| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.09224203490028636, | |
| "eval_steps": 1000, | |
| "global_step": 630000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 490.5409240722656, | |
| "learning_rate": 1.4641588553791733e-08, | |
| "loss": 11.6484, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 8.838762283325195, | |
| "eval_runtime": 75.1115, | |
| "eval_samples_per_second": 10.984, | |
| "eval_steps_per_second": 5.498, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 313.693603515625, | |
| "learning_rate": 2.9283177107583466e-08, | |
| "loss": 6.1041, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 4.824796199798584, | |
| "eval_runtime": 75.0269, | |
| "eval_samples_per_second": 10.996, | |
| "eval_steps_per_second": 5.505, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 273.5600280761719, | |
| "learning_rate": 4.39247656613752e-08, | |
| "loss": 4.6414, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 4.450352191925049, | |
| "eval_runtime": 95.6828, | |
| "eval_samples_per_second": 8.622, | |
| "eval_steps_per_second": 4.316, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 250.93833923339844, | |
| "learning_rate": 5.856635421516693e-08, | |
| "loss": 4.373, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 4.234192848205566, | |
| "eval_runtime": 75.0756, | |
| "eval_samples_per_second": 10.989, | |
| "eval_steps_per_second": 5.501, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 204.94479370117188, | |
| "learning_rate": 7.320794276895867e-08, | |
| "loss": 4.1452, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 3.9963951110839844, | |
| "eval_runtime": 95.7015, | |
| "eval_samples_per_second": 8.621, | |
| "eval_steps_per_second": 4.316, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 167.37818908691406, | |
| "learning_rate": 8.78495313227504e-08, | |
| "loss": 4.0086, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 3.9861972332000732, | |
| "eval_runtime": 75.3345, | |
| "eval_samples_per_second": 10.951, | |
| "eval_steps_per_second": 5.482, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 166.5489959716797, | |
| "learning_rate": 1.0249111987654213e-07, | |
| "loss": 3.9908, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 3.9468181133270264, | |
| "eval_runtime": 75.5485, | |
| "eval_samples_per_second": 10.92, | |
| "eval_steps_per_second": 5.467, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 182.9307861328125, | |
| "learning_rate": 1.1713270843033386e-07, | |
| "loss": 3.9448, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 3.8646774291992188, | |
| "eval_runtime": 96.5287, | |
| "eval_samples_per_second": 8.547, | |
| "eval_steps_per_second": 4.279, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 139.25579833984375, | |
| "learning_rate": 1.3177429698412561e-07, | |
| "loss": 3.9426, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 3.868206739425659, | |
| "eval_runtime": 75.2358, | |
| "eval_samples_per_second": 10.966, | |
| "eval_steps_per_second": 5.489, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 134.8657684326172, | |
| "learning_rate": 1.4641588553791734e-07, | |
| "loss": 3.8819, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 3.861171245574951, | |
| "eval_runtime": 96.0503, | |
| "eval_samples_per_second": 8.589, | |
| "eval_steps_per_second": 4.3, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 115.51847076416016, | |
| "learning_rate": 1.6105747409170906e-07, | |
| "loss": 3.8613, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 3.767599105834961, | |
| "eval_runtime": 75.225, | |
| "eval_samples_per_second": 10.967, | |
| "eval_steps_per_second": 5.49, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 109.70362854003906, | |
| "learning_rate": 1.756990626455008e-07, | |
| "loss": 3.8343, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 3.7472667694091797, | |
| "eval_runtime": 75.0741, | |
| "eval_samples_per_second": 10.989, | |
| "eval_steps_per_second": 5.501, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 103.31382751464844, | |
| "learning_rate": 1.9034065119929256e-07, | |
| "loss": 3.7918, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 3.759472131729126, | |
| "eval_runtime": 96.0111, | |
| "eval_samples_per_second": 8.593, | |
| "eval_steps_per_second": 4.302, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 116.83769226074219, | |
| "learning_rate": 2.0498223975308426e-07, | |
| "loss": 3.7645, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 3.653149366378784, | |
| "eval_runtime": 75.074, | |
| "eval_samples_per_second": 10.989, | |
| "eval_steps_per_second": 5.501, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 102.68473052978516, | |
| "learning_rate": 2.19623828306876e-07, | |
| "loss": 3.7331, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 3.789041519165039, | |
| "eval_runtime": 96.0471, | |
| "eval_samples_per_second": 8.59, | |
| "eval_steps_per_second": 4.3, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 116.87753295898438, | |
| "learning_rate": 2.3426541686066773e-07, | |
| "loss": 3.7257, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 3.6204185485839844, | |
| "eval_runtime": 75.0683, | |
| "eval_samples_per_second": 10.99, | |
| "eval_steps_per_second": 5.502, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 95.3843002319336, | |
| "learning_rate": 2.489070054144595e-07, | |
| "loss": 3.6836, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 3.65740966796875, | |
| "eval_runtime": 95.9655, | |
| "eval_samples_per_second": 8.597, | |
| "eval_steps_per_second": 4.304, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 113.17263793945312, | |
| "learning_rate": 2.6354859396825123e-07, | |
| "loss": 3.6574, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 3.6075878143310547, | |
| "eval_runtime": 75.2673, | |
| "eval_samples_per_second": 10.961, | |
| "eval_steps_per_second": 5.487, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 115.56730651855469, | |
| "learning_rate": 2.781901825220429e-07, | |
| "loss": 3.6319, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 3.502887725830078, | |
| "eval_runtime": 75.054, | |
| "eval_samples_per_second": 10.992, | |
| "eval_steps_per_second": 5.503, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 91.19989776611328, | |
| "learning_rate": 2.928317710758347e-07, | |
| "loss": 3.5851, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 3.496408224105835, | |
| "eval_runtime": 96.1511, | |
| "eval_samples_per_second": 8.58, | |
| "eval_steps_per_second": 4.295, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 98.3852310180664, | |
| "learning_rate": 3.0747335962962637e-07, | |
| "loss": 3.5755, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 3.501962900161743, | |
| "eval_runtime": 75.0818, | |
| "eval_samples_per_second": 10.988, | |
| "eval_steps_per_second": 5.501, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 87.96759796142578, | |
| "learning_rate": 3.221149481834181e-07, | |
| "loss": 3.5306, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 3.4395623207092285, | |
| "eval_runtime": 95.7612, | |
| "eval_samples_per_second": 8.615, | |
| "eval_steps_per_second": 4.313, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 117.33857727050781, | |
| "learning_rate": 3.367565367372098e-07, | |
| "loss": 3.5465, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 3.4450230598449707, | |
| "eval_runtime": 75.1763, | |
| "eval_samples_per_second": 10.974, | |
| "eval_steps_per_second": 5.494, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 84.39014434814453, | |
| "learning_rate": 3.513981252910016e-07, | |
| "loss": 3.5045, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 3.398813247680664, | |
| "eval_runtime": 75.038, | |
| "eval_samples_per_second": 10.994, | |
| "eval_steps_per_second": 5.504, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 91.13440704345703, | |
| "learning_rate": 3.660397138447933e-07, | |
| "loss": 3.4932, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 3.4234652519226074, | |
| "eval_runtime": 96.7065, | |
| "eval_samples_per_second": 8.531, | |
| "eval_steps_per_second": 4.271, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 79.27528381347656, | |
| "learning_rate": 3.806813023985851e-07, | |
| "loss": 3.4615, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 3.360214948654175, | |
| "eval_runtime": 75.1229, | |
| "eval_samples_per_second": 10.982, | |
| "eval_steps_per_second": 5.498, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 106.40711975097656, | |
| "learning_rate": 3.953228909523768e-07, | |
| "loss": 3.4459, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 3.4171066284179688, | |
| "eval_runtime": 95.7756, | |
| "eval_samples_per_second": 8.614, | |
| "eval_steps_per_second": 4.312, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 101.22091674804688, | |
| "learning_rate": 4.099644795061685e-07, | |
| "loss": 3.4484, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 3.440232515335083, | |
| "eval_runtime": 75.1872, | |
| "eval_samples_per_second": 10.973, | |
| "eval_steps_per_second": 5.493, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 85.2155990600586, | |
| "learning_rate": 4.2460606805996026e-07, | |
| "loss": 3.4244, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 3.295353651046753, | |
| "eval_runtime": 75.0816, | |
| "eval_samples_per_second": 10.988, | |
| "eval_steps_per_second": 5.501, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 123.67411041259766, | |
| "learning_rate": 4.39247656613752e-07, | |
| "loss": 3.4244, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 3.3576502799987793, | |
| "eval_runtime": 95.7774, | |
| "eval_samples_per_second": 8.614, | |
| "eval_steps_per_second": 4.312, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 265.1561584472656, | |
| "learning_rate": 4.5388924516754376e-07, | |
| "loss": 3.3943, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 3.247262954711914, | |
| "eval_runtime": 75.0879, | |
| "eval_samples_per_second": 10.987, | |
| "eval_steps_per_second": 5.5, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 78.62483978271484, | |
| "learning_rate": 4.6853083372133546e-07, | |
| "loss": 3.3792, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 3.255089044570923, | |
| "eval_runtime": 95.9793, | |
| "eval_samples_per_second": 8.596, | |
| "eval_steps_per_second": 4.303, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 77.11738586425781, | |
| "learning_rate": 4.831724222751272e-07, | |
| "loss": 3.3503, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 3.1970388889312744, | |
| "eval_runtime": 75.0707, | |
| "eval_samples_per_second": 10.99, | |
| "eval_steps_per_second": 5.501, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 105.60401153564453, | |
| "learning_rate": 4.97814010828919e-07, | |
| "loss": 3.3165, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 3.2812023162841797, | |
| "eval_runtime": 95.8908, | |
| "eval_samples_per_second": 8.604, | |
| "eval_steps_per_second": 4.307, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 73.19610595703125, | |
| "learning_rate": 5.124555993827106e-07, | |
| "loss": 3.3296, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 3.2438435554504395, | |
| "eval_runtime": 75.2106, | |
| "eval_samples_per_second": 10.969, | |
| "eval_steps_per_second": 5.491, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 92.63853454589844, | |
| "learning_rate": 5.270971879365025e-07, | |
| "loss": 3.3123, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 3.1740996837615967, | |
| "eval_runtime": 75.0587, | |
| "eval_samples_per_second": 10.991, | |
| "eval_steps_per_second": 5.502, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 76.13302612304688, | |
| "learning_rate": 5.417387764902941e-07, | |
| "loss": 3.3046, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 3.2372987270355225, | |
| "eval_runtime": 95.751, | |
| "eval_samples_per_second": 8.616, | |
| "eval_steps_per_second": 4.313, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 92.608642578125, | |
| "learning_rate": 5.563803650440859e-07, | |
| "loss": 3.2746, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 3.2454912662506104, | |
| "eval_runtime": 75.0278, | |
| "eval_samples_per_second": 10.996, | |
| "eval_steps_per_second": 5.505, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 102.28934478759766, | |
| "learning_rate": 5.710219535978776e-07, | |
| "loss": 3.2682, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 3.196023941040039, | |
| "eval_runtime": 95.7842, | |
| "eval_samples_per_second": 8.613, | |
| "eval_steps_per_second": 4.312, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 108.18222045898438, | |
| "learning_rate": 5.856635421516694e-07, | |
| "loss": 3.2708, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 3.215292453765869, | |
| "eval_runtime": 75.1865, | |
| "eval_samples_per_second": 10.973, | |
| "eval_steps_per_second": 5.493, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 96.638427734375, | |
| "learning_rate": 6.003051307054611e-07, | |
| "loss": 3.2426, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 3.331897497177124, | |
| "eval_runtime": 75.005, | |
| "eval_samples_per_second": 10.999, | |
| "eval_steps_per_second": 5.506, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 103.09781646728516, | |
| "learning_rate": 6.149467192592527e-07, | |
| "loss": 3.2235, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 3.207122325897217, | |
| "eval_runtime": 95.9639, | |
| "eval_samples_per_second": 8.597, | |
| "eval_steps_per_second": 4.304, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 119.6423110961914, | |
| "learning_rate": 6.295883078130445e-07, | |
| "loss": 3.2281, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 3.1870551109313965, | |
| "eval_runtime": 74.9929, | |
| "eval_samples_per_second": 11.001, | |
| "eval_steps_per_second": 5.507, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 113.07027435302734, | |
| "learning_rate": 6.442298963668362e-07, | |
| "loss": 3.219, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 3.046499490737915, | |
| "eval_runtime": 95.8481, | |
| "eval_samples_per_second": 8.607, | |
| "eval_steps_per_second": 4.309, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 78.94286346435547, | |
| "learning_rate": 6.588714849206281e-07, | |
| "loss": 3.2089, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 3.217085599899292, | |
| "eval_runtime": 75.0114, | |
| "eval_samples_per_second": 10.998, | |
| "eval_steps_per_second": 5.506, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 97.2042007446289, | |
| "learning_rate": 6.735130734744196e-07, | |
| "loss": 3.1798, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 3.0830495357513428, | |
| "eval_runtime": 75.0234, | |
| "eval_samples_per_second": 10.997, | |
| "eval_steps_per_second": 5.505, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 119.12738037109375, | |
| "learning_rate": 6.881546620282115e-07, | |
| "loss": 3.1809, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 3.1285533905029297, | |
| "eval_runtime": 95.8319, | |
| "eval_samples_per_second": 8.609, | |
| "eval_steps_per_second": 4.31, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 65.7905502319336, | |
| "learning_rate": 7.027962505820032e-07, | |
| "loss": 3.1605, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 3.175480604171753, | |
| "eval_runtime": 75.0379, | |
| "eval_samples_per_second": 10.994, | |
| "eval_steps_per_second": 5.504, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 119.85379791259766, | |
| "learning_rate": 7.174378391357949e-07, | |
| "loss": 3.1485, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 3.1343507766723633, | |
| "eval_runtime": 95.7086, | |
| "eval_samples_per_second": 8.62, | |
| "eval_steps_per_second": 4.315, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 72.57598114013672, | |
| "learning_rate": 7.320794276895866e-07, | |
| "loss": 3.144, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 3.1388068199157715, | |
| "eval_runtime": 75.0332, | |
| "eval_samples_per_second": 10.995, | |
| "eval_steps_per_second": 5.504, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 101.29464721679688, | |
| "learning_rate": 7.467210162433784e-07, | |
| "loss": 3.1287, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 3.132037878036499, | |
| "eval_runtime": 95.9227, | |
| "eval_samples_per_second": 8.601, | |
| "eval_steps_per_second": 4.306, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 110.46088409423828, | |
| "learning_rate": 7.613626047971702e-07, | |
| "loss": 3.1234, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 3.025822162628174, | |
| "eval_runtime": 75.1384, | |
| "eval_samples_per_second": 10.98, | |
| "eval_steps_per_second": 5.497, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 88.59445190429688, | |
| "learning_rate": 7.760041933509619e-07, | |
| "loss": 3.1065, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 3.075002908706665, | |
| "eval_runtime": 75.005, | |
| "eval_samples_per_second": 10.999, | |
| "eval_steps_per_second": 5.506, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 71.0448989868164, | |
| "learning_rate": 7.906457819047536e-07, | |
| "loss": 3.1247, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 3.009894371032715, | |
| "eval_runtime": 103.8658, | |
| "eval_samples_per_second": 7.943, | |
| "eval_steps_per_second": 3.976, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 71.39112854003906, | |
| "learning_rate": 8.052873704585454e-07, | |
| "loss": 3.1066, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 3.0463435649871826, | |
| "eval_runtime": 75.0114, | |
| "eval_samples_per_second": 10.998, | |
| "eval_steps_per_second": 5.506, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 65.42823028564453, | |
| "learning_rate": 8.19928959012337e-07, | |
| "loss": 3.0938, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 3.003645181655884, | |
| "eval_runtime": 95.848, | |
| "eval_samples_per_second": 8.607, | |
| "eval_steps_per_second": 4.309, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 49.959877014160156, | |
| "learning_rate": 8.345705475661288e-07, | |
| "loss": 3.0987, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 3.0445501804351807, | |
| "eval_runtime": 75.3866, | |
| "eval_samples_per_second": 10.944, | |
| "eval_steps_per_second": 5.478, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 73.73646545410156, | |
| "learning_rate": 8.492121361199205e-07, | |
| "loss": 3.0884, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 3.1307623386383057, | |
| "eval_runtime": 75.0205, | |
| "eval_samples_per_second": 10.997, | |
| "eval_steps_per_second": 5.505, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 70.4371566772461, | |
| "learning_rate": 8.638537246737122e-07, | |
| "loss": 3.0493, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 3.093940496444702, | |
| "eval_runtime": 96.0292, | |
| "eval_samples_per_second": 8.591, | |
| "eval_steps_per_second": 4.301, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 105.82594299316406, | |
| "learning_rate": 8.78495313227504e-07, | |
| "loss": 3.039, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 3.0275042057037354, | |
| "eval_runtime": 75.0337, | |
| "eval_samples_per_second": 10.995, | |
| "eval_steps_per_second": 5.504, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 102.49614715576172, | |
| "learning_rate": 8.931369017812958e-07, | |
| "loss": 3.062, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.973200798034668, | |
| "eval_runtime": 95.9411, | |
| "eval_samples_per_second": 8.599, | |
| "eval_steps_per_second": 4.305, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 75.26753234863281, | |
| "learning_rate": 9.077784903350875e-07, | |
| "loss": 3.039, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 3.0531740188598633, | |
| "eval_runtime": 75.0299, | |
| "eval_samples_per_second": 10.996, | |
| "eval_steps_per_second": 5.504, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 80.71424102783203, | |
| "learning_rate": 9.224200788888792e-07, | |
| "loss": 3.0477, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.993370294570923, | |
| "eval_runtime": 95.8376, | |
| "eval_samples_per_second": 8.608, | |
| "eval_steps_per_second": 4.309, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 166.16552734375, | |
| "learning_rate": 9.370616674426709e-07, | |
| "loss": 3.0393, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 3.027719020843506, | |
| "eval_runtime": 75.1115, | |
| "eval_samples_per_second": 10.984, | |
| "eval_steps_per_second": 5.498, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 86.70442199707031, | |
| "learning_rate": 9.517032559964627e-07, | |
| "loss": 3.0254, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.9751687049865723, | |
| "eval_runtime": 75.0016, | |
| "eval_samples_per_second": 11.0, | |
| "eval_steps_per_second": 5.507, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 86.4237289428711, | |
| "learning_rate": 9.663448445502544e-07, | |
| "loss": 3.0057, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 3.0547940731048584, | |
| "eval_runtime": 95.8012, | |
| "eval_samples_per_second": 8.612, | |
| "eval_steps_per_second": 4.311, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 69.26152801513672, | |
| "learning_rate": 9.809864331040462e-07, | |
| "loss": 3.0044, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.9488420486450195, | |
| "eval_runtime": 75.0827, | |
| "eval_samples_per_second": 10.988, | |
| "eval_steps_per_second": 5.501, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 85.0170669555664, | |
| "learning_rate": 9.95628021657838e-07, | |
| "loss": 2.9895, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.9108245372772217, | |
| "eval_runtime": 95.6907, | |
| "eval_samples_per_second": 8.622, | |
| "eval_steps_per_second": 4.316, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 105.4040756225586, | |
| "learning_rate": 1.0102696102116297e-06, | |
| "loss": 2.9791, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.9387757778167725, | |
| "eval_runtime": 75.1792, | |
| "eval_samples_per_second": 10.974, | |
| "eval_steps_per_second": 5.494, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 63.04122543334961, | |
| "learning_rate": 1.0249111987654212e-06, | |
| "loss": 2.9898, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 3.011551856994629, | |
| "eval_runtime": 75.0439, | |
| "eval_samples_per_second": 10.994, | |
| "eval_steps_per_second": 5.503, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 125.3316650390625, | |
| "learning_rate": 1.0395527873192132e-06, | |
| "loss": 2.9872, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.9619126319885254, | |
| "eval_runtime": 95.8269, | |
| "eval_samples_per_second": 8.609, | |
| "eval_steps_per_second": 4.31, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 93.01313781738281, | |
| "learning_rate": 1.054194375873005e-06, | |
| "loss": 2.9775, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 3.0116209983825684, | |
| "eval_runtime": 75.0043, | |
| "eval_samples_per_second": 10.999, | |
| "eval_steps_per_second": 5.506, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 70.66936492919922, | |
| "learning_rate": 1.0688359644267965e-06, | |
| "loss": 2.9808, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 3.014275550842285, | |
| "eval_runtime": 95.804, | |
| "eval_samples_per_second": 8.611, | |
| "eval_steps_per_second": 4.311, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 70.04747009277344, | |
| "learning_rate": 1.0834775529805882e-06, | |
| "loss": 2.9661, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 3.061206102371216, | |
| "eval_runtime": 75.0519, | |
| "eval_samples_per_second": 10.992, | |
| "eval_steps_per_second": 5.503, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 66.63554382324219, | |
| "learning_rate": 1.09811914153438e-06, | |
| "loss": 2.9643, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.9404237270355225, | |
| "eval_runtime": 75.0388, | |
| "eval_samples_per_second": 10.994, | |
| "eval_steps_per_second": 5.504, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 65.95869445800781, | |
| "learning_rate": 1.1127607300881717e-06, | |
| "loss": 2.9639, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.9306540489196777, | |
| "eval_runtime": 95.942, | |
| "eval_samples_per_second": 8.599, | |
| "eval_steps_per_second": 4.305, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 96.67823028564453, | |
| "learning_rate": 1.1274023186419635e-06, | |
| "loss": 2.9388, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.9036476612091064, | |
| "eval_runtime": 75.2879, | |
| "eval_samples_per_second": 10.958, | |
| "eval_steps_per_second": 5.486, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 61.048980712890625, | |
| "learning_rate": 1.1420439071957552e-06, | |
| "loss": 2.9723, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.9100253582000732, | |
| "eval_runtime": 95.6634, | |
| "eval_samples_per_second": 8.624, | |
| "eval_steps_per_second": 4.317, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 84.32980346679688, | |
| "learning_rate": 1.156685495749547e-06, | |
| "loss": 2.9403, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.951533555984497, | |
| "eval_runtime": 75.2112, | |
| "eval_samples_per_second": 10.969, | |
| "eval_steps_per_second": 5.491, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 78.58013916015625, | |
| "learning_rate": 1.1713270843033387e-06, | |
| "loss": 2.9315, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.9593875408172607, | |
| "eval_runtime": 95.9075, | |
| "eval_samples_per_second": 8.602, | |
| "eval_steps_per_second": 4.306, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 111.2406005859375, | |
| "learning_rate": 1.1859686728571305e-06, | |
| "loss": 2.943, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.9718501567840576, | |
| "eval_runtime": 75.2332, | |
| "eval_samples_per_second": 10.966, | |
| "eval_steps_per_second": 5.49, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 97.3222427368164, | |
| "learning_rate": 1.2006102614109222e-06, | |
| "loss": 2.9236, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.9419431686401367, | |
| "eval_runtime": 74.9884, | |
| "eval_samples_per_second": 11.002, | |
| "eval_steps_per_second": 5.508, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 272.546630859375, | |
| "learning_rate": 1.2152518499647137e-06, | |
| "loss": 2.9088, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.906754970550537, | |
| "eval_runtime": 96.1313, | |
| "eval_samples_per_second": 8.582, | |
| "eval_steps_per_second": 4.296, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 86.16685485839844, | |
| "learning_rate": 1.2298934385185055e-06, | |
| "loss": 2.9249, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.927184581756592, | |
| "eval_runtime": 74.9953, | |
| "eval_samples_per_second": 11.001, | |
| "eval_steps_per_second": 5.507, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 48.68775177001953, | |
| "learning_rate": 1.2445350270722975e-06, | |
| "loss": 2.9086, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.993474006652832, | |
| "eval_runtime": 95.786, | |
| "eval_samples_per_second": 8.613, | |
| "eval_steps_per_second": 4.312, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 73.69239807128906, | |
| "learning_rate": 1.259176615626089e-06, | |
| "loss": 2.916, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.879518747329712, | |
| "eval_runtime": 75.0661, | |
| "eval_samples_per_second": 10.99, | |
| "eval_steps_per_second": 5.502, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 81.12676239013672, | |
| "learning_rate": 1.2738182041798807e-06, | |
| "loss": 2.963, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.9365947246551514, | |
| "eval_runtime": 74.9513, | |
| "eval_samples_per_second": 11.007, | |
| "eval_steps_per_second": 5.51, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 73.390380859375, | |
| "learning_rate": 1.2884597927336725e-06, | |
| "loss": 2.8899, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 3.00091290473938, | |
| "eval_runtime": 103.6343, | |
| "eval_samples_per_second": 7.961, | |
| "eval_steps_per_second": 3.985, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 63.2940788269043, | |
| "learning_rate": 1.3031013812874642e-06, | |
| "loss": 2.9109, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.857473611831665, | |
| "eval_runtime": 75.1506, | |
| "eval_samples_per_second": 10.978, | |
| "eval_steps_per_second": 5.496, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 58.969947814941406, | |
| "learning_rate": 1.3177429698412562e-06, | |
| "loss": 2.8997, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.8435328006744385, | |
| "eval_runtime": 95.6436, | |
| "eval_samples_per_second": 8.626, | |
| "eval_steps_per_second": 4.318, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 85.3018569946289, | |
| "learning_rate": 1.3323845583950475e-06, | |
| "loss": 2.8939, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.8604986667633057, | |
| "eval_runtime": 75.0321, | |
| "eval_samples_per_second": 10.995, | |
| "eval_steps_per_second": 5.504, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 77.29539489746094, | |
| "learning_rate": 1.3470261469488393e-06, | |
| "loss": 2.9039, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.9332242012023926, | |
| "eval_runtime": 75.0204, | |
| "eval_samples_per_second": 10.997, | |
| "eval_steps_per_second": 5.505, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 84.76435852050781, | |
| "learning_rate": 1.3616677355026312e-06, | |
| "loss": 2.8846, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.8225491046905518, | |
| "eval_runtime": 95.901, | |
| "eval_samples_per_second": 8.603, | |
| "eval_steps_per_second": 4.307, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 64.92876434326172, | |
| "learning_rate": 1.376309324056423e-06, | |
| "loss": 2.8728, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.7463650703430176, | |
| "eval_runtime": 74.9691, | |
| "eval_samples_per_second": 11.005, | |
| "eval_steps_per_second": 5.509, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 78.40308380126953, | |
| "learning_rate": 1.3909509126102147e-06, | |
| "loss": 2.8671, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.727618932723999, | |
| "eval_runtime": 95.9006, | |
| "eval_samples_per_second": 8.603, | |
| "eval_steps_per_second": 4.307, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 74.5372314453125, | |
| "learning_rate": 1.4055925011640065e-06, | |
| "loss": 2.893, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.779794692993164, | |
| "eval_runtime": 75.0188, | |
| "eval_samples_per_second": 10.997, | |
| "eval_steps_per_second": 5.505, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 110.36092376708984, | |
| "learning_rate": 1.4202340897177982e-06, | |
| "loss": 2.8587, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.7951598167419434, | |
| "eval_runtime": 103.6888, | |
| "eval_samples_per_second": 7.956, | |
| "eval_steps_per_second": 3.983, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 77.4548110961914, | |
| "learning_rate": 1.4348756782715898e-06, | |
| "loss": 2.8774, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.9320247173309326, | |
| "eval_runtime": 75.1206, | |
| "eval_samples_per_second": 10.982, | |
| "eval_steps_per_second": 5.498, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 56.37371063232422, | |
| "learning_rate": 1.4495172668253815e-06, | |
| "loss": 2.8618, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.8696322441101074, | |
| "eval_runtime": 74.9633, | |
| "eval_samples_per_second": 11.005, | |
| "eval_steps_per_second": 5.509, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 79.53195190429688, | |
| "learning_rate": 1.4641588553791733e-06, | |
| "loss": 2.8607, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.8158628940582275, | |
| "eval_runtime": 95.9613, | |
| "eval_samples_per_second": 8.597, | |
| "eval_steps_per_second": 4.304, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 64.08206939697266, | |
| "learning_rate": 1.478800443932965e-06, | |
| "loss": 2.8482, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.781191349029541, | |
| "eval_runtime": 75.3986, | |
| "eval_samples_per_second": 10.942, | |
| "eval_steps_per_second": 5.478, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 64.09700012207031, | |
| "learning_rate": 1.4934420324867568e-06, | |
| "loss": 2.856, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.8596715927124023, | |
| "eval_runtime": 95.6436, | |
| "eval_samples_per_second": 8.626, | |
| "eval_steps_per_second": 4.318, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 60.58209991455078, | |
| "learning_rate": 1.5080836210405485e-06, | |
| "loss": 2.8449, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.8443682193756104, | |
| "eval_runtime": 75.0915, | |
| "eval_samples_per_second": 10.987, | |
| "eval_steps_per_second": 5.5, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 64.66394805908203, | |
| "learning_rate": 1.5227252095943405e-06, | |
| "loss": 2.8547, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.8253190517425537, | |
| "eval_runtime": 74.9511, | |
| "eval_samples_per_second": 11.007, | |
| "eval_steps_per_second": 5.51, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 72.93558502197266, | |
| "learning_rate": 1.5373667981481318e-06, | |
| "loss": 2.8508, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.8918566703796387, | |
| "eval_runtime": 95.8796, | |
| "eval_samples_per_second": 8.605, | |
| "eval_steps_per_second": 4.307, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 76.92417907714844, | |
| "learning_rate": 1.5520083867019238e-06, | |
| "loss": 2.852, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.8885250091552734, | |
| "eval_runtime": 75.0272, | |
| "eval_samples_per_second": 10.996, | |
| "eval_steps_per_second": 5.505, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 61.644500732421875, | |
| "learning_rate": 1.5666499752557155e-06, | |
| "loss": 2.8452, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.766432046890259, | |
| "eval_runtime": 97.2331, | |
| "eval_samples_per_second": 8.485, | |
| "eval_steps_per_second": 4.248, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 76.87417602539062, | |
| "learning_rate": 1.5812915638095073e-06, | |
| "loss": 2.8166, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.7734806537628174, | |
| "eval_runtime": 76.1146, | |
| "eval_samples_per_second": 10.839, | |
| "eval_steps_per_second": 5.426, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 71.81310272216797, | |
| "learning_rate": 1.595933152363299e-06, | |
| "loss": 2.8396, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.792924404144287, | |
| "eval_runtime": 97.4645, | |
| "eval_samples_per_second": 8.465, | |
| "eval_steps_per_second": 4.237, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 59.734291076660156, | |
| "learning_rate": 1.6105747409170908e-06, | |
| "loss": 2.8095, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.7745141983032227, | |
| "eval_runtime": 76.6193, | |
| "eval_samples_per_second": 10.768, | |
| "eval_steps_per_second": 5.39, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 76.67354583740234, | |
| "learning_rate": 1.6252163294708825e-06, | |
| "loss": 2.8317, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.776149034500122, | |
| "eval_runtime": 76.58, | |
| "eval_samples_per_second": 10.773, | |
| "eval_steps_per_second": 5.393, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 124.78726959228516, | |
| "learning_rate": 1.639857918024674e-06, | |
| "loss": 2.8099, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.8111283779144287, | |
| "eval_runtime": 95.6948, | |
| "eval_samples_per_second": 8.621, | |
| "eval_steps_per_second": 4.316, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 62.90610885620117, | |
| "learning_rate": 1.6544995065784658e-06, | |
| "loss": 2.8286, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.858586549758911, | |
| "eval_runtime": 74.9833, | |
| "eval_samples_per_second": 11.002, | |
| "eval_steps_per_second": 5.508, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 60.4992561340332, | |
| "learning_rate": 1.6691410951322576e-06, | |
| "loss": 2.8343, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.857048749923706, | |
| "eval_runtime": 95.7153, | |
| "eval_samples_per_second": 8.619, | |
| "eval_steps_per_second": 4.315, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 54.388065338134766, | |
| "learning_rate": 1.6837826836860493e-06, | |
| "loss": 2.8369, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.802098512649536, | |
| "eval_runtime": 75.1891, | |
| "eval_samples_per_second": 10.972, | |
| "eval_steps_per_second": 5.493, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 53.773902893066406, | |
| "learning_rate": 1.698424272239841e-06, | |
| "loss": 2.8027, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.7923638820648193, | |
| "eval_runtime": 75.0022, | |
| "eval_samples_per_second": 11.0, | |
| "eval_steps_per_second": 5.507, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 80.11760711669922, | |
| "learning_rate": 1.7130658607936328e-06, | |
| "loss": 2.8181, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.7276864051818848, | |
| "eval_runtime": 95.8648, | |
| "eval_samples_per_second": 8.606, | |
| "eval_steps_per_second": 4.308, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 93.17306518554688, | |
| "learning_rate": 1.7277074493474243e-06, | |
| "loss": 2.8024, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.8029587268829346, | |
| "eval_runtime": 74.9841, | |
| "eval_samples_per_second": 11.002, | |
| "eval_steps_per_second": 5.508, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 63.65019989013672, | |
| "learning_rate": 1.742349037901216e-06, | |
| "loss": 2.8031, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.8437631130218506, | |
| "eval_runtime": 95.9819, | |
| "eval_samples_per_second": 8.595, | |
| "eval_steps_per_second": 4.303, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 63.70858383178711, | |
| "learning_rate": 1.756990626455008e-06, | |
| "loss": 2.8067, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.7934324741363525, | |
| "eval_runtime": 75.1472, | |
| "eval_samples_per_second": 10.978, | |
| "eval_steps_per_second": 5.496, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 56.11475372314453, | |
| "learning_rate": 1.7716322150087998e-06, | |
| "loss": 2.8209, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.808687210083008, | |
| "eval_runtime": 74.9779, | |
| "eval_samples_per_second": 11.003, | |
| "eval_steps_per_second": 5.508, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 68.00253295898438, | |
| "learning_rate": 1.7862738035625916e-06, | |
| "loss": 2.8113, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.973874092102051, | |
| "eval_runtime": 95.8935, | |
| "eval_samples_per_second": 8.603, | |
| "eval_steps_per_second": 4.307, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 67.90374755859375, | |
| "learning_rate": 1.8009153921163833e-06, | |
| "loss": 2.8085, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.8363542556762695, | |
| "eval_runtime": 74.9744, | |
| "eval_samples_per_second": 11.004, | |
| "eval_steps_per_second": 5.509, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 54.21482467651367, | |
| "learning_rate": 1.815556980670175e-06, | |
| "loss": 2.8024, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.862858295440674, | |
| "eval_runtime": 95.7463, | |
| "eval_samples_per_second": 8.617, | |
| "eval_steps_per_second": 4.313, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 73.39325714111328, | |
| "learning_rate": 1.8301985692239666e-06, | |
| "loss": 2.7906, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.76910400390625, | |
| "eval_runtime": 75.0224, | |
| "eval_samples_per_second": 10.997, | |
| "eval_steps_per_second": 5.505, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 59.4721794128418, | |
| "learning_rate": 1.8448401577777583e-06, | |
| "loss": 2.8233, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.7822389602661133, | |
| "eval_runtime": 95.6608, | |
| "eval_samples_per_second": 8.624, | |
| "eval_steps_per_second": 4.317, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 69.88265228271484, | |
| "learning_rate": 1.85948174633155e-06, | |
| "loss": 2.7905, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.810521364212036, | |
| "eval_runtime": 75.1741, | |
| "eval_samples_per_second": 10.975, | |
| "eval_steps_per_second": 5.494, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 57.1430549621582, | |
| "learning_rate": 1.8741233348853418e-06, | |
| "loss": 2.8324, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.7673442363739014, | |
| "eval_runtime": 75.0005, | |
| "eval_samples_per_second": 11.0, | |
| "eval_steps_per_second": 5.507, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 60.84886169433594, | |
| "learning_rate": 1.8887649234391336e-06, | |
| "loss": 2.7855, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.761514902114868, | |
| "eval_runtime": 95.9983, | |
| "eval_samples_per_second": 8.594, | |
| "eval_steps_per_second": 4.302, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 44.72441482543945, | |
| "learning_rate": 1.9034065119929253e-06, | |
| "loss": 2.7882, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.704122304916382, | |
| "eval_runtime": 74.9992, | |
| "eval_samples_per_second": 11.0, | |
| "eval_steps_per_second": 5.507, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 62.372440338134766, | |
| "learning_rate": 1.918048100546717e-06, | |
| "loss": 2.7787, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.721027374267578, | |
| "eval_runtime": 95.7358, | |
| "eval_samples_per_second": 8.617, | |
| "eval_steps_per_second": 4.314, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 66.38520812988281, | |
| "learning_rate": 1.932689689100509e-06, | |
| "loss": 2.7689, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.728421211242676, | |
| "eval_runtime": 75.1015, | |
| "eval_samples_per_second": 10.985, | |
| "eval_steps_per_second": 5.499, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 95.22692108154297, | |
| "learning_rate": 1.9473312776543006e-06, | |
| "loss": 2.7857, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.66815447807312, | |
| "eval_runtime": 75.0123, | |
| "eval_samples_per_second": 10.998, | |
| "eval_steps_per_second": 5.506, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 89.40083312988281, | |
| "learning_rate": 1.9619728662080923e-06, | |
| "loss": 2.7883, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.7113566398620605, | |
| "eval_runtime": 95.7697, | |
| "eval_samples_per_second": 8.614, | |
| "eval_steps_per_second": 4.312, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 81.26580047607422, | |
| "learning_rate": 1.976614454761884e-06, | |
| "loss": 2.7819, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.7667925357818604, | |
| "eval_runtime": 74.9113, | |
| "eval_samples_per_second": 11.013, | |
| "eval_steps_per_second": 5.513, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 70.14020538330078, | |
| "learning_rate": 1.991256043315676e-06, | |
| "loss": 2.7797, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.767988920211792, | |
| "eval_runtime": 95.7035, | |
| "eval_samples_per_second": 8.62, | |
| "eval_steps_per_second": 4.315, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 54.9051513671875, | |
| "learning_rate": 2.0058976318694676e-06, | |
| "loss": 2.7491, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.8340063095092773, | |
| "eval_runtime": 75.0666, | |
| "eval_samples_per_second": 10.99, | |
| "eval_steps_per_second": 5.502, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 77.1761474609375, | |
| "learning_rate": 2.0205392204232593e-06, | |
| "loss": 2.758, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.757105827331543, | |
| "eval_runtime": 74.953, | |
| "eval_samples_per_second": 11.007, | |
| "eval_steps_per_second": 5.51, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 79.28630065917969, | |
| "learning_rate": 2.0351808089770507e-06, | |
| "loss": 2.7981, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.856295585632324, | |
| "eval_runtime": 96.1389, | |
| "eval_samples_per_second": 8.581, | |
| "eval_steps_per_second": 4.296, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 70.3088607788086, | |
| "learning_rate": 2.0498223975308424e-06, | |
| "loss": 2.7733, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.756226062774658, | |
| "eval_runtime": 74.9334, | |
| "eval_samples_per_second": 11.01, | |
| "eval_steps_per_second": 5.512, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 42.964439392089844, | |
| "learning_rate": 2.0644639860846346e-06, | |
| "loss": 2.7643, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.7820403575897217, | |
| "eval_runtime": 95.7318, | |
| "eval_samples_per_second": 8.618, | |
| "eval_steps_per_second": 4.314, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 48.390541076660156, | |
| "learning_rate": 2.0791055746384263e-06, | |
| "loss": 2.7708, | |
| "step": 142000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.8036890029907227, | |
| "eval_runtime": 74.9876, | |
| "eval_samples_per_second": 11.002, | |
| "eval_steps_per_second": 5.508, | |
| "step": 142000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 53.37461853027344, | |
| "learning_rate": 2.093747163192218e-06, | |
| "loss": 2.7535, | |
| "step": 143000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.692978858947754, | |
| "eval_runtime": 95.9397, | |
| "eval_samples_per_second": 8.599, | |
| "eval_steps_per_second": 4.305, | |
| "step": 143000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 60.01034164428711, | |
| "learning_rate": 2.10838875174601e-06, | |
| "loss": 2.7677, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.740020751953125, | |
| "eval_runtime": 75.2482, | |
| "eval_samples_per_second": 10.964, | |
| "eval_steps_per_second": 5.489, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 65.03019714355469, | |
| "learning_rate": 2.123030340299801e-06, | |
| "loss": 2.7438, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.6849639415740967, | |
| "eval_runtime": 74.9511, | |
| "eval_samples_per_second": 11.007, | |
| "eval_steps_per_second": 5.51, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 66.77202606201172, | |
| "learning_rate": 2.137671928853593e-06, | |
| "loss": 2.7816, | |
| "step": 146000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.6878929138183594, | |
| "eval_runtime": 95.6358, | |
| "eval_samples_per_second": 8.626, | |
| "eval_steps_per_second": 4.318, | |
| "step": 146000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 38.58710479736328, | |
| "learning_rate": 2.1523135174073847e-06, | |
| "loss": 2.7873, | |
| "step": 147000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.6576905250549316, | |
| "eval_runtime": 74.9871, | |
| "eval_samples_per_second": 11.002, | |
| "eval_steps_per_second": 5.508, | |
| "step": 147000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 59.993080139160156, | |
| "learning_rate": 2.1669551059611764e-06, | |
| "loss": 2.7334, | |
| "step": 148000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.703524589538574, | |
| "eval_runtime": 95.5679, | |
| "eval_samples_per_second": 8.633, | |
| "eval_steps_per_second": 4.322, | |
| "step": 148000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 58.45066833496094, | |
| "learning_rate": 2.181596694514968e-06, | |
| "loss": 2.7596, | |
| "step": 149000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.7554209232330322, | |
| "eval_runtime": 74.9888, | |
| "eval_samples_per_second": 11.002, | |
| "eval_steps_per_second": 5.507, | |
| "step": 149000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 64.96820068359375, | |
| "learning_rate": 2.19623828306876e-06, | |
| "loss": 2.7615, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.6536672115325928, | |
| "eval_runtime": 74.9475, | |
| "eval_samples_per_second": 11.008, | |
| "eval_steps_per_second": 5.511, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 47.30535888671875, | |
| "learning_rate": 2.2108798716225517e-06, | |
| "loss": 2.7354, | |
| "step": 151000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.73598051071167, | |
| "eval_runtime": 95.8251, | |
| "eval_samples_per_second": 8.609, | |
| "eval_steps_per_second": 4.31, | |
| "step": 151000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 63.874759674072266, | |
| "learning_rate": 2.2255214601763434e-06, | |
| "loss": 2.7469, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.720163345336914, | |
| "eval_runtime": 74.9546, | |
| "eval_samples_per_second": 11.007, | |
| "eval_steps_per_second": 5.51, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 60.05183029174805, | |
| "learning_rate": 2.240163048730135e-06, | |
| "loss": 2.7431, | |
| "step": 153000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.6975433826446533, | |
| "eval_runtime": 95.9027, | |
| "eval_samples_per_second": 8.602, | |
| "eval_steps_per_second": 4.306, | |
| "step": 153000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 67.57109069824219, | |
| "learning_rate": 2.254804637283927e-06, | |
| "loss": 2.729, | |
| "step": 154000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.697463274002075, | |
| "eval_runtime": 74.9668, | |
| "eval_samples_per_second": 11.005, | |
| "eval_steps_per_second": 5.509, | |
| "step": 154000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 61.8995361328125, | |
| "learning_rate": 2.2694462258377187e-06, | |
| "loss": 2.7624, | |
| "step": 155000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.702453136444092, | |
| "eval_runtime": 95.857, | |
| "eval_samples_per_second": 8.607, | |
| "eval_steps_per_second": 4.308, | |
| "step": 155000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 60.828304290771484, | |
| "learning_rate": 2.2840878143915104e-06, | |
| "loss": 2.7486, | |
| "step": 156000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.703162908554077, | |
| "eval_runtime": 75.085, | |
| "eval_samples_per_second": 10.988, | |
| "eval_steps_per_second": 5.5, | |
| "step": 156000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 52.02991485595703, | |
| "learning_rate": 2.298729402945302e-06, | |
| "loss": 2.7346, | |
| "step": 157000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.7533764839172363, | |
| "eval_runtime": 74.9101, | |
| "eval_samples_per_second": 11.013, | |
| "eval_steps_per_second": 5.513, | |
| "step": 157000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 46.363529205322266, | |
| "learning_rate": 2.313370991499094e-06, | |
| "loss": 2.7476, | |
| "step": 158000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.612370491027832, | |
| "eval_runtime": 95.7878, | |
| "eval_samples_per_second": 8.613, | |
| "eval_steps_per_second": 4.312, | |
| "step": 158000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 59.908451080322266, | |
| "learning_rate": 2.3280125800528857e-06, | |
| "loss": 2.7345, | |
| "step": 159000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.8132786750793457, | |
| "eval_runtime": 74.9641, | |
| "eval_samples_per_second": 11.005, | |
| "eval_steps_per_second": 5.509, | |
| "step": 159000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 48.26115798950195, | |
| "learning_rate": 2.3426541686066774e-06, | |
| "loss": 2.7304, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.7734522819519043, | |
| "eval_runtime": 95.7078, | |
| "eval_samples_per_second": 8.62, | |
| "eval_steps_per_second": 4.315, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 55.67764663696289, | |
| "learning_rate": 2.357295757160469e-06, | |
| "loss": 2.7316, | |
| "step": 161000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.7094366550445557, | |
| "eval_runtime": 75.1541, | |
| "eval_samples_per_second": 10.977, | |
| "eval_steps_per_second": 5.495, | |
| "step": 161000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 74.25537872314453, | |
| "learning_rate": 2.371937345714261e-06, | |
| "loss": 2.7367, | |
| "step": 162000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.636099100112915, | |
| "eval_runtime": 75.2637, | |
| "eval_samples_per_second": 10.961, | |
| "eval_steps_per_second": 5.487, | |
| "step": 162000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 73.27501678466797, | |
| "learning_rate": 2.3865789342680527e-06, | |
| "loss": 2.7381, | |
| "step": 163000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.8240554332733154, | |
| "eval_runtime": 96.1397, | |
| "eval_samples_per_second": 8.581, | |
| "eval_steps_per_second": 4.296, | |
| "step": 163000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 79.56513977050781, | |
| "learning_rate": 2.4012205228218444e-06, | |
| "loss": 2.7252, | |
| "step": 164000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.670012950897217, | |
| "eval_runtime": 74.948, | |
| "eval_samples_per_second": 11.008, | |
| "eval_steps_per_second": 5.51, | |
| "step": 164000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 75.19647979736328, | |
| "learning_rate": 2.415862111375636e-06, | |
| "loss": 2.7358, | |
| "step": 165000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.7422537803649902, | |
| "eval_runtime": 95.7799, | |
| "eval_samples_per_second": 8.614, | |
| "eval_steps_per_second": 4.312, | |
| "step": 165000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 73.22459411621094, | |
| "learning_rate": 2.4305036999294275e-06, | |
| "loss": 2.7316, | |
| "step": 166000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.705203056335449, | |
| "eval_runtime": 75.0933, | |
| "eval_samples_per_second": 10.986, | |
| "eval_steps_per_second": 5.5, | |
| "step": 166000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 57.047245025634766, | |
| "learning_rate": 2.4451452884832192e-06, | |
| "loss": 2.7239, | |
| "step": 167000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.7708864212036133, | |
| "eval_runtime": 74.9497, | |
| "eval_samples_per_second": 11.007, | |
| "eval_steps_per_second": 5.51, | |
| "step": 167000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 79.20235443115234, | |
| "learning_rate": 2.459786877037011e-06, | |
| "loss": 2.7118, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.7727091312408447, | |
| "eval_runtime": 96.2784, | |
| "eval_samples_per_second": 8.569, | |
| "eval_steps_per_second": 4.29, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 55.22106170654297, | |
| "learning_rate": 2.474428465590803e-06, | |
| "loss": 2.7325, | |
| "step": 169000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.647690534591675, | |
| "eval_runtime": 74.9199, | |
| "eval_samples_per_second": 11.012, | |
| "eval_steps_per_second": 5.513, | |
| "step": 169000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 64.41899871826172, | |
| "learning_rate": 2.489070054144595e-06, | |
| "loss": 2.7135, | |
| "step": 170000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.6558783054351807, | |
| "eval_runtime": 103.5276, | |
| "eval_samples_per_second": 7.969, | |
| "eval_steps_per_second": 3.989, | |
| "step": 170000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 57.375343322753906, | |
| "learning_rate": 2.5037116426983867e-06, | |
| "loss": 2.7279, | |
| "step": 171000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.5775904655456543, | |
| "eval_runtime": 74.9254, | |
| "eval_samples_per_second": 11.011, | |
| "eval_steps_per_second": 5.512, | |
| "step": 171000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 70.312255859375, | |
| "learning_rate": 2.518353231252178e-06, | |
| "loss": 2.7104, | |
| "step": 172000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.61749267578125, | |
| "eval_runtime": 95.7541, | |
| "eval_samples_per_second": 8.616, | |
| "eval_steps_per_second": 4.313, | |
| "step": 172000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 51.519561767578125, | |
| "learning_rate": 2.53299481980597e-06, | |
| "loss": 2.7306, | |
| "step": 173000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.7134809494018555, | |
| "eval_runtime": 75.1688, | |
| "eval_samples_per_second": 10.975, | |
| "eval_steps_per_second": 5.494, | |
| "step": 173000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 51.85505294799805, | |
| "learning_rate": 2.5476364083597615e-06, | |
| "loss": 2.7344, | |
| "step": 174000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.6391634941101074, | |
| "eval_runtime": 74.8776, | |
| "eval_samples_per_second": 11.018, | |
| "eval_steps_per_second": 5.516, | |
| "step": 174000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 49.310359954833984, | |
| "learning_rate": 2.5622779969135536e-06, | |
| "loss": 2.7166, | |
| "step": 175000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.644277334213257, | |
| "eval_runtime": 95.9839, | |
| "eval_samples_per_second": 8.595, | |
| "eval_steps_per_second": 4.303, | |
| "step": 175000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 55.3402214050293, | |
| "learning_rate": 2.576919585467345e-06, | |
| "loss": 2.7325, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.6863160133361816, | |
| "eval_runtime": 74.8934, | |
| "eval_samples_per_second": 11.016, | |
| "eval_steps_per_second": 5.515, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 88.28662109375, | |
| "learning_rate": 2.5915611740211367e-06, | |
| "loss": 2.7363, | |
| "step": 177000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.635762929916382, | |
| "eval_runtime": 95.8689, | |
| "eval_samples_per_second": 8.606, | |
| "eval_steps_per_second": 4.308, | |
| "step": 177000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 54.152061462402344, | |
| "learning_rate": 2.6062027625749285e-06, | |
| "loss": 2.7308, | |
| "step": 178000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.6707890033721924, | |
| "eval_runtime": 75.0171, | |
| "eval_samples_per_second": 10.997, | |
| "eval_steps_per_second": 5.505, | |
| "step": 178000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 57.176002502441406, | |
| "learning_rate": 2.6208443511287202e-06, | |
| "loss": 2.7079, | |
| "step": 179000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.698444128036499, | |
| "eval_runtime": 74.8872, | |
| "eval_samples_per_second": 11.017, | |
| "eval_steps_per_second": 5.515, | |
| "step": 179000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 48.09297180175781, | |
| "learning_rate": 2.6354859396825124e-06, | |
| "loss": 2.7096, | |
| "step": 180000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.6643295288085938, | |
| "eval_runtime": 95.8171, | |
| "eval_samples_per_second": 8.61, | |
| "eval_steps_per_second": 4.31, | |
| "step": 180000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 53.34381866455078, | |
| "learning_rate": 2.6501275282363037e-06, | |
| "loss": 2.7171, | |
| "step": 181000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.65159273147583, | |
| "eval_runtime": 74.9201, | |
| "eval_samples_per_second": 11.012, | |
| "eval_steps_per_second": 5.513, | |
| "step": 181000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 53.656951904296875, | |
| "learning_rate": 2.664769116790095e-06, | |
| "loss": 2.7048, | |
| "step": 182000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.6368868350982666, | |
| "eval_runtime": 95.7287, | |
| "eval_samples_per_second": 8.618, | |
| "eval_steps_per_second": 4.314, | |
| "step": 182000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 71.44660186767578, | |
| "learning_rate": 2.6794107053438872e-06, | |
| "loss": 2.7236, | |
| "step": 183000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.7588698863983154, | |
| "eval_runtime": 74.9883, | |
| "eval_samples_per_second": 11.002, | |
| "eval_steps_per_second": 5.508, | |
| "step": 183000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 62.191505432128906, | |
| "learning_rate": 2.6940522938976785e-06, | |
| "loss": 2.7078, | |
| "step": 184000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.7348010540008545, | |
| "eval_runtime": 74.9125, | |
| "eval_samples_per_second": 11.013, | |
| "eval_steps_per_second": 5.513, | |
| "step": 184000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 55.455528259277344, | |
| "learning_rate": 2.7086938824514707e-06, | |
| "loss": 2.7133, | |
| "step": 185000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.7168068885803223, | |
| "eval_runtime": 95.9132, | |
| "eval_samples_per_second": 8.602, | |
| "eval_steps_per_second": 4.306, | |
| "step": 185000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 49.198707580566406, | |
| "learning_rate": 2.7233354710052625e-06, | |
| "loss": 2.7181, | |
| "step": 186000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.6445090770721436, | |
| "eval_runtime": 74.8503, | |
| "eval_samples_per_second": 11.022, | |
| "eval_steps_per_second": 5.518, | |
| "step": 186000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 69.39476013183594, | |
| "learning_rate": 2.7379770595590542e-06, | |
| "loss": 2.694, | |
| "step": 187000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.668306589126587, | |
| "eval_runtime": 95.7168, | |
| "eval_samples_per_second": 8.619, | |
| "eval_steps_per_second": 4.315, | |
| "step": 187000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 49.924476623535156, | |
| "learning_rate": 2.752618648112846e-06, | |
| "loss": 2.7187, | |
| "step": 188000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.689119338989258, | |
| "eval_runtime": 74.8676, | |
| "eval_samples_per_second": 11.019, | |
| "eval_steps_per_second": 5.516, | |
| "step": 188000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 46.9813346862793, | |
| "learning_rate": 2.7672602366666373e-06, | |
| "loss": 2.7244, | |
| "step": 189000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.6233108043670654, | |
| "eval_runtime": 95.9325, | |
| "eval_samples_per_second": 8.6, | |
| "eval_steps_per_second": 4.305, | |
| "step": 189000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 55.19742965698242, | |
| "learning_rate": 2.7819018252204295e-06, | |
| "loss": 2.7045, | |
| "step": 190000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.6683340072631836, | |
| "eval_runtime": 75.0381, | |
| "eval_samples_per_second": 10.994, | |
| "eval_steps_per_second": 5.504, | |
| "step": 190000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 40.58945846557617, | |
| "learning_rate": 2.796543413774221e-06, | |
| "loss": 2.7182, | |
| "step": 191000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.5416364669799805, | |
| "eval_runtime": 74.9499, | |
| "eval_samples_per_second": 11.007, | |
| "eval_steps_per_second": 5.51, | |
| "step": 191000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 59.873573303222656, | |
| "learning_rate": 2.811185002328013e-06, | |
| "loss": 2.694, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.7568399906158447, | |
| "eval_runtime": 95.8753, | |
| "eval_samples_per_second": 8.605, | |
| "eval_steps_per_second": 4.308, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 49.662471771240234, | |
| "learning_rate": 2.8258265908818043e-06, | |
| "loss": 2.7121, | |
| "step": 193000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.6501502990722656, | |
| "eval_runtime": 74.9192, | |
| "eval_samples_per_second": 11.012, | |
| "eval_steps_per_second": 5.513, | |
| "step": 193000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 42.26154327392578, | |
| "learning_rate": 2.8404681794355965e-06, | |
| "loss": 2.6814, | |
| "step": 194000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.660658359527588, | |
| "eval_runtime": 95.7557, | |
| "eval_samples_per_second": 8.616, | |
| "eval_steps_per_second": 4.313, | |
| "step": 194000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 56.657474517822266, | |
| "learning_rate": 2.855109767989388e-06, | |
| "loss": 2.699, | |
| "step": 195000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.631808042526245, | |
| "eval_runtime": 75.0945, | |
| "eval_samples_per_second": 10.986, | |
| "eval_steps_per_second": 5.5, | |
| "step": 195000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 52.05348587036133, | |
| "learning_rate": 2.8697513565431795e-06, | |
| "loss": 2.6997, | |
| "step": 196000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.626267433166504, | |
| "eval_runtime": 76.2341, | |
| "eval_samples_per_second": 10.822, | |
| "eval_steps_per_second": 5.418, | |
| "step": 196000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 49.89586639404297, | |
| "learning_rate": 2.8843929450969717e-06, | |
| "loss": 2.6881, | |
| "step": 197000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.6203720569610596, | |
| "eval_runtime": 96.0809, | |
| "eval_samples_per_second": 8.587, | |
| "eval_steps_per_second": 4.298, | |
| "step": 197000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 49.57963562011719, | |
| "learning_rate": 2.899034533650763e-06, | |
| "loss": 2.7143, | |
| "step": 198000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.601503372192383, | |
| "eval_runtime": 74.8871, | |
| "eval_samples_per_second": 11.017, | |
| "eval_steps_per_second": 5.515, | |
| "step": 198000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 57.84087371826172, | |
| "learning_rate": 2.9136761222045552e-06, | |
| "loss": 2.6896, | |
| "step": 199000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.655690908432007, | |
| "eval_runtime": 95.448, | |
| "eval_samples_per_second": 8.643, | |
| "eval_steps_per_second": 4.327, | |
| "step": 199000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 51.44375228881836, | |
| "learning_rate": 2.9283177107583465e-06, | |
| "loss": 2.6857, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.590942144393921, | |
| "eval_runtime": 74.9631, | |
| "eval_samples_per_second": 11.005, | |
| "eval_steps_per_second": 5.509, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 54.060970306396484, | |
| "learning_rate": 2.9429592993121387e-06, | |
| "loss": 2.6882, | |
| "step": 201000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.717146873474121, | |
| "eval_runtime": 95.7384, | |
| "eval_samples_per_second": 8.617, | |
| "eval_steps_per_second": 4.314, | |
| "step": 201000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 43.254676818847656, | |
| "learning_rate": 2.95760088786593e-06, | |
| "loss": 2.6999, | |
| "step": 202000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.6694703102111816, | |
| "eval_runtime": 75.1451, | |
| "eval_samples_per_second": 10.979, | |
| "eval_steps_per_second": 5.496, | |
| "step": 202000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 48.996421813964844, | |
| "learning_rate": 2.972242476419722e-06, | |
| "loss": 2.6919, | |
| "step": 203000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.65441632270813, | |
| "eval_runtime": 74.8418, | |
| "eval_samples_per_second": 11.023, | |
| "eval_steps_per_second": 5.518, | |
| "step": 203000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 64.13751220703125, | |
| "learning_rate": 2.9868840649735135e-06, | |
| "loss": 2.6926, | |
| "step": 204000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.673851251602173, | |
| "eval_runtime": 95.6289, | |
| "eval_samples_per_second": 8.627, | |
| "eval_steps_per_second": 4.319, | |
| "step": 204000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 51.9734001159668, | |
| "learning_rate": 3.0015256535273053e-06, | |
| "loss": 2.6686, | |
| "step": 205000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.6541659832000732, | |
| "eval_runtime": 74.8434, | |
| "eval_samples_per_second": 11.023, | |
| "eval_steps_per_second": 5.518, | |
| "step": 205000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 40.7435302734375, | |
| "learning_rate": 3.016167242081097e-06, | |
| "loss": 2.6833, | |
| "step": 206000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.6632096767425537, | |
| "eval_runtime": 95.7779, | |
| "eval_samples_per_second": 8.614, | |
| "eval_steps_per_second": 4.312, | |
| "step": 206000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 57.3190803527832, | |
| "learning_rate": 3.030808830634889e-06, | |
| "loss": 2.6855, | |
| "step": 207000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.565784454345703, | |
| "eval_runtime": 76.5683, | |
| "eval_samples_per_second": 10.775, | |
| "eval_steps_per_second": 5.394, | |
| "step": 207000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 49.840736389160156, | |
| "learning_rate": 3.045450419188681e-06, | |
| "loss": 2.6655, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.6578309535980225, | |
| "eval_runtime": 76.0025, | |
| "eval_samples_per_second": 10.855, | |
| "eval_steps_per_second": 5.434, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 46.31571578979492, | |
| "learning_rate": 3.0600920077424723e-06, | |
| "loss": 2.7052, | |
| "step": 209000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.7100558280944824, | |
| "eval_runtime": 97.7041, | |
| "eval_samples_per_second": 8.444, | |
| "eval_steps_per_second": 4.227, | |
| "step": 209000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 55.01320266723633, | |
| "learning_rate": 3.0747335962962636e-06, | |
| "loss": 2.7003, | |
| "step": 210000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.6395130157470703, | |
| "eval_runtime": 75.3617, | |
| "eval_samples_per_second": 10.947, | |
| "eval_steps_per_second": 5.48, | |
| "step": 210000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 60.59393310546875, | |
| "learning_rate": 3.089375184850056e-06, | |
| "loss": 2.68, | |
| "step": 211000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.625278949737549, | |
| "eval_runtime": 96.3447, | |
| "eval_samples_per_second": 8.563, | |
| "eval_steps_per_second": 4.287, | |
| "step": 211000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 45.25587463378906, | |
| "learning_rate": 3.1040167734038475e-06, | |
| "loss": 2.6903, | |
| "step": 212000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.598447561264038, | |
| "eval_runtime": 75.8018, | |
| "eval_samples_per_second": 10.884, | |
| "eval_steps_per_second": 5.448, | |
| "step": 212000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 51.60664749145508, | |
| "learning_rate": 3.1186583619576393e-06, | |
| "loss": 2.6726, | |
| "step": 213000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.6069204807281494, | |
| "eval_runtime": 75.3029, | |
| "eval_samples_per_second": 10.956, | |
| "eval_steps_per_second": 5.485, | |
| "step": 213000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 48.45505905151367, | |
| "learning_rate": 3.133299950511431e-06, | |
| "loss": 2.6935, | |
| "step": 214000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.618152141571045, | |
| "eval_runtime": 96.5915, | |
| "eval_samples_per_second": 8.541, | |
| "eval_steps_per_second": 4.276, | |
| "step": 214000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 46.21786880493164, | |
| "learning_rate": 3.147941539065223e-06, | |
| "loss": 2.688, | |
| "step": 215000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.586667776107788, | |
| "eval_runtime": 75.391, | |
| "eval_samples_per_second": 10.943, | |
| "eval_steps_per_second": 5.478, | |
| "step": 215000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 79.90039825439453, | |
| "learning_rate": 3.1625831276190145e-06, | |
| "loss": 2.6829, | |
| "step": 216000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.563133955001831, | |
| "eval_runtime": 96.2319, | |
| "eval_samples_per_second": 8.573, | |
| "eval_steps_per_second": 4.292, | |
| "step": 216000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 49.727264404296875, | |
| "learning_rate": 3.177224716172806e-06, | |
| "loss": 2.6738, | |
| "step": 217000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.619941473007202, | |
| "eval_runtime": 74.8649, | |
| "eval_samples_per_second": 11.02, | |
| "eval_steps_per_second": 5.517, | |
| "step": 217000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 68.52893829345703, | |
| "learning_rate": 3.191866304726598e-06, | |
| "loss": 2.6622, | |
| "step": 218000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.6587114334106445, | |
| "eval_runtime": 95.7442, | |
| "eval_samples_per_second": 8.617, | |
| "eval_steps_per_second": 4.314, | |
| "step": 218000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 63.71025466918945, | |
| "learning_rate": 3.2065078932803894e-06, | |
| "loss": 2.6832, | |
| "step": 219000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.598963737487793, | |
| "eval_runtime": 75.1499, | |
| "eval_samples_per_second": 10.978, | |
| "eval_steps_per_second": 5.496, | |
| "step": 219000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 54.349361419677734, | |
| "learning_rate": 3.2211494818341815e-06, | |
| "loss": 2.6613, | |
| "step": 220000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.629615306854248, | |
| "eval_runtime": 74.8449, | |
| "eval_samples_per_second": 11.023, | |
| "eval_steps_per_second": 5.518, | |
| "step": 220000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 54.800376892089844, | |
| "learning_rate": 3.235791070387973e-06, | |
| "loss": 2.685, | |
| "step": 221000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.5904054641723633, | |
| "eval_runtime": 95.7217, | |
| "eval_samples_per_second": 8.619, | |
| "eval_steps_per_second": 4.315, | |
| "step": 221000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 53.165672302246094, | |
| "learning_rate": 3.250432658941765e-06, | |
| "loss": 2.6736, | |
| "step": 222000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.6516149044036865, | |
| "eval_runtime": 74.8894, | |
| "eval_samples_per_second": 11.016, | |
| "eval_steps_per_second": 5.515, | |
| "step": 222000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 81.56725311279297, | |
| "learning_rate": 3.2650742474955564e-06, | |
| "loss": 2.6636, | |
| "step": 223000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.7000627517700195, | |
| "eval_runtime": 95.7364, | |
| "eval_samples_per_second": 8.617, | |
| "eval_steps_per_second": 4.314, | |
| "step": 223000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 42.29210662841797, | |
| "learning_rate": 3.279715836049348e-06, | |
| "loss": 2.6812, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.664086103439331, | |
| "eval_runtime": 74.9971, | |
| "eval_samples_per_second": 11.0, | |
| "eval_steps_per_second": 5.507, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 41.341575622558594, | |
| "learning_rate": 3.2943574246031403e-06, | |
| "loss": 2.681, | |
| "step": 225000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.7260851860046387, | |
| "eval_runtime": 74.8808, | |
| "eval_samples_per_second": 11.018, | |
| "eval_steps_per_second": 5.515, | |
| "step": 225000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 56.54241943359375, | |
| "learning_rate": 3.3089990131569316e-06, | |
| "loss": 2.6515, | |
| "step": 226000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.631478786468506, | |
| "eval_runtime": 95.9423, | |
| "eval_samples_per_second": 8.599, | |
| "eval_steps_per_second": 4.305, | |
| "step": 226000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 46.822330474853516, | |
| "learning_rate": 3.3236406017107238e-06, | |
| "loss": 2.668, | |
| "step": 227000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.711561918258667, | |
| "eval_runtime": 74.8607, | |
| "eval_samples_per_second": 11.02, | |
| "eval_steps_per_second": 5.517, | |
| "step": 227000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 43.4654655456543, | |
| "learning_rate": 3.338282190264515e-06, | |
| "loss": 2.6744, | |
| "step": 228000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.6422581672668457, | |
| "eval_runtime": 95.6494, | |
| "eval_samples_per_second": 8.625, | |
| "eval_steps_per_second": 4.318, | |
| "step": 228000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 43.6857795715332, | |
| "learning_rate": 3.3529237788183073e-06, | |
| "loss": 2.6626, | |
| "step": 229000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.695249557495117, | |
| "eval_runtime": 74.8743, | |
| "eval_samples_per_second": 11.018, | |
| "eval_steps_per_second": 5.516, | |
| "step": 229000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 58.39930725097656, | |
| "learning_rate": 3.3675653673720986e-06, | |
| "loss": 2.6679, | |
| "step": 230000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.6393015384674072, | |
| "eval_runtime": 74.8495, | |
| "eval_samples_per_second": 11.022, | |
| "eval_steps_per_second": 5.518, | |
| "step": 230000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 44.445709228515625, | |
| "learning_rate": 3.3822069559258904e-06, | |
| "loss": 2.6668, | |
| "step": 231000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.7629072666168213, | |
| "eval_runtime": 95.8302, | |
| "eval_samples_per_second": 8.609, | |
| "eval_steps_per_second": 4.31, | |
| "step": 231000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 40.28990173339844, | |
| "learning_rate": 3.396848544479682e-06, | |
| "loss": 2.6773, | |
| "step": 232000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.695685863494873, | |
| "eval_runtime": 74.7742, | |
| "eval_samples_per_second": 11.033, | |
| "eval_steps_per_second": 5.523, | |
| "step": 232000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 50.713233947753906, | |
| "learning_rate": 3.411490133033474e-06, | |
| "loss": 2.646, | |
| "step": 233000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.659492254257202, | |
| "eval_runtime": 95.7767, | |
| "eval_samples_per_second": 8.614, | |
| "eval_steps_per_second": 4.312, | |
| "step": 233000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 79.29195404052734, | |
| "learning_rate": 3.4261317215872656e-06, | |
| "loss": 2.6608, | |
| "step": 234000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.702548027038574, | |
| "eval_runtime": 74.8568, | |
| "eval_samples_per_second": 11.021, | |
| "eval_steps_per_second": 5.517, | |
| "step": 234000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 64.88552856445312, | |
| "learning_rate": 3.4407733101410574e-06, | |
| "loss": 2.6629, | |
| "step": 235000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.6832387447357178, | |
| "eval_runtime": 95.7323, | |
| "eval_samples_per_second": 8.618, | |
| "eval_steps_per_second": 4.314, | |
| "step": 235000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 54.41705322265625, | |
| "learning_rate": 3.4554148986948487e-06, | |
| "loss": 2.6726, | |
| "step": 236000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.638201951980591, | |
| "eval_runtime": 75.0538, | |
| "eval_samples_per_second": 10.992, | |
| "eval_steps_per_second": 5.503, | |
| "step": 236000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 47.16751480102539, | |
| "learning_rate": 3.470056487248641e-06, | |
| "loss": 2.661, | |
| "step": 237000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.7070186138153076, | |
| "eval_runtime": 74.8317, | |
| "eval_samples_per_second": 11.025, | |
| "eval_steps_per_second": 5.519, | |
| "step": 237000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 44.628997802734375, | |
| "learning_rate": 3.484698075802432e-06, | |
| "loss": 2.6687, | |
| "step": 238000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.645284652709961, | |
| "eval_runtime": 95.6957, | |
| "eval_samples_per_second": 8.621, | |
| "eval_steps_per_second": 4.316, | |
| "step": 238000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 41.38969039916992, | |
| "learning_rate": 3.4993396643562244e-06, | |
| "loss": 2.6702, | |
| "step": 239000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.644817590713501, | |
| "eval_runtime": 74.7903, | |
| "eval_samples_per_second": 11.031, | |
| "eval_steps_per_second": 5.522, | |
| "step": 239000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 64.58867645263672, | |
| "learning_rate": 3.513981252910016e-06, | |
| "loss": 2.6417, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.6666617393493652, | |
| "eval_runtime": 95.5852, | |
| "eval_samples_per_second": 8.631, | |
| "eval_steps_per_second": 4.321, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 44.54737854003906, | |
| "learning_rate": 3.528622841463808e-06, | |
| "loss": 2.6597, | |
| "step": 241000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.606701612472534, | |
| "eval_runtime": 74.9721, | |
| "eval_samples_per_second": 11.004, | |
| "eval_steps_per_second": 5.509, | |
| "step": 241000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 63.05255126953125, | |
| "learning_rate": 3.5432644300175996e-06, | |
| "loss": 2.639, | |
| "step": 242000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.721276044845581, | |
| "eval_runtime": 74.8, | |
| "eval_samples_per_second": 11.029, | |
| "eval_steps_per_second": 5.521, | |
| "step": 242000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 63.65214920043945, | |
| "learning_rate": 3.557906018571391e-06, | |
| "loss": 2.6419, | |
| "step": 243000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.6757595539093018, | |
| "eval_runtime": 95.5642, | |
| "eval_samples_per_second": 8.633, | |
| "eval_steps_per_second": 4.322, | |
| "step": 243000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 60.95127487182617, | |
| "learning_rate": 3.572547607125183e-06, | |
| "loss": 2.6346, | |
| "step": 244000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.5521128177642822, | |
| "eval_runtime": 74.8449, | |
| "eval_samples_per_second": 11.023, | |
| "eval_steps_per_second": 5.518, | |
| "step": 244000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 34.42070007324219, | |
| "learning_rate": 3.5871891956789744e-06, | |
| "loss": 2.6748, | |
| "step": 245000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.5943429470062256, | |
| "eval_runtime": 95.5809, | |
| "eval_samples_per_second": 8.631, | |
| "eval_steps_per_second": 4.321, | |
| "step": 245000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 50.500213623046875, | |
| "learning_rate": 3.6018307842327666e-06, | |
| "loss": 2.6669, | |
| "step": 246000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.6257340908050537, | |
| "eval_runtime": 74.8799, | |
| "eval_samples_per_second": 11.018, | |
| "eval_steps_per_second": 5.516, | |
| "step": 246000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 40.18623733520508, | |
| "learning_rate": 3.616472372786558e-06, | |
| "loss": 2.64, | |
| "step": 247000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.5401906967163086, | |
| "eval_runtime": 95.7899, | |
| "eval_samples_per_second": 8.613, | |
| "eval_steps_per_second": 4.312, | |
| "step": 247000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 54.12990951538086, | |
| "learning_rate": 3.63111396134035e-06, | |
| "loss": 2.6398, | |
| "step": 248000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.5751349925994873, | |
| "eval_runtime": 75.2498, | |
| "eval_samples_per_second": 10.963, | |
| "eval_steps_per_second": 5.488, | |
| "step": 248000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 54.11725616455078, | |
| "learning_rate": 3.6457555498941414e-06, | |
| "loss": 2.6261, | |
| "step": 249000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.578989028930664, | |
| "eval_runtime": 74.8168, | |
| "eval_samples_per_second": 11.027, | |
| "eval_steps_per_second": 5.52, | |
| "step": 249000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 49.80808639526367, | |
| "learning_rate": 3.660397138447933e-06, | |
| "loss": 2.6424, | |
| "step": 250000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.5562169551849365, | |
| "eval_runtime": 95.8177, | |
| "eval_samples_per_second": 8.61, | |
| "eval_steps_per_second": 4.31, | |
| "step": 250000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 61.51396560668945, | |
| "learning_rate": 3.6750387270017254e-06, | |
| "loss": 2.6531, | |
| "step": 251000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.537543773651123, | |
| "eval_runtime": 74.9434, | |
| "eval_samples_per_second": 11.008, | |
| "eval_steps_per_second": 5.511, | |
| "step": 251000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 69.51727294921875, | |
| "learning_rate": 3.6896803155555167e-06, | |
| "loss": 2.6588, | |
| "step": 252000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.599710464477539, | |
| "eval_runtime": 102.9802, | |
| "eval_samples_per_second": 8.011, | |
| "eval_steps_per_second": 4.01, | |
| "step": 252000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 55.579795837402344, | |
| "learning_rate": 3.704321904109309e-06, | |
| "loss": 2.6438, | |
| "step": 253000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.5952088832855225, | |
| "eval_runtime": 75.3086, | |
| "eval_samples_per_second": 10.955, | |
| "eval_steps_per_second": 5.484, | |
| "step": 253000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 45.27565383911133, | |
| "learning_rate": 3.7189634926631e-06, | |
| "loss": 2.6215, | |
| "step": 254000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.5829055309295654, | |
| "eval_runtime": 74.7515, | |
| "eval_samples_per_second": 11.037, | |
| "eval_steps_per_second": 5.525, | |
| "step": 254000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 44.96015548706055, | |
| "learning_rate": 3.7336050812168924e-06, | |
| "loss": 2.6283, | |
| "step": 255000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.6275458335876465, | |
| "eval_runtime": 95.5562, | |
| "eval_samples_per_second": 8.634, | |
| "eval_steps_per_second": 4.322, | |
| "step": 255000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 38.68233871459961, | |
| "learning_rate": 3.7482466697706837e-06, | |
| "loss": 2.641, | |
| "step": 256000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.5264251232147217, | |
| "eval_runtime": 74.8122, | |
| "eval_samples_per_second": 11.028, | |
| "eval_steps_per_second": 5.52, | |
| "step": 256000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 42.972618103027344, | |
| "learning_rate": 3.7628882583244754e-06, | |
| "loss": 2.6546, | |
| "step": 257000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.525606632232666, | |
| "eval_runtime": 95.3847, | |
| "eval_samples_per_second": 8.649, | |
| "eval_steps_per_second": 4.33, | |
| "step": 257000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 50.30706024169922, | |
| "learning_rate": 3.777529846878267e-06, | |
| "loss": 2.6542, | |
| "step": 258000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.575317859649658, | |
| "eval_runtime": 74.8866, | |
| "eval_samples_per_second": 11.017, | |
| "eval_steps_per_second": 5.515, | |
| "step": 258000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 65.63154602050781, | |
| "learning_rate": 3.792171435432059e-06, | |
| "loss": 2.6473, | |
| "step": 259000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.6257107257843018, | |
| "eval_runtime": 74.8156, | |
| "eval_samples_per_second": 11.027, | |
| "eval_steps_per_second": 5.52, | |
| "step": 259000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 47.780609130859375, | |
| "learning_rate": 3.8068130239858507e-06, | |
| "loss": 2.6523, | |
| "step": 260000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.6211636066436768, | |
| "eval_runtime": 95.7469, | |
| "eval_samples_per_second": 8.616, | |
| "eval_steps_per_second": 4.313, | |
| "step": 260000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 55.50344467163086, | |
| "learning_rate": 3.821454612539642e-06, | |
| "loss": 2.6307, | |
| "step": 261000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.6138713359832764, | |
| "eval_runtime": 74.8053, | |
| "eval_samples_per_second": 11.029, | |
| "eval_steps_per_second": 5.521, | |
| "step": 261000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 59.76543426513672, | |
| "learning_rate": 3.836096201093434e-06, | |
| "loss": 2.662, | |
| "step": 262000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.666452407836914, | |
| "eval_runtime": 95.67, | |
| "eval_samples_per_second": 8.623, | |
| "eval_steps_per_second": 4.317, | |
| "step": 262000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 76.32318878173828, | |
| "learning_rate": 3.8507377896472255e-06, | |
| "loss": 2.6497, | |
| "step": 263000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.642090320587158, | |
| "eval_runtime": 74.8226, | |
| "eval_samples_per_second": 11.026, | |
| "eval_steps_per_second": 5.52, | |
| "step": 263000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 33.338584899902344, | |
| "learning_rate": 3.865379378201018e-06, | |
| "loss": 2.6369, | |
| "step": 264000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.6893866062164307, | |
| "eval_runtime": 95.5516, | |
| "eval_samples_per_second": 8.634, | |
| "eval_steps_per_second": 4.322, | |
| "step": 264000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 66.35092163085938, | |
| "learning_rate": 3.88002096675481e-06, | |
| "loss": 2.6394, | |
| "step": 265000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.6854238510131836, | |
| "eval_runtime": 74.9093, | |
| "eval_samples_per_second": 11.013, | |
| "eval_steps_per_second": 5.513, | |
| "step": 265000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 49.542320251464844, | |
| "learning_rate": 3.894662555308601e-06, | |
| "loss": 2.6358, | |
| "step": 266000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.639975070953369, | |
| "eval_runtime": 74.7199, | |
| "eval_samples_per_second": 11.041, | |
| "eval_steps_per_second": 5.527, | |
| "step": 266000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 47.11073303222656, | |
| "learning_rate": 3.909304143862393e-06, | |
| "loss": 2.6567, | |
| "step": 267000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.6232967376708984, | |
| "eval_runtime": 96.0037, | |
| "eval_samples_per_second": 8.593, | |
| "eval_steps_per_second": 4.302, | |
| "step": 267000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 43.28693389892578, | |
| "learning_rate": 3.923945732416185e-06, | |
| "loss": 2.6497, | |
| "step": 268000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.6127660274505615, | |
| "eval_runtime": 74.7657, | |
| "eval_samples_per_second": 11.034, | |
| "eval_steps_per_second": 5.524, | |
| "step": 268000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 36.58399963378906, | |
| "learning_rate": 3.938587320969977e-06, | |
| "loss": 2.6327, | |
| "step": 269000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.5707271099090576, | |
| "eval_runtime": 95.7149, | |
| "eval_samples_per_second": 8.619, | |
| "eval_steps_per_second": 4.315, | |
| "step": 269000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 34.05764389038086, | |
| "learning_rate": 3.953228909523768e-06, | |
| "loss": 2.5982, | |
| "step": 270000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.5980732440948486, | |
| "eval_runtime": 74.9457, | |
| "eval_samples_per_second": 11.008, | |
| "eval_steps_per_second": 5.511, | |
| "step": 270000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 46.130401611328125, | |
| "learning_rate": 3.9678704980775595e-06, | |
| "loss": 2.6492, | |
| "step": 271000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.5685958862304688, | |
| "eval_runtime": 79.9423, | |
| "eval_samples_per_second": 10.32, | |
| "eval_steps_per_second": 5.166, | |
| "step": 271000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 45.223052978515625, | |
| "learning_rate": 3.982512086631352e-06, | |
| "loss": 2.6187, | |
| "step": 272000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.686868190765381, | |
| "eval_runtime": 97.0067, | |
| "eval_samples_per_second": 8.505, | |
| "eval_steps_per_second": 4.257, | |
| "step": 272000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 68.07273864746094, | |
| "learning_rate": 3.997153675185143e-06, | |
| "loss": 2.6348, | |
| "step": 273000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.598745822906494, | |
| "eval_runtime": 74.7772, | |
| "eval_samples_per_second": 11.033, | |
| "eval_steps_per_second": 5.523, | |
| "step": 273000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 55.39958190917969, | |
| "learning_rate": 4.011795263738935e-06, | |
| "loss": 2.6339, | |
| "step": 274000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.793588399887085, | |
| "eval_runtime": 95.6218, | |
| "eval_samples_per_second": 8.628, | |
| "eval_steps_per_second": 4.319, | |
| "step": 274000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 46.7374382019043, | |
| "learning_rate": 4.0264368522927265e-06, | |
| "loss": 2.6154, | |
| "step": 275000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.607264995574951, | |
| "eval_runtime": 74.9463, | |
| "eval_samples_per_second": 11.008, | |
| "eval_steps_per_second": 5.511, | |
| "step": 275000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 45.974037170410156, | |
| "learning_rate": 4.041078440846519e-06, | |
| "loss": 2.6517, | |
| "step": 276000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.603538751602173, | |
| "eval_runtime": 74.8767, | |
| "eval_samples_per_second": 11.018, | |
| "eval_steps_per_second": 5.516, | |
| "step": 276000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 46.00688171386719, | |
| "learning_rate": 4.05572002940031e-06, | |
| "loss": 2.6418, | |
| "step": 277000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.6350746154785156, | |
| "eval_runtime": 96.1011, | |
| "eval_samples_per_second": 8.585, | |
| "eval_steps_per_second": 4.298, | |
| "step": 277000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 73.03669738769531, | |
| "learning_rate": 4.070361617954101e-06, | |
| "loss": 2.6235, | |
| "step": 278000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.5305094718933105, | |
| "eval_runtime": 74.8288, | |
| "eval_samples_per_second": 11.025, | |
| "eval_steps_per_second": 5.519, | |
| "step": 278000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 41.87487030029297, | |
| "learning_rate": 4.0850032065078935e-06, | |
| "loss": 2.6279, | |
| "step": 279000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.5468451976776123, | |
| "eval_runtime": 95.6834, | |
| "eval_samples_per_second": 8.622, | |
| "eval_steps_per_second": 4.316, | |
| "step": 279000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 49.32594299316406, | |
| "learning_rate": 4.099644795061685e-06, | |
| "loss": 2.6161, | |
| "step": 280000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.6616108417510986, | |
| "eval_runtime": 74.9047, | |
| "eval_samples_per_second": 11.014, | |
| "eval_steps_per_second": 5.514, | |
| "step": 280000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 53.41552734375, | |
| "learning_rate": 4.114286383615477e-06, | |
| "loss": 2.6354, | |
| "step": 281000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.677363872528076, | |
| "eval_runtime": 95.9109, | |
| "eval_samples_per_second": 8.602, | |
| "eval_steps_per_second": 4.306, | |
| "step": 281000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 39.76441955566406, | |
| "learning_rate": 4.128927972169269e-06, | |
| "loss": 2.6431, | |
| "step": 282000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.5935537815093994, | |
| "eval_runtime": 75.0858, | |
| "eval_samples_per_second": 10.987, | |
| "eval_steps_per_second": 5.5, | |
| "step": 282000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 37.35220718383789, | |
| "learning_rate": 4.1435695607230605e-06, | |
| "loss": 2.6335, | |
| "step": 283000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.5552804470062256, | |
| "eval_runtime": 74.727, | |
| "eval_samples_per_second": 11.04, | |
| "eval_steps_per_second": 5.527, | |
| "step": 283000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 82.63373565673828, | |
| "learning_rate": 4.158211149276853e-06, | |
| "loss": 2.6379, | |
| "step": 284000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.6075127124786377, | |
| "eval_runtime": 95.7342, | |
| "eval_samples_per_second": 8.618, | |
| "eval_steps_per_second": 4.314, | |
| "step": 284000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 43.660396575927734, | |
| "learning_rate": 4.172852737830644e-06, | |
| "loss": 2.6288, | |
| "step": 285000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.646052360534668, | |
| "eval_runtime": 74.7867, | |
| "eval_samples_per_second": 11.031, | |
| "eval_steps_per_second": 5.522, | |
| "step": 285000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 84.4545669555664, | |
| "learning_rate": 4.187494326384436e-06, | |
| "loss": 2.6322, | |
| "step": 286000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.6136434078216553, | |
| "eval_runtime": 95.9788, | |
| "eval_samples_per_second": 8.596, | |
| "eval_steps_per_second": 4.303, | |
| "step": 286000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 63.179813385009766, | |
| "learning_rate": 4.2021359149382275e-06, | |
| "loss": 2.6312, | |
| "step": 287000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.6379587650299072, | |
| "eval_runtime": 74.9615, | |
| "eval_samples_per_second": 11.006, | |
| "eval_steps_per_second": 5.509, | |
| "step": 287000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 59.3049201965332, | |
| "learning_rate": 4.21677750349202e-06, | |
| "loss": 2.6047, | |
| "step": 288000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.60385799407959, | |
| "eval_runtime": 74.7494, | |
| "eval_samples_per_second": 11.037, | |
| "eval_steps_per_second": 5.525, | |
| "step": 288000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 43.60575866699219, | |
| "learning_rate": 4.231419092045811e-06, | |
| "loss": 2.6223, | |
| "step": 289000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.672245502471924, | |
| "eval_runtime": 95.4279, | |
| "eval_samples_per_second": 8.645, | |
| "eval_steps_per_second": 4.328, | |
| "step": 289000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 38.0888786315918, | |
| "learning_rate": 4.246060680599602e-06, | |
| "loss": 2.6231, | |
| "step": 290000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.523240089416504, | |
| "eval_runtime": 74.7272, | |
| "eval_samples_per_second": 11.04, | |
| "eval_steps_per_second": 5.527, | |
| "step": 290000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 47.68942642211914, | |
| "learning_rate": 4.2607022691533945e-06, | |
| "loss": 2.6282, | |
| "step": 291000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.6057043075561523, | |
| "eval_runtime": 95.5262, | |
| "eval_samples_per_second": 8.636, | |
| "eval_steps_per_second": 4.323, | |
| "step": 291000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 44.74800491333008, | |
| "learning_rate": 4.275343857707186e-06, | |
| "loss": 2.6191, | |
| "step": 292000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.541307210922241, | |
| "eval_runtime": 74.9271, | |
| "eval_samples_per_second": 11.011, | |
| "eval_steps_per_second": 5.512, | |
| "step": 292000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 42.66278839111328, | |
| "learning_rate": 4.289985446260978e-06, | |
| "loss": 2.6013, | |
| "step": 293000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.644083023071289, | |
| "eval_runtime": 96.0242, | |
| "eval_samples_per_second": 8.592, | |
| "eval_steps_per_second": 4.301, | |
| "step": 293000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 35.30427551269531, | |
| "learning_rate": 4.304627034814769e-06, | |
| "loss": 2.6046, | |
| "step": 294000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.644864559173584, | |
| "eval_runtime": 74.8348, | |
| "eval_samples_per_second": 11.024, | |
| "eval_steps_per_second": 5.519, | |
| "step": 294000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 55.9124870300293, | |
| "learning_rate": 4.3192686233685615e-06, | |
| "loss": 2.6076, | |
| "step": 295000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.56697154045105, | |
| "eval_runtime": 75.651, | |
| "eval_samples_per_second": 10.905, | |
| "eval_steps_per_second": 5.459, | |
| "step": 295000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 44.417022705078125, | |
| "learning_rate": 4.333910211922353e-06, | |
| "loss": 2.6097, | |
| "step": 296000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.5623719692230225, | |
| "eval_runtime": 95.6054, | |
| "eval_samples_per_second": 8.629, | |
| "eval_steps_per_second": 4.32, | |
| "step": 296000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 45.69809341430664, | |
| "learning_rate": 4.348551800476144e-06, | |
| "loss": 2.6227, | |
| "step": 297000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.730081558227539, | |
| "eval_runtime": 74.6867, | |
| "eval_samples_per_second": 11.046, | |
| "eval_steps_per_second": 5.53, | |
| "step": 297000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 39.38439178466797, | |
| "learning_rate": 4.363193389029936e-06, | |
| "loss": 2.6253, | |
| "step": 298000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.595525026321411, | |
| "eval_runtime": 95.8343, | |
| "eval_samples_per_second": 8.609, | |
| "eval_steps_per_second": 4.31, | |
| "step": 298000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 39.93308639526367, | |
| "learning_rate": 4.3778349775837285e-06, | |
| "loss": 2.6177, | |
| "step": 299000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.6082019805908203, | |
| "eval_runtime": 74.7352, | |
| "eval_samples_per_second": 11.039, | |
| "eval_steps_per_second": 5.526, | |
| "step": 299000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 63.840782165527344, | |
| "learning_rate": 4.39247656613752e-06, | |
| "loss": 2.6275, | |
| "step": 300000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.5048768520355225, | |
| "eval_runtime": 75.2695, | |
| "eval_samples_per_second": 10.961, | |
| "eval_steps_per_second": 5.487, | |
| "step": 300000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 39.90363311767578, | |
| "learning_rate": 4.407118154691312e-06, | |
| "loss": 2.6198, | |
| "step": 301000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.526975631713867, | |
| "eval_runtime": 95.5077, | |
| "eval_samples_per_second": 8.638, | |
| "eval_steps_per_second": 4.324, | |
| "step": 301000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 44.53697204589844, | |
| "learning_rate": 4.421759743245103e-06, | |
| "loss": 2.6176, | |
| "step": 302000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.582653045654297, | |
| "eval_runtime": 74.761, | |
| "eval_samples_per_second": 11.035, | |
| "eval_steps_per_second": 5.524, | |
| "step": 302000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 67.8877944946289, | |
| "learning_rate": 4.4364013317988955e-06, | |
| "loss": 2.6304, | |
| "step": 303000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.6658573150634766, | |
| "eval_runtime": 95.8482, | |
| "eval_samples_per_second": 8.607, | |
| "eval_steps_per_second": 4.309, | |
| "step": 303000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 38.599971771240234, | |
| "learning_rate": 4.451042920352687e-06, | |
| "loss": 2.5968, | |
| "step": 304000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.568730354309082, | |
| "eval_runtime": 74.8521, | |
| "eval_samples_per_second": 11.022, | |
| "eval_steps_per_second": 5.518, | |
| "step": 304000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 51.99705505371094, | |
| "learning_rate": 4.465684508906479e-06, | |
| "loss": 2.6146, | |
| "step": 305000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.642608880996704, | |
| "eval_runtime": 74.7133, | |
| "eval_samples_per_second": 11.042, | |
| "eval_steps_per_second": 5.528, | |
| "step": 305000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 58.74104690551758, | |
| "learning_rate": 4.48032609746027e-06, | |
| "loss": 2.6105, | |
| "step": 306000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.552302837371826, | |
| "eval_runtime": 95.4477, | |
| "eval_samples_per_second": 8.643, | |
| "eval_steps_per_second": 4.327, | |
| "step": 306000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 37.7462158203125, | |
| "learning_rate": 4.4949676860140625e-06, | |
| "loss": 2.5963, | |
| "step": 307000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.533169746398926, | |
| "eval_runtime": 74.8923, | |
| "eval_samples_per_second": 11.016, | |
| "eval_steps_per_second": 5.515, | |
| "step": 307000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 39.184391021728516, | |
| "learning_rate": 4.509609274567854e-06, | |
| "loss": 2.6195, | |
| "step": 308000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.5383059978485107, | |
| "eval_runtime": 95.6484, | |
| "eval_samples_per_second": 8.625, | |
| "eval_steps_per_second": 4.318, | |
| "step": 308000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 40.16402053833008, | |
| "learning_rate": 4.524250863121646e-06, | |
| "loss": 2.616, | |
| "step": 309000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.618685483932495, | |
| "eval_runtime": 74.7258, | |
| "eval_samples_per_second": 11.04, | |
| "eval_steps_per_second": 5.527, | |
| "step": 309000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 37.97475814819336, | |
| "learning_rate": 4.538892451675437e-06, | |
| "loss": 2.6022, | |
| "step": 310000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.5952703952789307, | |
| "eval_runtime": 95.6397, | |
| "eval_samples_per_second": 8.626, | |
| "eval_steps_per_second": 4.318, | |
| "step": 310000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 53.99909210205078, | |
| "learning_rate": 4.553534040229229e-06, | |
| "loss": 2.5939, | |
| "step": 311000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.5446667671203613, | |
| "eval_runtime": 74.682, | |
| "eval_samples_per_second": 11.047, | |
| "eval_steps_per_second": 5.53, | |
| "step": 311000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 45.01235580444336, | |
| "learning_rate": 4.568175628783021e-06, | |
| "loss": 2.6115, | |
| "step": 312000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.615330934524536, | |
| "eval_runtime": 74.6971, | |
| "eval_samples_per_second": 11.045, | |
| "eval_steps_per_second": 5.529, | |
| "step": 312000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 46.55107498168945, | |
| "learning_rate": 4.582817217336812e-06, | |
| "loss": 2.6223, | |
| "step": 313000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.5805556774139404, | |
| "eval_runtime": 95.6057, | |
| "eval_samples_per_second": 8.629, | |
| "eval_steps_per_second": 4.32, | |
| "step": 313000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 51.727203369140625, | |
| "learning_rate": 4.597458805890604e-06, | |
| "loss": 2.6132, | |
| "step": 314000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.566413164138794, | |
| "eval_runtime": 74.7772, | |
| "eval_samples_per_second": 11.033, | |
| "eval_steps_per_second": 5.523, | |
| "step": 314000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 41.56552505493164, | |
| "learning_rate": 4.612100394444396e-06, | |
| "loss": 2.6014, | |
| "step": 315000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.597524881362915, | |
| "eval_runtime": 95.7861, | |
| "eval_samples_per_second": 8.613, | |
| "eval_steps_per_second": 4.312, | |
| "step": 315000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 35.12276840209961, | |
| "learning_rate": 4.626741982998188e-06, | |
| "loss": 2.6105, | |
| "step": 316000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.5419981479644775, | |
| "eval_runtime": 74.7674, | |
| "eval_samples_per_second": 11.034, | |
| "eval_steps_per_second": 5.524, | |
| "step": 316000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 32.75632095336914, | |
| "learning_rate": 4.641383571551979e-06, | |
| "loss": 2.6076, | |
| "step": 317000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.614522695541382, | |
| "eval_runtime": 74.713, | |
| "eval_samples_per_second": 11.042, | |
| "eval_steps_per_second": 5.528, | |
| "step": 317000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 72.66175842285156, | |
| "learning_rate": 4.656025160105771e-06, | |
| "loss": 2.6031, | |
| "step": 318000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.636115312576294, | |
| "eval_runtime": 95.4957, | |
| "eval_samples_per_second": 8.639, | |
| "eval_steps_per_second": 4.325, | |
| "step": 318000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 56.245540618896484, | |
| "learning_rate": 4.670666748659563e-06, | |
| "loss": 2.5956, | |
| "step": 319000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.656207323074341, | |
| "eval_runtime": 74.7116, | |
| "eval_samples_per_second": 11.042, | |
| "eval_steps_per_second": 5.528, | |
| "step": 319000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 40.125789642333984, | |
| "learning_rate": 4.685308337213355e-06, | |
| "loss": 2.6136, | |
| "step": 320000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.6252167224884033, | |
| "eval_runtime": 95.5473, | |
| "eval_samples_per_second": 8.634, | |
| "eval_steps_per_second": 4.322, | |
| "step": 320000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 30.78213119506836, | |
| "learning_rate": 4.699949925767147e-06, | |
| "loss": 2.6112, | |
| "step": 321000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.5026865005493164, | |
| "eval_runtime": 74.9699, | |
| "eval_samples_per_second": 11.004, | |
| "eval_steps_per_second": 5.509, | |
| "step": 321000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 43.604705810546875, | |
| "learning_rate": 4.714591514320938e-06, | |
| "loss": 2.6137, | |
| "step": 322000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.5527615547180176, | |
| "eval_runtime": 74.7501, | |
| "eval_samples_per_second": 11.037, | |
| "eval_steps_per_second": 5.525, | |
| "step": 322000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 51.488155364990234, | |
| "learning_rate": 4.7292331028747305e-06, | |
| "loss": 2.6012, | |
| "step": 323000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.573512077331543, | |
| "eval_runtime": 96.1372, | |
| "eval_samples_per_second": 8.581, | |
| "eval_steps_per_second": 4.296, | |
| "step": 323000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 42.72104263305664, | |
| "learning_rate": 4.743874691428522e-06, | |
| "loss": 2.6057, | |
| "step": 324000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.625537633895874, | |
| "eval_runtime": 74.7491, | |
| "eval_samples_per_second": 11.037, | |
| "eval_steps_per_second": 5.525, | |
| "step": 324000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 45.53932571411133, | |
| "learning_rate": 4.758516279982313e-06, | |
| "loss": 2.6134, | |
| "step": 325000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.558391809463501, | |
| "eval_runtime": 95.5834, | |
| "eval_samples_per_second": 8.631, | |
| "eval_steps_per_second": 4.321, | |
| "step": 325000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 48.866275787353516, | |
| "learning_rate": 4.773157868536105e-06, | |
| "loss": 2.6041, | |
| "step": 326000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.5378012657165527, | |
| "eval_runtime": 74.7093, | |
| "eval_samples_per_second": 11.043, | |
| "eval_steps_per_second": 5.528, | |
| "step": 326000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 35.03339385986328, | |
| "learning_rate": 4.787799457089897e-06, | |
| "loss": 2.5948, | |
| "step": 327000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.563570737838745, | |
| "eval_runtime": 95.4651, | |
| "eval_samples_per_second": 8.642, | |
| "eval_steps_per_second": 4.326, | |
| "step": 327000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 42.4345817565918, | |
| "learning_rate": 4.802441045643689e-06, | |
| "loss": 2.604, | |
| "step": 328000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.592179536819458, | |
| "eval_runtime": 74.6574, | |
| "eval_samples_per_second": 11.05, | |
| "eval_steps_per_second": 5.532, | |
| "step": 328000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 56.61566925048828, | |
| "learning_rate": 4.81708263419748e-06, | |
| "loss": 2.6091, | |
| "step": 329000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.5877678394317627, | |
| "eval_runtime": 74.6766, | |
| "eval_samples_per_second": 11.048, | |
| "eval_steps_per_second": 5.531, | |
| "step": 329000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 43.33776092529297, | |
| "learning_rate": 4.831724222751272e-06, | |
| "loss": 2.6022, | |
| "step": 330000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.6100189685821533, | |
| "eval_runtime": 95.502, | |
| "eval_samples_per_second": 8.639, | |
| "eval_steps_per_second": 4.325, | |
| "step": 330000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 36.602630615234375, | |
| "learning_rate": 4.846365811305064e-06, | |
| "loss": 2.5769, | |
| "step": 331000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.5708513259887695, | |
| "eval_runtime": 74.7367, | |
| "eval_samples_per_second": 11.039, | |
| "eval_steps_per_second": 5.526, | |
| "step": 331000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 43.569435119628906, | |
| "learning_rate": 4.861007399858855e-06, | |
| "loss": 2.5931, | |
| "step": 332000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.564967632293701, | |
| "eval_runtime": 95.3119, | |
| "eval_samples_per_second": 8.656, | |
| "eval_steps_per_second": 4.333, | |
| "step": 332000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 32.60426712036133, | |
| "learning_rate": 4.875648988412647e-06, | |
| "loss": 2.5972, | |
| "step": 333000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.572070360183716, | |
| "eval_runtime": 74.6662, | |
| "eval_samples_per_second": 11.049, | |
| "eval_steps_per_second": 5.531, | |
| "step": 333000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 29.82908821105957, | |
| "learning_rate": 4.8902905769664385e-06, | |
| "loss": 2.5879, | |
| "step": 334000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.556232452392578, | |
| "eval_runtime": 74.7002, | |
| "eval_samples_per_second": 11.044, | |
| "eval_steps_per_second": 5.529, | |
| "step": 334000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 42.57914352416992, | |
| "learning_rate": 4.904932165520231e-06, | |
| "loss": 2.6053, | |
| "step": 335000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.5889346599578857, | |
| "eval_runtime": 95.415, | |
| "eval_samples_per_second": 8.646, | |
| "eval_steps_per_second": 4.328, | |
| "step": 335000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 41.65904235839844, | |
| "learning_rate": 4.919573754074022e-06, | |
| "loss": 2.5853, | |
| "step": 336000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.564220428466797, | |
| "eval_runtime": 75.0285, | |
| "eval_samples_per_second": 10.996, | |
| "eval_steps_per_second": 5.505, | |
| "step": 336000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 36.339805603027344, | |
| "learning_rate": 4.934215342627814e-06, | |
| "loss": 2.601, | |
| "step": 337000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.616079568862915, | |
| "eval_runtime": 95.5747, | |
| "eval_samples_per_second": 8.632, | |
| "eval_steps_per_second": 4.321, | |
| "step": 337000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 45.61557388305664, | |
| "learning_rate": 4.948856931181606e-06, | |
| "loss": 2.5803, | |
| "step": 338000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.6592965126037598, | |
| "eval_runtime": 74.8749, | |
| "eval_samples_per_second": 11.018, | |
| "eval_steps_per_second": 5.516, | |
| "step": 338000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 52.03131103515625, | |
| "learning_rate": 4.963498519735398e-06, | |
| "loss": 2.593, | |
| "step": 339000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.596527099609375, | |
| "eval_runtime": 95.738, | |
| "eval_samples_per_second": 8.617, | |
| "eval_steps_per_second": 4.314, | |
| "step": 339000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 35.49449157714844, | |
| "learning_rate": 4.97814010828919e-06, | |
| "loss": 2.5997, | |
| "step": 340000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.633748769760132, | |
| "eval_runtime": 74.5989, | |
| "eval_samples_per_second": 11.059, | |
| "eval_steps_per_second": 5.536, | |
| "step": 340000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 54.275081634521484, | |
| "learning_rate": 4.992781696842981e-06, | |
| "loss": 2.5905, | |
| "step": 341000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.56416392326355, | |
| "eval_runtime": 74.6523, | |
| "eval_samples_per_second": 11.051, | |
| "eval_steps_per_second": 5.532, | |
| "step": 341000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 41.0302619934082, | |
| "learning_rate": 5.007423285396773e-06, | |
| "loss": 2.5862, | |
| "step": 342000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.618197202682495, | |
| "eval_runtime": 95.5993, | |
| "eval_samples_per_second": 8.63, | |
| "eval_steps_per_second": 4.32, | |
| "step": 342000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 63.483768463134766, | |
| "learning_rate": 5.0220648739505655e-06, | |
| "loss": 2.5804, | |
| "step": 343000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.5387542247772217, | |
| "eval_runtime": 74.7839, | |
| "eval_samples_per_second": 11.032, | |
| "eval_steps_per_second": 5.523, | |
| "step": 343000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 44.93665313720703, | |
| "learning_rate": 5.036706462504356e-06, | |
| "loss": 2.5952, | |
| "step": 344000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.513009548187256, | |
| "eval_runtime": 96.0331, | |
| "eval_samples_per_second": 8.591, | |
| "eval_steps_per_second": 4.301, | |
| "step": 344000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 32.70128631591797, | |
| "learning_rate": 5.051348051058148e-06, | |
| "loss": 2.5809, | |
| "step": 345000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.621497631072998, | |
| "eval_runtime": 74.6905, | |
| "eval_samples_per_second": 11.046, | |
| "eval_steps_per_second": 5.529, | |
| "step": 345000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 48.31204605102539, | |
| "learning_rate": 5.06598963961194e-06, | |
| "loss": 2.5855, | |
| "step": 346000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.7315196990966797, | |
| "eval_runtime": 74.6218, | |
| "eval_samples_per_second": 11.056, | |
| "eval_steps_per_second": 5.535, | |
| "step": 346000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 35.62407302856445, | |
| "learning_rate": 5.080631228165731e-06, | |
| "loss": 2.6069, | |
| "step": 347000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.50812029838562, | |
| "eval_runtime": 95.4592, | |
| "eval_samples_per_second": 8.642, | |
| "eval_steps_per_second": 4.326, | |
| "step": 347000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 42.37205505371094, | |
| "learning_rate": 5.095272816719523e-06, | |
| "loss": 2.5716, | |
| "step": 348000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.4942855834960938, | |
| "eval_runtime": 74.6742, | |
| "eval_samples_per_second": 11.048, | |
| "eval_steps_per_second": 5.531, | |
| "step": 348000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 47.90432357788086, | |
| "learning_rate": 5.109914405273315e-06, | |
| "loss": 2.5962, | |
| "step": 349000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.545471668243408, | |
| "eval_runtime": 95.481, | |
| "eval_samples_per_second": 8.64, | |
| "eval_steps_per_second": 4.325, | |
| "step": 349000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 57.815704345703125, | |
| "learning_rate": 5.124555993827107e-06, | |
| "loss": 2.5763, | |
| "step": 350000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.4934654235839844, | |
| "eval_runtime": 74.8205, | |
| "eval_samples_per_second": 11.026, | |
| "eval_steps_per_second": 5.52, | |
| "step": 350000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 46.640071868896484, | |
| "learning_rate": 5.139197582380898e-06, | |
| "loss": 2.5946, | |
| "step": 351000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.5673718452453613, | |
| "eval_runtime": 74.6438, | |
| "eval_samples_per_second": 11.052, | |
| "eval_steps_per_second": 5.533, | |
| "step": 351000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 39.76240539550781, | |
| "learning_rate": 5.15383917093469e-06, | |
| "loss": 2.5928, | |
| "step": 352000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.5679984092712402, | |
| "eval_runtime": 74.6621, | |
| "eval_samples_per_second": 11.05, | |
| "eval_steps_per_second": 5.532, | |
| "step": 352000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 78.83277893066406, | |
| "learning_rate": 5.168480759488482e-06, | |
| "loss": 2.5809, | |
| "step": 353000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.5745747089385986, | |
| "eval_runtime": 88.8716, | |
| "eval_samples_per_second": 9.283, | |
| "eval_steps_per_second": 4.647, | |
| "step": 353000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 31.719282150268555, | |
| "learning_rate": 5.1831223480422734e-06, | |
| "loss": 2.5817, | |
| "step": 354000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.542511224746704, | |
| "eval_runtime": 74.7387, | |
| "eval_samples_per_second": 11.038, | |
| "eval_steps_per_second": 5.526, | |
| "step": 354000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 45.4350471496582, | |
| "learning_rate": 5.197763936596066e-06, | |
| "loss": 2.5853, | |
| "step": 355000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.6151788234710693, | |
| "eval_runtime": 88.7294, | |
| "eval_samples_per_second": 9.298, | |
| "eval_steps_per_second": 4.655, | |
| "step": 355000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 43.207645416259766, | |
| "learning_rate": 5.212405525149857e-06, | |
| "loss": 2.5861, | |
| "step": 356000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.5360398292541504, | |
| "eval_runtime": 74.7605, | |
| "eval_samples_per_second": 11.035, | |
| "eval_steps_per_second": 5.524, | |
| "step": 356000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 32.29416275024414, | |
| "learning_rate": 5.227047113703649e-06, | |
| "loss": 2.5792, | |
| "step": 357000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.475013494491577, | |
| "eval_runtime": 74.695, | |
| "eval_samples_per_second": 11.045, | |
| "eval_steps_per_second": 5.529, | |
| "step": 357000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 41.070499420166016, | |
| "learning_rate": 5.2416887022574404e-06, | |
| "loss": 2.5846, | |
| "step": 358000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.6203396320343018, | |
| "eval_runtime": 88.6304, | |
| "eval_samples_per_second": 9.308, | |
| "eval_steps_per_second": 4.66, | |
| "step": 358000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 38.02358627319336, | |
| "learning_rate": 5.256330290811233e-06, | |
| "loss": 2.5994, | |
| "step": 359000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.52642560005188, | |
| "eval_runtime": 74.6571, | |
| "eval_samples_per_second": 11.051, | |
| "eval_steps_per_second": 5.532, | |
| "step": 359000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 34.377044677734375, | |
| "learning_rate": 5.270971879365025e-06, | |
| "loss": 2.5857, | |
| "step": 360000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.5763497352600098, | |
| "eval_runtime": 88.7937, | |
| "eval_samples_per_second": 9.291, | |
| "eval_steps_per_second": 4.651, | |
| "step": 360000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 37.10789489746094, | |
| "learning_rate": 5.285613467918815e-06, | |
| "loss": 2.5775, | |
| "step": 361000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.560091257095337, | |
| "eval_runtime": 74.7099, | |
| "eval_samples_per_second": 11.043, | |
| "eval_steps_per_second": 5.528, | |
| "step": 361000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 35.48027420043945, | |
| "learning_rate": 5.3002550564726074e-06, | |
| "loss": 2.5951, | |
| "step": 362000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.540125846862793, | |
| "eval_runtime": 74.6487, | |
| "eval_samples_per_second": 11.052, | |
| "eval_steps_per_second": 5.533, | |
| "step": 362000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 53.1136589050293, | |
| "learning_rate": 5.3148966450264e-06, | |
| "loss": 2.5838, | |
| "step": 363000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.5976662635803223, | |
| "eval_runtime": 88.7661, | |
| "eval_samples_per_second": 9.294, | |
| "eval_steps_per_second": 4.653, | |
| "step": 363000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 47.28069305419922, | |
| "learning_rate": 5.32953823358019e-06, | |
| "loss": 2.6007, | |
| "step": 364000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.577742338180542, | |
| "eval_runtime": 74.7236, | |
| "eval_samples_per_second": 11.041, | |
| "eval_steps_per_second": 5.527, | |
| "step": 364000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 37.87571716308594, | |
| "learning_rate": 5.344179822133982e-06, | |
| "loss": 2.5998, | |
| "step": 365000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.5661630630493164, | |
| "eval_runtime": 94.3883, | |
| "eval_samples_per_second": 8.74, | |
| "eval_steps_per_second": 4.376, | |
| "step": 365000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 50.52229309082031, | |
| "learning_rate": 5.3588214106877744e-06, | |
| "loss": 2.5764, | |
| "step": 366000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.5430634021759033, | |
| "eval_runtime": 74.7841, | |
| "eval_samples_per_second": 11.032, | |
| "eval_steps_per_second": 5.523, | |
| "step": 366000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 33.59963607788086, | |
| "learning_rate": 5.373462999241567e-06, | |
| "loss": 2.5736, | |
| "step": 367000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.5755114555358887, | |
| "eval_runtime": 88.7229, | |
| "eval_samples_per_second": 9.299, | |
| "eval_steps_per_second": 4.655, | |
| "step": 367000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 39.84903335571289, | |
| "learning_rate": 5.388104587795357e-06, | |
| "loss": 2.5516, | |
| "step": 368000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.574408769607544, | |
| "eval_runtime": 74.6854, | |
| "eval_samples_per_second": 11.046, | |
| "eval_steps_per_second": 5.53, | |
| "step": 368000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 36.43976593017578, | |
| "learning_rate": 5.402746176349149e-06, | |
| "loss": 2.5917, | |
| "step": 369000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.5506107807159424, | |
| "eval_runtime": 74.6219, | |
| "eval_samples_per_second": 11.056, | |
| "eval_steps_per_second": 5.535, | |
| "step": 369000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 32.55131149291992, | |
| "learning_rate": 5.4173877649029414e-06, | |
| "loss": 2.5869, | |
| "step": 370000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.5814473628997803, | |
| "eval_runtime": 88.8501, | |
| "eval_samples_per_second": 9.285, | |
| "eval_steps_per_second": 4.648, | |
| "step": 370000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 58.352046966552734, | |
| "learning_rate": 5.432029353456733e-06, | |
| "loss": 2.5719, | |
| "step": 371000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.650160312652588, | |
| "eval_runtime": 74.7626, | |
| "eval_samples_per_second": 11.035, | |
| "eval_steps_per_second": 5.524, | |
| "step": 371000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 35.47008514404297, | |
| "learning_rate": 5.446670942010525e-06, | |
| "loss": 2.5916, | |
| "step": 372000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.493919610977173, | |
| "eval_runtime": 88.7051, | |
| "eval_samples_per_second": 9.3, | |
| "eval_steps_per_second": 4.656, | |
| "step": 372000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 52.115318298339844, | |
| "learning_rate": 5.461312530564316e-06, | |
| "loss": 2.5711, | |
| "step": 373000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.626227855682373, | |
| "eval_runtime": 74.7738, | |
| "eval_samples_per_second": 11.033, | |
| "eval_steps_per_second": 5.523, | |
| "step": 373000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 55.728118896484375, | |
| "learning_rate": 5.4759541191181084e-06, | |
| "loss": 2.5898, | |
| "step": 374000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.645984172821045, | |
| "eval_runtime": 74.6433, | |
| "eval_samples_per_second": 11.053, | |
| "eval_steps_per_second": 5.533, | |
| "step": 374000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 37.5969123840332, | |
| "learning_rate": 5.4905957076719e-06, | |
| "loss": 2.613, | |
| "step": 375000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.5514795780181885, | |
| "eval_runtime": 89.1041, | |
| "eval_samples_per_second": 9.259, | |
| "eval_steps_per_second": 4.635, | |
| "step": 375000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 50.98681640625, | |
| "learning_rate": 5.505237296225692e-06, | |
| "loss": 2.5843, | |
| "step": 376000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.5230400562286377, | |
| "eval_runtime": 74.666, | |
| "eval_samples_per_second": 11.049, | |
| "eval_steps_per_second": 5.531, | |
| "step": 376000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 64.90864562988281, | |
| "learning_rate": 5.519878884779484e-06, | |
| "loss": 2.5803, | |
| "step": 377000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.566574811935425, | |
| "eval_runtime": 88.7387, | |
| "eval_samples_per_second": 9.297, | |
| "eval_steps_per_second": 4.654, | |
| "step": 377000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 31.084749221801758, | |
| "learning_rate": 5.534520473333275e-06, | |
| "loss": 2.5823, | |
| "step": 378000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.599928140640259, | |
| "eval_runtime": 74.8013, | |
| "eval_samples_per_second": 11.029, | |
| "eval_steps_per_second": 5.521, | |
| "step": 378000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 37.018863677978516, | |
| "learning_rate": 5.549162061887067e-06, | |
| "loss": 2.5735, | |
| "step": 379000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.5852713584899902, | |
| "eval_runtime": 74.637, | |
| "eval_samples_per_second": 11.053, | |
| "eval_steps_per_second": 5.533, | |
| "step": 379000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 47.78419876098633, | |
| "learning_rate": 5.563803650440859e-06, | |
| "loss": 2.5962, | |
| "step": 380000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.5050272941589355, | |
| "eval_runtime": 89.0068, | |
| "eval_samples_per_second": 9.269, | |
| "eval_steps_per_second": 4.64, | |
| "step": 380000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 49.62971115112305, | |
| "learning_rate": 5.578445238994651e-06, | |
| "loss": 2.572, | |
| "step": 381000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.5525805950164795, | |
| "eval_runtime": 74.676, | |
| "eval_samples_per_second": 11.048, | |
| "eval_steps_per_second": 5.531, | |
| "step": 381000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 41.620235443115234, | |
| "learning_rate": 5.593086827548442e-06, | |
| "loss": 2.583, | |
| "step": 382000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.5529444217681885, | |
| "eval_runtime": 88.7249, | |
| "eval_samples_per_second": 9.298, | |
| "eval_steps_per_second": 4.655, | |
| "step": 382000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 32.2930793762207, | |
| "learning_rate": 5.607728416102234e-06, | |
| "loss": 2.5632, | |
| "step": 383000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.5800976753234863, | |
| "eval_runtime": 74.7218, | |
| "eval_samples_per_second": 11.041, | |
| "eval_steps_per_second": 5.527, | |
| "step": 383000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 48.742530822753906, | |
| "learning_rate": 5.622370004656026e-06, | |
| "loss": 2.5652, | |
| "step": 384000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.5238680839538574, | |
| "eval_runtime": 88.7907, | |
| "eval_samples_per_second": 9.292, | |
| "eval_steps_per_second": 4.651, | |
| "step": 384000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 35.834388732910156, | |
| "learning_rate": 5.637011593209816e-06, | |
| "loss": 2.5829, | |
| "step": 385000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.4672865867614746, | |
| "eval_runtime": 74.6529, | |
| "eval_samples_per_second": 11.051, | |
| "eval_steps_per_second": 5.532, | |
| "step": 385000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 68.92035675048828, | |
| "learning_rate": 5.651653181763609e-06, | |
| "loss": 2.5608, | |
| "step": 386000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.5575194358825684, | |
| "eval_runtime": 74.5939, | |
| "eval_samples_per_second": 11.06, | |
| "eval_steps_per_second": 5.537, | |
| "step": 386000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 50.190208435058594, | |
| "learning_rate": 5.666294770317401e-06, | |
| "loss": 2.5675, | |
| "step": 387000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.5356907844543457, | |
| "eval_runtime": 88.6507, | |
| "eval_samples_per_second": 9.306, | |
| "eval_steps_per_second": 4.659, | |
| "step": 387000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 44.1893424987793, | |
| "learning_rate": 5.680936358871193e-06, | |
| "loss": 2.5636, | |
| "step": 388000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.586111545562744, | |
| "eval_runtime": 74.6289, | |
| "eval_samples_per_second": 11.055, | |
| "eval_steps_per_second": 5.534, | |
| "step": 388000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 40.74356460571289, | |
| "learning_rate": 5.695577947424984e-06, | |
| "loss": 2.556, | |
| "step": 389000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.5448148250579834, | |
| "eval_runtime": 88.7042, | |
| "eval_samples_per_second": 9.301, | |
| "eval_steps_per_second": 4.656, | |
| "step": 389000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 50.917518615722656, | |
| "learning_rate": 5.710219535978776e-06, | |
| "loss": 2.5693, | |
| "step": 390000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.6050689220428467, | |
| "eval_runtime": 74.8093, | |
| "eval_samples_per_second": 11.028, | |
| "eval_steps_per_second": 5.521, | |
| "step": 390000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 30.194284439086914, | |
| "learning_rate": 5.724861124532568e-06, | |
| "loss": 2.58, | |
| "step": 391000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.5194711685180664, | |
| "eval_runtime": 74.7688, | |
| "eval_samples_per_second": 11.034, | |
| "eval_steps_per_second": 5.524, | |
| "step": 391000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 35.72700119018555, | |
| "learning_rate": 5.739502713086359e-06, | |
| "loss": 2.5755, | |
| "step": 392000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.473149538040161, | |
| "eval_runtime": 88.7279, | |
| "eval_samples_per_second": 9.298, | |
| "eval_steps_per_second": 4.655, | |
| "step": 392000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 40.50430679321289, | |
| "learning_rate": 5.754144301640151e-06, | |
| "loss": 2.5705, | |
| "step": 393000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.583292245864868, | |
| "eval_runtime": 74.6506, | |
| "eval_samples_per_second": 11.051, | |
| "eval_steps_per_second": 5.532, | |
| "step": 393000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 38.33802032470703, | |
| "learning_rate": 5.7687858901939434e-06, | |
| "loss": 2.5743, | |
| "step": 394000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.6046974658966064, | |
| "eval_runtime": 88.8354, | |
| "eval_samples_per_second": 9.287, | |
| "eval_steps_per_second": 4.649, | |
| "step": 394000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 36.271080017089844, | |
| "learning_rate": 5.783427478747735e-06, | |
| "loss": 2.5732, | |
| "step": 395000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.5364186763763428, | |
| "eval_runtime": 74.7791, | |
| "eval_samples_per_second": 11.032, | |
| "eval_steps_per_second": 5.523, | |
| "step": 395000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 41.960426330566406, | |
| "learning_rate": 5.798069067301526e-06, | |
| "loss": 2.573, | |
| "step": 396000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.4924538135528564, | |
| "eval_runtime": 74.6168, | |
| "eval_samples_per_second": 11.056, | |
| "eval_steps_per_second": 5.535, | |
| "step": 396000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 34.67692565917969, | |
| "learning_rate": 5.812710655855318e-06, | |
| "loss": 2.5909, | |
| "step": 397000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.6636910438537598, | |
| "eval_runtime": 88.6833, | |
| "eval_samples_per_second": 9.303, | |
| "eval_steps_per_second": 4.657, | |
| "step": 397000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 35.99394989013672, | |
| "learning_rate": 5.8273522444091104e-06, | |
| "loss": 2.5664, | |
| "step": 398000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.502495288848877, | |
| "eval_runtime": 74.5822, | |
| "eval_samples_per_second": 11.062, | |
| "eval_steps_per_second": 5.538, | |
| "step": 398000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 33.0992546081543, | |
| "learning_rate": 5.841993832962901e-06, | |
| "loss": 2.5634, | |
| "step": 399000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.4681994915008545, | |
| "eval_runtime": 88.6562, | |
| "eval_samples_per_second": 9.306, | |
| "eval_steps_per_second": 4.658, | |
| "step": 399000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 48.14725875854492, | |
| "learning_rate": 5.856635421516693e-06, | |
| "loss": 2.5751, | |
| "step": 400000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.547281503677368, | |
| "eval_runtime": 74.6694, | |
| "eval_samples_per_second": 11.049, | |
| "eval_steps_per_second": 5.531, | |
| "step": 400000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 27.271160125732422, | |
| "learning_rate": 5.871277010070485e-06, | |
| "loss": 2.5798, | |
| "step": 401000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.4551727771759033, | |
| "eval_runtime": 88.5982, | |
| "eval_samples_per_second": 9.312, | |
| "eval_steps_per_second": 4.661, | |
| "step": 401000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 42.731956481933594, | |
| "learning_rate": 5.8859185986242774e-06, | |
| "loss": 2.5643, | |
| "step": 402000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.467008113861084, | |
| "eval_runtime": 74.7978, | |
| "eval_samples_per_second": 11.03, | |
| "eval_steps_per_second": 5.522, | |
| "step": 402000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 37.62224578857422, | |
| "learning_rate": 5.900560187178068e-06, | |
| "loss": 2.5783, | |
| "step": 403000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.4793624877929688, | |
| "eval_runtime": 74.6072, | |
| "eval_samples_per_second": 11.058, | |
| "eval_steps_per_second": 5.536, | |
| "step": 403000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 33.82321548461914, | |
| "learning_rate": 5.91520177573186e-06, | |
| "loss": 2.5599, | |
| "step": 404000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.5051112174987793, | |
| "eval_runtime": 88.887, | |
| "eval_samples_per_second": 9.281, | |
| "eval_steps_per_second": 4.646, | |
| "step": 404000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 38.417205810546875, | |
| "learning_rate": 5.929843364285652e-06, | |
| "loss": 2.5591, | |
| "step": 405000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.4766504764556885, | |
| "eval_runtime": 74.6288, | |
| "eval_samples_per_second": 11.055, | |
| "eval_steps_per_second": 5.534, | |
| "step": 405000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 37.80118179321289, | |
| "learning_rate": 5.944484952839444e-06, | |
| "loss": 2.5938, | |
| "step": 406000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.46614146232605, | |
| "eval_runtime": 88.8603, | |
| "eval_samples_per_second": 9.284, | |
| "eval_steps_per_second": 4.648, | |
| "step": 406000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 31.764890670776367, | |
| "learning_rate": 5.959126541393235e-06, | |
| "loss": 2.5676, | |
| "step": 407000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.558773994445801, | |
| "eval_runtime": 74.7445, | |
| "eval_samples_per_second": 11.038, | |
| "eval_steps_per_second": 5.525, | |
| "step": 407000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 26.849288940429688, | |
| "learning_rate": 5.973768129947027e-06, | |
| "loss": 2.5805, | |
| "step": 408000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.568739652633667, | |
| "eval_runtime": 74.605, | |
| "eval_samples_per_second": 11.058, | |
| "eval_steps_per_second": 5.536, | |
| "step": 408000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 34.30747604370117, | |
| "learning_rate": 5.988409718500819e-06, | |
| "loss": 2.5582, | |
| "step": 409000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.5398943424224854, | |
| "eval_runtime": 89.3871, | |
| "eval_samples_per_second": 9.23, | |
| "eval_steps_per_second": 4.62, | |
| "step": 409000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 28.676551818847656, | |
| "learning_rate": 6.003051307054611e-06, | |
| "loss": 2.5675, | |
| "step": 410000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.5639803409576416, | |
| "eval_runtime": 74.7489, | |
| "eval_samples_per_second": 11.037, | |
| "eval_steps_per_second": 5.525, | |
| "step": 410000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 31.36862564086914, | |
| "learning_rate": 6.017692895608403e-06, | |
| "loss": 2.558, | |
| "step": 411000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.550550937652588, | |
| "eval_runtime": 89.1468, | |
| "eval_samples_per_second": 9.254, | |
| "eval_steps_per_second": 4.633, | |
| "step": 411000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 53.808528900146484, | |
| "learning_rate": 6.032334484162194e-06, | |
| "loss": 2.5706, | |
| "step": 412000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.5042293071746826, | |
| "eval_runtime": 74.77, | |
| "eval_samples_per_second": 11.034, | |
| "eval_steps_per_second": 5.524, | |
| "step": 412000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 33.744991302490234, | |
| "learning_rate": 6.046976072715985e-06, | |
| "loss": 2.5493, | |
| "step": 413000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.567261219024658, | |
| "eval_runtime": 88.8853, | |
| "eval_samples_per_second": 9.282, | |
| "eval_steps_per_second": 4.646, | |
| "step": 413000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 35.459835052490234, | |
| "learning_rate": 6.061617661269778e-06, | |
| "loss": 2.5576, | |
| "step": 414000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.517771005630493, | |
| "eval_runtime": 74.6445, | |
| "eval_samples_per_second": 11.052, | |
| "eval_steps_per_second": 5.533, | |
| "step": 414000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 29.082275390625, | |
| "learning_rate": 6.07625924982357e-06, | |
| "loss": 2.5644, | |
| "step": 415000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.6622846126556396, | |
| "eval_runtime": 74.6381, | |
| "eval_samples_per_second": 11.053, | |
| "eval_steps_per_second": 5.533, | |
| "step": 415000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 33.123802185058594, | |
| "learning_rate": 6.090900838377362e-06, | |
| "loss": 2.5636, | |
| "step": 416000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.468601942062378, | |
| "eval_runtime": 88.6295, | |
| "eval_samples_per_second": 9.308, | |
| "eval_steps_per_second": 4.66, | |
| "step": 416000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 29.530460357666016, | |
| "learning_rate": 6.105542426931152e-06, | |
| "loss": 2.5537, | |
| "step": 417000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.502995014190674, | |
| "eval_runtime": 74.6451, | |
| "eval_samples_per_second": 11.052, | |
| "eval_steps_per_second": 5.533, | |
| "step": 417000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 34.51593780517578, | |
| "learning_rate": 6.120184015484945e-06, | |
| "loss": 2.5498, | |
| "step": 418000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.4599108695983887, | |
| "eval_runtime": 89.0393, | |
| "eval_samples_per_second": 9.266, | |
| "eval_steps_per_second": 4.638, | |
| "step": 418000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 69.78622436523438, | |
| "learning_rate": 6.134825604038737e-06, | |
| "loss": 2.5641, | |
| "step": 419000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.533233880996704, | |
| "eval_runtime": 74.7606, | |
| "eval_samples_per_second": 11.035, | |
| "eval_steps_per_second": 5.524, | |
| "step": 419000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 37.08543014526367, | |
| "learning_rate": 6.149467192592527e-06, | |
| "loss": 2.5594, | |
| "step": 420000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.632356882095337, | |
| "eval_runtime": 74.6365, | |
| "eval_samples_per_second": 11.054, | |
| "eval_steps_per_second": 5.533, | |
| "step": 420000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 36.292423248291016, | |
| "learning_rate": 6.164108781146319e-06, | |
| "loss": 2.5503, | |
| "step": 421000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.5228469371795654, | |
| "eval_runtime": 88.5975, | |
| "eval_samples_per_second": 9.312, | |
| "eval_steps_per_second": 4.662, | |
| "step": 421000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 34.91773986816406, | |
| "learning_rate": 6.178750369700112e-06, | |
| "loss": 2.556, | |
| "step": 422000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.5192246437072754, | |
| "eval_runtime": 74.6474, | |
| "eval_samples_per_second": 11.052, | |
| "eval_steps_per_second": 5.533, | |
| "step": 422000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 28.986318588256836, | |
| "learning_rate": 6.193391958253904e-06, | |
| "loss": 2.5706, | |
| "step": 423000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.4696004390716553, | |
| "eval_runtime": 88.7451, | |
| "eval_samples_per_second": 9.296, | |
| "eval_steps_per_second": 4.654, | |
| "step": 423000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 29.763254165649414, | |
| "learning_rate": 6.208033546807695e-06, | |
| "loss": 2.5512, | |
| "step": 424000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.575294256210327, | |
| "eval_runtime": 74.8028, | |
| "eval_samples_per_second": 11.029, | |
| "eval_steps_per_second": 5.521, | |
| "step": 424000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 36.24395751953125, | |
| "learning_rate": 6.222675135361486e-06, | |
| "loss": 2.5634, | |
| "step": 425000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.550208806991577, | |
| "eval_runtime": 74.6793, | |
| "eval_samples_per_second": 11.047, | |
| "eval_steps_per_second": 5.53, | |
| "step": 425000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 29.8460636138916, | |
| "learning_rate": 6.237316723915279e-06, | |
| "loss": 2.5697, | |
| "step": 426000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.5694708824157715, | |
| "eval_runtime": 88.7935, | |
| "eval_samples_per_second": 9.291, | |
| "eval_steps_per_second": 4.651, | |
| "step": 426000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 50.25217819213867, | |
| "learning_rate": 6.25195831246907e-06, | |
| "loss": 2.551, | |
| "step": 427000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.550706624984741, | |
| "eval_runtime": 74.6395, | |
| "eval_samples_per_second": 11.053, | |
| "eval_steps_per_second": 5.533, | |
| "step": 427000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 32.787391662597656, | |
| "learning_rate": 6.266599901022862e-06, | |
| "loss": 2.5591, | |
| "step": 428000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.5466034412384033, | |
| "eval_runtime": 88.7357, | |
| "eval_samples_per_second": 9.297, | |
| "eval_steps_per_second": 4.654, | |
| "step": 428000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 39.36776351928711, | |
| "learning_rate": 6.281241489576653e-06, | |
| "loss": 2.5547, | |
| "step": 429000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.4820621013641357, | |
| "eval_runtime": 74.7807, | |
| "eval_samples_per_second": 11.032, | |
| "eval_steps_per_second": 5.523, | |
| "step": 429000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 39.31442642211914, | |
| "learning_rate": 6.295883078130446e-06, | |
| "loss": 2.5622, | |
| "step": 430000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.617039918899536, | |
| "eval_runtime": 89.1322, | |
| "eval_samples_per_second": 9.256, | |
| "eval_steps_per_second": 4.634, | |
| "step": 430000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 46.105777740478516, | |
| "learning_rate": 6.310524666684237e-06, | |
| "loss": 2.5665, | |
| "step": 431000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.545649290084839, | |
| "eval_runtime": 74.5958, | |
| "eval_samples_per_second": 11.06, | |
| "eval_steps_per_second": 5.537, | |
| "step": 431000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 36.128662109375, | |
| "learning_rate": 6.325166255238029e-06, | |
| "loss": 2.5821, | |
| "step": 432000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.5234498977661133, | |
| "eval_runtime": 74.6321, | |
| "eval_samples_per_second": 11.054, | |
| "eval_steps_per_second": 5.534, | |
| "step": 432000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 25.52347183227539, | |
| "learning_rate": 6.339807843791821e-06, | |
| "loss": 2.5569, | |
| "step": 433000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.5337672233581543, | |
| "eval_runtime": 88.6702, | |
| "eval_samples_per_second": 9.304, | |
| "eval_steps_per_second": 4.658, | |
| "step": 433000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 41.64098358154297, | |
| "learning_rate": 6.354449432345612e-06, | |
| "loss": 2.5632, | |
| "step": 434000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.5711653232574463, | |
| "eval_runtime": 74.6523, | |
| "eval_samples_per_second": 11.051, | |
| "eval_steps_per_second": 5.532, | |
| "step": 434000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 41.7122688293457, | |
| "learning_rate": 6.369091020899404e-06, | |
| "loss": 2.588, | |
| "step": 435000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.548222541809082, | |
| "eval_runtime": 89.057, | |
| "eval_samples_per_second": 9.264, | |
| "eval_steps_per_second": 4.637, | |
| "step": 435000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 40.96338653564453, | |
| "learning_rate": 6.383732609453196e-06, | |
| "loss": 2.5794, | |
| "step": 436000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.4672553539276123, | |
| "eval_runtime": 74.8012, | |
| "eval_samples_per_second": 11.029, | |
| "eval_steps_per_second": 5.521, | |
| "step": 436000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 30.040346145629883, | |
| "learning_rate": 6.398374198006988e-06, | |
| "loss": 2.5489, | |
| "step": 437000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.5354793071746826, | |
| "eval_runtime": 74.6068, | |
| "eval_samples_per_second": 11.058, | |
| "eval_steps_per_second": 5.536, | |
| "step": 437000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 42.75343322753906, | |
| "learning_rate": 6.413015786560779e-06, | |
| "loss": 2.5638, | |
| "step": 438000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.5378284454345703, | |
| "eval_runtime": 89.2076, | |
| "eval_samples_per_second": 9.248, | |
| "eval_steps_per_second": 4.63, | |
| "step": 438000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 43.05962371826172, | |
| "learning_rate": 6.427657375114571e-06, | |
| "loss": 2.5384, | |
| "step": 439000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.5371294021606445, | |
| "eval_runtime": 74.6255, | |
| "eval_samples_per_second": 11.055, | |
| "eval_steps_per_second": 5.534, | |
| "step": 439000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 36.83192443847656, | |
| "learning_rate": 6.442298963668363e-06, | |
| "loss": 2.5481, | |
| "step": 440000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.5858242511749268, | |
| "eval_runtime": 88.6555, | |
| "eval_samples_per_second": 9.306, | |
| "eval_steps_per_second": 4.658, | |
| "step": 440000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 33.47575759887695, | |
| "learning_rate": 6.456940552222154e-06, | |
| "loss": 2.5498, | |
| "step": 441000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.5402233600616455, | |
| "eval_runtime": 74.7407, | |
| "eval_samples_per_second": 11.038, | |
| "eval_steps_per_second": 5.526, | |
| "step": 441000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 41.94609451293945, | |
| "learning_rate": 6.471582140775946e-06, | |
| "loss": 2.561, | |
| "step": 442000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.605259895324707, | |
| "eval_runtime": 74.9512, | |
| "eval_samples_per_second": 11.007, | |
| "eval_steps_per_second": 5.51, | |
| "step": 442000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 19.982908248901367, | |
| "learning_rate": 6.486223729329738e-06, | |
| "loss": 2.5588, | |
| "step": 443000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.5843842029571533, | |
| "eval_runtime": 88.7552, | |
| "eval_samples_per_second": 9.295, | |
| "eval_steps_per_second": 4.653, | |
| "step": 443000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 57.40386199951172, | |
| "learning_rate": 6.50086531788353e-06, | |
| "loss": 2.5735, | |
| "step": 444000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.6279358863830566, | |
| "eval_runtime": 74.6147, | |
| "eval_samples_per_second": 11.057, | |
| "eval_steps_per_second": 5.535, | |
| "step": 444000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 41.1192741394043, | |
| "learning_rate": 6.515506906437321e-06, | |
| "loss": 2.5533, | |
| "step": 445000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.5092525482177734, | |
| "eval_runtime": 89.3712, | |
| "eval_samples_per_second": 9.231, | |
| "eval_steps_per_second": 4.621, | |
| "step": 445000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 32.98606491088867, | |
| "learning_rate": 6.530148494991113e-06, | |
| "loss": 2.5607, | |
| "step": 446000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.5889837741851807, | |
| "eval_runtime": 74.6817, | |
| "eval_samples_per_second": 11.047, | |
| "eval_steps_per_second": 5.53, | |
| "step": 446000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 41.232357025146484, | |
| "learning_rate": 6.544790083544905e-06, | |
| "loss": 2.5588, | |
| "step": 447000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.467031717300415, | |
| "eval_runtime": 88.7084, | |
| "eval_samples_per_second": 9.3, | |
| "eval_steps_per_second": 4.656, | |
| "step": 447000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 72.1984634399414, | |
| "learning_rate": 6.559431672098696e-06, | |
| "loss": 2.5572, | |
| "step": 448000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.5372323989868164, | |
| "eval_runtime": 74.6878, | |
| "eval_samples_per_second": 11.046, | |
| "eval_steps_per_second": 5.53, | |
| "step": 448000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 36.4392204284668, | |
| "learning_rate": 6.574073260652488e-06, | |
| "loss": 2.5337, | |
| "step": 449000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.5478267669677734, | |
| "eval_runtime": 74.5728, | |
| "eval_samples_per_second": 11.063, | |
| "eval_steps_per_second": 5.538, | |
| "step": 449000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 34.9202766418457, | |
| "learning_rate": 6.5887148492062806e-06, | |
| "loss": 2.5564, | |
| "step": 450000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.465947151184082, | |
| "eval_runtime": 88.7189, | |
| "eval_samples_per_second": 9.299, | |
| "eval_steps_per_second": 4.655, | |
| "step": 450000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 39.647132873535156, | |
| "learning_rate": 6.603356437760072e-06, | |
| "loss": 2.5621, | |
| "step": 451000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.5845820903778076, | |
| "eval_runtime": 74.6226, | |
| "eval_samples_per_second": 11.056, | |
| "eval_steps_per_second": 5.535, | |
| "step": 451000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 33.027671813964844, | |
| "learning_rate": 6.617998026313863e-06, | |
| "loss": 2.5541, | |
| "step": 452000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.5217037200927734, | |
| "eval_runtime": 88.777, | |
| "eval_samples_per_second": 9.293, | |
| "eval_steps_per_second": 4.652, | |
| "step": 452000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 30.724512100219727, | |
| "learning_rate": 6.632639614867655e-06, | |
| "loss": 2.5594, | |
| "step": 453000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.509258508682251, | |
| "eval_runtime": 74.7622, | |
| "eval_samples_per_second": 11.035, | |
| "eval_steps_per_second": 5.524, | |
| "step": 453000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 29.195533752441406, | |
| "learning_rate": 6.6472812034214476e-06, | |
| "loss": 2.5462, | |
| "step": 454000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.488044500350952, | |
| "eval_runtime": 74.612, | |
| "eval_samples_per_second": 11.057, | |
| "eval_steps_per_second": 5.535, | |
| "step": 454000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 41.07986068725586, | |
| "learning_rate": 6.661922791975238e-06, | |
| "loss": 2.5504, | |
| "step": 455000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.5311644077301025, | |
| "eval_runtime": 88.9117, | |
| "eval_samples_per_second": 9.279, | |
| "eval_steps_per_second": 4.645, | |
| "step": 455000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 33.23712158203125, | |
| "learning_rate": 6.67656438052903e-06, | |
| "loss": 2.538, | |
| "step": 456000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.492626428604126, | |
| "eval_runtime": 74.5715, | |
| "eval_samples_per_second": 11.063, | |
| "eval_steps_per_second": 5.538, | |
| "step": 456000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 42.68756103515625, | |
| "learning_rate": 6.691205969082822e-06, | |
| "loss": 2.5204, | |
| "step": 457000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.58370304107666, | |
| "eval_runtime": 88.7612, | |
| "eval_samples_per_second": 9.295, | |
| "eval_steps_per_second": 4.653, | |
| "step": 457000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 64.60575866699219, | |
| "learning_rate": 6.7058475576366146e-06, | |
| "loss": 2.5611, | |
| "step": 458000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.6022603511810303, | |
| "eval_runtime": 74.7033, | |
| "eval_samples_per_second": 11.044, | |
| "eval_steps_per_second": 5.529, | |
| "step": 458000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 52.22064208984375, | |
| "learning_rate": 6.720489146190405e-06, | |
| "loss": 2.5452, | |
| "step": 459000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.6357836723327637, | |
| "eval_runtime": 88.7513, | |
| "eval_samples_per_second": 9.296, | |
| "eval_steps_per_second": 4.653, | |
| "step": 459000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 34.85495376586914, | |
| "learning_rate": 6.735130734744197e-06, | |
| "loss": 2.5756, | |
| "step": 460000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.5200676918029785, | |
| "eval_runtime": 74.5868, | |
| "eval_samples_per_second": 11.061, | |
| "eval_steps_per_second": 5.537, | |
| "step": 460000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 33.7723503112793, | |
| "learning_rate": 6.749772323297989e-06, | |
| "loss": 2.5329, | |
| "step": 461000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.4919097423553467, | |
| "eval_runtime": 74.6394, | |
| "eval_samples_per_second": 11.053, | |
| "eval_steps_per_second": 5.533, | |
| "step": 461000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 37.637420654296875, | |
| "learning_rate": 6.764413911851781e-06, | |
| "loss": 2.551, | |
| "step": 462000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.452228307723999, | |
| "eval_runtime": 88.7249, | |
| "eval_samples_per_second": 9.298, | |
| "eval_steps_per_second": 4.655, | |
| "step": 462000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 24.536401748657227, | |
| "learning_rate": 6.779055500405573e-06, | |
| "loss": 2.5563, | |
| "step": 463000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.494086742401123, | |
| "eval_runtime": 74.6768, | |
| "eval_samples_per_second": 11.048, | |
| "eval_steps_per_second": 5.53, | |
| "step": 463000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 36.97923278808594, | |
| "learning_rate": 6.793697088959364e-06, | |
| "loss": 2.553, | |
| "step": 464000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.5208866596221924, | |
| "eval_runtime": 88.7626, | |
| "eval_samples_per_second": 9.294, | |
| "eval_steps_per_second": 4.653, | |
| "step": 464000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 41.09996032714844, | |
| "learning_rate": 6.8083386775131555e-06, | |
| "loss": 2.5181, | |
| "step": 465000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.4860949516296387, | |
| "eval_runtime": 74.724, | |
| "eval_samples_per_second": 11.041, | |
| "eval_steps_per_second": 5.527, | |
| "step": 465000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 32.66045379638672, | |
| "learning_rate": 6.822980266066948e-06, | |
| "loss": 2.5581, | |
| "step": 466000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.568377733230591, | |
| "eval_runtime": 75.6998, | |
| "eval_samples_per_second": 10.898, | |
| "eval_steps_per_second": 5.456, | |
| "step": 466000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 32.50819396972656, | |
| "learning_rate": 6.83762185462074e-06, | |
| "loss": 2.5579, | |
| "step": 467000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.5605528354644775, | |
| "eval_runtime": 88.7915, | |
| "eval_samples_per_second": 9.291, | |
| "eval_steps_per_second": 4.651, | |
| "step": 467000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 28.087833404541016, | |
| "learning_rate": 6.852263443174531e-06, | |
| "loss": 2.5367, | |
| "step": 468000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.4373321533203125, | |
| "eval_runtime": 74.6151, | |
| "eval_samples_per_second": 11.057, | |
| "eval_steps_per_second": 5.535, | |
| "step": 468000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 24.929182052612305, | |
| "learning_rate": 6.8669050317283225e-06, | |
| "loss": 2.525, | |
| "step": 469000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.5279572010040283, | |
| "eval_runtime": 88.694, | |
| "eval_samples_per_second": 9.302, | |
| "eval_steps_per_second": 4.656, | |
| "step": 469000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 27.20203399658203, | |
| "learning_rate": 6.881546620282115e-06, | |
| "loss": 2.5362, | |
| "step": 470000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.5852034091949463, | |
| "eval_runtime": 74.7835, | |
| "eval_samples_per_second": 11.032, | |
| "eval_steps_per_second": 5.523, | |
| "step": 470000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 25.984107971191406, | |
| "learning_rate": 6.896188208835907e-06, | |
| "loss": 2.5573, | |
| "step": 471000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.5982773303985596, | |
| "eval_runtime": 74.6024, | |
| "eval_samples_per_second": 11.059, | |
| "eval_steps_per_second": 5.536, | |
| "step": 471000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 34.37070846557617, | |
| "learning_rate": 6.910829797389697e-06, | |
| "loss": 2.5387, | |
| "step": 472000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.5567188262939453, | |
| "eval_runtime": 88.7033, | |
| "eval_samples_per_second": 9.301, | |
| "eval_steps_per_second": 4.656, | |
| "step": 472000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 35.77717971801758, | |
| "learning_rate": 6.9254713859434895e-06, | |
| "loss": 2.5461, | |
| "step": 473000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.500488758087158, | |
| "eval_runtime": 74.5895, | |
| "eval_samples_per_second": 11.061, | |
| "eval_steps_per_second": 5.537, | |
| "step": 473000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 39.12084197998047, | |
| "learning_rate": 6.940112974497282e-06, | |
| "loss": 2.5294, | |
| "step": 474000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.567323923110962, | |
| "eval_runtime": 88.7207, | |
| "eval_samples_per_second": 9.299, | |
| "eval_steps_per_second": 4.655, | |
| "step": 474000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 39.28538513183594, | |
| "learning_rate": 6.954754563051074e-06, | |
| "loss": 2.552, | |
| "step": 475000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.4914865493774414, | |
| "eval_runtime": 74.6134, | |
| "eval_samples_per_second": 11.057, | |
| "eval_steps_per_second": 5.535, | |
| "step": 475000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 28.785789489746094, | |
| "learning_rate": 6.969396151604864e-06, | |
| "loss": 2.5472, | |
| "step": 476000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.5251002311706543, | |
| "eval_runtime": 88.9687, | |
| "eval_samples_per_second": 9.273, | |
| "eval_steps_per_second": 4.642, | |
| "step": 476000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 29.67142677307129, | |
| "learning_rate": 6.9840377401586565e-06, | |
| "loss": 2.5435, | |
| "step": 477000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.5729432106018066, | |
| "eval_runtime": 74.5981, | |
| "eval_samples_per_second": 11.059, | |
| "eval_steps_per_second": 5.536, | |
| "step": 477000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 29.99863052368164, | |
| "learning_rate": 6.998679328712449e-06, | |
| "loss": 2.5487, | |
| "step": 478000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.535391330718994, | |
| "eval_runtime": 74.581, | |
| "eval_samples_per_second": 11.062, | |
| "eval_steps_per_second": 5.538, | |
| "step": 478000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 41.351619720458984, | |
| "learning_rate": 7.01332091726624e-06, | |
| "loss": 2.5679, | |
| "step": 479000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.525803804397583, | |
| "eval_runtime": 88.6559, | |
| "eval_samples_per_second": 9.306, | |
| "eval_steps_per_second": 4.658, | |
| "step": 479000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 38.389102935791016, | |
| "learning_rate": 7.027962505820032e-06, | |
| "loss": 2.5501, | |
| "step": 480000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.555030107498169, | |
| "eval_runtime": 74.6654, | |
| "eval_samples_per_second": 11.049, | |
| "eval_steps_per_second": 5.531, | |
| "step": 480000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 25.928979873657227, | |
| "learning_rate": 7.0426040943738235e-06, | |
| "loss": 2.5245, | |
| "step": 481000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.562833786010742, | |
| "eval_runtime": 88.8709, | |
| "eval_samples_per_second": 9.283, | |
| "eval_steps_per_second": 4.647, | |
| "step": 481000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 26.164514541625977, | |
| "learning_rate": 7.057245682927616e-06, | |
| "loss": 2.5322, | |
| "step": 482000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.5449910163879395, | |
| "eval_runtime": 74.7155, | |
| "eval_samples_per_second": 11.042, | |
| "eval_steps_per_second": 5.528, | |
| "step": 482000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 32.9320182800293, | |
| "learning_rate": 7.071887271481407e-06, | |
| "loss": 2.522, | |
| "step": 483000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.516918897628784, | |
| "eval_runtime": 74.5959, | |
| "eval_samples_per_second": 11.06, | |
| "eval_steps_per_second": 5.536, | |
| "step": 483000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 24.265871047973633, | |
| "learning_rate": 7.086528860035199e-06, | |
| "loss": 2.5404, | |
| "step": 484000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.5522592067718506, | |
| "eval_runtime": 88.5094, | |
| "eval_samples_per_second": 9.321, | |
| "eval_steps_per_second": 4.666, | |
| "step": 484000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 34.12384033203125, | |
| "learning_rate": 7.101170448588991e-06, | |
| "loss": 2.5504, | |
| "step": 485000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.5303263664245605, | |
| "eval_runtime": 74.586, | |
| "eval_samples_per_second": 11.061, | |
| "eval_steps_per_second": 5.537, | |
| "step": 485000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 61.21946716308594, | |
| "learning_rate": 7.115812037142782e-06, | |
| "loss": 2.5445, | |
| "step": 486000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.5049057006835938, | |
| "eval_runtime": 88.9345, | |
| "eval_samples_per_second": 9.276, | |
| "eval_steps_per_second": 4.644, | |
| "step": 486000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 70.74236297607422, | |
| "learning_rate": 7.130453625696574e-06, | |
| "loss": 2.5292, | |
| "step": 487000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.4680702686309814, | |
| "eval_runtime": 74.7359, | |
| "eval_samples_per_second": 11.039, | |
| "eval_steps_per_second": 5.526, | |
| "step": 487000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 25.825979232788086, | |
| "learning_rate": 7.145095214250366e-06, | |
| "loss": 2.5356, | |
| "step": 488000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.4915049076080322, | |
| "eval_runtime": 74.585, | |
| "eval_samples_per_second": 11.061, | |
| "eval_steps_per_second": 5.537, | |
| "step": 488000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 35.21977233886719, | |
| "learning_rate": 7.159736802804158e-06, | |
| "loss": 2.5506, | |
| "step": 489000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.475767135620117, | |
| "eval_runtime": 88.6633, | |
| "eval_samples_per_second": 9.305, | |
| "eval_steps_per_second": 4.658, | |
| "step": 489000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 27.019886016845703, | |
| "learning_rate": 7.174378391357949e-06, | |
| "loss": 2.5399, | |
| "step": 490000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.5398621559143066, | |
| "eval_runtime": 74.544, | |
| "eval_samples_per_second": 11.067, | |
| "eval_steps_per_second": 5.54, | |
| "step": 490000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 27.912006378173828, | |
| "learning_rate": 7.189019979911741e-06, | |
| "loss": 2.5384, | |
| "step": 491000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.525010108947754, | |
| "eval_runtime": 88.5171, | |
| "eval_samples_per_second": 9.32, | |
| "eval_steps_per_second": 4.666, | |
| "step": 491000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 30.21108055114746, | |
| "learning_rate": 7.203661568465533e-06, | |
| "loss": 2.5517, | |
| "step": 492000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.4748849868774414, | |
| "eval_runtime": 74.7588, | |
| "eval_samples_per_second": 11.035, | |
| "eval_steps_per_second": 5.524, | |
| "step": 492000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 29.793901443481445, | |
| "learning_rate": 7.218303157019324e-06, | |
| "loss": 2.5446, | |
| "step": 493000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.467487096786499, | |
| "eval_runtime": 88.7576, | |
| "eval_samples_per_second": 9.295, | |
| "eval_steps_per_second": 4.653, | |
| "step": 493000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 28.16090202331543, | |
| "learning_rate": 7.232944745573116e-06, | |
| "loss": 2.559, | |
| "step": 494000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.5055534839630127, | |
| "eval_runtime": 74.7138, | |
| "eval_samples_per_second": 11.042, | |
| "eval_steps_per_second": 5.528, | |
| "step": 494000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 32.094730377197266, | |
| "learning_rate": 7.247586334126908e-06, | |
| "loss": 2.5501, | |
| "step": 495000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.5964102745056152, | |
| "eval_runtime": 74.9562, | |
| "eval_samples_per_second": 11.006, | |
| "eval_steps_per_second": 5.51, | |
| "step": 495000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 33.27901840209961, | |
| "learning_rate": 7.2622279226807e-06, | |
| "loss": 2.5366, | |
| "step": 496000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.439891815185547, | |
| "eval_runtime": 88.794, | |
| "eval_samples_per_second": 9.291, | |
| "eval_steps_per_second": 4.651, | |
| "step": 496000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 43.62042999267578, | |
| "learning_rate": 7.2768695112344915e-06, | |
| "loss": 2.5349, | |
| "step": 497000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.524001359939575, | |
| "eval_runtime": 74.6053, | |
| "eval_samples_per_second": 11.058, | |
| "eval_steps_per_second": 5.536, | |
| "step": 497000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 60.96129608154297, | |
| "learning_rate": 7.291511099788283e-06, | |
| "loss": 2.5448, | |
| "step": 498000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.521202564239502, | |
| "eval_runtime": 88.6666, | |
| "eval_samples_per_second": 9.305, | |
| "eval_steps_per_second": 4.658, | |
| "step": 498000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 35.02910232543945, | |
| "learning_rate": 7.306152688342075e-06, | |
| "loss": 2.537, | |
| "step": 499000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.505171298980713, | |
| "eval_runtime": 74.7312, | |
| "eval_samples_per_second": 11.04, | |
| "eval_steps_per_second": 5.526, | |
| "step": 499000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 31.013050079345703, | |
| "learning_rate": 7.320794276895866e-06, | |
| "loss": 2.5467, | |
| "step": 500000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.4867501258850098, | |
| "eval_runtime": 74.6206, | |
| "eval_samples_per_second": 11.056, | |
| "eval_steps_per_second": 5.535, | |
| "step": 500000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 37.47949981689453, | |
| "learning_rate": 7.3354358654496585e-06, | |
| "loss": 2.5407, | |
| "step": 501000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.5458617210388184, | |
| "eval_runtime": 88.9434, | |
| "eval_samples_per_second": 9.276, | |
| "eval_steps_per_second": 4.643, | |
| "step": 501000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 47.31396484375, | |
| "learning_rate": 7.350077454003451e-06, | |
| "loss": 2.5313, | |
| "step": 502000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.411341667175293, | |
| "eval_runtime": 74.6183, | |
| "eval_samples_per_second": 11.056, | |
| "eval_steps_per_second": 5.535, | |
| "step": 502000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 31.15127944946289, | |
| "learning_rate": 7.364719042557242e-06, | |
| "loss": 2.5366, | |
| "step": 503000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.4842355251312256, | |
| "eval_runtime": 88.7591, | |
| "eval_samples_per_second": 9.295, | |
| "eval_steps_per_second": 4.653, | |
| "step": 503000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 27.516429901123047, | |
| "learning_rate": 7.379360631111033e-06, | |
| "loss": 2.5214, | |
| "step": 504000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.5037267208099365, | |
| "eval_runtime": 74.6844, | |
| "eval_samples_per_second": 11.046, | |
| "eval_steps_per_second": 5.53, | |
| "step": 504000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 25.75136947631836, | |
| "learning_rate": 7.3940022196648255e-06, | |
| "loss": 2.5469, | |
| "step": 505000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.4592418670654297, | |
| "eval_runtime": 88.8258, | |
| "eval_samples_per_second": 9.288, | |
| "eval_steps_per_second": 4.65, | |
| "step": 505000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 30.610952377319336, | |
| "learning_rate": 7.408643808218618e-06, | |
| "loss": 2.5315, | |
| "step": 506000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.5430240631103516, | |
| "eval_runtime": 74.5293, | |
| "eval_samples_per_second": 11.069, | |
| "eval_steps_per_second": 5.541, | |
| "step": 506000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 26.383150100708008, | |
| "learning_rate": 7.423285396772408e-06, | |
| "loss": 2.5414, | |
| "step": 507000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.4935925006866455, | |
| "eval_runtime": 74.608, | |
| "eval_samples_per_second": 11.058, | |
| "eval_steps_per_second": 5.536, | |
| "step": 507000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 41.32442855834961, | |
| "learning_rate": 7.4379269853262e-06, | |
| "loss": 2.5358, | |
| "step": 508000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.4858062267303467, | |
| "eval_runtime": 88.6146, | |
| "eval_samples_per_second": 9.31, | |
| "eval_steps_per_second": 4.661, | |
| "step": 508000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 27.008840560913086, | |
| "learning_rate": 7.4525685738799925e-06, | |
| "loss": 2.5192, | |
| "step": 509000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.46337890625, | |
| "eval_runtime": 74.6729, | |
| "eval_samples_per_second": 11.048, | |
| "eval_steps_per_second": 5.531, | |
| "step": 509000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 31.72559928894043, | |
| "learning_rate": 7.467210162433785e-06, | |
| "loss": 2.5431, | |
| "step": 510000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.615093469619751, | |
| "eval_runtime": 88.9599, | |
| "eval_samples_per_second": 9.274, | |
| "eval_steps_per_second": 4.643, | |
| "step": 510000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 41.91428756713867, | |
| "learning_rate": 7.481851750987575e-06, | |
| "loss": 2.546, | |
| "step": 511000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.4940452575683594, | |
| "eval_runtime": 74.6792, | |
| "eval_samples_per_second": 11.047, | |
| "eval_steps_per_second": 5.53, | |
| "step": 511000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 33.08389663696289, | |
| "learning_rate": 7.496493339541367e-06, | |
| "loss": 2.523, | |
| "step": 512000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.472357988357544, | |
| "eval_runtime": 74.5358, | |
| "eval_samples_per_second": 11.069, | |
| "eval_steps_per_second": 5.541, | |
| "step": 512000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 30.30219841003418, | |
| "learning_rate": 7.5111349280951595e-06, | |
| "loss": 2.5399, | |
| "step": 513000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.5458850860595703, | |
| "eval_runtime": 88.6531, | |
| "eval_samples_per_second": 9.306, | |
| "eval_steps_per_second": 4.659, | |
| "step": 513000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 30.642229080200195, | |
| "learning_rate": 7.525776516648951e-06, | |
| "loss": 2.5253, | |
| "step": 514000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.5789878368377686, | |
| "eval_runtime": 74.5705, | |
| "eval_samples_per_second": 11.063, | |
| "eval_steps_per_second": 5.538, | |
| "step": 514000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 39.65602493286133, | |
| "learning_rate": 7.540418105202742e-06, | |
| "loss": 2.5315, | |
| "step": 515000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.501187801361084, | |
| "eval_runtime": 88.5681, | |
| "eval_samples_per_second": 9.315, | |
| "eval_steps_per_second": 4.663, | |
| "step": 515000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 29.685272216796875, | |
| "learning_rate": 7.555059693756534e-06, | |
| "loss": 2.5209, | |
| "step": 516000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.5158517360687256, | |
| "eval_runtime": 74.732, | |
| "eval_samples_per_second": 11.039, | |
| "eval_steps_per_second": 5.526, | |
| "step": 516000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 26.941364288330078, | |
| "learning_rate": 7.5697012823103265e-06, | |
| "loss": 2.5267, | |
| "step": 517000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.5034916400909424, | |
| "eval_runtime": 74.5657, | |
| "eval_samples_per_second": 11.064, | |
| "eval_steps_per_second": 5.539, | |
| "step": 517000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 30.716243743896484, | |
| "learning_rate": 7.584342870864118e-06, | |
| "loss": 2.5341, | |
| "step": 518000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.466562032699585, | |
| "eval_runtime": 88.7982, | |
| "eval_samples_per_second": 9.291, | |
| "eval_steps_per_second": 4.651, | |
| "step": 518000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 51.75357437133789, | |
| "learning_rate": 7.59898445941791e-06, | |
| "loss": 2.5457, | |
| "step": 519000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.5445785522460938, | |
| "eval_runtime": 74.53, | |
| "eval_samples_per_second": 11.069, | |
| "eval_steps_per_second": 5.541, | |
| "step": 519000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 34.443023681640625, | |
| "learning_rate": 7.613626047971701e-06, | |
| "loss": 2.5313, | |
| "step": 520000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.506009101867676, | |
| "eval_runtime": 88.555, | |
| "eval_samples_per_second": 9.316, | |
| "eval_steps_per_second": 4.664, | |
| "step": 520000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 31.235965728759766, | |
| "learning_rate": 7.628267636525493e-06, | |
| "loss": 2.5275, | |
| "step": 521000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.5120317935943604, | |
| "eval_runtime": 74.6094, | |
| "eval_samples_per_second": 11.058, | |
| "eval_steps_per_second": 5.535, | |
| "step": 521000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 29.263076782226562, | |
| "learning_rate": 7.642909225079284e-06, | |
| "loss": 2.5309, | |
| "step": 522000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.5825254917144775, | |
| "eval_runtime": 88.7861, | |
| "eval_samples_per_second": 9.292, | |
| "eval_steps_per_second": 4.652, | |
| "step": 522000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 22.8249454498291, | |
| "learning_rate": 7.657550813633077e-06, | |
| "loss": 2.534, | |
| "step": 523000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.4425950050354004, | |
| "eval_runtime": 74.5795, | |
| "eval_samples_per_second": 11.062, | |
| "eval_steps_per_second": 5.538, | |
| "step": 523000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 26.066471099853516, | |
| "learning_rate": 7.672192402186868e-06, | |
| "loss": 2.5071, | |
| "step": 524000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.509237051010132, | |
| "eval_runtime": 74.8845, | |
| "eval_samples_per_second": 11.017, | |
| "eval_steps_per_second": 5.515, | |
| "step": 524000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 46.68310546875, | |
| "learning_rate": 7.68683399074066e-06, | |
| "loss": 2.5324, | |
| "step": 525000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.531177282333374, | |
| "eval_runtime": 89.0215, | |
| "eval_samples_per_second": 9.267, | |
| "eval_steps_per_second": 4.639, | |
| "step": 525000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 31.326271057128906, | |
| "learning_rate": 7.701475579294451e-06, | |
| "loss": 2.5266, | |
| "step": 526000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.495670795440674, | |
| "eval_runtime": 74.673, | |
| "eval_samples_per_second": 11.048, | |
| "eval_steps_per_second": 5.531, | |
| "step": 526000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 41.735721588134766, | |
| "learning_rate": 7.716117167848244e-06, | |
| "loss": 2.5443, | |
| "step": 527000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.530324935913086, | |
| "eval_runtime": 89.1796, | |
| "eval_samples_per_second": 9.251, | |
| "eval_steps_per_second": 4.631, | |
| "step": 527000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 26.984756469726562, | |
| "learning_rate": 7.730758756402035e-06, | |
| "loss": 2.5231, | |
| "step": 528000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.526041269302368, | |
| "eval_runtime": 74.8795, | |
| "eval_samples_per_second": 11.018, | |
| "eval_steps_per_second": 5.516, | |
| "step": 528000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 40.371009826660156, | |
| "learning_rate": 7.745400344955827e-06, | |
| "loss": 2.5324, | |
| "step": 529000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.5326287746429443, | |
| "eval_runtime": 74.6843, | |
| "eval_samples_per_second": 11.046, | |
| "eval_steps_per_second": 5.53, | |
| "step": 529000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 25.49151039123535, | |
| "learning_rate": 7.76004193350962e-06, | |
| "loss": 2.531, | |
| "step": 530000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.5524654388427734, | |
| "eval_runtime": 88.777, | |
| "eval_samples_per_second": 9.293, | |
| "eval_steps_per_second": 4.652, | |
| "step": 530000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 24.5642032623291, | |
| "learning_rate": 7.774683522063411e-06, | |
| "loss": 2.5473, | |
| "step": 531000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.5063366889953613, | |
| "eval_runtime": 74.7154, | |
| "eval_samples_per_second": 11.042, | |
| "eval_steps_per_second": 5.528, | |
| "step": 531000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 29.164342880249023, | |
| "learning_rate": 7.789325110617202e-06, | |
| "loss": 2.5579, | |
| "step": 532000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.5238850116729736, | |
| "eval_runtime": 88.8674, | |
| "eval_samples_per_second": 9.283, | |
| "eval_steps_per_second": 4.647, | |
| "step": 532000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 31.728139877319336, | |
| "learning_rate": 7.803966699170994e-06, | |
| "loss": 2.5455, | |
| "step": 533000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.530641555786133, | |
| "eval_runtime": 74.6942, | |
| "eval_samples_per_second": 11.045, | |
| "eval_steps_per_second": 5.529, | |
| "step": 533000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 30.494529724121094, | |
| "learning_rate": 7.818608287724787e-06, | |
| "loss": 2.5345, | |
| "step": 534000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.532782793045044, | |
| "eval_runtime": 74.8909, | |
| "eval_samples_per_second": 11.016, | |
| "eval_steps_per_second": 5.515, | |
| "step": 534000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 31.76959800720215, | |
| "learning_rate": 7.833249876278576e-06, | |
| "loss": 2.5307, | |
| "step": 535000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.5115082263946533, | |
| "eval_runtime": 88.5627, | |
| "eval_samples_per_second": 9.315, | |
| "eval_steps_per_second": 4.663, | |
| "step": 535000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 37.1898307800293, | |
| "learning_rate": 7.84789146483237e-06, | |
| "loss": 2.5271, | |
| "step": 536000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.613095998764038, | |
| "eval_runtime": 74.8201, | |
| "eval_samples_per_second": 11.026, | |
| "eval_steps_per_second": 5.52, | |
| "step": 536000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 46.06565475463867, | |
| "learning_rate": 7.86253305338616e-06, | |
| "loss": 2.5351, | |
| "step": 537000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.5240702629089355, | |
| "eval_runtime": 88.8498, | |
| "eval_samples_per_second": 9.285, | |
| "eval_steps_per_second": 4.648, | |
| "step": 537000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 48.30146408081055, | |
| "learning_rate": 7.877174641939954e-06, | |
| "loss": 2.5067, | |
| "step": 538000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.445352077484131, | |
| "eval_runtime": 81.7531, | |
| "eval_samples_per_second": 10.091, | |
| "eval_steps_per_second": 5.052, | |
| "step": 538000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 26.811046600341797, | |
| "learning_rate": 7.891816230493743e-06, | |
| "loss": 2.508, | |
| "step": 539000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.4756014347076416, | |
| "eval_runtime": 89.498, | |
| "eval_samples_per_second": 9.218, | |
| "eval_steps_per_second": 4.615, | |
| "step": 539000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 38.2576789855957, | |
| "learning_rate": 7.906457819047536e-06, | |
| "loss": 2.5324, | |
| "step": 540000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.415710926055908, | |
| "eval_runtime": 75.1208, | |
| "eval_samples_per_second": 10.982, | |
| "eval_steps_per_second": 5.498, | |
| "step": 540000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 36.25407409667969, | |
| "learning_rate": 7.921099407601328e-06, | |
| "loss": 2.5211, | |
| "step": 541000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.5010883808135986, | |
| "eval_runtime": 74.6035, | |
| "eval_samples_per_second": 11.058, | |
| "eval_steps_per_second": 5.536, | |
| "step": 541000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 27.875274658203125, | |
| "learning_rate": 7.935740996155119e-06, | |
| "loss": 2.5319, | |
| "step": 542000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.4954843521118164, | |
| "eval_runtime": 89.0529, | |
| "eval_samples_per_second": 9.264, | |
| "eval_steps_per_second": 4.638, | |
| "step": 542000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 30.717681884765625, | |
| "learning_rate": 7.95038258470891e-06, | |
| "loss": 2.5361, | |
| "step": 543000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.5567915439605713, | |
| "eval_runtime": 76.6726, | |
| "eval_samples_per_second": 10.76, | |
| "eval_steps_per_second": 5.387, | |
| "step": 543000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 27.22251319885254, | |
| "learning_rate": 7.965024173262703e-06, | |
| "loss": 2.548, | |
| "step": 544000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.518052101135254, | |
| "eval_runtime": 91.1463, | |
| "eval_samples_per_second": 9.051, | |
| "eval_steps_per_second": 4.531, | |
| "step": 544000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 24.037654876708984, | |
| "learning_rate": 7.979665761816495e-06, | |
| "loss": 2.5258, | |
| "step": 545000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.6096935272216797, | |
| "eval_runtime": 76.5086, | |
| "eval_samples_per_second": 10.783, | |
| "eval_steps_per_second": 5.398, | |
| "step": 545000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 40.470664978027344, | |
| "learning_rate": 7.994307350370286e-06, | |
| "loss": 2.5173, | |
| "step": 546000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.543060302734375, | |
| "eval_runtime": 75.9324, | |
| "eval_samples_per_second": 10.865, | |
| "eval_steps_per_second": 5.439, | |
| "step": 546000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 29.762210845947266, | |
| "learning_rate": 8.008948938924079e-06, | |
| "loss": 2.5249, | |
| "step": 547000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.4692766666412354, | |
| "eval_runtime": 90.7767, | |
| "eval_samples_per_second": 9.088, | |
| "eval_steps_per_second": 4.55, | |
| "step": 547000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 27.77049446105957, | |
| "learning_rate": 8.02359052747787e-06, | |
| "loss": 2.5087, | |
| "step": 548000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.480736017227173, | |
| "eval_runtime": 76.3978, | |
| "eval_samples_per_second": 10.799, | |
| "eval_steps_per_second": 5.406, | |
| "step": 548000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 29.757713317871094, | |
| "learning_rate": 8.038232116031662e-06, | |
| "loss": 2.5288, | |
| "step": 549000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.4918410778045654, | |
| "eval_runtime": 92.7712, | |
| "eval_samples_per_second": 8.893, | |
| "eval_steps_per_second": 4.452, | |
| "step": 549000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 36.95774841308594, | |
| "learning_rate": 8.052873704585453e-06, | |
| "loss": 2.5337, | |
| "step": 550000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.440648317337036, | |
| "eval_runtime": 75.8485, | |
| "eval_samples_per_second": 10.877, | |
| "eval_steps_per_second": 5.445, | |
| "step": 550000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 42.54120635986328, | |
| "learning_rate": 8.067515293139246e-06, | |
| "loss": 2.5361, | |
| "step": 551000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.4498894214630127, | |
| "eval_runtime": 90.2465, | |
| "eval_samples_per_second": 9.142, | |
| "eval_steps_per_second": 4.576, | |
| "step": 551000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 32.604347229003906, | |
| "learning_rate": 8.082156881693037e-06, | |
| "loss": 2.5226, | |
| "step": 552000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.461261034011841, | |
| "eval_runtime": 76.3392, | |
| "eval_samples_per_second": 10.807, | |
| "eval_steps_per_second": 5.41, | |
| "step": 552000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 38.40324783325195, | |
| "learning_rate": 8.096798470246829e-06, | |
| "loss": 2.5331, | |
| "step": 553000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.507526397705078, | |
| "eval_runtime": 75.972, | |
| "eval_samples_per_second": 10.859, | |
| "eval_steps_per_second": 5.436, | |
| "step": 553000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 34.65354919433594, | |
| "learning_rate": 8.11144005880062e-06, | |
| "loss": 2.5268, | |
| "step": 554000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.4727320671081543, | |
| "eval_runtime": 89.1458, | |
| "eval_samples_per_second": 9.255, | |
| "eval_steps_per_second": 4.633, | |
| "step": 554000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 36.14072799682617, | |
| "learning_rate": 8.126081647354413e-06, | |
| "loss": 2.5297, | |
| "step": 555000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.5081801414489746, | |
| "eval_runtime": 75.1359, | |
| "eval_samples_per_second": 10.98, | |
| "eval_steps_per_second": 5.497, | |
| "step": 555000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 21.90192413330078, | |
| "learning_rate": 8.140723235908203e-06, | |
| "loss": 2.5182, | |
| "step": 556000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.542210340499878, | |
| "eval_runtime": 89.2503, | |
| "eval_samples_per_second": 9.244, | |
| "eval_steps_per_second": 4.627, | |
| "step": 556000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 29.731470108032227, | |
| "learning_rate": 8.155364824461996e-06, | |
| "loss": 2.5396, | |
| "step": 557000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.5540778636932373, | |
| "eval_runtime": 74.5655, | |
| "eval_samples_per_second": 11.064, | |
| "eval_steps_per_second": 5.539, | |
| "step": 557000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 36.37150955200195, | |
| "learning_rate": 8.170006413015787e-06, | |
| "loss": 2.5462, | |
| "step": 558000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.5844576358795166, | |
| "eval_runtime": 74.52, | |
| "eval_samples_per_second": 11.071, | |
| "eval_steps_per_second": 5.542, | |
| "step": 558000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 25.697357177734375, | |
| "learning_rate": 8.18464800156958e-06, | |
| "loss": 2.5018, | |
| "step": 559000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.4566192626953125, | |
| "eval_runtime": 91.6957, | |
| "eval_samples_per_second": 8.997, | |
| "eval_steps_per_second": 4.504, | |
| "step": 559000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 48.198944091796875, | |
| "learning_rate": 8.19928959012337e-06, | |
| "loss": 2.5175, | |
| "step": 560000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.5511298179626465, | |
| "eval_runtime": 77.1596, | |
| "eval_samples_per_second": 10.692, | |
| "eval_steps_per_second": 5.353, | |
| "step": 560000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 35.16044235229492, | |
| "learning_rate": 8.213931178677163e-06, | |
| "loss": 2.5186, | |
| "step": 561000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.5079469680786133, | |
| "eval_runtime": 94.2533, | |
| "eval_samples_per_second": 8.753, | |
| "eval_steps_per_second": 4.382, | |
| "step": 561000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 24.49595832824707, | |
| "learning_rate": 8.228572767230954e-06, | |
| "loss": 2.5321, | |
| "step": 562000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.4904894828796387, | |
| "eval_runtime": 74.9718, | |
| "eval_samples_per_second": 11.004, | |
| "eval_steps_per_second": 5.509, | |
| "step": 562000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 33.582340240478516, | |
| "learning_rate": 8.243214355784745e-06, | |
| "loss": 2.531, | |
| "step": 563000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.6183409690856934, | |
| "eval_runtime": 74.5558, | |
| "eval_samples_per_second": 11.066, | |
| "eval_steps_per_second": 5.539, | |
| "step": 563000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 24.678638458251953, | |
| "learning_rate": 8.257855944338538e-06, | |
| "loss": 2.5162, | |
| "step": 564000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.525707244873047, | |
| "eval_runtime": 88.6578, | |
| "eval_samples_per_second": 9.305, | |
| "eval_steps_per_second": 4.658, | |
| "step": 564000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 33.279022216796875, | |
| "learning_rate": 8.27249753289233e-06, | |
| "loss": 2.5074, | |
| "step": 565000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.5521037578582764, | |
| "eval_runtime": 74.5573, | |
| "eval_samples_per_second": 11.065, | |
| "eval_steps_per_second": 5.539, | |
| "step": 565000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 37.84657287597656, | |
| "learning_rate": 8.287139121446121e-06, | |
| "loss": 2.5216, | |
| "step": 566000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.581077814102173, | |
| "eval_runtime": 88.7044, | |
| "eval_samples_per_second": 9.301, | |
| "eval_steps_per_second": 4.656, | |
| "step": 566000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 34.67258834838867, | |
| "learning_rate": 8.301780709999912e-06, | |
| "loss": 2.5553, | |
| "step": 567000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.5216948986053467, | |
| "eval_runtime": 74.6784, | |
| "eval_samples_per_second": 11.047, | |
| "eval_steps_per_second": 5.53, | |
| "step": 567000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 31.939085006713867, | |
| "learning_rate": 8.316422298553705e-06, | |
| "loss": 2.5188, | |
| "step": 568000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.483720302581787, | |
| "eval_runtime": 88.8032, | |
| "eval_samples_per_second": 9.29, | |
| "eval_steps_per_second": 4.651, | |
| "step": 568000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 70.68443298339844, | |
| "learning_rate": 8.331063887107497e-06, | |
| "loss": 2.521, | |
| "step": 569000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.486253499984741, | |
| "eval_runtime": 74.511, | |
| "eval_samples_per_second": 11.072, | |
| "eval_steps_per_second": 5.543, | |
| "step": 569000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 36.54584503173828, | |
| "learning_rate": 8.345705475661288e-06, | |
| "loss": 2.5131, | |
| "step": 570000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.49752140045166, | |
| "eval_runtime": 74.6321, | |
| "eval_samples_per_second": 11.054, | |
| "eval_steps_per_second": 5.534, | |
| "step": 570000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 33.440093994140625, | |
| "learning_rate": 8.36034706421508e-06, | |
| "loss": 2.522, | |
| "step": 571000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.4143617153167725, | |
| "eval_runtime": 88.6944, | |
| "eval_samples_per_second": 9.302, | |
| "eval_steps_per_second": 4.656, | |
| "step": 571000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 34.93145751953125, | |
| "learning_rate": 8.374988652768872e-06, | |
| "loss": 2.5145, | |
| "step": 572000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.463707447052002, | |
| "eval_runtime": 74.5869, | |
| "eval_samples_per_second": 11.061, | |
| "eval_steps_per_second": 5.537, | |
| "step": 572000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 31.742279052734375, | |
| "learning_rate": 8.389630241322662e-06, | |
| "loss": 2.5006, | |
| "step": 573000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.5146420001983643, | |
| "eval_runtime": 88.6696, | |
| "eval_samples_per_second": 9.304, | |
| "eval_steps_per_second": 4.658, | |
| "step": 573000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 53.028282165527344, | |
| "learning_rate": 8.404271829876455e-06, | |
| "loss": 2.5507, | |
| "step": 574000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.531402587890625, | |
| "eval_runtime": 74.5529, | |
| "eval_samples_per_second": 11.066, | |
| "eval_steps_per_second": 5.54, | |
| "step": 574000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 57.27425003051758, | |
| "learning_rate": 8.418913418430246e-06, | |
| "loss": 2.5357, | |
| "step": 575000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.6296398639678955, | |
| "eval_runtime": 74.7514, | |
| "eval_samples_per_second": 11.037, | |
| "eval_steps_per_second": 5.525, | |
| "step": 575000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 22.733678817749023, | |
| "learning_rate": 8.43355500698404e-06, | |
| "loss": 2.5193, | |
| "step": 576000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.570042133331299, | |
| "eval_runtime": 88.802, | |
| "eval_samples_per_second": 9.29, | |
| "eval_steps_per_second": 4.651, | |
| "step": 576000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 35.834075927734375, | |
| "learning_rate": 8.448196595537829e-06, | |
| "loss": 2.5336, | |
| "step": 577000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.5378034114837646, | |
| "eval_runtime": 74.6827, | |
| "eval_samples_per_second": 11.047, | |
| "eval_steps_per_second": 5.53, | |
| "step": 577000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 36.09931945800781, | |
| "learning_rate": 8.462838184091622e-06, | |
| "loss": 2.505, | |
| "step": 578000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.4723126888275146, | |
| "eval_runtime": 88.9314, | |
| "eval_samples_per_second": 9.277, | |
| "eval_steps_per_second": 4.644, | |
| "step": 578000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 29.487991333007812, | |
| "learning_rate": 8.477479772645413e-06, | |
| "loss": 2.5118, | |
| "step": 579000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.4950342178344727, | |
| "eval_runtime": 74.6665, | |
| "eval_samples_per_second": 11.049, | |
| "eval_steps_per_second": 5.531, | |
| "step": 579000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 35.32073974609375, | |
| "learning_rate": 8.492121361199205e-06, | |
| "loss": 2.527, | |
| "step": 580000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.5424089431762695, | |
| "eval_runtime": 74.5322, | |
| "eval_samples_per_second": 11.069, | |
| "eval_steps_per_second": 5.541, | |
| "step": 580000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 40.19975280761719, | |
| "learning_rate": 8.506762949752998e-06, | |
| "loss": 2.531, | |
| "step": 581000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.5420637130737305, | |
| "eval_runtime": 88.8561, | |
| "eval_samples_per_second": 9.285, | |
| "eval_steps_per_second": 4.648, | |
| "step": 581000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 27.63242530822754, | |
| "learning_rate": 8.521404538306789e-06, | |
| "loss": 2.5215, | |
| "step": 582000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.4698994159698486, | |
| "eval_runtime": 74.5737, | |
| "eval_samples_per_second": 11.063, | |
| "eval_steps_per_second": 5.538, | |
| "step": 582000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 45.67693328857422, | |
| "learning_rate": 8.53604612686058e-06, | |
| "loss": 2.5103, | |
| "step": 583000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.5570404529571533, | |
| "eval_runtime": 88.6527, | |
| "eval_samples_per_second": 9.306, | |
| "eval_steps_per_second": 4.659, | |
| "step": 583000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 33.481082916259766, | |
| "learning_rate": 8.550687715414372e-06, | |
| "loss": 2.5258, | |
| "step": 584000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.529367208480835, | |
| "eval_runtime": 78.065, | |
| "eval_samples_per_second": 10.568, | |
| "eval_steps_per_second": 5.29, | |
| "step": 584000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 20.300424575805664, | |
| "learning_rate": 8.565329303968165e-06, | |
| "loss": 2.4886, | |
| "step": 585000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.5173099040985107, | |
| "eval_runtime": 88.6295, | |
| "eval_samples_per_second": 9.308, | |
| "eval_steps_per_second": 4.66, | |
| "step": 585000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 30.857240676879883, | |
| "learning_rate": 8.579970892521956e-06, | |
| "loss": 2.5094, | |
| "step": 586000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.6584701538085938, | |
| "eval_runtime": 74.5434, | |
| "eval_samples_per_second": 11.067, | |
| "eval_steps_per_second": 5.54, | |
| "step": 586000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 25.00079917907715, | |
| "learning_rate": 8.594612481075747e-06, | |
| "loss": 2.5294, | |
| "step": 587000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.546011209487915, | |
| "eval_runtime": 74.5637, | |
| "eval_samples_per_second": 11.064, | |
| "eval_steps_per_second": 5.539, | |
| "step": 587000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 30.173933029174805, | |
| "learning_rate": 8.609254069629539e-06, | |
| "loss": 2.5104, | |
| "step": 588000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.46292781829834, | |
| "eval_runtime": 88.6384, | |
| "eval_samples_per_second": 9.307, | |
| "eval_steps_per_second": 4.659, | |
| "step": 588000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 34.49174118041992, | |
| "learning_rate": 8.623895658183332e-06, | |
| "loss": 2.4978, | |
| "step": 589000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.4769954681396484, | |
| "eval_runtime": 74.6204, | |
| "eval_samples_per_second": 11.056, | |
| "eval_steps_per_second": 5.535, | |
| "step": 589000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 31.314254760742188, | |
| "learning_rate": 8.638537246737123e-06, | |
| "loss": 2.5209, | |
| "step": 590000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.4981024265289307, | |
| "eval_runtime": 88.6067, | |
| "eval_samples_per_second": 9.311, | |
| "eval_steps_per_second": 4.661, | |
| "step": 590000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 44.28144454956055, | |
| "learning_rate": 8.653178835290914e-06, | |
| "loss": 2.5353, | |
| "step": 591000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.546908140182495, | |
| "eval_runtime": 74.6528, | |
| "eval_samples_per_second": 11.051, | |
| "eval_steps_per_second": 5.532, | |
| "step": 591000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 22.053375244140625, | |
| "learning_rate": 8.667820423844706e-06, | |
| "loss": 2.5199, | |
| "step": 592000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.51155161857605, | |
| "eval_runtime": 74.5424, | |
| "eval_samples_per_second": 11.068, | |
| "eval_steps_per_second": 5.54, | |
| "step": 592000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 31.350740432739258, | |
| "learning_rate": 8.682462012398499e-06, | |
| "loss": 2.4976, | |
| "step": 593000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.5021212100982666, | |
| "eval_runtime": 88.8346, | |
| "eval_samples_per_second": 9.287, | |
| "eval_steps_per_second": 4.649, | |
| "step": 593000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 31.255252838134766, | |
| "learning_rate": 8.697103600952288e-06, | |
| "loss": 2.5163, | |
| "step": 594000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.4919252395629883, | |
| "eval_runtime": 74.5758, | |
| "eval_samples_per_second": 11.063, | |
| "eval_steps_per_second": 5.538, | |
| "step": 594000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 32.16548156738281, | |
| "learning_rate": 8.711745189506081e-06, | |
| "loss": 2.4954, | |
| "step": 595000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.508427381515503, | |
| "eval_runtime": 88.8381, | |
| "eval_samples_per_second": 9.287, | |
| "eval_steps_per_second": 4.649, | |
| "step": 595000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 38.885704040527344, | |
| "learning_rate": 8.726386778059873e-06, | |
| "loss": 2.5091, | |
| "step": 596000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.5161032676696777, | |
| "eval_runtime": 74.6717, | |
| "eval_samples_per_second": 11.048, | |
| "eval_steps_per_second": 5.531, | |
| "step": 596000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 26.605031967163086, | |
| "learning_rate": 8.741028366613666e-06, | |
| "loss": 2.5106, | |
| "step": 597000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.480731248855591, | |
| "eval_runtime": 88.9373, | |
| "eval_samples_per_second": 9.276, | |
| "eval_steps_per_second": 4.644, | |
| "step": 597000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 31.664562225341797, | |
| "learning_rate": 8.755669955167457e-06, | |
| "loss": 2.4986, | |
| "step": 598000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.454038619995117, | |
| "eval_runtime": 74.4456, | |
| "eval_samples_per_second": 11.082, | |
| "eval_steps_per_second": 5.548, | |
| "step": 598000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 30.46480369567871, | |
| "learning_rate": 8.770311543721248e-06, | |
| "loss": 2.5167, | |
| "step": 599000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.481914758682251, | |
| "eval_runtime": 74.5377, | |
| "eval_samples_per_second": 11.068, | |
| "eval_steps_per_second": 5.541, | |
| "step": 599000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 66.7420654296875, | |
| "learning_rate": 8.78495313227504e-06, | |
| "loss": 2.5257, | |
| "step": 600000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.4934213161468506, | |
| "eval_runtime": 88.8231, | |
| "eval_samples_per_second": 9.288, | |
| "eval_steps_per_second": 4.65, | |
| "step": 600000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 25.715648651123047, | |
| "learning_rate": 8.799594720828831e-06, | |
| "loss": 2.517, | |
| "step": 601000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.441848039627075, | |
| "eval_runtime": 74.6384, | |
| "eval_samples_per_second": 11.053, | |
| "eval_steps_per_second": 5.533, | |
| "step": 601000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 40.46959686279297, | |
| "learning_rate": 8.814236309382624e-06, | |
| "loss": 2.5514, | |
| "step": 602000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.470050096511841, | |
| "eval_runtime": 88.7602, | |
| "eval_samples_per_second": 9.295, | |
| "eval_steps_per_second": 4.653, | |
| "step": 602000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 32.37881088256836, | |
| "learning_rate": 8.828877897936415e-06, | |
| "loss": 2.5062, | |
| "step": 603000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.5241613388061523, | |
| "eval_runtime": 74.6312, | |
| "eval_samples_per_second": 11.054, | |
| "eval_steps_per_second": 5.534, | |
| "step": 603000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 48.49308395385742, | |
| "learning_rate": 8.843519486490207e-06, | |
| "loss": 2.5172, | |
| "step": 604000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.5067596435546875, | |
| "eval_runtime": 74.543, | |
| "eval_samples_per_second": 11.067, | |
| "eval_steps_per_second": 5.54, | |
| "step": 604000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 27.66318130493164, | |
| "learning_rate": 8.858161075043998e-06, | |
| "loss": 2.5241, | |
| "step": 605000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.4602746963500977, | |
| "eval_runtime": 88.5077, | |
| "eval_samples_per_second": 9.321, | |
| "eval_steps_per_second": 4.666, | |
| "step": 605000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 48.21938705444336, | |
| "learning_rate": 8.872802663597791e-06, | |
| "loss": 2.5155, | |
| "step": 606000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.481112480163574, | |
| "eval_runtime": 74.5722, | |
| "eval_samples_per_second": 11.063, | |
| "eval_steps_per_second": 5.538, | |
| "step": 606000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 29.03439712524414, | |
| "learning_rate": 8.887444252151582e-06, | |
| "loss": 2.5271, | |
| "step": 607000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.524092197418213, | |
| "eval_runtime": 88.7735, | |
| "eval_samples_per_second": 9.293, | |
| "eval_steps_per_second": 4.652, | |
| "step": 607000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 19.625823974609375, | |
| "learning_rate": 8.902085840705374e-06, | |
| "loss": 2.4987, | |
| "step": 608000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.5538923740386963, | |
| "eval_runtime": 74.6497, | |
| "eval_samples_per_second": 11.052, | |
| "eval_steps_per_second": 5.533, | |
| "step": 608000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 63.533599853515625, | |
| "learning_rate": 8.916727429259165e-06, | |
| "loss": 2.5101, | |
| "step": 609000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.502268075942993, | |
| "eval_runtime": 74.5661, | |
| "eval_samples_per_second": 11.064, | |
| "eval_steps_per_second": 5.539, | |
| "step": 609000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 21.927827835083008, | |
| "learning_rate": 8.931369017812958e-06, | |
| "loss": 2.5147, | |
| "step": 610000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.5037426948547363, | |
| "eval_runtime": 89.0991, | |
| "eval_samples_per_second": 9.259, | |
| "eval_steps_per_second": 4.635, | |
| "step": 610000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 27.656044006347656, | |
| "learning_rate": 8.94601060636675e-06, | |
| "loss": 2.5236, | |
| "step": 611000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.487699508666992, | |
| "eval_runtime": 74.5421, | |
| "eval_samples_per_second": 11.068, | |
| "eval_steps_per_second": 5.54, | |
| "step": 611000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 19.147541046142578, | |
| "learning_rate": 8.96065219492054e-06, | |
| "loss": 2.5209, | |
| "step": 612000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.465284585952759, | |
| "eval_runtime": 88.8409, | |
| "eval_samples_per_second": 9.286, | |
| "eval_steps_per_second": 4.649, | |
| "step": 612000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 38.874507904052734, | |
| "learning_rate": 8.975293783474332e-06, | |
| "loss": 2.4915, | |
| "step": 613000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.500398874282837, | |
| "eval_runtime": 74.6884, | |
| "eval_samples_per_second": 11.046, | |
| "eval_steps_per_second": 5.53, | |
| "step": 613000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 91.2654037475586, | |
| "learning_rate": 8.989935372028125e-06, | |
| "loss": 2.5087, | |
| "step": 614000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.511294364929199, | |
| "eval_runtime": 88.9508, | |
| "eval_samples_per_second": 9.275, | |
| "eval_steps_per_second": 4.643, | |
| "step": 614000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 25.057418823242188, | |
| "learning_rate": 9.004576960581916e-06, | |
| "loss": 2.518, | |
| "step": 615000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.5428690910339355, | |
| "eval_runtime": 74.509, | |
| "eval_samples_per_second": 11.072, | |
| "eval_steps_per_second": 5.543, | |
| "step": 615000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 47.45814514160156, | |
| "learning_rate": 9.019218549135708e-06, | |
| "loss": 2.5108, | |
| "step": 616000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.516467809677124, | |
| "eval_runtime": 74.5781, | |
| "eval_samples_per_second": 11.062, | |
| "eval_steps_per_second": 5.538, | |
| "step": 616000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 38.216609954833984, | |
| "learning_rate": 9.033860137689499e-06, | |
| "loss": 2.501, | |
| "step": 617000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.532259464263916, | |
| "eval_runtime": 88.6384, | |
| "eval_samples_per_second": 9.307, | |
| "eval_steps_per_second": 4.659, | |
| "step": 617000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 22.716007232666016, | |
| "learning_rate": 9.048501726243292e-06, | |
| "loss": 2.4959, | |
| "step": 618000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.4635117053985596, | |
| "eval_runtime": 74.6568, | |
| "eval_samples_per_second": 11.051, | |
| "eval_steps_per_second": 5.532, | |
| "step": 618000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 30.824867248535156, | |
| "learning_rate": 9.063143314797083e-06, | |
| "loss": 2.5062, | |
| "step": 619000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.512939214706421, | |
| "eval_runtime": 89.075, | |
| "eval_samples_per_second": 9.262, | |
| "eval_steps_per_second": 4.637, | |
| "step": 619000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 58.68292999267578, | |
| "learning_rate": 9.077784903350875e-06, | |
| "loss": 2.5045, | |
| "step": 620000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.5159168243408203, | |
| "eval_runtime": 74.6453, | |
| "eval_samples_per_second": 11.052, | |
| "eval_steps_per_second": 5.533, | |
| "step": 620000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 34.04876708984375, | |
| "learning_rate": 9.092426491904666e-06, | |
| "loss": 2.5157, | |
| "step": 621000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.50462007522583, | |
| "eval_runtime": 74.5748, | |
| "eval_samples_per_second": 11.063, | |
| "eval_steps_per_second": 5.538, | |
| "step": 621000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 21.843368530273438, | |
| "learning_rate": 9.107068080458457e-06, | |
| "loss": 2.5001, | |
| "step": 622000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.6030919551849365, | |
| "eval_runtime": 88.9981, | |
| "eval_samples_per_second": 9.27, | |
| "eval_steps_per_second": 4.641, | |
| "step": 622000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 80.11573028564453, | |
| "learning_rate": 9.12170966901225e-06, | |
| "loss": 2.5089, | |
| "step": 623000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.5459847450256348, | |
| "eval_runtime": 79.1187, | |
| "eval_samples_per_second": 10.427, | |
| "eval_steps_per_second": 5.22, | |
| "step": 623000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 33.59737014770508, | |
| "learning_rate": 9.136351257566042e-06, | |
| "loss": 2.5009, | |
| "step": 624000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.5228402614593506, | |
| "eval_runtime": 88.6038, | |
| "eval_samples_per_second": 9.311, | |
| "eval_steps_per_second": 4.661, | |
| "step": 624000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 87.70807647705078, | |
| "learning_rate": 9.150992846119835e-06, | |
| "loss": 2.5444, | |
| "step": 625000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.4817819595336914, | |
| "eval_runtime": 74.6477, | |
| "eval_samples_per_second": 11.052, | |
| "eval_steps_per_second": 5.533, | |
| "step": 625000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 36.25197219848633, | |
| "learning_rate": 9.165634434673624e-06, | |
| "loss": 2.5222, | |
| "step": 626000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.5177390575408936, | |
| "eval_runtime": 74.5677, | |
| "eval_samples_per_second": 11.064, | |
| "eval_steps_per_second": 5.539, | |
| "step": 626000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 27.811765670776367, | |
| "learning_rate": 9.180276023227417e-06, | |
| "loss": 2.5234, | |
| "step": 627000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.4546000957489014, | |
| "eval_runtime": 89.1778, | |
| "eval_samples_per_second": 9.251, | |
| "eval_steps_per_second": 4.631, | |
| "step": 627000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 23.489614486694336, | |
| "learning_rate": 9.194917611781209e-06, | |
| "loss": 2.5004, | |
| "step": 628000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.509915351867676, | |
| "eval_runtime": 74.8877, | |
| "eval_samples_per_second": 11.016, | |
| "eval_steps_per_second": 5.515, | |
| "step": 628000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 27.403156280517578, | |
| "learning_rate": 9.209559200335e-06, | |
| "loss": 2.5133, | |
| "step": 629000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.4226651191711426, | |
| "eval_runtime": 88.7661, | |
| "eval_samples_per_second": 9.294, | |
| "eval_steps_per_second": 4.653, | |
| "step": 629000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 30.951892852783203, | |
| "learning_rate": 9.224200788888791e-06, | |
| "loss": 2.5104, | |
| "step": 630000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.4871816635131836, | |
| "eval_runtime": 74.6946, | |
| "eval_samples_per_second": 11.045, | |
| "eval_steps_per_second": 5.529, | |
| "step": 630000 | |
| } | |
| ], | |
| "logging_steps": 1000, | |
| "max_steps": 6829858, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 70000, | |
| "total_flos": 2.0736382681586196e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |