoch": 254.4, | |
| "grad_norm": 0.44422510266304016, | |
| "learning_rate": 8.094666666666667e-06, | |
| "loss": 0.0004, | |
| "step": 31800 | |
| }, | |
| { | |
| "epoch": 256.0, | |
| "grad_norm": 0.024682149291038513, | |
| "learning_rate": 8.00577777777778e-06, | |
| "loss": 0.0005, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 256.0, | |
| "eval_loss": 1.5940375328063965, | |
| "eval_runtime": 42.3505, | |
| "eval_samples_per_second": 5.903, | |
| "eval_steps_per_second": 1.488, | |
| "eval_wer": 0.49745906267645396, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 257.6, | |
| "grad_norm": 0.019801704213023186, | |
| "learning_rate": 7.91688888888889e-06, | |
| "loss": 0.0005, | |
| "step": 32200 | |
| }, | |
| { | |
| "epoch": 259.2, | |
| "grad_norm": 0.006728316657245159, | |
| "learning_rate": 7.828000000000002e-06, | |
| "loss": 0.0003, | |
| "step": 32400 | |
| }, | |
| { | |
| "epoch": 260.8, | |
| "grad_norm": 0.1475154608488083, | |
| "learning_rate": 7.739111111111112e-06, | |
| "loss": 0.0005, | |
| "step": 32600 | |
| }, | |
| { | |
| "epoch": 262.4, | |
| "grad_norm": 0.038090407848358154, | |
| "learning_rate": 7.650222222222223e-06, | |
| "loss": 0.0005, | |
| "step": 32800 | |
| }, | |
| { | |
| "epoch": 264.0, | |
| "grad_norm": 1.3189762830734253, | |
| "learning_rate": 7.561333333333334e-06, | |
| "loss": 0.0003, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 264.0, | |
| "eval_loss": 1.5760223865509033, | |
| "eval_runtime": 41.6476, | |
| "eval_samples_per_second": 6.003, | |
| "eval_steps_per_second": 1.513, | |
| "eval_wer": 0.5002823263692829, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 265.6, | |
| "grad_norm": 0.005491426680237055, | |
| "learning_rate": 7.4728888888888895e-06, | |
| "loss": 0.0007, | |
| "step": 33200 | |
| }, | |
| { | |
| "epoch": 267.2, | |
| "grad_norm": 0.010416628792881966, | |
| "learning_rate": 7.384e-06, | |
| "loss": 0.0008, | |
| "step": 33400 | |
| }, | |
| { | |
| "epoch": 268.8, | |
| "grad_norm": 0.004440742079168558, | |
| "learning_rate": 7.295111111111112e-06, | |
| "loss": 0.0006, | |
| "step": 33600 | |
| }, | |
| { | |
| "epoch": 270.4, | |
| "grad_norm": 0.010887986980378628, | |
| "learning_rate": 7.206222222222223e-06, | |
| "loss": 0.0007, | |
| "step": 33800 | |
| }, | |
| { | |
| "epoch": 272.0, | |
| "grad_norm": 0.02552446536719799, | |
| "learning_rate": 7.117333333333334e-06, | |
| "loss": 0.0004, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 272.0, | |
| "eval_loss": 1.5940096378326416, | |
| "eval_runtime": 41.5805, | |
| "eval_samples_per_second": 6.012, | |
| "eval_steps_per_second": 1.515, | |
| "eval_wer": 0.4872953133822699, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 273.6, | |
| "grad_norm": 0.0572277270257473, | |
| "learning_rate": 7.028444444444445e-06, | |
| "loss": 0.0006, | |
| "step": 34200 | |
| }, | |
| { | |
| "epoch": 275.2, | |
| "grad_norm": 0.10096795111894608, | |
| "learning_rate": 6.9395555555555565e-06, | |
| "loss": 0.0009, | |
| "step": 34400 | |
| }, | |
| { | |
| "epoch": 276.8, | |
| "grad_norm": 0.005929913371801376, | |
| "learning_rate": 6.850666666666668e-06, | |
| "loss": 0.0005, | |
| "step": 34600 | |
| }, | |
| { | |
| "epoch": 278.4, | |
| "grad_norm": 0.005341435316950083, | |
| "learning_rate": 6.761777777777778e-06, | |
| "loss": 0.0005, | |
| "step": 34800 | |
| }, | |
| { | |
| "epoch": 280.0, | |
| "grad_norm": 0.021666768938302994, | |
| "learning_rate": 6.6728888888888895e-06, | |
| "loss": 0.0003, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 280.0, | |
| "eval_loss": 1.6009721755981445, | |
| "eval_runtime": 41.0006, | |
| "eval_samples_per_second": 6.097, | |
| "eval_steps_per_second": 1.537, | |
| "eval_wer": 0.46809712027103334, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 281.6, | |
| "grad_norm": 0.019466301426291466, | |
| "learning_rate": 6.584444444444446e-06, | |
| "loss": 0.0005, | |
| "step": 35200 | |
| }, | |
| { | |
| "epoch": 283.2, | |
| "grad_norm": 0.007609171327203512, | |
| "learning_rate": 6.495555555555556e-06, | |
| "loss": 0.0006, | |
| "step": 35400 | |
| }, | |
| { | |
| "epoch": 284.8, | |
| "grad_norm": 0.006095775868743658, | |
| "learning_rate": 6.4066666666666674e-06, | |
| "loss": 0.0004, | |
| "step": 35600 | |
| }, | |
| { | |
| "epoch": 286.4, | |
| "grad_norm": 0.008476600050926208, | |
| "learning_rate": 6.317777777777778e-06, | |
| "loss": 0.0002, | |
| "step": 35800 | |
| }, | |
| { | |
| "epoch": 288.0, | |
| "grad_norm": 0.06994141638278961, | |
| "learning_rate": 6.22888888888889e-06, | |
| "loss": 0.0004, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 288.0, | |
| "eval_loss": 1.5837336778640747, | |
| "eval_runtime": 42.3396, | |
| "eval_samples_per_second": 5.905, | |
| "eval_steps_per_second": 1.488, | |
| "eval_wer": 0.484472049689441, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 289.6, | |
| "grad_norm": 0.9534348845481873, | |
| "learning_rate": 6.1400000000000005e-06, | |
| "loss": 0.0003, | |
| "step": 36200 | |
| }, | |
| { | |
| "epoch": 291.2, | |
| "grad_norm": 0.00798807479441166, | |
| "learning_rate": 6.051111111111112e-06, | |
| "loss": 0.0003, | |
| "step": 36400 | |
| }, | |
| { | |
| "epoch": 292.8, | |
| "grad_norm": 0.4499492347240448, | |
| "learning_rate": 5.962222222222222e-06, | |
| "loss": 0.0004, | |
| "step": 36600 | |
| }, | |
| { | |
| "epoch": 294.4, | |
| "grad_norm": 0.00747877499088645, | |
| "learning_rate": 5.873333333333334e-06, | |
| "loss": 0.0006, | |
| "step": 36800 | |
| }, | |
| { | |
| "epoch": 296.0, | |
| "grad_norm": 0.007594792637974024, | |
| "learning_rate": 5.784444444444445e-06, | |
| "loss": 0.0006, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 296.0, | |
| "eval_loss": 1.5838834047317505, | |
| "eval_runtime": 41.0456, | |
| "eval_samples_per_second": 6.091, | |
| "eval_steps_per_second": 1.535, | |
| "eval_wer": 0.47939017504234893, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 297.6, | |
| "grad_norm": 0.0062100524082779884, | |
| "learning_rate": 5.695555555555556e-06, | |
| "loss": 0.0003, | |
| "step": 37200 | |
| }, | |
| { | |
| "epoch": 299.2, | |
| "grad_norm": 1.5888539552688599, | |
| "learning_rate": 5.606666666666667e-06, | |
| "loss": 0.0006, | |
| "step": 37400 | |
| }, | |
| { | |
| "epoch": 300.8, | |
| "grad_norm": 0.004372656811028719, | |
| "learning_rate": 5.517777777777779e-06, | |
| "loss": 0.0003, | |
| "step": 37600 | |
| }, | |
| { | |
| "epoch": 302.4, | |
| "grad_norm": 0.004411238245666027, | |
| "learning_rate": 5.428888888888889e-06, | |
| "loss": 0.0004, | |
| "step": 37800 | |
| }, | |
| { | |
| "epoch": 304.0, | |
| "grad_norm": 0.007507936097681522, | |
| "learning_rate": 5.3400000000000005e-06, | |
| "loss": 0.0002, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 304.0, | |
| "eval_loss": 1.5652457475662231, | |
| "eval_runtime": 41.4549, | |
| "eval_samples_per_second": 6.031, | |
| "eval_steps_per_second": 1.52, | |
| "eval_wer": 0.4754376058723885, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 305.6, | |
| "grad_norm": 0.005323062185198069, | |
| "learning_rate": 5.251555555555557e-06, | |
| "loss": 0.0005, | |
| "step": 38200 | |
| }, | |
| { | |
| "epoch": 307.2, | |
| "grad_norm": 0.0021106544882059097, | |
| "learning_rate": 5.162666666666667e-06, | |
| "loss": 0.0005, | |
| "step": 38400 | |
| }, | |
| { | |
| "epoch": 308.8, | |
| "grad_norm": 0.0051486073061823845, | |
| "learning_rate": 5.0737777777777785e-06, | |
| "loss": 0.0007, | |
| "step": 38600 | |
| }, | |
| { | |
| "epoch": 310.4, | |
| "grad_norm": 0.06730670481920242, | |
| "learning_rate": 4.984888888888889e-06, | |
| "loss": 0.0004, | |
| "step": 38800 | |
| }, | |
| { | |
| "epoch": 312.0, | |
| "grad_norm": 0.005158218555152416, | |
| "learning_rate": 4.896e-06, | |
| "loss": 0.0003, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 312.0, | |
| "eval_loss": 1.6083264350891113, | |
| "eval_runtime": 41.1796, | |
| "eval_samples_per_second": 6.071, | |
| "eval_steps_per_second": 1.53, | |
| "eval_wer": 0.48334274421230944, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 313.6, | |
| "grad_norm": 0.007136846426874399, | |
| "learning_rate": 4.8071111111111115e-06, | |
| "loss": 0.0002, | |
| "step": 39200 | |
| }, | |
| { | |
| "epoch": 315.2, | |
| "grad_norm": 0.0384252667427063, | |
| "learning_rate": 4.718222222222222e-06, | |
| "loss": 0.0005, | |
| "step": 39400 | |
| }, | |
| { | |
| "epoch": 316.8, | |
| "grad_norm": 0.03144264966249466, | |
| "learning_rate": 4.629333333333333e-06, | |
| "loss": 0.0003, | |
| "step": 39600 | |
| }, | |
| { | |
| "epoch": 318.4, | |
| "grad_norm": 0.04305962473154068, | |
| "learning_rate": 4.540444444444445e-06, | |
| "loss": 0.0002, | |
| "step": 39800 | |
| }, | |
| { | |
| "epoch": 320.0, | |
| "grad_norm": 0.011067772284150124, | |
| "learning_rate": 4.451555555555556e-06, | |
| "loss": 0.0002, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 320.0, | |
| "eval_loss": 1.575042724609375, | |
| "eval_runtime": 42.1507, | |
| "eval_samples_per_second": 5.931, | |
| "eval_steps_per_second": 1.495, | |
| "eval_wer": 0.5189158667419537, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 321.6, | |
| "grad_norm": 0.002925801556557417, | |
| "learning_rate": 4.362666666666667e-06, | |
| "loss": 0.0004, | |
| "step": 40200 | |
| }, | |
| { | |
| "epoch": 323.2, | |
| "grad_norm": 0.03247452154755592, | |
| "learning_rate": 4.2737777777777785e-06, | |
| "loss": 0.0002, | |
| "step": 40400 | |
| }, | |
| { | |
| "epoch": 324.8, | |
| "grad_norm": 0.017400383949279785, | |
| "learning_rate": 4.18488888888889e-06, | |
| "loss": 0.0002, | |
| "step": 40600 | |
| }, | |
| { | |
| "epoch": 326.4, | |
| "grad_norm": 0.0033240150660276413, | |
| "learning_rate": 4.096e-06, | |
| "loss": 0.0001, | |
| "step": 40800 | |
| }, | |
| { | |
| "epoch": 328.0, | |
| "grad_norm": 0.009032553061842918, | |
| "learning_rate": 4.0071111111111116e-06, | |
| "loss": 0.0004, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 328.0, | |
| "eval_loss": 1.619897484779358, | |
| "eval_runtime": 44.7114, | |
| "eval_samples_per_second": 5.591, | |
| "eval_steps_per_second": 1.409, | |
| "eval_wer": 0.5979672501411631, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 329.6, | |
| "grad_norm": 0.0036150990054011345, | |
| "learning_rate": 3.918222222222223e-06, | |
| "loss": 0.0002, | |
| "step": 41200 | |
| }, | |
| { | |
| "epoch": 331.2, | |
| "grad_norm": 0.029861323535442352, | |
| "learning_rate": 3.829333333333334e-06, | |
| "loss": 0.0002, | |
| "step": 41400 | |
| }, | |
| { | |
| "epoch": 332.8, | |
| "grad_norm": 0.02380683459341526, | |
| "learning_rate": 3.740444444444445e-06, | |
| "loss": 0.0001, | |
| "step": 41600 | |
| }, | |
| { | |
| "epoch": 334.4, | |
| "grad_norm": 0.031281813979148865, | |
| "learning_rate": 3.651555555555556e-06, | |
| "loss": 0.0002, | |
| "step": 41800 | |
| }, | |
| { | |
| "epoch": 336.0, | |
| "grad_norm": 0.0028394584078341722, | |
| "learning_rate": 3.5626666666666672e-06, | |
| "loss": 0.0001, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 336.0, | |
| "eval_loss": 1.5782560110092163, | |
| "eval_runtime": 42.7351, | |
| "eval_samples_per_second": 5.85, | |
| "eval_steps_per_second": 1.474, | |
| "eval_wer": 0.5352907961603613, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 337.6, | |
| "grad_norm": 0.11405123770236969, | |
| "learning_rate": 3.473777777777778e-06, | |
| "loss": 0.0002, | |
| "step": 42200 | |
| }, | |
| { | |
| "epoch": 339.2, | |
| "grad_norm": 0.022922609001398087, | |
| "learning_rate": 3.3848888888888894e-06, | |
| "loss": 0.0003, | |
| "step": 42400 | |
| }, | |
| { | |
| "epoch": 340.8, | |
| "grad_norm": 0.0035330464597791433, | |
| "learning_rate": 3.2960000000000003e-06, | |
| "loss": 0.0002, | |
| "step": 42600 | |
| }, | |
| { | |
| "epoch": 342.4, | |
| "grad_norm": 0.0057142325676977634, | |
| "learning_rate": 3.2071111111111116e-06, | |
| "loss": 0.0003, | |
| "step": 42800 | |
| }, | |
| { | |
| "epoch": 344.0, | |
| "grad_norm": 0.009726474992930889, | |
| "learning_rate": 3.1182222222222225e-06, | |
| "loss": 0.0001, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 344.0, | |
| "eval_loss": 1.5897696018218994, | |
| "eval_runtime": 42.1045, | |
| "eval_samples_per_second": 5.938, | |
| "eval_steps_per_second": 1.496, | |
| "eval_wer": 0.5098814229249012, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 345.6, | |
| "grad_norm": 0.002822835696861148, | |
| "learning_rate": 3.0293333333333338e-06, | |
| "loss": 0.0001, | |
| "step": 43200 | |
| }, | |
| { | |
| "epoch": 347.2, | |
| "grad_norm": 0.18968430161476135, | |
| "learning_rate": 2.9404444444444447e-06, | |
| "loss": 0.0003, | |
| "step": 43400 | |
| }, | |
| { | |
| "epoch": 348.8, | |
| "grad_norm": 0.01890464872121811, | |
| "learning_rate": 2.8515555555555555e-06, | |
| "loss": 0.0004, | |
| "step": 43600 | |
| }, | |
| { | |
| "epoch": 350.4, | |
| "grad_norm": 0.01565505564212799, | |
| "learning_rate": 2.7631111111111113e-06, | |
| "loss": 0.0006, | |
| "step": 43800 | |
| }, | |
| { | |
| "epoch": 352.0, | |
| "grad_norm": 0.031101664528250694, | |
| "learning_rate": 2.6742222222222226e-06, | |
| "loss": 0.0005, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 352.0, | |
| "eval_loss": 1.6004997491836548, | |
| "eval_runtime": 43.7134, | |
| "eval_samples_per_second": 5.719, | |
| "eval_steps_per_second": 1.441, | |
| "eval_wer": 0.5832862789384529, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 353.6, | |
| "grad_norm": 0.0026319867465645075, | |
| "learning_rate": 2.5853333333333335e-06, | |
| "loss": 0.0002, | |
| "step": 44200 | |
| }, | |
| { | |
| "epoch": 355.2, | |
| "grad_norm": 0.0039254105649888515, | |
| "learning_rate": 2.4964444444444448e-06, | |
| "loss": 0.0002, | |
| "step": 44400 | |
| }, | |
| { | |
| "epoch": 356.8, | |
| "grad_norm": 0.10020512342453003, | |
| "learning_rate": 2.4075555555555556e-06, | |
| "loss": 0.0002, | |
| "step": 44600 | |
| }, | |
| { | |
| "epoch": 358.4, | |
| "grad_norm": 0.0036830666940659285, | |
| "learning_rate": 2.318666666666667e-06, | |
| "loss": 0.0001, | |
| "step": 44800 | |
| }, | |
| { | |
| "epoch": 360.0, | |
| "grad_norm": 0.008613605052232742, | |
| "learning_rate": 2.229777777777778e-06, | |
| "loss": 0.0002, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 360.0, | |
| "eval_loss": 1.5903429985046387, | |
| "eval_runtime": 41.6423, | |
| "eval_samples_per_second": 6.004, | |
| "eval_steps_per_second": 1.513, | |
| "eval_wer": 0.4872953133822699, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 361.6, | |
| "grad_norm": 0.0025289321783930063, | |
| "learning_rate": 2.140888888888889e-06, | |
| "loss": 0.0003, | |
| "step": 45200 | |
| }, | |
| { | |
| "epoch": 363.2, | |
| "grad_norm": 0.004556621424853802, | |
| "learning_rate": 2.052e-06, | |
| "loss": 0.0002, | |
| "step": 45400 | |
| }, | |
| { | |
| "epoch": 364.8, | |
| "grad_norm": 0.06288538128137589, | |
| "learning_rate": 1.9631111111111113e-06, | |
| "loss": 0.0002, | |
| "step": 45600 | |
| }, | |
| { | |
| "epoch": 366.4, | |
| "grad_norm": 0.002961724065244198, | |
| "learning_rate": 1.8742222222222222e-06, | |
| "loss": 0.0001, | |
| "step": 45800 | |
| }, | |
| { | |
| "epoch": 368.0, | |
| "grad_norm": 0.0020394865423440933, | |
| "learning_rate": 1.7853333333333333e-06, | |
| "loss": 0.0002, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 368.0, | |
| "eval_loss": 1.619638442993164, | |
| "eval_runtime": 42.1006, | |
| "eval_samples_per_second": 5.938, | |
| "eval_steps_per_second": 1.496, | |
| "eval_wer": 0.5149632975719932, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 369.6, | |
| "grad_norm": 0.0018333194311708212, | |
| "learning_rate": 1.6964444444444444e-06, | |
| "loss": 0.0001, | |
| "step": 46200 | |
| }, | |
| { | |
| "epoch": 371.2, | |
| "grad_norm": 0.00915595330297947, | |
| "learning_rate": 1.6075555555555559e-06, | |
| "loss": 0.0001, | |
| "step": 46400 | |
| }, | |
| { | |
| "epoch": 372.8, | |
| "grad_norm": 0.006657126825302839, | |
| "learning_rate": 1.518666666666667e-06, | |
| "loss": 0.0001, | |
| "step": 46600 | |
| }, | |
| { | |
| "epoch": 374.4, | |
| "grad_norm": 0.1112598404288292, | |
| "learning_rate": 1.429777777777778e-06, | |
| "loss": 0.0001, | |
| "step": 46800 | |
| }, | |
| { | |
| "epoch": 376.0, | |
| "grad_norm": 0.004303216468542814, | |
| "learning_rate": 1.3408888888888892e-06, | |
| "loss": 0.0001, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 376.0, | |
| "eval_loss": 1.6212029457092285, | |
| "eval_runtime": 42.453, | |
| "eval_samples_per_second": 5.889, | |
| "eval_steps_per_second": 1.484, | |
| "eval_wer": 0.5251270468661773, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 377.6, | |
| "grad_norm": 0.003241022815927863, | |
| "learning_rate": 1.2520000000000003e-06, | |
| "loss": 0.0001, | |
| "step": 47200 | |
| }, | |
| { | |
| "epoch": 379.2, | |
| "grad_norm": 0.008798100054264069, | |
| "learning_rate": 1.1631111111111113e-06, | |
| "loss": 0.0001, | |
| "step": 47400 | |
| }, | |
| { | |
| "epoch": 380.8, | |
| "grad_norm": 0.013746335171163082, | |
| "learning_rate": 1.0742222222222224e-06, | |
| "loss": 0.0001, | |
| "step": 47600 | |
| }, | |
| { | |
| "epoch": 382.4, | |
| "grad_norm": 0.0022988717537373304, | |
| "learning_rate": 9.853333333333333e-07, | |
| "loss": 0.0001, | |
| "step": 47800 | |
| }, | |
| { | |
| "epoch": 384.0, | |
| "grad_norm": 0.0472625233232975, | |
| "learning_rate": 8.964444444444445e-07, | |
| "loss": 0.0002, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 384.0, | |
| "eval_loss": 1.618031620979309, | |
| "eval_runtime": 43.7587, | |
| "eval_samples_per_second": 5.713, | |
| "eval_steps_per_second": 1.44, | |
| "eval_wer": 0.5539243365330322, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 385.6, | |
| "grad_norm": 0.0067636617459356785, | |
| "learning_rate": 8.075555555555556e-07, | |
| "loss": 0.0001, | |
| "step": 48200 | |
| }, | |
| { | |
| "epoch": 387.2, | |
| "grad_norm": 0.0014746059896424413, | |
| "learning_rate": 7.186666666666667e-07, | |
| "loss": 0.0001, | |
| "step": 48400 | |
| }, | |
| { | |
| "epoch": 388.8, | |
| "grad_norm": 0.03201240673661232, | |
| "learning_rate": 6.297777777777778e-07, | |
| "loss": 0.0001, | |
| "step": 48600 | |
| }, | |
| { | |
| "epoch": 390.4, | |
| "grad_norm": 0.0024084942415356636, | |
| "learning_rate": 5.408888888888889e-07, | |
| "loss": 0.0001, | |
| "step": 48800 | |
| }, | |
| { | |
| "epoch": 392.0, | |
| "grad_norm": 0.0010368505027145147, | |
| "learning_rate": 4.5244444444444445e-07, | |
| "loss": 0.0001, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 392.0, | |
| "eval_loss": 1.6104307174682617, | |
| "eval_runtime": 41.3895, | |
| "eval_samples_per_second": 6.04, | |
| "eval_steps_per_second": 1.522, | |
| "eval_wer": 0.49632975719932243, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 393.6, | |
| "grad_norm": 0.6977916359901428, | |
| "learning_rate": 3.635555555555556e-07, | |
| "loss": 0.0001, | |
| "step": 49200 | |
| }, | |
| { | |
| "epoch": 395.2, | |
| "grad_norm": 0.0007687339093536139, | |
| "learning_rate": 2.746666666666667e-07, | |
| "loss": 0.0001, | |
| "step": 49400 | |
| }, | |
| { | |
| "epoch": 396.8, | |
| "grad_norm": 0.009420102462172508, | |
| "learning_rate": 1.8577777777777778e-07, | |
| "loss": 0.0001, | |
| "step": 49600 | |
| }, | |
| { | |
| "epoch": 398.4, | |
| "grad_norm": 0.0071104601956903934, | |
| "learning_rate": 9.68888888888889e-08, | |
| "loss": 0.0001, | |
| "step": 49800 | |
| }, | |
| { | |
| "epoch": 400.0, | |
| "grad_norm": 0.0014255736023187637, | |
| "learning_rate": 8e-09, | |
| "loss": 0.0001, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 400.0, | |
| "eval_loss": 1.6090388298034668, | |
| "eval_runtime": 42.8761, | |
| "eval_samples_per_second": 5.831, | |
| "eval_steps_per_second": 1.469, | |
| "eval_wer": 0.510446075663467, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 400.0, | |
| "step": 50000, | |
| "total_flos": 1.9695108096e+19, | |
| "train_loss": 0.05668430684482679, | |
| "train_runtime": 102928.0936, | |
| "train_samples_per_second": 7.772, | |
| "train_steps_per_second": 0.486 | |
| } | |
| ], | |
| "logging_steps": 200, | |
| "max_steps": 50000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 400, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.9695108096e+19, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |