| { | |
| "best_metric": 118.26401526639184, | |
| "best_model_checkpoint": "/esat/audioslave/qmeeus/exp/huggingface/outputs/la-whisper-small-covost2/checkpoint-50", | |
| "epoch": 4.501969611705121, | |
| "global_step": 2000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 6.900000000000001e-06, | |
| "loss": 5.246, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.44e-05, | |
| "loss": 2.6943, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 2.1667492389678955, | |
| "eval_runtime": 6734.5431, | |
| "eval_sacrebleu": 118.26401526639184, | |
| "eval_samples_per_second": 0.505, | |
| "eval_steps_per_second": 0.252, | |
| "eval_wer": 686.689662169017, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 2.19e-05, | |
| "loss": 1.9855, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 2.94e-05, | |
| "loss": 1.5505, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 1.6016461849212646, | |
| "eval_runtime": 7083.1054, | |
| "eval_sacrebleu": 259.9306589539216, | |
| "eval_samples_per_second": 0.48, | |
| "eval_steps_per_second": 0.24, | |
| "eval_wer": 165.6115789117717, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 2.9636842105263158e-05, | |
| "loss": 1.5057, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 2.9242105263157893e-05, | |
| "loss": 1.4093, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 1.58578622341156, | |
| "eval_runtime": 3061.6014, | |
| "eval_sacrebleu": 496.73346747625675, | |
| "eval_samples_per_second": 1.11, | |
| "eval_steps_per_second": 0.555, | |
| "eval_wer": 197.01058469446417, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 2.8847368421052634e-05, | |
| "loss": 1.3543, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2.845263157894737e-05, | |
| "loss": 1.3209, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 1.5648311376571655, | |
| "eval_runtime": 4753.6305, | |
| "eval_sacrebleu": 724.2490824821294, | |
| "eval_samples_per_second": 0.715, | |
| "eval_steps_per_second": 0.357, | |
| "eval_wer": 121.87954414798281, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 2.8057894736842104e-05, | |
| "loss": 1.2593, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.7663157894736842e-05, | |
| "loss": 1.2941, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 1.5596481561660767, | |
| "eval_runtime": 1255.7531, | |
| "eval_sacrebleu": 820.1240805356855, | |
| "eval_samples_per_second": 2.706, | |
| "eval_steps_per_second": 1.353, | |
| "eval_wer": 161.71587027831322, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 2.726842105263158e-05, | |
| "loss": 1.2667, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.687368421052632e-05, | |
| "loss": 1.2078, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 1.5073782205581665, | |
| "eval_runtime": 1290.5503, | |
| "eval_sacrebleu": 1022.0043170726522, | |
| "eval_samples_per_second": 2.633, | |
| "eval_steps_per_second": 1.316, | |
| "eval_wer": 140.3875418484326, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.6478947368421053e-05, | |
| "loss": 1.1966, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 2.6084210526315788e-05, | |
| "loss": 1.1532, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 1.497180700302124, | |
| "eval_runtime": 4184.4699, | |
| "eval_sacrebleu": 174.83502311336932, | |
| "eval_samples_per_second": 0.812, | |
| "eval_steps_per_second": 0.406, | |
| "eval_wer": 610.3716478982788, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 2.568947368421053e-05, | |
| "loss": 1.1028, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 2.5294736842105264e-05, | |
| "loss": 1.0167, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 1.4551299810409546, | |
| "eval_runtime": 791.8848, | |
| "eval_sacrebleu": 1904.0920904088528, | |
| "eval_samples_per_second": 4.291, | |
| "eval_steps_per_second": 2.146, | |
| "eval_wer": 82.7635183118596, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 2.49e-05, | |
| "loss": 1.0012, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 2.4505263157894737e-05, | |
| "loss": 0.8842, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 1.4295964241027832, | |
| "eval_runtime": 800.8358, | |
| "eval_sacrebleu": 1883.6113185691272, | |
| "eval_samples_per_second": 4.243, | |
| "eval_steps_per_second": 2.122, | |
| "eval_wer": 81.39055155388726, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 2.4110526315789475e-05, | |
| "loss": 0.5407, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 2.371578947368421e-05, | |
| "loss": 0.5619, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "eval_loss": 1.4332941770553589, | |
| "eval_runtime": 899.1709, | |
| "eval_sacrebleu": 1817.9439847694805, | |
| "eval_samples_per_second": 3.779, | |
| "eval_steps_per_second": 1.89, | |
| "eval_wer": 84.93118257752528, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 2.3321052631578948e-05, | |
| "loss": 0.5429, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 2.2926315789473683e-05, | |
| "loss": 0.5523, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "eval_loss": 1.4236555099487305, | |
| "eval_runtime": 1007.519, | |
| "eval_sacrebleu": 1517.1744129968472, | |
| "eval_samples_per_second": 3.373, | |
| "eval_steps_per_second": 1.686, | |
| "eval_wer": 104.09184674174021, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 2.2531578947368424e-05, | |
| "loss": 0.5684, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.213684210526316e-05, | |
| "loss": 0.4881, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "eval_loss": 1.4413496255874634, | |
| "eval_runtime": 983.5837, | |
| "eval_sacrebleu": 1650.1807231081336, | |
| "eval_samples_per_second": 3.455, | |
| "eval_steps_per_second": 1.727, | |
| "eval_wer": 97.20672280274594, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 2.1742105263157894e-05, | |
| "loss": 0.5024, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 2.1347368421052632e-05, | |
| "loss": 0.471, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "eval_loss": 1.3961360454559326, | |
| "eval_runtime": 818.7087, | |
| "eval_sacrebleu": 1885.001364213634, | |
| "eval_samples_per_second": 4.15, | |
| "eval_steps_per_second": 2.075, | |
| "eval_wer": 82.26640965811099, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.095263157894737e-05, | |
| "loss": 0.4683, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 2.0557894736842105e-05, | |
| "loss": 0.4412, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "eval_loss": 1.3986111879348755, | |
| "eval_runtime": 764.1712, | |
| "eval_sacrebleu": 2145.9785743484185, | |
| "eval_samples_per_second": 4.447, | |
| "eval_steps_per_second": 2.223, | |
| "eval_wer": 72.04693787832674, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 2.0163157894736843e-05, | |
| "loss": 0.4794, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 1.9768421052631577e-05, | |
| "loss": 0.4625, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "eval_loss": 1.3885091543197632, | |
| "eval_runtime": 843.5439, | |
| "eval_sacrebleu": 1837.7812162939947, | |
| "eval_samples_per_second": 4.028, | |
| "eval_steps_per_second": 2.014, | |
| "eval_wer": 87.4471610699672, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 1.937368421052632e-05, | |
| "loss": 0.4706, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 1.8978947368421054e-05, | |
| "loss": 0.4195, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_loss": 1.4094804525375366, | |
| "eval_runtime": 811.6593, | |
| "eval_sacrebleu": 1909.2654907091217, | |
| "eval_samples_per_second": 4.186, | |
| "eval_steps_per_second": 2.093, | |
| "eval_wer": 78.69196171925196, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 1.858421052631579e-05, | |
| "loss": 0.4444, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 1.8189473684210527e-05, | |
| "loss": 0.4532, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "eval_loss": 1.3891242742538452, | |
| "eval_runtime": 809.0214, | |
| "eval_sacrebleu": 1925.2237669771318, | |
| "eval_samples_per_second": 4.2, | |
| "eval_steps_per_second": 2.1, | |
| "eval_wer": 82.01616448547564, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 1.7794736842105265e-05, | |
| "loss": 0.4294, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1.74e-05, | |
| "loss": 0.3201, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_loss": 1.4414749145507812, | |
| "eval_runtime": 822.9952, | |
| "eval_sacrebleu": 1919.20196297517, | |
| "eval_samples_per_second": 4.129, | |
| "eval_steps_per_second": 2.064, | |
| "eval_wer": 80.44367792769943, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1.7005263157894738e-05, | |
| "loss": 0.1981, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1.6610526315789472e-05, | |
| "loss": 0.1955, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "eval_loss": 1.4410473108291626, | |
| "eval_runtime": 941.3392, | |
| "eval_sacrebleu": 1540.5045548236765, | |
| "eval_samples_per_second": 3.61, | |
| "eval_steps_per_second": 1.805, | |
| "eval_wer": 101.01450745662981, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1.621578947368421e-05, | |
| "loss": 0.191, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 1.582105263157895e-05, | |
| "loss": 0.2111, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "eval_loss": 1.434527039527893, | |
| "eval_runtime": 854.9114, | |
| "eval_sacrebleu": 1735.9647924357162, | |
| "eval_samples_per_second": 3.975, | |
| "eval_steps_per_second": 1.987, | |
| "eval_wer": 90.92692164620743, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 1.5426315789473683e-05, | |
| "loss": 0.2043, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 1.5031578947368423e-05, | |
| "loss": 0.1981, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "eval_loss": 1.4597235918045044, | |
| "eval_runtime": 878.1026, | |
| "eval_sacrebleu": 1730.324971075036, | |
| "eval_samples_per_second": 3.87, | |
| "eval_steps_per_second": 1.935, | |
| "eval_wer": 91.53562612018533, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 1.4636842105263158e-05, | |
| "loss": 0.1862, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 1.4242105263157896e-05, | |
| "loss": 0.2052, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "eval_loss": 1.443906307220459, | |
| "eval_runtime": 758.1394, | |
| "eval_sacrebleu": 2143.363030526311, | |
| "eval_samples_per_second": 4.482, | |
| "eval_steps_per_second": 2.241, | |
| "eval_wer": 72.49332115924385, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 1.384736842105263e-05, | |
| "loss": 0.2018, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 1.3452631578947369e-05, | |
| "loss": 0.1886, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "eval_loss": 1.4702341556549072, | |
| "eval_runtime": 802.8723, | |
| "eval_sacrebleu": 1965.5005446719592, | |
| "eval_samples_per_second": 4.232, | |
| "eval_steps_per_second": 2.116, | |
| "eval_wer": 77.75185147610834, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 1.3057894736842105e-05, | |
| "loss": 0.1874, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 1.2663157894736843e-05, | |
| "loss": 0.1918, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "eval_loss": 1.4518498182296753, | |
| "eval_runtime": 782.9672, | |
| "eval_sacrebleu": 2057.451707817952, | |
| "eval_samples_per_second": 4.34, | |
| "eval_steps_per_second": 2.17, | |
| "eval_wer": 75.49288153934597, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 1.2268421052631578e-05, | |
| "loss": 0.1819, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 1.1873684210526316e-05, | |
| "loss": 0.1755, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "eval_loss": 1.4787976741790771, | |
| "eval_runtime": 797.1285, | |
| "eval_sacrebleu": 1954.2236766241735, | |
| "eval_samples_per_second": 4.263, | |
| "eval_steps_per_second": 2.131, | |
| "eval_wer": 78.29968550268845, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 1.1478947368421053e-05, | |
| "loss": 0.172, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 1.108421052631579e-05, | |
| "loss": 0.1769, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "eval_loss": 1.4588199853897095, | |
| "eval_runtime": 886.5481, | |
| "eval_sacrebleu": 1774.1463556159297, | |
| "eval_samples_per_second": 3.833, | |
| "eval_steps_per_second": 1.916, | |
| "eval_wer": 91.92790233674884, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 1.0689473684210526e-05, | |
| "loss": 0.1893, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 1.0294736842105264e-05, | |
| "loss": 0.1104, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "eval_loss": 1.5280550718307495, | |
| "eval_runtime": 860.6622, | |
| "eval_sacrebleu": 1838.1998881180943, | |
| "eval_samples_per_second": 3.948, | |
| "eval_steps_per_second": 1.974, | |
| "eval_wer": 84.73166277772141, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 9.9e-06, | |
| "loss": 0.069, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 9.505263157894737e-06, | |
| "loss": 0.0718, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "eval_loss": 1.5133227109909058, | |
| "eval_runtime": 790.7595, | |
| "eval_sacrebleu": 2058.095479486138, | |
| "eval_samples_per_second": 4.297, | |
| "eval_steps_per_second": 2.149, | |
| "eval_wer": 76.03057049135978, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 9.110526315789473e-06, | |
| "loss": 0.0735, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 8.715789473684211e-06, | |
| "loss": 0.0855, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "eval_loss": 1.527108907699585, | |
| "eval_runtime": 856.1919, | |
| "eval_sacrebleu": 1720.107239864863, | |
| "eval_samples_per_second": 3.969, | |
| "eval_steps_per_second": 1.984, | |
| "eval_wer": 89.13462513949477, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 8.321052631578947e-06, | |
| "loss": 0.0705, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 7.926315789473684e-06, | |
| "loss": 0.0717, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "eval_loss": 1.5289273262023926, | |
| "eval_runtime": 783.842, | |
| "eval_sacrebleu": 2007.516276406263, | |
| "eval_samples_per_second": 4.335, | |
| "eval_steps_per_second": 2.168, | |
| "eval_wer": 75.9291197456968, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 7.531578947368421e-06, | |
| "loss": 0.0728, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 7.1368421052631585e-06, | |
| "loss": 0.0707, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "eval_loss": 1.5366449356079102, | |
| "eval_runtime": 778.1169, | |
| "eval_sacrebleu": 2149.64780863619, | |
| "eval_samples_per_second": 4.367, | |
| "eval_steps_per_second": 2.183, | |
| "eval_wer": 71.95225051570796, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 6.742105263157895e-06, | |
| "loss": 0.0715, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 6.347368421052632e-06, | |
| "loss": 0.0704, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "eval_loss": 1.5355422496795654, | |
| "eval_runtime": 742.6818, | |
| "eval_sacrebleu": 2179.5147468855334, | |
| "eval_samples_per_second": 4.575, | |
| "eval_steps_per_second": 2.288, | |
| "eval_wer": 69.87589192113896, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 5.952631578947369e-06, | |
| "loss": 0.0667, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 5.557894736842106e-06, | |
| "loss": 0.0676, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "eval_loss": 1.5392969846725464, | |
| "eval_runtime": 767.4869, | |
| "eval_sacrebleu": 2086.2196870181765, | |
| "eval_samples_per_second": 4.427, | |
| "eval_steps_per_second": 2.214, | |
| "eval_wer": 73.24743836867201, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 5.163157894736842e-06, | |
| "loss": 0.0725, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 4.76842105263158e-06, | |
| "loss": 0.0748, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "eval_loss": 1.5397995710372925, | |
| "eval_runtime": 800.0285, | |
| "eval_sacrebleu": 1879.1609534484007, | |
| "eval_samples_per_second": 4.247, | |
| "eval_steps_per_second": 2.124, | |
| "eval_wer": 80.72774001555578, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 4.373684210526316e-06, | |
| "loss": 0.0761, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 3.978947368421053e-06, | |
| "loss": 0.0695, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "eval_loss": 1.5350741147994995, | |
| "eval_runtime": 802.9873, | |
| "eval_sacrebleu": 2001.847643597036, | |
| "eval_samples_per_second": 4.232, | |
| "eval_steps_per_second": 2.116, | |
| "eval_wer": 78.83061107165804, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 3.5842105263157898e-06, | |
| "loss": 0.0718, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 3.1894736842105266e-06, | |
| "loss": 0.033, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "eval_loss": 1.5806833505630493, | |
| "eval_runtime": 818.7159, | |
| "eval_sacrebleu": 1892.0435299189799, | |
| "eval_samples_per_second": 4.15, | |
| "eval_steps_per_second": 2.075, | |
| "eval_wer": 82.26302796658888, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 2.7947368421052635e-06, | |
| "loss": 0.0297, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 2.4000000000000003e-06, | |
| "loss": 0.0317, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "eval_loss": 1.5843309164047241, | |
| "eval_runtime": 799.3661, | |
| "eval_sacrebleu": 1967.1172131517576, | |
| "eval_samples_per_second": 4.251, | |
| "eval_steps_per_second": 2.125, | |
| "eval_wer": 78.77650400730445, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 2.005263157894737e-06, | |
| "loss": 0.0306, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 1.6105263157894738e-06, | |
| "loss": 0.0302, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "eval_loss": 1.5848406553268433, | |
| "eval_runtime": 792.2648, | |
| "eval_sacrebleu": 1969.6752766606157, | |
| "eval_samples_per_second": 4.289, | |
| "eval_steps_per_second": 2.144, | |
| "eval_wer": 79.12481823408069, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 1.2157894736842105e-06, | |
| "loss": 0.027, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 8.210526315789474e-07, | |
| "loss": 0.0337, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "eval_loss": 1.5807627439498901, | |
| "eval_runtime": 771.2125, | |
| "eval_sacrebleu": 2062.9545573784067, | |
| "eval_samples_per_second": 4.406, | |
| "eval_steps_per_second": 2.203, | |
| "eval_wer": 74.15373169659463, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 4.263157894736842e-07, | |
| "loss": 0.0308, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 3.157894736842105e-08, | |
| "loss": 0.0306, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "eval_loss": 1.5844563245773315, | |
| "eval_runtime": 771.453, | |
| "eval_sacrebleu": 2090.6715503549444, | |
| "eval_samples_per_second": 4.405, | |
| "eval_steps_per_second": 2.202, | |
| "eval_wer": 73.00057488755876, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "step": 2000, | |
| "total_flos": 1.846946562048e+19, | |
| "train_loss": 0.524174674898386, | |
| "train_runtime": 70623.6184, | |
| "train_samples_per_second": 0.906, | |
| "train_steps_per_second": 0.028 | |
| } | |
| ], | |
| "max_steps": 2000, | |
| "num_train_epochs": 5, | |
| "total_flos": 1.846946562048e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |