| { |
| "best_global_step": 180, |
| "best_metric": 0.028741171583533287, |
| "best_model_checkpoint": "saves_stability/lora/llama-3-8b-instruct/train_copa_1757340254/checkpoint-180", |
| "epoch": 10.0, |
| "eval_steps": 45, |
| "global_step": 900, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.05555555555555555, |
| "grad_norm": 9.29712200164795, |
| "learning_rate": 2.2222222222222225e-06, |
| "loss": 0.5549, |
| "num_input_tokens_seen": 1632, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.1111111111111111, |
| "grad_norm": 8.06989860534668, |
| "learning_rate": 5e-06, |
| "loss": 0.6222, |
| "num_input_tokens_seen": 3232, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.16666666666666666, |
| "grad_norm": 9.607221603393555, |
| "learning_rate": 7.777777777777777e-06, |
| "loss": 0.6035, |
| "num_input_tokens_seen": 4832, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.2222222222222222, |
| "grad_norm": 8.147689819335938, |
| "learning_rate": 1.0555555555555555e-05, |
| "loss": 0.5399, |
| "num_input_tokens_seen": 6432, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.2777777777777778, |
| "grad_norm": 1.7882366180419922, |
| "learning_rate": 1.3333333333333333e-05, |
| "loss": 0.3046, |
| "num_input_tokens_seen": 7968, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.3333333333333333, |
| "grad_norm": 0.08489096909761429, |
| "learning_rate": 1.6111111111111115e-05, |
| "loss": 0.053, |
| "num_input_tokens_seen": 9504, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.3888888888888889, |
| "grad_norm": 4.197780132293701, |
| "learning_rate": 1.888888888888889e-05, |
| "loss": 0.154, |
| "num_input_tokens_seen": 11104, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.4444444444444444, |
| "grad_norm": 6.075568199157715, |
| "learning_rate": 2.1666666666666667e-05, |
| "loss": 0.2574, |
| "num_input_tokens_seen": 12704, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 0.056911613792181015, |
| "learning_rate": 2.4444444444444445e-05, |
| "loss": 0.1204, |
| "num_input_tokens_seen": 14240, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.5, |
| "eval_loss": 0.07262720912694931, |
| "eval_runtime": 0.6595, |
| "eval_samples_per_second": 60.655, |
| "eval_steps_per_second": 15.164, |
| "num_input_tokens_seen": 14240, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.5555555555555556, |
| "grad_norm": 4.138186454772949, |
| "learning_rate": 2.7222222222222223e-05, |
| "loss": 0.0856, |
| "num_input_tokens_seen": 15808, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.6111111111111112, |
| "grad_norm": 0.16636769473552704, |
| "learning_rate": 3e-05, |
| "loss": 0.102, |
| "num_input_tokens_seen": 17344, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.6666666666666666, |
| "grad_norm": 4.960498809814453, |
| "learning_rate": 3.277777777777778e-05, |
| "loss": 0.0599, |
| "num_input_tokens_seen": 18912, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.7222222222222222, |
| "grad_norm": 0.3227786719799042, |
| "learning_rate": 3.555555555555556e-05, |
| "loss": 0.0957, |
| "num_input_tokens_seen": 20448, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.7777777777777778, |
| "grad_norm": 0.1255882829427719, |
| "learning_rate": 3.8333333333333334e-05, |
| "loss": 0.0338, |
| "num_input_tokens_seen": 21984, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.8333333333333334, |
| "grad_norm": 0.5282731652259827, |
| "learning_rate": 4.111111111111111e-05, |
| "loss": 0.1162, |
| "num_input_tokens_seen": 23552, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.8888888888888888, |
| "grad_norm": 0.13714739680290222, |
| "learning_rate": 4.388888888888889e-05, |
| "loss": 0.05, |
| "num_input_tokens_seen": 25120, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.9444444444444444, |
| "grad_norm": 0.019420327618718147, |
| "learning_rate": 4.666666666666667e-05, |
| "loss": 0.0236, |
| "num_input_tokens_seen": 26656, |
| "step": 85 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 13.050488471984863, |
| "learning_rate": 4.9444444444444446e-05, |
| "loss": 0.3342, |
| "num_input_tokens_seen": 28192, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.06154817342758179, |
| "eval_runtime": 0.6509, |
| "eval_samples_per_second": 61.452, |
| "eval_steps_per_second": 15.363, |
| "num_input_tokens_seen": 28192, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.0555555555555556, |
| "grad_norm": 4.5402750968933105, |
| "learning_rate": 4.9996991493233693e-05, |
| "loss": 0.0178, |
| "num_input_tokens_seen": 29792, |
| "step": 95 |
| }, |
| { |
| "epoch": 1.1111111111111112, |
| "grad_norm": 0.007287744432687759, |
| "learning_rate": 4.99847706754774e-05, |
| "loss": 0.0188, |
| "num_input_tokens_seen": 31328, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.1666666666666667, |
| "grad_norm": 0.4953938126564026, |
| "learning_rate": 4.9963154107272295e-05, |
| "loss": 0.0392, |
| "num_input_tokens_seen": 32832, |
| "step": 105 |
| }, |
| { |
| "epoch": 1.2222222222222223, |
| "grad_norm": 7.272425174713135, |
| "learning_rate": 4.993214991772563e-05, |
| "loss": 0.0175, |
| "num_input_tokens_seen": 34304, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.2777777777777777, |
| "grad_norm": 0.004101940896362066, |
| "learning_rate": 4.989176976624511e-05, |
| "loss": 0.1593, |
| "num_input_tokens_seen": 35840, |
| "step": 115 |
| }, |
| { |
| "epoch": 1.3333333333333333, |
| "grad_norm": 6.7382917404174805, |
| "learning_rate": 4.9842028838154285e-05, |
| "loss": 0.2217, |
| "num_input_tokens_seen": 37376, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.3888888888888888, |
| "grad_norm": 0.01841416023671627, |
| "learning_rate": 4.978294583898196e-05, |
| "loss": 0.1021, |
| "num_input_tokens_seen": 38944, |
| "step": 125 |
| }, |
| { |
| "epoch": 1.4444444444444444, |
| "grad_norm": 8.32706069946289, |
| "learning_rate": 4.971454298742779e-05, |
| "loss": 0.0367, |
| "num_input_tokens_seen": 40512, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.5, |
| "grad_norm": 0.09243153035640717, |
| "learning_rate": 4.963684600700679e-05, |
| "loss": 0.0623, |
| "num_input_tokens_seen": 42080, |
| "step": 135 |
| }, |
| { |
| "epoch": 1.5, |
| "eval_loss": 0.0626690685749054, |
| "eval_runtime": 0.6595, |
| "eval_samples_per_second": 60.651, |
| "eval_steps_per_second": 15.163, |
| "num_input_tokens_seen": 42080, |
| "step": 135 |
| }, |
| { |
| "epoch": 1.5555555555555556, |
| "grad_norm": 6.175180912017822, |
| "learning_rate": 4.9549884116375714e-05, |
| "loss": 0.0692, |
| "num_input_tokens_seen": 43680, |
| "step": 140 |
| }, |
| { |
| "epoch": 1.6111111111111112, |
| "grad_norm": 0.0063971783965826035, |
| "learning_rate": 4.9453690018345144e-05, |
| "loss": 0.0105, |
| "num_input_tokens_seen": 45216, |
| "step": 145 |
| }, |
| { |
| "epoch": 1.6666666666666665, |
| "grad_norm": 2.9428696632385254, |
| "learning_rate": 4.934829988758131e-05, |
| "loss": 0.0298, |
| "num_input_tokens_seen": 46720, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.7222222222222223, |
| "grad_norm": 0.013507647439837456, |
| "learning_rate": 4.923375335700223e-05, |
| "loss": 0.001, |
| "num_input_tokens_seen": 48288, |
| "step": 155 |
| }, |
| { |
| "epoch": 1.7777777777777777, |
| "grad_norm": 0.19752782583236694, |
| "learning_rate": 4.9110093502873476e-05, |
| "loss": 0.0422, |
| "num_input_tokens_seen": 49888, |
| "step": 160 |
| }, |
| { |
| "epoch": 1.8333333333333335, |
| "grad_norm": 0.004462855402380228, |
| "learning_rate": 4.897736682860885e-05, |
| "loss": 0.0009, |
| "num_input_tokens_seen": 51424, |
| "step": 165 |
| }, |
| { |
| "epoch": 1.8888888888888888, |
| "grad_norm": 11.805179595947266, |
| "learning_rate": 4.883562324728241e-05, |
| "loss": 0.08, |
| "num_input_tokens_seen": 52992, |
| "step": 170 |
| }, |
| { |
| "epoch": 1.9444444444444444, |
| "grad_norm": 0.1971927285194397, |
| "learning_rate": 4.868491606285823e-05, |
| "loss": 0.085, |
| "num_input_tokens_seen": 54592, |
| "step": 175 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.013780980370938778, |
| "learning_rate": 4.8525301950144894e-05, |
| "loss": 0.0032, |
| "num_input_tokens_seen": 56192, |
| "step": 180 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.028741171583533287, |
| "eval_runtime": 0.6592, |
| "eval_samples_per_second": 60.677, |
| "eval_steps_per_second": 15.169, |
| "num_input_tokens_seen": 56192, |
| "step": 180 |
| }, |
| { |
| "epoch": 2.0555555555555554, |
| "grad_norm": 0.19373683631420135, |
| "learning_rate": 4.835684093348244e-05, |
| "loss": 0.0007, |
| "num_input_tokens_seen": 57760, |
| "step": 185 |
| }, |
| { |
| "epoch": 2.111111111111111, |
| "grad_norm": 0.0025918094906955957, |
| "learning_rate": 4.817959636416969e-05, |
| "loss": 0.0051, |
| "num_input_tokens_seen": 59264, |
| "step": 190 |
| }, |
| { |
| "epoch": 2.1666666666666665, |
| "grad_norm": 0.0018202380742877722, |
| "learning_rate": 4.7993634896640394e-05, |
| "loss": 0.0003, |
| "num_input_tokens_seen": 60768, |
| "step": 195 |
| }, |
| { |
| "epoch": 2.2222222222222223, |
| "grad_norm": 0.0017153556691482663, |
| "learning_rate": 4.779902646339722e-05, |
| "loss": 0.0005, |
| "num_input_tokens_seen": 62272, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.2777777777777777, |
| "grad_norm": 0.001437992905266583, |
| "learning_rate": 4.759584424871302e-05, |
| "loss": 0.0003, |
| "num_input_tokens_seen": 63808, |
| "step": 205 |
| }, |
| { |
| "epoch": 2.3333333333333335, |
| "grad_norm": 0.0007443541544489563, |
| "learning_rate": 4.7384164661109176e-05, |
| "loss": 0.0073, |
| "num_input_tokens_seen": 65344, |
| "step": 210 |
| }, |
| { |
| "epoch": 2.388888888888889, |
| "grad_norm": 0.008513362146914005, |
| "learning_rate": 4.7164067304621536e-05, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 66912, |
| "step": 215 |
| }, |
| { |
| "epoch": 2.4444444444444446, |
| "grad_norm": 12.437213897705078, |
| "learning_rate": 4.693563494886455e-05, |
| "loss": 0.0754, |
| "num_input_tokens_seen": 68480, |
| "step": 220 |
| }, |
| { |
| "epoch": 2.5, |
| "grad_norm": 0.005083396099507809, |
| "learning_rate": 4.669895349790502e-05, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 70048, |
| "step": 225 |
| }, |
| { |
| "epoch": 2.5, |
| "eval_loss": 0.03706792742013931, |
| "eval_runtime": 0.6527, |
| "eval_samples_per_second": 61.288, |
| "eval_steps_per_second": 15.322, |
| "num_input_tokens_seen": 70048, |
| "step": 225 |
| }, |
| { |
| "epoch": 2.5555555555555554, |
| "grad_norm": 0.0015420983545482159, |
| "learning_rate": 4.645411195795709e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 71680, |
| "step": 230 |
| }, |
| { |
| "epoch": 2.611111111111111, |
| "grad_norm": 0.006656634155660868, |
| "learning_rate": 4.620120240391065e-05, |
| "loss": 0.0414, |
| "num_input_tokens_seen": 73280, |
| "step": 235 |
| }, |
| { |
| "epoch": 2.6666666666666665, |
| "grad_norm": 0.0006671576993539929, |
| "learning_rate": 4.5940319944705736e-05, |
| "loss": 0.0007, |
| "num_input_tokens_seen": 74752, |
| "step": 240 |
| }, |
| { |
| "epoch": 2.7222222222222223, |
| "grad_norm": 0.0009212616132572293, |
| "learning_rate": 4.567156268756594e-05, |
| "loss": 0.0266, |
| "num_input_tokens_seen": 76288, |
| "step": 245 |
| }, |
| { |
| "epoch": 2.7777777777777777, |
| "grad_norm": 0.02251543290913105, |
| "learning_rate": 4.539503170110431e-05, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 77888, |
| "step": 250 |
| }, |
| { |
| "epoch": 2.8333333333333335, |
| "grad_norm": 0.16550374031066895, |
| "learning_rate": 4.5110830977315556e-05, |
| "loss": 0.0003, |
| "num_input_tokens_seen": 79456, |
| "step": 255 |
| }, |
| { |
| "epoch": 2.888888888888889, |
| "grad_norm": 0.00410516606643796, |
| "learning_rate": 4.4819067392468944e-05, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 81088, |
| "step": 260 |
| }, |
| { |
| "epoch": 2.9444444444444446, |
| "grad_norm": 0.0006467625498771667, |
| "learning_rate": 4.4519850666916484e-05, |
| "loss": 0.0191, |
| "num_input_tokens_seen": 82592, |
| "step": 265 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 1.5037493705749512, |
| "learning_rate": 4.4213293323831585e-05, |
| "loss": 0.0012, |
| "num_input_tokens_seen": 84192, |
| "step": 270 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.0342894122004509, |
| "eval_runtime": 0.6504, |
| "eval_samples_per_second": 61.5, |
| "eval_steps_per_second": 15.375, |
| "num_input_tokens_seen": 84192, |
| "step": 270 |
| }, |
| { |
| "epoch": 3.0555555555555554, |
| "grad_norm": 0.0008526512538082898, |
| "learning_rate": 4.38995106468937e-05, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 85696, |
| "step": 275 |
| }, |
| { |
| "epoch": 3.111111111111111, |
| "grad_norm": 0.007796874735504389, |
| "learning_rate": 4.357862063693486e-05, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 87296, |
| "step": 280 |
| }, |
| { |
| "epoch": 3.1666666666666665, |
| "grad_norm": 0.000615858007222414, |
| "learning_rate": 4.325074396756437e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 88832, |
| "step": 285 |
| }, |
| { |
| "epoch": 3.2222222222222223, |
| "grad_norm": 0.0012873270316049457, |
| "learning_rate": 4.2916003939788403e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 90368, |
| "step": 290 |
| }, |
| { |
| "epoch": 3.2777777777777777, |
| "grad_norm": 0.0019479271722957492, |
| "learning_rate": 4.257452643564155e-05, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 91968, |
| "step": 295 |
| }, |
| { |
| "epoch": 3.3333333333333335, |
| "grad_norm": 0.0017480638343840837, |
| "learning_rate": 4.22264398708477e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 93568, |
| "step": 300 |
| }, |
| { |
| "epoch": 3.388888888888889, |
| "grad_norm": 0.00035299535375088453, |
| "learning_rate": 4.1871875146528195e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 95168, |
| "step": 305 |
| }, |
| { |
| "epoch": 3.4444444444444446, |
| "grad_norm": 0.0007915609166957438, |
| "learning_rate": 4.1510965599975196e-05, |
| "loss": 0.0002, |
| "num_input_tokens_seen": 96704, |
| "step": 310 |
| }, |
| { |
| "epoch": 3.5, |
| "grad_norm": 0.001771848532371223, |
| "learning_rate": 4.114384695450906e-05, |
| "loss": 0.0002, |
| "num_input_tokens_seen": 98304, |
| "step": 315 |
| }, |
| { |
| "epoch": 3.5, |
| "eval_loss": 0.030501116067171097, |
| "eval_runtime": 0.6501, |
| "eval_samples_per_second": 61.533, |
| "eval_steps_per_second": 15.383, |
| "num_input_tokens_seen": 98304, |
| "step": 315 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "grad_norm": 0.0005711625562980771, |
| "learning_rate": 4.077065726843828e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 99840, |
| "step": 320 |
| }, |
| { |
| "epoch": 3.611111111111111, |
| "grad_norm": 0.005383889656513929, |
| "learning_rate": 4.039153688314145e-05, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 101376, |
| "step": 325 |
| }, |
| { |
| "epoch": 3.6666666666666665, |
| "grad_norm": 0.0005096430541016161, |
| "learning_rate": 4.000662837029062e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 102976, |
| "step": 330 |
| }, |
| { |
| "epoch": 3.7222222222222223, |
| "grad_norm": 0.002894325414672494, |
| "learning_rate": 3.961607647823583e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 104576, |
| "step": 335 |
| }, |
| { |
| "epoch": 3.7777777777777777, |
| "grad_norm": 0.004392088856548071, |
| "learning_rate": 3.9220028077571295e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 106112, |
| "step": 340 |
| }, |
| { |
| "epoch": 3.8333333333333335, |
| "grad_norm": 0.0030133503023535013, |
| "learning_rate": 3.881863210590332e-05, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 107712, |
| "step": 345 |
| }, |
| { |
| "epoch": 3.888888888888889, |
| "grad_norm": 0.000523722730576992, |
| "learning_rate": 3.841203951184095e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 109344, |
| "step": 350 |
| }, |
| { |
| "epoch": 3.9444444444444446, |
| "grad_norm": 0.0006850851932540536, |
| "learning_rate": 3.8000403198230387e-05, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 110944, |
| "step": 355 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.0012206757673993707, |
| "learning_rate": 3.75838779646545e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 112544, |
| "step": 360 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.030581694096326828, |
| "eval_runtime": 0.6501, |
| "eval_samples_per_second": 61.533, |
| "eval_steps_per_second": 15.383, |
| "num_input_tokens_seen": 112544, |
| "step": 360 |
| }, |
| { |
| "epoch": 4.055555555555555, |
| "grad_norm": 0.0006223992677405477, |
| "learning_rate": 3.7162620449219e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 114144, |
| "step": 365 |
| }, |
| { |
| "epoch": 4.111111111111111, |
| "grad_norm": 0.0020501227118074894, |
| "learning_rate": 3.673678906964727e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 115712, |
| "step": 370 |
| }, |
| { |
| "epoch": 4.166666666666667, |
| "grad_norm": 0.000992553774267435, |
| "learning_rate": 3.630654396370594e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 117312, |
| "step": 375 |
| }, |
| { |
| "epoch": 4.222222222222222, |
| "grad_norm": 0.007863037288188934, |
| "learning_rate": 3.5872046928983626e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 118848, |
| "step": 380 |
| }, |
| { |
| "epoch": 4.277777777777778, |
| "grad_norm": 0.0031219911761581898, |
| "learning_rate": 3.543346136204545e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 120416, |
| "step": 385 |
| }, |
| { |
| "epoch": 4.333333333333333, |
| "grad_norm": 0.0004113060422241688, |
| "learning_rate": 3.499095219698631e-05, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 122016, |
| "step": 390 |
| }, |
| { |
| "epoch": 4.388888888888889, |
| "grad_norm": 0.008797045797109604, |
| "learning_rate": 3.454468584340588e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 123584, |
| "step": 395 |
| }, |
| { |
| "epoch": 4.444444444444445, |
| "grad_norm": 0.0010580262169241905, |
| "learning_rate": 3.409483012382879e-05, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 125216, |
| "step": 400 |
| }, |
| { |
| "epoch": 4.5, |
| "grad_norm": 0.001766764558851719, |
| "learning_rate": 3.364155421059342e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 126784, |
| "step": 405 |
| }, |
| { |
| "epoch": 4.5, |
| "eval_loss": 0.030802279710769653, |
| "eval_runtime": 0.6455, |
| "eval_samples_per_second": 61.972, |
| "eval_steps_per_second": 15.493, |
| "num_input_tokens_seen": 126784, |
| "step": 405 |
| }, |
| { |
| "epoch": 4.555555555555555, |
| "grad_norm": 0.0004768424551002681, |
| "learning_rate": 3.318502856223311e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 128352, |
| "step": 410 |
| }, |
| { |
| "epoch": 4.611111111111111, |
| "grad_norm": 0.0003829093184322119, |
| "learning_rate": 3.272542485937369e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 129920, |
| "step": 415 |
| }, |
| { |
| "epoch": 4.666666666666667, |
| "grad_norm": 0.0007033026195131242, |
| "learning_rate": 3.2262915940171376e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 131488, |
| "step": 420 |
| }, |
| { |
| "epoch": 4.722222222222222, |
| "grad_norm": 0.010801518335938454, |
| "learning_rate": 3.1797675735315455e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 133056, |
| "step": 425 |
| }, |
| { |
| "epoch": 4.777777777777778, |
| "grad_norm": 0.000611345109064132, |
| "learning_rate": 3.132987920262005e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 134624, |
| "step": 430 |
| }, |
| { |
| "epoch": 4.833333333333333, |
| "grad_norm": 0.0005447659641504288, |
| "learning_rate": 3.085970226122962e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 136192, |
| "step": 435 |
| }, |
| { |
| "epoch": 4.888888888888889, |
| "grad_norm": 0.00023752034758217633, |
| "learning_rate": 3.0387321725463e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 137824, |
| "step": 440 |
| }, |
| { |
| "epoch": 4.944444444444445, |
| "grad_norm": 0.0006889897049404681, |
| "learning_rate": 2.9912915238320754e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 139392, |
| "step": 445 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.005286247935146093, |
| "learning_rate": 2.9436661204680882e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 140960, |
| "step": 450 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 0.032153837382793427, |
| "eval_runtime": 0.6438, |
| "eval_samples_per_second": 62.129, |
| "eval_steps_per_second": 15.532, |
| "num_input_tokens_seen": 140960, |
| "step": 450 |
| }, |
| { |
| "epoch": 5.055555555555555, |
| "grad_norm": 0.00041354564018547535, |
| "learning_rate": 2.8958738724208072e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 142560, |
| "step": 455 |
| }, |
| { |
| "epoch": 5.111111111111111, |
| "grad_norm": 0.00027760869124904275, |
| "learning_rate": 2.8479327524001636e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 144096, |
| "step": 460 |
| }, |
| { |
| "epoch": 5.166666666666667, |
| "grad_norm": 0.005650023929774761, |
| "learning_rate": 2.7998607891007495e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 145632, |
| "step": 465 |
| }, |
| { |
| "epoch": 5.222222222222222, |
| "grad_norm": 0.0003373593499418348, |
| "learning_rate": 2.7516760604219617e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 147232, |
| "step": 470 |
| }, |
| { |
| "epoch": 5.277777777777778, |
| "grad_norm": 0.0002709739492274821, |
| "learning_rate": 2.7033966866696457e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 148864, |
| "step": 475 |
| }, |
| { |
| "epoch": 5.333333333333333, |
| "grad_norm": 0.0003414044331293553, |
| "learning_rate": 2.6550408237417885e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 150432, |
| "step": 480 |
| }, |
| { |
| "epoch": 5.388888888888889, |
| "grad_norm": 0.0003046887868549675, |
| "learning_rate": 2.6066266563008267e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 152032, |
| "step": 485 |
| }, |
| { |
| "epoch": 5.444444444444445, |
| "grad_norm": 0.0003448141214903444, |
| "learning_rate": 2.5581723909351406e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 153600, |
| "step": 490 |
| }, |
| { |
| "epoch": 5.5, |
| "grad_norm": 0.001966169336810708, |
| "learning_rate": 2.5096962493123012e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 155200, |
| "step": 495 |
| }, |
| { |
| "epoch": 5.5, |
| "eval_loss": 0.03312332555651665, |
| "eval_runtime": 0.6521, |
| "eval_samples_per_second": 61.338, |
| "eval_steps_per_second": 15.334, |
| "num_input_tokens_seen": 155200, |
| "step": 495 |
| }, |
| { |
| "epoch": 5.555555555555555, |
| "grad_norm": 0.0001966792915482074, |
| "learning_rate": 2.461216461326642e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 156800, |
| "step": 500 |
| }, |
| { |
| "epoch": 5.611111111111111, |
| "grad_norm": 0.0006682435632683337, |
| "learning_rate": 2.4127512582437485e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 158336, |
| "step": 505 |
| }, |
| { |
| "epoch": 5.666666666666667, |
| "grad_norm": 0.00018110951350536197, |
| "learning_rate": 2.364318865844416e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 159904, |
| "step": 510 |
| }, |
| { |
| "epoch": 5.722222222222222, |
| "grad_norm": 0.000245875766268, |
| "learning_rate": 2.3159374975706884e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 161504, |
| "step": 515 |
| }, |
| { |
| "epoch": 5.777777777777778, |
| "grad_norm": 0.00044317811261862516, |
| "learning_rate": 2.2676253476765196e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 163008, |
| "step": 520 |
| }, |
| { |
| "epoch": 5.833333333333333, |
| "grad_norm": 0.0015351676847785711, |
| "learning_rate": 2.2194005843856636e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 164512, |
| "step": 525 |
| }, |
| { |
| "epoch": 5.888888888888889, |
| "grad_norm": 0.0007818671292625368, |
| "learning_rate": 2.1712813430593436e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 166080, |
| "step": 530 |
| }, |
| { |
| "epoch": 5.944444444444445, |
| "grad_norm": 0.007299670483916998, |
| "learning_rate": 2.1232857193762924e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 167680, |
| "step": 535 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 0.00026146473828703165, |
| "learning_rate": 2.0754317625276983e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 169216, |
| "step": 540 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 0.03473258018493652, |
| "eval_runtime": 0.6438, |
| "eval_samples_per_second": 62.136, |
| "eval_steps_per_second": 15.534, |
| "num_input_tokens_seen": 169216, |
| "step": 540 |
| }, |
| { |
| "epoch": 6.055555555555555, |
| "grad_norm": 0.0003463253378868103, |
| "learning_rate": 2.02773746842965e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 170784, |
| "step": 545 |
| }, |
| { |
| "epoch": 6.111111111111111, |
| "grad_norm": 0.00023809084086678922, |
| "learning_rate": 1.980220772955602e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 172352, |
| "step": 550 |
| }, |
| { |
| "epoch": 6.166666666666667, |
| "grad_norm": 0.0004561399109661579, |
| "learning_rate": 1.932899545191433e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 173920, |
| "step": 555 |
| }, |
| { |
| "epoch": 6.222222222222222, |
| "grad_norm": 0.0001660750131122768, |
| "learning_rate": 1.8857915807156092e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 175488, |
| "step": 560 |
| }, |
| { |
| "epoch": 6.277777777777778, |
| "grad_norm": 0.0003734901256393641, |
| "learning_rate": 1.838914594906995e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 177024, |
| "step": 565 |
| }, |
| { |
| "epoch": 6.333333333333333, |
| "grad_norm": 0.0010137949138879776, |
| "learning_rate": 1.792286216282824e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 178624, |
| "step": 570 |
| }, |
| { |
| "epoch": 6.388888888888889, |
| "grad_norm": 0.002834319369867444, |
| "learning_rate": 1.7459239798693364e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 180096, |
| "step": 575 |
| }, |
| { |
| "epoch": 6.444444444444445, |
| "grad_norm": 0.0011464239796623588, |
| "learning_rate": 1.699845320607571e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 181600, |
| "step": 580 |
| }, |
| { |
| "epoch": 6.5, |
| "grad_norm": 0.0004644300788640976, |
| "learning_rate": 1.6540675667967974e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 183232, |
| "step": 585 |
| }, |
| { |
| "epoch": 6.5, |
| "eval_loss": 0.03466637060046196, |
| "eval_runtime": 0.6521, |
| "eval_samples_per_second": 61.342, |
| "eval_steps_per_second": 15.335, |
| "num_input_tokens_seen": 183232, |
| "step": 585 |
| }, |
| { |
| "epoch": 6.555555555555555, |
| "grad_norm": 0.0002930274058599025, |
| "learning_rate": 1.60860793357805e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 184768, |
| "step": 590 |
| }, |
| { |
| "epoch": 6.611111111111111, |
| "grad_norm": 0.00017562598804943264, |
| "learning_rate": 1.56348351646022e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 186208, |
| "step": 595 |
| }, |
| { |
| "epoch": 6.666666666666667, |
| "grad_norm": 0.00043825848842971027, |
| "learning_rate": 1.5187112848911323e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 187776, |
| "step": 600 |
| }, |
| { |
| "epoch": 6.722222222222222, |
| "grad_norm": 0.0003627918194979429, |
| "learning_rate": 1.47430807587603e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 189344, |
| "step": 605 |
| }, |
| { |
| "epoch": 6.777777777777778, |
| "grad_norm": 0.0002561718283686787, |
| "learning_rate": 1.430290587645865e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 190912, |
| "step": 610 |
| }, |
| { |
| "epoch": 6.833333333333333, |
| "grad_norm": 0.0001283789169974625, |
| "learning_rate": 1.3866753733777765e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 192512, |
| "step": 615 |
| }, |
| { |
| "epoch": 6.888888888888889, |
| "grad_norm": 0.0008394067408517003, |
| "learning_rate": 1.343478834970121e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 194112, |
| "step": 620 |
| }, |
| { |
| "epoch": 6.944444444444445, |
| "grad_norm": 0.0042058066464960575, |
| "learning_rate": 1.3007172168743854e-05, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 195712, |
| "step": 625 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 0.0012665780959650874, |
| "learning_rate": 1.2584065999863102e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 197248, |
| "step": 630 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_loss": 0.03552483394742012, |
| "eval_runtime": 0.6459, |
| "eval_samples_per_second": 61.925, |
| "eval_steps_per_second": 15.481, |
| "num_input_tokens_seen": 197248, |
| "step": 630 |
| }, |
| { |
| "epoch": 7.055555555555555, |
| "grad_norm": 0.0005709715187549591, |
| "learning_rate": 1.2165628955985314e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 198784, |
| "step": 635 |
| }, |
| { |
| "epoch": 7.111111111111111, |
| "grad_norm": 0.001730955089442432, |
| "learning_rate": 1.175201839416988e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 200352, |
| "step": 640 |
| }, |
| { |
| "epoch": 7.166666666666667, |
| "grad_norm": 0.0001659291738178581, |
| "learning_rate": 1.1343389856433658e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 201856, |
| "step": 645 |
| }, |
| { |
| "epoch": 7.222222222222222, |
| "grad_norm": 0.00039199876482598484, |
| "learning_rate": 1.0939897011258001e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 203488, |
| "step": 650 |
| }, |
| { |
| "epoch": 7.277777777777778, |
| "grad_norm": 0.0002975580282509327, |
| "learning_rate": 1.0541691595800337e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 205056, |
| "step": 655 |
| }, |
| { |
| "epoch": 7.333333333333333, |
| "grad_norm": 0.00024556013522669673, |
| "learning_rate": 1.0148923358832022e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 206656, |
| "step": 660 |
| }, |
| { |
| "epoch": 7.388888888888889, |
| "grad_norm": 0.00021077270503155887, |
| "learning_rate": 9.761740004423927e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 208288, |
| "step": 665 |
| }, |
| { |
| "epoch": 7.444444444444445, |
| "grad_norm": 0.0007728920318186283, |
| "learning_rate": 9.380287136401e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 209856, |
| "step": 670 |
| }, |
| { |
| "epoch": 7.5, |
| "grad_norm": 0.0004005390510428697, |
| "learning_rate": 9.00470820358663e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 211424, |
| "step": 675 |
| }, |
| { |
| "epoch": 7.5, |
| "eval_loss": 0.04022820666432381, |
| "eval_runtime": 0.6486, |
| "eval_samples_per_second": 61.67, |
| "eval_steps_per_second": 15.418, |
| "num_input_tokens_seen": 211424, |
| "step": 675 |
| }, |
| { |
| "epoch": 7.555555555555555, |
| "grad_norm": 0.00018772909243125468, |
| "learning_rate": 8.635144445857406e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 212928, |
| "step": 680 |
| }, |
| { |
| "epoch": 7.611111111111111, |
| "grad_norm": 0.002668946050107479, |
| "learning_rate": 8.271734841028553e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 214496, |
| "step": 685 |
| }, |
| { |
| "epoch": 7.666666666666667, |
| "grad_norm": 0.002437896328046918, |
| "learning_rate": 7.914616052590071e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 216064, |
| "step": 690 |
| }, |
| { |
| "epoch": 7.722222222222222, |
| "grad_norm": 0.003041669959202409, |
| "learning_rate": 7.563922378313218e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 217600, |
| "step": 695 |
| }, |
| { |
| "epoch": 7.777777777777778, |
| "grad_norm": 0.0003606882819440216, |
| "learning_rate": 7.219785699746573e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 219136, |
| "step": 700 |
| }, |
| { |
| "epoch": 7.833333333333333, |
| "grad_norm": 0.0001433530997019261, |
| "learning_rate": 6.882335432620779e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 220704, |
| "step": 705 |
| }, |
| { |
| "epoch": 7.888888888888889, |
| "grad_norm": 0.00030211801640689373, |
| "learning_rate": 6.55169847818059e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 222272, |
| "step": 710 |
| }, |
| { |
| "epoch": 7.944444444444445, |
| "grad_norm": 0.0019358351128175855, |
| "learning_rate": 6.22799917546252e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 223872, |
| "step": 715 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 0.0008805663674138486, |
| "learning_rate": 5.9113592545359945e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 225440, |
| "step": 720 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 0.031073996797204018, |
| "eval_runtime": 0.6444, |
| "eval_samples_per_second": 62.073, |
| "eval_steps_per_second": 15.518, |
| "num_input_tokens_seen": 225440, |
| "step": 720 |
| }, |
| { |
| "epoch": 8.055555555555555, |
| "grad_norm": 0.001252516289241612, |
| "learning_rate": 5.601897790725643e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 226912, |
| "step": 725 |
| }, |
| { |
| "epoch": 8.11111111111111, |
| "grad_norm": 0.0020089331082999706, |
| "learning_rate": 5.299731159831953e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 228512, |
| "step": 730 |
| }, |
| { |
| "epoch": 8.166666666666666, |
| "grad_norm": 0.003648359328508377, |
| "learning_rate": 5.004972994367102e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 230080, |
| "step": 735 |
| }, |
| { |
| "epoch": 8.222222222222221, |
| "grad_norm": 0.0001459253835491836, |
| "learning_rate": 4.7177341408224e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 231616, |
| "step": 740 |
| }, |
| { |
| "epoch": 8.277777777777779, |
| "grad_norm": 0.00015077361604198813, |
| "learning_rate": 4.438122617983443e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 233184, |
| "step": 745 |
| }, |
| { |
| "epoch": 8.333333333333334, |
| "grad_norm": 0.00017217070853803307, |
| "learning_rate": 4.166243576308712e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 234688, |
| "step": 750 |
| }, |
| { |
| "epoch": 8.38888888888889, |
| "grad_norm": 0.00033677066676318645, |
| "learning_rate": 3.9021992583867325e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 236256, |
| "step": 755 |
| }, |
| { |
| "epoch": 8.444444444444445, |
| "grad_norm": 0.00042958115227520466, |
| "learning_rate": 3.6460889604868626e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 237856, |
| "step": 760 |
| }, |
| { |
| "epoch": 8.5, |
| "grad_norm": 0.0008320572669617832, |
| "learning_rate": 3.398008995217988e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 239392, |
| "step": 765 |
| }, |
| { |
| "epoch": 8.5, |
| "eval_loss": 0.03386698663234711, |
| "eval_runtime": 0.6486, |
| "eval_samples_per_second": 61.667, |
| "eval_steps_per_second": 15.417, |
| "num_input_tokens_seen": 239392, |
| "step": 765 |
| }, |
| { |
| "epoch": 8.555555555555555, |
| "grad_norm": 0.0004391979018691927, |
| "learning_rate": 3.158052655309332e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 240960, |
| "step": 770 |
| }, |
| { |
| "epoch": 8.61111111111111, |
| "grad_norm": 0.00025793720851652324, |
| "learning_rate": 2.9263101785268254e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 242496, |
| "step": 775 |
| }, |
| { |
| "epoch": 8.666666666666666, |
| "grad_norm": 0.003735892241820693, |
| "learning_rate": 2.7028687137384267e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 244064, |
| "step": 780 |
| }, |
| { |
| "epoch": 8.722222222222221, |
| "grad_norm": 0.00047287100460380316, |
| "learning_rate": 2.487812288140945e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 245664, |
| "step": 785 |
| }, |
| { |
| "epoch": 8.777777777777779, |
| "grad_norm": 0.0001731937809381634, |
| "learning_rate": 2.281221775660894e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 247264, |
| "step": 790 |
| }, |
| { |
| "epoch": 8.833333333333334, |
| "grad_norm": 0.00022953731240704656, |
| "learning_rate": 2.0831748665410765e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 248832, |
| "step": 795 |
| }, |
| { |
| "epoch": 8.88888888888889, |
| "grad_norm": 0.00018339429516345263, |
| "learning_rate": 1.893746038124497e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 250432, |
| "step": 800 |
| }, |
| { |
| "epoch": 8.944444444444445, |
| "grad_norm": 0.002470877021551132, |
| "learning_rate": 1.713006526846439e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 252064, |
| "step": 805 |
| }, |
| { |
| "epoch": 9.0, |
| "grad_norm": 0.00016042040078900754, |
| "learning_rate": 1.541024301445404e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 253632, |
| "step": 810 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_loss": 0.03408951312303543, |
| "eval_runtime": 0.651, |
| "eval_samples_per_second": 61.447, |
| "eval_steps_per_second": 15.362, |
| "num_input_tokens_seen": 253632, |
| "step": 810 |
| }, |
| { |
| "epoch": 9.055555555555555, |
| "grad_norm": 0.003850726643577218, |
| "learning_rate": 1.3778640374027985e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 255232, |
| "step": 815 |
| }, |
| { |
| "epoch": 9.11111111111111, |
| "grad_norm": 0.0004153129702899605, |
| "learning_rate": 1.2235870926211619e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 256800, |
| "step": 820 |
| }, |
| { |
| "epoch": 9.166666666666666, |
| "grad_norm": 0.00011726022057700902, |
| "learning_rate": 1.0782514843499653e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 258368, |
| "step": 825 |
| }, |
| { |
| "epoch": 9.222222222222221, |
| "grad_norm": 0.002642204985022545, |
| "learning_rate": 9.419118673676924e-07, |
| "loss": 0.0, |
| "num_input_tokens_seen": 259872, |
| "step": 830 |
| }, |
| { |
| "epoch": 9.277777777777779, |
| "grad_norm": 0.00014779038610868156, |
| "learning_rate": 8.146195134284052e-07, |
| "loss": 0.0, |
| "num_input_tokens_seen": 261376, |
| "step": 835 |
| }, |
| { |
| "epoch": 9.333333333333334, |
| "grad_norm": 0.002704200567677617, |
| "learning_rate": 6.964222919805391e-07, |
| "loss": 0.0, |
| "num_input_tokens_seen": 262944, |
| "step": 840 |
| }, |
| { |
| "epoch": 9.38888888888889, |
| "grad_norm": 0.0003720213717315346, |
| "learning_rate": 5.87364652165176e-07, |
| "loss": 0.0, |
| "num_input_tokens_seen": 264544, |
| "step": 845 |
| }, |
| { |
| "epoch": 9.444444444444445, |
| "grad_norm": 0.0018081723246723413, |
| "learning_rate": 4.874876061005173e-07, |
| "loss": 0.0, |
| "num_input_tokens_seen": 266080, |
| "step": 850 |
| }, |
| { |
| "epoch": 9.5, |
| "grad_norm": 0.00048440590035170317, |
| "learning_rate": 3.9682871345891883e-07, |
| "loss": 0.0, |
| "num_input_tokens_seen": 267680, |
| "step": 855 |
| }, |
| { |
| "epoch": 9.5, |
| "eval_loss": 0.03737674281001091, |
| "eval_runtime": 0.65, |
| "eval_samples_per_second": 61.539, |
| "eval_steps_per_second": 15.385, |
| "num_input_tokens_seen": 267680, |
| "step": 855 |
| }, |
| { |
| "epoch": 9.555555555555555, |
| "grad_norm": 0.002349090063944459, |
| "learning_rate": 3.1542206734221924e-07, |
| "loss": 0.0, |
| "num_input_tokens_seen": 269280, |
| "step": 860 |
| }, |
| { |
| "epoch": 9.61111111111111, |
| "grad_norm": 0.0005039243842475116, |
| "learning_rate": 2.4329828146074095e-07, |
| "loss": 0.0, |
| "num_input_tokens_seen": 270912, |
| "step": 865 |
| }, |
| { |
| "epoch": 9.666666666666666, |
| "grad_norm": 0.00017508874589111656, |
| "learning_rate": 1.8048447862070718e-07, |
| "loss": 0.0, |
| "num_input_tokens_seen": 272512, |
| "step": 870 |
| }, |
| { |
| "epoch": 9.722222222222221, |
| "grad_norm": 0.00020758512255270034, |
| "learning_rate": 1.2700428052447033e-07, |
| "loss": 0.0, |
| "num_input_tokens_seen": 274048, |
| "step": 875 |
| }, |
| { |
| "epoch": 9.777777777777779, |
| "grad_norm": 0.006015616003423929, |
| "learning_rate": 8.28777988873486e-08, |
| "loss": 0.0, |
| "num_input_tokens_seen": 275648, |
| "step": 880 |
| }, |
| { |
| "epoch": 9.833333333333334, |
| "grad_norm": 0.004514203406870365, |
| "learning_rate": 4.8121627874450625e-08, |
| "loss": 0.0, |
| "num_input_tokens_seen": 277248, |
| "step": 885 |
| }, |
| { |
| "epoch": 9.88888888888889, |
| "grad_norm": 0.00042101097642444074, |
| "learning_rate": 2.2748837860270267e-08, |
| "loss": 0.0, |
| "num_input_tokens_seen": 278816, |
| "step": 890 |
| }, |
| { |
| "epoch": 9.944444444444445, |
| "grad_norm": 0.000147135928273201, |
| "learning_rate": 6.768970513457151e-09, |
| "loss": 0.0, |
| "num_input_tokens_seen": 280416, |
| "step": 895 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 0.003430998418480158, |
| "learning_rate": 1.8803520859811406e-10, |
| "loss": 0.0, |
| "num_input_tokens_seen": 281984, |
| "step": 900 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_loss": 0.04089144617319107, |
| "eval_runtime": 0.6561, |
| "eval_samples_per_second": 60.966, |
| "eval_steps_per_second": 15.241, |
| "num_input_tokens_seen": 281984, |
| "step": 900 |
| }, |
| { |
| "epoch": 10.0, |
| "num_input_tokens_seen": 281984, |
| "step": 900, |
| "total_flos": 1.2722449331257344e+16, |
| "train_loss": 0.029389885180409893, |
| "train_runtime": 220.5131, |
| "train_samples_per_second": 16.326, |
| "train_steps_per_second": 4.081 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 900, |
| "num_input_tokens_seen": 281984, |
| "num_train_epochs": 10, |
| "save_steps": 45, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.2722449331257344e+16, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
