| { |
| "best_global_step": 180, |
| "best_metric": 0.04244411736726761, |
| "best_model_checkpoint": "saves/lora/llama-3-8b-instruct/train_copa_1753094178/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": 6.86073112487793, |
| "learning_rate": 2.2222222222222225e-06, |
| "loss": 0.5525, |
| "num_input_tokens_seen": 1536, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.1111111111111111, |
| "grad_norm": 7.967911243438721, |
| "learning_rate": 5e-06, |
| "loss": 0.6403, |
| "num_input_tokens_seen": 3168, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.16666666666666666, |
| "grad_norm": 8.87765884399414, |
| "learning_rate": 7.777777777777777e-06, |
| "loss": 0.6012, |
| "num_input_tokens_seen": 4736, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.2222222222222222, |
| "grad_norm": 6.550626754760742, |
| "learning_rate": 1.0555555555555555e-05, |
| "loss": 0.4236, |
| "num_input_tokens_seen": 6304, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.2777777777777778, |
| "grad_norm": 2.794219493865967, |
| "learning_rate": 1.3333333333333333e-05, |
| "loss": 0.147, |
| "num_input_tokens_seen": 7840, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.3333333333333333, |
| "grad_norm": 0.07369916886091232, |
| "learning_rate": 1.6111111111111115e-05, |
| "loss": 0.0189, |
| "num_input_tokens_seen": 9408, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.3888888888888889, |
| "grad_norm": 0.0047037783078849316, |
| "learning_rate": 1.888888888888889e-05, |
| "loss": 0.1336, |
| "num_input_tokens_seen": 10912, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.4444444444444444, |
| "grad_norm": 0.06288556754589081, |
| "learning_rate": 2.1666666666666667e-05, |
| "loss": 0.0597, |
| "num_input_tokens_seen": 12448, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 3.0885512828826904, |
| "learning_rate": 2.4444444444444445e-05, |
| "loss": 0.0489, |
| "num_input_tokens_seen": 14016, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.5, |
| "eval_loss": 0.15566711127758026, |
| "eval_runtime": 0.6268, |
| "eval_samples_per_second": 63.812, |
| "eval_steps_per_second": 15.953, |
| "num_input_tokens_seen": 14016, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.5555555555555556, |
| "grad_norm": 3.646979808807373, |
| "learning_rate": 2.7222222222222223e-05, |
| "loss": 0.1599, |
| "num_input_tokens_seen": 15584, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.6111111111111112, |
| "grad_norm": 0.1446634978055954, |
| "learning_rate": 3e-05, |
| "loss": 0.1532, |
| "num_input_tokens_seen": 17184, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.6666666666666666, |
| "grad_norm": 6.1540422439575195, |
| "learning_rate": 3.277777777777778e-05, |
| "loss": 0.0488, |
| "num_input_tokens_seen": 18752, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.7222222222222222, |
| "grad_norm": 5.831511497497559, |
| "learning_rate": 3.555555555555556e-05, |
| "loss": 0.1306, |
| "num_input_tokens_seen": 20352, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.7777777777777778, |
| "grad_norm": 0.42319995164871216, |
| "learning_rate": 3.8333333333333334e-05, |
| "loss": 0.0936, |
| "num_input_tokens_seen": 21952, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.8333333333333334, |
| "grad_norm": 3.3543989658355713, |
| "learning_rate": 4.111111111111111e-05, |
| "loss": 0.0789, |
| "num_input_tokens_seen": 23456, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.8888888888888888, |
| "grad_norm": 0.27214357256889343, |
| "learning_rate": 4.388888888888889e-05, |
| "loss": 0.1988, |
| "num_input_tokens_seen": 25056, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.9444444444444444, |
| "grad_norm": 0.26215964555740356, |
| "learning_rate": 4.666666666666667e-05, |
| "loss": 0.0413, |
| "num_input_tokens_seen": 26560, |
| "step": 85 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.06982027739286423, |
| "learning_rate": 4.9444444444444446e-05, |
| "loss": 0.2106, |
| "num_input_tokens_seen": 28096, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.08737044036388397, |
| "eval_runtime": 0.6265, |
| "eval_samples_per_second": 63.85, |
| "eval_steps_per_second": 15.963, |
| "num_input_tokens_seen": 28096, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.0555555555555556, |
| "grad_norm": 3.8017995357513428, |
| "learning_rate": 4.9996991493233693e-05, |
| "loss": 0.1241, |
| "num_input_tokens_seen": 29696, |
| "step": 95 |
| }, |
| { |
| "epoch": 1.1111111111111112, |
| "grad_norm": 0.4133705496788025, |
| "learning_rate": 4.99847706754774e-05, |
| "loss": 0.0412, |
| "num_input_tokens_seen": 31232, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.1666666666666667, |
| "grad_norm": 0.5425562858581543, |
| "learning_rate": 4.9963154107272295e-05, |
| "loss": 0.025, |
| "num_input_tokens_seen": 32768, |
| "step": 105 |
| }, |
| { |
| "epoch": 1.2222222222222223, |
| "grad_norm": 0.0055565787479281425, |
| "learning_rate": 4.993214991772563e-05, |
| "loss": 0.0024, |
| "num_input_tokens_seen": 34304, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.2777777777777777, |
| "grad_norm": 0.10500931739807129, |
| "learning_rate": 4.989176976624511e-05, |
| "loss": 0.0087, |
| "num_input_tokens_seen": 35872, |
| "step": 115 |
| }, |
| { |
| "epoch": 1.3333333333333333, |
| "grad_norm": 0.2568105161190033, |
| "learning_rate": 4.9842028838154285e-05, |
| "loss": 0.029, |
| "num_input_tokens_seen": 37408, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.3888888888888888, |
| "grad_norm": 5.573173522949219, |
| "learning_rate": 4.978294583898196e-05, |
| "loss": 0.064, |
| "num_input_tokens_seen": 38976, |
| "step": 125 |
| }, |
| { |
| "epoch": 1.4444444444444444, |
| "grad_norm": 0.014998064376413822, |
| "learning_rate": 4.971454298742779e-05, |
| "loss": 0.0551, |
| "num_input_tokens_seen": 40576, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.5, |
| "grad_norm": 0.017064576968550682, |
| "learning_rate": 4.963684600700679e-05, |
| "loss": 0.0645, |
| "num_input_tokens_seen": 42144, |
| "step": 135 |
| }, |
| { |
| "epoch": 1.5, |
| "eval_loss": 0.10639457404613495, |
| "eval_runtime": 0.6457, |
| "eval_samples_per_second": 61.944, |
| "eval_steps_per_second": 15.486, |
| "num_input_tokens_seen": 42144, |
| "step": 135 |
| }, |
| { |
| "epoch": 1.5555555555555556, |
| "grad_norm": 0.008660639636218548, |
| "learning_rate": 4.9549884116375714e-05, |
| "loss": 0.013, |
| "num_input_tokens_seen": 43680, |
| "step": 140 |
| }, |
| { |
| "epoch": 1.6111111111111112, |
| "grad_norm": 0.010728226974606514, |
| "learning_rate": 4.9453690018345144e-05, |
| "loss": 0.1366, |
| "num_input_tokens_seen": 45248, |
| "step": 145 |
| }, |
| { |
| "epoch": 1.6666666666666665, |
| "grad_norm": 0.004510143306106329, |
| "learning_rate": 4.934829988758131e-05, |
| "loss": 0.0008, |
| "num_input_tokens_seen": 46816, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.7222222222222223, |
| "grad_norm": 5.634449005126953, |
| "learning_rate": 4.923375335700223e-05, |
| "loss": 0.1196, |
| "num_input_tokens_seen": 48384, |
| "step": 155 |
| }, |
| { |
| "epoch": 1.7777777777777777, |
| "grad_norm": 0.0038581849075853825, |
| "learning_rate": 4.9110093502873476e-05, |
| "loss": 0.0026, |
| "num_input_tokens_seen": 49952, |
| "step": 160 |
| }, |
| { |
| "epoch": 1.8333333333333335, |
| "grad_norm": 0.0023771314881742, |
| "learning_rate": 4.897736682860885e-05, |
| "loss": 0.0112, |
| "num_input_tokens_seen": 51520, |
| "step": 165 |
| }, |
| { |
| "epoch": 1.8888888888888888, |
| "grad_norm": 0.10062141716480255, |
| "learning_rate": 4.883562324728241e-05, |
| "loss": 0.0257, |
| "num_input_tokens_seen": 53024, |
| "step": 170 |
| }, |
| { |
| "epoch": 1.9444444444444444, |
| "grad_norm": 5.290853023529053, |
| "learning_rate": 4.868491606285823e-05, |
| "loss": 0.0341, |
| "num_input_tokens_seen": 54592, |
| "step": 175 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 1.3561640977859497, |
| "learning_rate": 4.8525301950144894e-05, |
| "loss": 0.1351, |
| "num_input_tokens_seen": 56128, |
| "step": 180 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.04244411736726761, |
| "eval_runtime": 0.644, |
| "eval_samples_per_second": 62.113, |
| "eval_steps_per_second": 15.528, |
| "num_input_tokens_seen": 56128, |
| "step": 180 |
| }, |
| { |
| "epoch": 2.0555555555555554, |
| "grad_norm": 0.024022074416279793, |
| "learning_rate": 4.835684093348244e-05, |
| "loss": 0.0006, |
| "num_input_tokens_seen": 57696, |
| "step": 185 |
| }, |
| { |
| "epoch": 2.111111111111111, |
| "grad_norm": 0.007055311929434538, |
| "learning_rate": 4.817959636416969e-05, |
| "loss": 0.0004, |
| "num_input_tokens_seen": 59264, |
| "step": 190 |
| }, |
| { |
| "epoch": 2.1666666666666665, |
| "grad_norm": 0.002355724573135376, |
| "learning_rate": 4.7993634896640394e-05, |
| "loss": 0.0005, |
| "num_input_tokens_seen": 60864, |
| "step": 195 |
| }, |
| { |
| "epoch": 2.2222222222222223, |
| "grad_norm": 0.15802322328090668, |
| "learning_rate": 4.779902646339722e-05, |
| "loss": 0.0011, |
| "num_input_tokens_seen": 62464, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.2777777777777777, |
| "grad_norm": 1.6008630990982056, |
| "learning_rate": 4.759584424871302e-05, |
| "loss": 0.0133, |
| "num_input_tokens_seen": 64032, |
| "step": 205 |
| }, |
| { |
| "epoch": 2.3333333333333335, |
| "grad_norm": 0.001915144152007997, |
| "learning_rate": 4.7384164661109176e-05, |
| "loss": 0.0005, |
| "num_input_tokens_seen": 65568, |
| "step": 210 |
| }, |
| { |
| "epoch": 2.388888888888889, |
| "grad_norm": 0.0661412924528122, |
| "learning_rate": 4.7164067304621536e-05, |
| "loss": 0.0009, |
| "num_input_tokens_seen": 67104, |
| "step": 215 |
| }, |
| { |
| "epoch": 2.4444444444444446, |
| "grad_norm": 0.0029477274511009455, |
| "learning_rate": 4.693563494886455e-05, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 68704, |
| "step": 220 |
| }, |
| { |
| "epoch": 2.5, |
| "grad_norm": 0.02449549362063408, |
| "learning_rate": 4.669895349790502e-05, |
| "loss": 0.0005, |
| "num_input_tokens_seen": 70272, |
| "step": 225 |
| }, |
| { |
| "epoch": 2.5, |
| "eval_loss": 0.060432981699705124, |
| "eval_runtime": 0.6415, |
| "eval_samples_per_second": 62.354, |
| "eval_steps_per_second": 15.589, |
| "num_input_tokens_seen": 70272, |
| "step": 225 |
| }, |
| { |
| "epoch": 2.5555555555555554, |
| "grad_norm": 0.1013827696442604, |
| "learning_rate": 4.645411195795709e-05, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 71808, |
| "step": 230 |
| }, |
| { |
| "epoch": 2.611111111111111, |
| "grad_norm": 0.023388486355543137, |
| "learning_rate": 4.620120240391065e-05, |
| "loss": 0.0398, |
| "num_input_tokens_seen": 73408, |
| "step": 235 |
| }, |
| { |
| "epoch": 2.6666666666666665, |
| "grad_norm": 0.6744654774665833, |
| "learning_rate": 4.5940319944705736e-05, |
| "loss": 0.0031, |
| "num_input_tokens_seen": 74912, |
| "step": 240 |
| }, |
| { |
| "epoch": 2.7222222222222223, |
| "grad_norm": 0.9937024116516113, |
| "learning_rate": 4.567156268756594e-05, |
| "loss": 0.0007, |
| "num_input_tokens_seen": 76544, |
| "step": 245 |
| }, |
| { |
| "epoch": 2.7777777777777777, |
| "grad_norm": 0.004736816510558128, |
| "learning_rate": 4.539503170110431e-05, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 78112, |
| "step": 250 |
| }, |
| { |
| "epoch": 2.8333333333333335, |
| "grad_norm": 0.001398882013745606, |
| "learning_rate": 4.5110830977315556e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 79712, |
| "step": 255 |
| }, |
| { |
| "epoch": 2.888888888888889, |
| "grad_norm": 0.003790005575865507, |
| "learning_rate": 4.4819067392468944e-05, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 81280, |
| "step": 260 |
| }, |
| { |
| "epoch": 2.9444444444444446, |
| "grad_norm": 0.0022235652431845665, |
| "learning_rate": 4.4519850666916484e-05, |
| "loss": 0.047, |
| "num_input_tokens_seen": 82848, |
| "step": 265 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.001825512619689107, |
| "learning_rate": 4.4213293323831585e-05, |
| "loss": 0.0005, |
| "num_input_tokens_seen": 84352, |
| "step": 270 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.047240711748600006, |
| "eval_runtime": 0.6479, |
| "eval_samples_per_second": 61.737, |
| "eval_steps_per_second": 15.434, |
| "num_input_tokens_seen": 84352, |
| "step": 270 |
| }, |
| { |
| "epoch": 3.0555555555555554, |
| "grad_norm": 0.0017462774412706494, |
| "learning_rate": 4.38995106468937e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 85920, |
| "step": 275 |
| }, |
| { |
| "epoch": 3.111111111111111, |
| "grad_norm": 0.005454895552247763, |
| "learning_rate": 4.357862063693486e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 87520, |
| "step": 280 |
| }, |
| { |
| "epoch": 3.1666666666666665, |
| "grad_norm": 0.002084760693833232, |
| "learning_rate": 4.325074396756437e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 89088, |
| "step": 285 |
| }, |
| { |
| "epoch": 3.2222222222222223, |
| "grad_norm": 0.0011266639921814203, |
| "learning_rate": 4.2916003939788403e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 90688, |
| "step": 290 |
| }, |
| { |
| "epoch": 3.2777777777777777, |
| "grad_norm": 0.0031179827637970448, |
| "learning_rate": 4.257452643564155e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 92160, |
| "step": 295 |
| }, |
| { |
| "epoch": 3.3333333333333335, |
| "grad_norm": 0.002318532206118107, |
| "learning_rate": 4.22264398708477e-05, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 93760, |
| "step": 300 |
| }, |
| { |
| "epoch": 3.388888888888889, |
| "grad_norm": 0.0009932003449648619, |
| "learning_rate": 4.1871875146528195e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 95360, |
| "step": 305 |
| }, |
| { |
| "epoch": 3.4444444444444446, |
| "grad_norm": 0.0008774871821515262, |
| "learning_rate": 4.1510965599975196e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 96928, |
| "step": 310 |
| }, |
| { |
| "epoch": 3.5, |
| "grad_norm": 0.0006412393413484097, |
| "learning_rate": 4.114384695450906e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 98464, |
| "step": 315 |
| }, |
| { |
| "epoch": 3.5, |
| "eval_loss": 0.04881405085325241, |
| "eval_runtime": 0.652, |
| "eval_samples_per_second": 61.346, |
| "eval_steps_per_second": 15.337, |
| "num_input_tokens_seen": 98464, |
| "step": 315 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "grad_norm": 0.0077088987454771996, |
| "learning_rate": 4.077065726843828e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 100064, |
| "step": 320 |
| }, |
| { |
| "epoch": 3.611111111111111, |
| "grad_norm": 0.0006322628469206393, |
| "learning_rate": 4.039153688314145e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 101600, |
| "step": 325 |
| }, |
| { |
| "epoch": 3.6666666666666665, |
| "grad_norm": 0.0006218113121576607, |
| "learning_rate": 4.000662837029062e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 103200, |
| "step": 330 |
| }, |
| { |
| "epoch": 3.7222222222222223, |
| "grad_norm": 0.0009763144189491868, |
| "learning_rate": 3.961607647823583e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 104768, |
| "step": 335 |
| }, |
| { |
| "epoch": 3.7777777777777777, |
| "grad_norm": 0.0009275155025534332, |
| "learning_rate": 3.9220028077571295e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 106304, |
| "step": 340 |
| }, |
| { |
| "epoch": 3.8333333333333335, |
| "grad_norm": 0.0008345640380866826, |
| "learning_rate": 3.881863210590332e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 107904, |
| "step": 345 |
| }, |
| { |
| "epoch": 3.888888888888889, |
| "grad_norm": 0.0004373028059490025, |
| "learning_rate": 3.841203951184095e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 109408, |
| "step": 350 |
| }, |
| { |
| "epoch": 3.9444444444444446, |
| "grad_norm": 0.016169369220733643, |
| "learning_rate": 3.8000403198230387e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 111008, |
| "step": 355 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.0005110779893584549, |
| "learning_rate": 3.75838779646545e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 112576, |
| "step": 360 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.05044294521212578, |
| "eval_runtime": 0.6488, |
| "eval_samples_per_second": 61.652, |
| "eval_steps_per_second": 15.413, |
| "num_input_tokens_seen": 112576, |
| "step": 360 |
| }, |
| { |
| "epoch": 4.055555555555555, |
| "grad_norm": 0.011152246035635471, |
| "learning_rate": 3.7162620449219e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 114144, |
| "step": 365 |
| }, |
| { |
| "epoch": 4.111111111111111, |
| "grad_norm": 0.0028684206772595644, |
| "learning_rate": 3.673678906964727e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 115712, |
| "step": 370 |
| }, |
| { |
| "epoch": 4.166666666666667, |
| "grad_norm": 0.0013409198727458715, |
| "learning_rate": 3.630654396370594e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 117216, |
| "step": 375 |
| }, |
| { |
| "epoch": 4.222222222222222, |
| "grad_norm": 0.0006328498711809516, |
| "learning_rate": 3.5872046928983626e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 118816, |
| "step": 380 |
| }, |
| { |
| "epoch": 4.277777777777778, |
| "grad_norm": 0.006735009141266346, |
| "learning_rate": 3.543346136204545e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 120352, |
| "step": 385 |
| }, |
| { |
| "epoch": 4.333333333333333, |
| "grad_norm": 0.0004646920715458691, |
| "learning_rate": 3.499095219698631e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 121920, |
| "step": 390 |
| }, |
| { |
| "epoch": 4.388888888888889, |
| "grad_norm": 0.0004425598890520632, |
| "learning_rate": 3.454468584340588e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 123456, |
| "step": 395 |
| }, |
| { |
| "epoch": 4.444444444444445, |
| "grad_norm": 0.0006759735988453031, |
| "learning_rate": 3.409483012382879e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 125056, |
| "step": 400 |
| }, |
| { |
| "epoch": 4.5, |
| "grad_norm": 0.00042739365017041564, |
| "learning_rate": 3.364155421059342e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 126624, |
| "step": 405 |
| }, |
| { |
| "epoch": 4.5, |
| "eval_loss": 0.05202624946832657, |
| "eval_runtime": 0.6449, |
| "eval_samples_per_second": 62.029, |
| "eval_steps_per_second": 15.507, |
| "num_input_tokens_seen": 126624, |
| "step": 405 |
| }, |
| { |
| "epoch": 4.555555555555555, |
| "grad_norm": 0.0029732573311775923, |
| "learning_rate": 3.318502856223311e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 128224, |
| "step": 410 |
| }, |
| { |
| "epoch": 4.611111111111111, |
| "grad_norm": 0.002195323584601283, |
| "learning_rate": 3.272542485937369e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 129728, |
| "step": 415 |
| }, |
| { |
| "epoch": 4.666666666666667, |
| "grad_norm": 0.0005148355267010629, |
| "learning_rate": 3.2262915940171376e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 131328, |
| "step": 420 |
| }, |
| { |
| "epoch": 4.722222222222222, |
| "grad_norm": 0.00025692099006846547, |
| "learning_rate": 3.1797675735315455e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 132896, |
| "step": 425 |
| }, |
| { |
| "epoch": 4.777777777777778, |
| "grad_norm": 0.0004263764712959528, |
| "learning_rate": 3.132987920262005e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 134496, |
| "step": 430 |
| }, |
| { |
| "epoch": 4.833333333333333, |
| "grad_norm": 0.0007016006857156754, |
| "learning_rate": 3.085970226122962e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 136064, |
| "step": 435 |
| }, |
| { |
| "epoch": 4.888888888888889, |
| "grad_norm": 0.0003838407574221492, |
| "learning_rate": 3.0387321725463e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 137664, |
| "step": 440 |
| }, |
| { |
| "epoch": 4.944444444444445, |
| "grad_norm": 0.0003138036991003901, |
| "learning_rate": 2.9912915238320754e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 139232, |
| "step": 445 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.0018180576153099537, |
| "learning_rate": 2.9436661204680882e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 140832, |
| "step": 450 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 0.050029732286930084, |
| "eval_runtime": 0.6427, |
| "eval_samples_per_second": 62.237, |
| "eval_steps_per_second": 15.559, |
| "num_input_tokens_seen": 140832, |
| "step": 450 |
| }, |
| { |
| "epoch": 5.055555555555555, |
| "grad_norm": 0.0005034798523411155, |
| "learning_rate": 2.8958738724208072e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 142368, |
| "step": 455 |
| }, |
| { |
| "epoch": 5.111111111111111, |
| "grad_norm": 0.0013201722176745534, |
| "learning_rate": 2.8479327524001636e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 144000, |
| "step": 460 |
| }, |
| { |
| "epoch": 5.166666666666667, |
| "grad_norm": 0.00037845983752049506, |
| "learning_rate": 2.7998607891007495e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 145632, |
| "step": 465 |
| }, |
| { |
| "epoch": 5.222222222222222, |
| "grad_norm": 0.011155317537486553, |
| "learning_rate": 2.7516760604219617e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 147168, |
| "step": 470 |
| }, |
| { |
| "epoch": 5.277777777777778, |
| "grad_norm": 0.0034261615946888924, |
| "learning_rate": 2.7033966866696457e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 148736, |
| "step": 475 |
| }, |
| { |
| "epoch": 5.333333333333333, |
| "grad_norm": 0.00042451301123946905, |
| "learning_rate": 2.6550408237417885e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 150304, |
| "step": 480 |
| }, |
| { |
| "epoch": 5.388888888888889, |
| "grad_norm": 0.004805035889148712, |
| "learning_rate": 2.6066266563008267e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 151872, |
| "step": 485 |
| }, |
| { |
| "epoch": 5.444444444444445, |
| "grad_norm": 0.00027324308757670224, |
| "learning_rate": 2.5581723909351406e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 153472, |
| "step": 490 |
| }, |
| { |
| "epoch": 5.5, |
| "grad_norm": 0.0004290080105420202, |
| "learning_rate": 2.5096962493123012e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 154976, |
| "step": 495 |
| }, |
| { |
| "epoch": 5.5, |
| "eval_loss": 0.04972325265407562, |
| "eval_runtime": 0.6384, |
| "eval_samples_per_second": 62.658, |
| "eval_steps_per_second": 15.664, |
| "num_input_tokens_seen": 154976, |
| "step": 495 |
| }, |
| { |
| "epoch": 5.555555555555555, |
| "grad_norm": 0.0024737718049436808, |
| "learning_rate": 2.461216461326642e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 156544, |
| "step": 500 |
| }, |
| { |
| "epoch": 5.611111111111111, |
| "grad_norm": 0.00022492738207802176, |
| "learning_rate": 2.4127512582437485e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 158112, |
| "step": 505 |
| }, |
| { |
| "epoch": 5.666666666666667, |
| "grad_norm": 0.0005133277154527605, |
| "learning_rate": 2.364318865844416e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 159680, |
| "step": 510 |
| }, |
| { |
| "epoch": 5.722222222222222, |
| "grad_norm": 0.0005640820600092411, |
| "learning_rate": 2.3159374975706884e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 161312, |
| "step": 515 |
| }, |
| { |
| "epoch": 5.777777777777778, |
| "grad_norm": 0.00028420338639989495, |
| "learning_rate": 2.2676253476765196e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 162880, |
| "step": 520 |
| }, |
| { |
| "epoch": 5.833333333333333, |
| "grad_norm": 0.000232808364671655, |
| "learning_rate": 2.2194005843856636e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 164448, |
| "step": 525 |
| }, |
| { |
| "epoch": 5.888888888888889, |
| "grad_norm": 0.00039837227086536586, |
| "learning_rate": 2.1712813430593436e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 166016, |
| "step": 530 |
| }, |
| { |
| "epoch": 5.944444444444445, |
| "grad_norm": 0.000358970690285787, |
| "learning_rate": 2.1232857193762924e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 167552, |
| "step": 535 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 0.000357713463017717, |
| "learning_rate": 2.0754317625276983e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 169056, |
| "step": 540 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 0.050714749842882156, |
| "eval_runtime": 0.6392, |
| "eval_samples_per_second": 62.577, |
| "eval_steps_per_second": 15.644, |
| "num_input_tokens_seen": 169056, |
| "step": 540 |
| }, |
| { |
| "epoch": 6.055555555555555, |
| "grad_norm": 0.0002469751925673336, |
| "learning_rate": 2.02773746842965e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 170592, |
| "step": 545 |
| }, |
| { |
| "epoch": 6.111111111111111, |
| "grad_norm": 0.00897254142910242, |
| "learning_rate": 1.980220772955602e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 172192, |
| "step": 550 |
| }, |
| { |
| "epoch": 6.166666666666667, |
| "grad_norm": 0.0006196287577040493, |
| "learning_rate": 1.932899545191433e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 173792, |
| "step": 555 |
| }, |
| { |
| "epoch": 6.222222222222222, |
| "grad_norm": 0.0007166682044044137, |
| "learning_rate": 1.8857915807156092e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 175360, |
| "step": 560 |
| }, |
| { |
| "epoch": 6.277777777777778, |
| "grad_norm": 0.0002675725845620036, |
| "learning_rate": 1.838914594906995e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 176992, |
| "step": 565 |
| }, |
| { |
| "epoch": 6.333333333333333, |
| "grad_norm": 0.0006918899598531425, |
| "learning_rate": 1.792286216282824e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 178592, |
| "step": 570 |
| }, |
| { |
| "epoch": 6.388888888888889, |
| "grad_norm": 0.000293716904707253, |
| "learning_rate": 1.7459239798693364e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 180128, |
| "step": 575 |
| }, |
| { |
| "epoch": 6.444444444444445, |
| "grad_norm": 0.005921915639191866, |
| "learning_rate": 1.699845320607571e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 181632, |
| "step": 580 |
| }, |
| { |
| "epoch": 6.5, |
| "grad_norm": 0.0012502821628004313, |
| "learning_rate": 1.6540675667967974e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 183200, |
| "step": 585 |
| }, |
| { |
| "epoch": 6.5, |
| "eval_loss": 0.050469737499952316, |
| "eval_runtime": 0.6439, |
| "eval_samples_per_second": 62.118, |
| "eval_steps_per_second": 15.529, |
| "num_input_tokens_seen": 183200, |
| "step": 585 |
| }, |
| { |
| "epoch": 6.555555555555555, |
| "grad_norm": 0.00030657771276310086, |
| "learning_rate": 1.60860793357805e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 184800, |
| "step": 590 |
| }, |
| { |
| "epoch": 6.611111111111111, |
| "grad_norm": 0.0005699010798707604, |
| "learning_rate": 1.56348351646022e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 186336, |
| "step": 595 |
| }, |
| { |
| "epoch": 6.666666666666667, |
| "grad_norm": 0.00024775974452495575, |
| "learning_rate": 1.5187112848911323e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 187904, |
| "step": 600 |
| }, |
| { |
| "epoch": 6.722222222222222, |
| "grad_norm": 0.0003301188407931477, |
| "learning_rate": 1.47430807587603e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 189472, |
| "step": 605 |
| }, |
| { |
| "epoch": 6.777777777777778, |
| "grad_norm": 0.004495295230299234, |
| "learning_rate": 1.430290587645865e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 191072, |
| "step": 610 |
| }, |
| { |
| "epoch": 6.833333333333333, |
| "grad_norm": 0.00022791529772803187, |
| "learning_rate": 1.3866753733777765e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 192608, |
| "step": 615 |
| }, |
| { |
| "epoch": 6.888888888888889, |
| "grad_norm": 0.0007268284098245203, |
| "learning_rate": 1.343478834970121e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 194208, |
| "step": 620 |
| }, |
| { |
| "epoch": 6.944444444444445, |
| "grad_norm": 0.002538523869588971, |
| "learning_rate": 1.3007172168743854e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 195776, |
| "step": 625 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 0.0002487303863745183, |
| "learning_rate": 1.2584065999863102e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 197344, |
| "step": 630 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_loss": 0.05317758396267891, |
| "eval_runtime": 0.6388, |
| "eval_samples_per_second": 62.621, |
| "eval_steps_per_second": 15.655, |
| "num_input_tokens_seen": 197344, |
| "step": 630 |
| }, |
| { |
| "epoch": 7.055555555555555, |
| "grad_norm": 0.00032867665868252516, |
| "learning_rate": 1.2165628955985314e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 198944, |
| "step": 635 |
| }, |
| { |
| "epoch": 7.111111111111111, |
| "grad_norm": 0.0007965990225784481, |
| "learning_rate": 1.175201839416988e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 200512, |
| "step": 640 |
| }, |
| { |
| "epoch": 7.166666666666667, |
| "grad_norm": 0.0002785587857943028, |
| "learning_rate": 1.1343389856433658e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 202016, |
| "step": 645 |
| }, |
| { |
| "epoch": 7.222222222222222, |
| "grad_norm": 0.00022766049369238317, |
| "learning_rate": 1.0939897011258001e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 203648, |
| "step": 650 |
| }, |
| { |
| "epoch": 7.277777777777778, |
| "grad_norm": 0.0001794523122953251, |
| "learning_rate": 1.0541691595800337e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 205184, |
| "step": 655 |
| }, |
| { |
| "epoch": 7.333333333333333, |
| "grad_norm": 0.00043583984370343387, |
| "learning_rate": 1.0148923358832022e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 206720, |
| "step": 660 |
| }, |
| { |
| "epoch": 7.388888888888889, |
| "grad_norm": 0.001430140808224678, |
| "learning_rate": 9.761740004423927e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 208320, |
| "step": 665 |
| }, |
| { |
| "epoch": 7.444444444444445, |
| "grad_norm": 0.00032269200892187655, |
| "learning_rate": 9.380287136401e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 209856, |
| "step": 670 |
| }, |
| { |
| "epoch": 7.5, |
| "grad_norm": 0.0002632564282976091, |
| "learning_rate": 9.00470820358663e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 211392, |
| "step": 675 |
| }, |
| { |
| "epoch": 7.5, |
| "eval_loss": 0.04903189465403557, |
| "eval_runtime": 0.6396, |
| "eval_samples_per_second": 62.541, |
| "eval_steps_per_second": 15.635, |
| "num_input_tokens_seen": 211392, |
| "step": 675 |
| }, |
| { |
| "epoch": 7.555555555555555, |
| "grad_norm": 0.0005279940087348223, |
| "learning_rate": 8.635144445857406e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 212960, |
| "step": 680 |
| }, |
| { |
| "epoch": 7.611111111111111, |
| "grad_norm": 0.005164884030818939, |
| "learning_rate": 8.271734841028553e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 214528, |
| "step": 685 |
| }, |
| { |
| "epoch": 7.666666666666667, |
| "grad_norm": 0.00020918868540320545, |
| "learning_rate": 7.914616052590071e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 216000, |
| "step": 690 |
| }, |
| { |
| "epoch": 7.722222222222222, |
| "grad_norm": 0.00018185449880547822, |
| "learning_rate": 7.563922378313218e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 217632, |
| "step": 695 |
| }, |
| { |
| "epoch": 7.777777777777778, |
| "grad_norm": 0.00021391564223449677, |
| "learning_rate": 7.219785699746573e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 219232, |
| "step": 700 |
| }, |
| { |
| "epoch": 7.833333333333333, |
| "grad_norm": 0.0007275750394910574, |
| "learning_rate": 6.882335432620779e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 220800, |
| "step": 705 |
| }, |
| { |
| "epoch": 7.888888888888889, |
| "grad_norm": 0.0003546305524650961, |
| "learning_rate": 6.55169847818059e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 222368, |
| "step": 710 |
| }, |
| { |
| "epoch": 7.944444444444445, |
| "grad_norm": 0.00037465011700987816, |
| "learning_rate": 6.22799917546252e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 223968, |
| "step": 715 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 0.00028891192050650716, |
| "learning_rate": 5.9113592545359945e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 225536, |
| "step": 720 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 0.04664245992898941, |
| "eval_runtime": 0.6378, |
| "eval_samples_per_second": 62.72, |
| "eval_steps_per_second": 15.68, |
| "num_input_tokens_seen": 225536, |
| "step": 720 |
| }, |
| { |
| "epoch": 8.055555555555555, |
| "grad_norm": 0.0012465757317841053, |
| "learning_rate": 5.601897790725643e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 227168, |
| "step": 725 |
| }, |
| { |
| "epoch": 8.11111111111111, |
| "grad_norm": 0.00019996908667962998, |
| "learning_rate": 5.299731159831953e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 228704, |
| "step": 730 |
| }, |
| { |
| "epoch": 8.166666666666666, |
| "grad_norm": 0.0002453059423714876, |
| "learning_rate": 5.004972994367102e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 230336, |
| "step": 735 |
| }, |
| { |
| "epoch": 8.222222222222221, |
| "grad_norm": 0.0005749266711063683, |
| "learning_rate": 4.7177341408224e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 231936, |
| "step": 740 |
| }, |
| { |
| "epoch": 8.277777777777779, |
| "grad_norm": 0.00034150900319218636, |
| "learning_rate": 4.438122617983443e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 233472, |
| "step": 745 |
| }, |
| { |
| "epoch": 8.333333333333334, |
| "grad_norm": 0.0002638312871567905, |
| "learning_rate": 4.166243576308712e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 235040, |
| "step": 750 |
| }, |
| { |
| "epoch": 8.38888888888889, |
| "grad_norm": 0.00024173247220460325, |
| "learning_rate": 3.9021992583867325e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 236608, |
| "step": 755 |
| }, |
| { |
| "epoch": 8.444444444444445, |
| "grad_norm": 0.00021123279293533415, |
| "learning_rate": 3.6460889604868626e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 238144, |
| "step": 760 |
| }, |
| { |
| "epoch": 8.5, |
| "grad_norm": 0.0004196509253233671, |
| "learning_rate": 3.398008995217988e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 239680, |
| "step": 765 |
| }, |
| { |
| "epoch": 8.5, |
| "eval_loss": 0.052941907197237015, |
| "eval_runtime": 0.6433, |
| "eval_samples_per_second": 62.175, |
| "eval_steps_per_second": 15.544, |
| "num_input_tokens_seen": 239680, |
| "step": 765 |
| }, |
| { |
| "epoch": 8.555555555555555, |
| "grad_norm": 0.00021833479695487767, |
| "learning_rate": 3.158052655309332e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 241280, |
| "step": 770 |
| }, |
| { |
| "epoch": 8.61111111111111, |
| "grad_norm": 0.0013561052037402987, |
| "learning_rate": 2.9263101785268254e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 242816, |
| "step": 775 |
| }, |
| { |
| "epoch": 8.666666666666666, |
| "grad_norm": 0.0002495679655112326, |
| "learning_rate": 2.7028687137384267e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 244352, |
| "step": 780 |
| }, |
| { |
| "epoch": 8.722222222222221, |
| "grad_norm": 0.00017657369608059525, |
| "learning_rate": 2.487812288140945e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 245856, |
| "step": 785 |
| }, |
| { |
| "epoch": 8.777777777777779, |
| "grad_norm": 0.0006603540387004614, |
| "learning_rate": 2.281221775660894e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 247456, |
| "step": 790 |
| }, |
| { |
| "epoch": 8.833333333333334, |
| "grad_norm": 0.0006224618409760296, |
| "learning_rate": 2.0831748665410765e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 248992, |
| "step": 795 |
| }, |
| { |
| "epoch": 8.88888888888889, |
| "grad_norm": 0.0004293640376999974, |
| "learning_rate": 1.893746038124497e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 250528, |
| "step": 800 |
| }, |
| { |
| "epoch": 8.944444444444445, |
| "grad_norm": 0.0024332255125045776, |
| "learning_rate": 1.713006526846439e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 252128, |
| "step": 805 |
| }, |
| { |
| "epoch": 9.0, |
| "grad_norm": 0.0001995310594793409, |
| "learning_rate": 1.541024301445404e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 253696, |
| "step": 810 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_loss": 0.05138952657580376, |
| "eval_runtime": 0.6291, |
| "eval_samples_per_second": 63.586, |
| "eval_steps_per_second": 15.896, |
| "num_input_tokens_seen": 253696, |
| "step": 810 |
| }, |
| { |
| "epoch": 9.055555555555555, |
| "grad_norm": 0.0019911914132535458, |
| "learning_rate": 1.3778640374027985e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 255296, |
| "step": 815 |
| }, |
| { |
| "epoch": 9.11111111111111, |
| "grad_norm": 0.00020865652186330408, |
| "learning_rate": 1.2235870926211619e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 256896, |
| "step": 820 |
| }, |
| { |
| "epoch": 9.166666666666666, |
| "grad_norm": 0.00027607433730736375, |
| "learning_rate": 1.0782514843499653e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 258432, |
| "step": 825 |
| }, |
| { |
| "epoch": 9.222222222222221, |
| "grad_norm": 0.0002628320944495499, |
| "learning_rate": 9.419118673676924e-07, |
| "loss": 0.0, |
| "num_input_tokens_seen": 260000, |
| "step": 830 |
| }, |
| { |
| "epoch": 9.277777777777779, |
| "grad_norm": 0.003769401926547289, |
| "learning_rate": 8.146195134284052e-07, |
| "loss": 0.0, |
| "num_input_tokens_seen": 261568, |
| "step": 835 |
| }, |
| { |
| "epoch": 9.333333333333334, |
| "grad_norm": 0.0003039254224859178, |
| "learning_rate": 6.964222919805391e-07, |
| "loss": 0.0, |
| "num_input_tokens_seen": 263200, |
| "step": 840 |
| }, |
| { |
| "epoch": 9.38888888888889, |
| "grad_norm": 0.0003862561716232449, |
| "learning_rate": 5.87364652165176e-07, |
| "loss": 0.0, |
| "num_input_tokens_seen": 264736, |
| "step": 845 |
| }, |
| { |
| "epoch": 9.444444444444445, |
| "grad_norm": 0.00027351416065357625, |
| "learning_rate": 4.874876061005173e-07, |
| "loss": 0.0, |
| "num_input_tokens_seen": 266304, |
| "step": 850 |
| }, |
| { |
| "epoch": 9.5, |
| "grad_norm": 0.0010773118119686842, |
| "learning_rate": 3.9682871345891883e-07, |
| "loss": 0.0, |
| "num_input_tokens_seen": 267840, |
| "step": 855 |
| }, |
| { |
| "epoch": 9.5, |
| "eval_loss": 0.05005338042974472, |
| "eval_runtime": 0.6404, |
| "eval_samples_per_second": 62.458, |
| "eval_steps_per_second": 15.614, |
| "num_input_tokens_seen": 267840, |
| "step": 855 |
| }, |
| { |
| "epoch": 9.555555555555555, |
| "grad_norm": 0.00021217566973064095, |
| "learning_rate": 3.1542206734221924e-07, |
| "loss": 0.0, |
| "num_input_tokens_seen": 269376, |
| "step": 860 |
| }, |
| { |
| "epoch": 9.61111111111111, |
| "grad_norm": 0.00023544387659057975, |
| "learning_rate": 2.4329828146074095e-07, |
| "loss": 0.0, |
| "num_input_tokens_seen": 270944, |
| "step": 865 |
| }, |
| { |
| "epoch": 9.666666666666666, |
| "grad_norm": 0.0007306839688681066, |
| "learning_rate": 1.8048447862070718e-07, |
| "loss": 0.0, |
| "num_input_tokens_seen": 272448, |
| "step": 870 |
| }, |
| { |
| "epoch": 9.722222222222221, |
| "grad_norm": 0.00023676318232901394, |
| "learning_rate": 1.2700428052447033e-07, |
| "loss": 0.0, |
| "num_input_tokens_seen": 273984, |
| "step": 875 |
| }, |
| { |
| "epoch": 9.777777777777779, |
| "grad_norm": 0.0002612364769447595, |
| "learning_rate": 8.28777988873486e-08, |
| "loss": 0.0, |
| "num_input_tokens_seen": 275520, |
| "step": 880 |
| }, |
| { |
| "epoch": 9.833333333333334, |
| "grad_norm": 0.00022536252799909562, |
| "learning_rate": 4.8121627874450625e-08, |
| "loss": 0.0, |
| "num_input_tokens_seen": 277152, |
| "step": 885 |
| }, |
| { |
| "epoch": 9.88888888888889, |
| "grad_norm": 0.0009130098042078316, |
| "learning_rate": 2.2748837860270267e-08, |
| "loss": 0.0, |
| "num_input_tokens_seen": 278688, |
| "step": 890 |
| }, |
| { |
| "epoch": 9.944444444444445, |
| "grad_norm": 0.0004009114345535636, |
| "learning_rate": 6.768970513457151e-09, |
| "loss": 0.0, |
| "num_input_tokens_seen": 280256, |
| "step": 895 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 0.0005631247768178582, |
| "learning_rate": 1.8803520859811406e-10, |
| "loss": 0.0, |
| "num_input_tokens_seen": 281856, |
| "step": 900 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_loss": 0.05062691122293472, |
| "eval_runtime": 0.6384, |
| "eval_samples_per_second": 62.655, |
| "eval_steps_per_second": 15.664, |
| "num_input_tokens_seen": 281856, |
| "step": 900 |
| }, |
| { |
| "epoch": 10.0, |
| "num_input_tokens_seen": 281856, |
| "step": 900, |
| "total_flos": 1.2716674274820096e+16, |
| "train_loss": 0.026365039415561314, |
| "train_runtime": 219.2046, |
| "train_samples_per_second": 16.423, |
| "train_steps_per_second": 4.106 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 900, |
| "num_input_tokens_seen": 281856, |
| "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": 1.2716674274820096e+16, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
