| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.093095281472035, | |
| "eval_steps": 500, | |
| "global_step": 3000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0036436509382401167, | |
| "grad_norm": 0.6875, | |
| "learning_rate": 9.987852283770651e-05, | |
| "loss": 3.4902, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007287301876480233, | |
| "grad_norm": 0.66796875, | |
| "learning_rate": 9.975704567541302e-05, | |
| "loss": 3.3432, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01093095281472035, | |
| "grad_norm": 0.5546875, | |
| "learning_rate": 9.963556851311953e-05, | |
| "loss": 3.2381, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.014574603752960467, | |
| "grad_norm": 0.65234375, | |
| "learning_rate": 9.951409135082604e-05, | |
| "loss": 3.2931, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.018218254691200583, | |
| "grad_norm": 0.6328125, | |
| "learning_rate": 9.939261418853257e-05, | |
| "loss": 3.3235, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0218619056294407, | |
| "grad_norm": 0.64453125, | |
| "learning_rate": 9.927113702623908e-05, | |
| "loss": 3.2988, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.025505556567680818, | |
| "grad_norm": 0.59765625, | |
| "learning_rate": 9.914965986394558e-05, | |
| "loss": 3.2927, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.029149207505920934, | |
| "grad_norm": 0.57421875, | |
| "learning_rate": 9.90281827016521e-05, | |
| "loss": 3.275, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.03279285844416105, | |
| "grad_norm": 0.640625, | |
| "learning_rate": 9.89067055393586e-05, | |
| "loss": 3.316, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.036436509382401165, | |
| "grad_norm": 0.57421875, | |
| "learning_rate": 9.878522837706513e-05, | |
| "loss": 3.2611, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04008016032064128, | |
| "grad_norm": 0.51171875, | |
| "learning_rate": 9.866375121477162e-05, | |
| "loss": 3.268, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.0437238112588814, | |
| "grad_norm": 0.703125, | |
| "learning_rate": 9.854227405247813e-05, | |
| "loss": 3.3032, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.04736746219712151, | |
| "grad_norm": 0.5546875, | |
| "learning_rate": 9.842079689018465e-05, | |
| "loss": 3.3334, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.051011113135361635, | |
| "grad_norm": 0.671875, | |
| "learning_rate": 9.829931972789116e-05, | |
| "loss": 3.1943, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.05465476407360175, | |
| "grad_norm": 0.6171875, | |
| "learning_rate": 9.817784256559767e-05, | |
| "loss": 3.2574, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.05829841501184187, | |
| "grad_norm": 0.66015625, | |
| "learning_rate": 9.805636540330418e-05, | |
| "loss": 3.3747, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.06194206595008198, | |
| "grad_norm": 0.52734375, | |
| "learning_rate": 9.793488824101069e-05, | |
| "loss": 3.2992, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.0655857168883221, | |
| "grad_norm": 0.50390625, | |
| "learning_rate": 9.781341107871722e-05, | |
| "loss": 3.2342, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.06922936782656222, | |
| "grad_norm": 0.65234375, | |
| "learning_rate": 9.769193391642371e-05, | |
| "loss": 3.356, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.07287301876480233, | |
| "grad_norm": 0.57421875, | |
| "learning_rate": 9.757045675413022e-05, | |
| "loss": 3.3618, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.07651666970304245, | |
| "grad_norm": 0.58984375, | |
| "learning_rate": 9.744897959183674e-05, | |
| "loss": 3.2931, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.08016032064128256, | |
| "grad_norm": 0.77734375, | |
| "learning_rate": 9.732750242954325e-05, | |
| "loss": 3.3246, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.08380397157952268, | |
| "grad_norm": 0.5859375, | |
| "learning_rate": 9.720602526724975e-05, | |
| "loss": 3.3181, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.0874476225177628, | |
| "grad_norm": 0.640625, | |
| "learning_rate": 9.708454810495627e-05, | |
| "loss": 3.2757, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.09109127345600292, | |
| "grad_norm": 0.55859375, | |
| "learning_rate": 9.696307094266278e-05, | |
| "loss": 3.2753, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.09473492439424303, | |
| "grad_norm": 0.58203125, | |
| "learning_rate": 9.68415937803693e-05, | |
| "loss": 3.3207, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.09837857533248315, | |
| "grad_norm": 0.63671875, | |
| "learning_rate": 9.67201166180758e-05, | |
| "loss": 3.3035, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.10202222627072327, | |
| "grad_norm": 0.578125, | |
| "learning_rate": 9.659863945578231e-05, | |
| "loss": 3.3025, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.10566587720896338, | |
| "grad_norm": 0.5859375, | |
| "learning_rate": 9.647716229348883e-05, | |
| "loss": 3.2066, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.1093095281472035, | |
| "grad_norm": 0.7109375, | |
| "learning_rate": 9.635568513119534e-05, | |
| "loss": 3.2757, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.11295317908544361, | |
| "grad_norm": 0.609375, | |
| "learning_rate": 9.623420796890185e-05, | |
| "loss": 3.1904, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.11659683002368373, | |
| "grad_norm": 0.60546875, | |
| "learning_rate": 9.611273080660836e-05, | |
| "loss": 3.1947, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.12024048096192384, | |
| "grad_norm": 0.6171875, | |
| "learning_rate": 9.599125364431487e-05, | |
| "loss": 3.2016, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.12388413190016397, | |
| "grad_norm": 0.640625, | |
| "learning_rate": 9.58697764820214e-05, | |
| "loss": 3.329, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.12752778283840407, | |
| "grad_norm": 0.66796875, | |
| "learning_rate": 9.574829931972789e-05, | |
| "loss": 3.2483, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.1311714337766442, | |
| "grad_norm": 0.57421875, | |
| "learning_rate": 9.56268221574344e-05, | |
| "loss": 3.2388, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.13481508471488432, | |
| "grad_norm": 0.58984375, | |
| "learning_rate": 9.550534499514092e-05, | |
| "loss": 3.2722, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.13845873565312444, | |
| "grad_norm": 0.58203125, | |
| "learning_rate": 9.538386783284743e-05, | |
| "loss": 3.2672, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.14210238659136454, | |
| "grad_norm": 0.5234375, | |
| "learning_rate": 9.526239067055394e-05, | |
| "loss": 3.3378, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.14574603752960466, | |
| "grad_norm": 0.55859375, | |
| "learning_rate": 9.514091350826045e-05, | |
| "loss": 3.2637, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.14938968846784478, | |
| "grad_norm": 0.70703125, | |
| "learning_rate": 9.501943634596696e-05, | |
| "loss": 3.2879, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.1530333394060849, | |
| "grad_norm": 0.6640625, | |
| "learning_rate": 9.489795918367348e-05, | |
| "loss": 3.2614, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.156676990344325, | |
| "grad_norm": 0.625, | |
| "learning_rate": 9.477648202137999e-05, | |
| "loss": 3.2469, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.16032064128256512, | |
| "grad_norm": 0.5703125, | |
| "learning_rate": 9.465500485908649e-05, | |
| "loss": 3.1614, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.16396429222080525, | |
| "grad_norm": 0.59765625, | |
| "learning_rate": 9.453352769679301e-05, | |
| "loss": 3.2658, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.16760794315904537, | |
| "grad_norm": 0.6953125, | |
| "learning_rate": 9.441205053449952e-05, | |
| "loss": 3.3253, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.1712515940972855, | |
| "grad_norm": 0.67578125, | |
| "learning_rate": 9.429057337220603e-05, | |
| "loss": 3.2311, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.1748952450355256, | |
| "grad_norm": 0.625, | |
| "learning_rate": 9.416909620991254e-05, | |
| "loss": 3.3117, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.1785388959737657, | |
| "grad_norm": 0.6640625, | |
| "learning_rate": 9.404761904761905e-05, | |
| "loss": 3.3513, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.18218254691200583, | |
| "grad_norm": 0.5703125, | |
| "learning_rate": 9.392614188532556e-05, | |
| "loss": 3.3071, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.18582619785024596, | |
| "grad_norm": 0.5703125, | |
| "learning_rate": 9.380466472303208e-05, | |
| "loss": 3.3047, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.18946984878848605, | |
| "grad_norm": 0.58984375, | |
| "learning_rate": 9.368318756073858e-05, | |
| "loss": 3.1964, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.19311349972672617, | |
| "grad_norm": 0.57421875, | |
| "learning_rate": 9.35617103984451e-05, | |
| "loss": 3.2459, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.1967571506649663, | |
| "grad_norm": 0.62109375, | |
| "learning_rate": 9.344023323615161e-05, | |
| "loss": 3.205, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.20040080160320642, | |
| "grad_norm": 0.66015625, | |
| "learning_rate": 9.331875607385812e-05, | |
| "loss": 3.2856, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.20404445254144654, | |
| "grad_norm": 0.52734375, | |
| "learning_rate": 9.319727891156463e-05, | |
| "loss": 3.185, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.20768810347968664, | |
| "grad_norm": 0.5546875, | |
| "learning_rate": 9.307580174927114e-05, | |
| "loss": 3.3071, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.21133175441792676, | |
| "grad_norm": 0.63671875, | |
| "learning_rate": 9.295432458697765e-05, | |
| "loss": 3.2363, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.21497540535616688, | |
| "grad_norm": 0.5625, | |
| "learning_rate": 9.283284742468417e-05, | |
| "loss": 3.2697, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.218619056294407, | |
| "grad_norm": 0.56640625, | |
| "learning_rate": 9.271137026239067e-05, | |
| "loss": 3.3037, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.2222627072326471, | |
| "grad_norm": 0.53125, | |
| "learning_rate": 9.258989310009719e-05, | |
| "loss": 3.2371, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.22590635817088722, | |
| "grad_norm": 0.61328125, | |
| "learning_rate": 9.24684159378037e-05, | |
| "loss": 3.3367, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.22955000910912735, | |
| "grad_norm": 0.5703125, | |
| "learning_rate": 9.234693877551021e-05, | |
| "loss": 3.2109, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.23319366004736747, | |
| "grad_norm": 0.59375, | |
| "learning_rate": 9.222546161321672e-05, | |
| "loss": 3.2374, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.2368373109856076, | |
| "grad_norm": 0.6875, | |
| "learning_rate": 9.210398445092323e-05, | |
| "loss": 3.3066, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.24048096192384769, | |
| "grad_norm": 0.6484375, | |
| "learning_rate": 9.198250728862974e-05, | |
| "loss": 3.2635, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.2441246128620878, | |
| "grad_norm": 0.60546875, | |
| "learning_rate": 9.186103012633626e-05, | |
| "loss": 3.26, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.24776826380032793, | |
| "grad_norm": 0.65234375, | |
| "learning_rate": 9.173955296404276e-05, | |
| "loss": 3.2641, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.25141191473856805, | |
| "grad_norm": 0.6015625, | |
| "learning_rate": 9.161807580174927e-05, | |
| "loss": 3.2907, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.25505556567680815, | |
| "grad_norm": 0.54296875, | |
| "learning_rate": 9.149659863945579e-05, | |
| "loss": 3.2567, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.2586992166150483, | |
| "grad_norm": 0.62890625, | |
| "learning_rate": 9.13751214771623e-05, | |
| "loss": 3.2838, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.2623428675532884, | |
| "grad_norm": 0.546875, | |
| "learning_rate": 9.125364431486881e-05, | |
| "loss": 3.2969, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.2659865184915285, | |
| "grad_norm": 0.6328125, | |
| "learning_rate": 9.113216715257532e-05, | |
| "loss": 3.2212, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.26963016942976864, | |
| "grad_norm": 0.6328125, | |
| "learning_rate": 9.101068999028183e-05, | |
| "loss": 3.212, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.27327382036800874, | |
| "grad_norm": 0.5859375, | |
| "learning_rate": 9.088921282798835e-05, | |
| "loss": 3.3488, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.2769174713062489, | |
| "grad_norm": 0.546875, | |
| "learning_rate": 9.076773566569486e-05, | |
| "loss": 3.2143, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.280561122244489, | |
| "grad_norm": 0.56640625, | |
| "learning_rate": 9.064625850340136e-05, | |
| "loss": 3.2518, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.2842047731827291, | |
| "grad_norm": 0.578125, | |
| "learning_rate": 9.052478134110788e-05, | |
| "loss": 3.2638, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.2878484241209692, | |
| "grad_norm": 0.58203125, | |
| "learning_rate": 9.040330417881439e-05, | |
| "loss": 3.2584, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.2914920750592093, | |
| "grad_norm": 0.62890625, | |
| "learning_rate": 9.02818270165209e-05, | |
| "loss": 3.2841, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.29513572599744947, | |
| "grad_norm": 0.55078125, | |
| "learning_rate": 9.01603498542274e-05, | |
| "loss": 3.261, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.29877937693568957, | |
| "grad_norm": 0.6171875, | |
| "learning_rate": 9.003887269193392e-05, | |
| "loss": 3.2954, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.30242302787392966, | |
| "grad_norm": 0.54296875, | |
| "learning_rate": 8.991739552964044e-05, | |
| "loss": 3.2337, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.3060666788121698, | |
| "grad_norm": 0.6171875, | |
| "learning_rate": 8.979591836734695e-05, | |
| "loss": 3.2881, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.3097103297504099, | |
| "grad_norm": 0.5546875, | |
| "learning_rate": 8.967444120505344e-05, | |
| "loss": 3.3519, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.31335398068865, | |
| "grad_norm": 0.5859375, | |
| "learning_rate": 8.955296404275997e-05, | |
| "loss": 3.3147, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.31699763162689015, | |
| "grad_norm": 0.62890625, | |
| "learning_rate": 8.943148688046648e-05, | |
| "loss": 3.2304, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.32064128256513025, | |
| "grad_norm": 0.60546875, | |
| "learning_rate": 8.931000971817299e-05, | |
| "loss": 3.2526, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.3242849335033704, | |
| "grad_norm": 0.6640625, | |
| "learning_rate": 8.91885325558795e-05, | |
| "loss": 3.309, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.3279285844416105, | |
| "grad_norm": 0.6484375, | |
| "learning_rate": 8.9067055393586e-05, | |
| "loss": 3.2513, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.3315722353798506, | |
| "grad_norm": 0.5703125, | |
| "learning_rate": 8.894557823129253e-05, | |
| "loss": 3.2135, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.33521588631809074, | |
| "grad_norm": 0.64453125, | |
| "learning_rate": 8.882410106899904e-05, | |
| "loss": 3.3048, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.33885953725633083, | |
| "grad_norm": 0.6015625, | |
| "learning_rate": 8.870262390670553e-05, | |
| "loss": 3.3047, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.342503188194571, | |
| "grad_norm": 0.6015625, | |
| "learning_rate": 8.858114674441206e-05, | |
| "loss": 3.2616, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.3461468391328111, | |
| "grad_norm": 0.5859375, | |
| "learning_rate": 8.845966958211857e-05, | |
| "loss": 3.2697, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.3497904900710512, | |
| "grad_norm": 0.72265625, | |
| "learning_rate": 8.833819241982508e-05, | |
| "loss": 3.2395, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.3534341410092913, | |
| "grad_norm": 0.61328125, | |
| "learning_rate": 8.821671525753159e-05, | |
| "loss": 3.2137, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.3570777919475314, | |
| "grad_norm": 0.625, | |
| "learning_rate": 8.80952380952381e-05, | |
| "loss": 3.2872, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.36072144288577157, | |
| "grad_norm": 0.5859375, | |
| "learning_rate": 8.797376093294462e-05, | |
| "loss": 3.2682, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.36436509382401167, | |
| "grad_norm": 0.5390625, | |
| "learning_rate": 8.785228377065113e-05, | |
| "loss": 3.204, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.36800874476225176, | |
| "grad_norm": 0.71875, | |
| "learning_rate": 8.773080660835762e-05, | |
| "loss": 3.2472, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.3716523957004919, | |
| "grad_norm": 0.609375, | |
| "learning_rate": 8.760932944606415e-05, | |
| "loss": 3.2638, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.375296046638732, | |
| "grad_norm": 0.60546875, | |
| "learning_rate": 8.748785228377066e-05, | |
| "loss": 3.2803, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.3789396975769721, | |
| "grad_norm": 0.66796875, | |
| "learning_rate": 8.736637512147716e-05, | |
| "loss": 3.273, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.38258334851521225, | |
| "grad_norm": 0.65625, | |
| "learning_rate": 8.724489795918367e-05, | |
| "loss": 3.2854, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.38622699945345235, | |
| "grad_norm": 0.640625, | |
| "learning_rate": 8.712342079689018e-05, | |
| "loss": 3.2373, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.3898706503916925, | |
| "grad_norm": 0.55859375, | |
| "learning_rate": 8.700194363459671e-05, | |
| "loss": 3.2259, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.3935143013299326, | |
| "grad_norm": 0.5078125, | |
| "learning_rate": 8.688046647230322e-05, | |
| "loss": 3.2402, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.3971579522681727, | |
| "grad_norm": 0.61328125, | |
| "learning_rate": 8.675898931000973e-05, | |
| "loss": 3.2379, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.40080160320641284, | |
| "grad_norm": 0.59375, | |
| "learning_rate": 8.663751214771624e-05, | |
| "loss": 3.2564, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.40444525414465293, | |
| "grad_norm": 0.69921875, | |
| "learning_rate": 8.651603498542274e-05, | |
| "loss": 3.2342, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.4080889050828931, | |
| "grad_norm": 0.53125, | |
| "learning_rate": 8.639455782312925e-05, | |
| "loss": 3.3336, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.4117325560211332, | |
| "grad_norm": 0.63671875, | |
| "learning_rate": 8.627308066083576e-05, | |
| "loss": 3.2684, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.4153762069593733, | |
| "grad_norm": 0.61328125, | |
| "learning_rate": 8.615160349854227e-05, | |
| "loss": 3.2581, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.4190198578976134, | |
| "grad_norm": 0.50390625, | |
| "learning_rate": 8.603012633624878e-05, | |
| "loss": 3.3428, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.4226635088358535, | |
| "grad_norm": 0.58203125, | |
| "learning_rate": 8.59086491739553e-05, | |
| "loss": 3.2331, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.42630715977409367, | |
| "grad_norm": 0.63671875, | |
| "learning_rate": 8.578717201166182e-05, | |
| "loss": 3.2203, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.42995081071233376, | |
| "grad_norm": 0.57421875, | |
| "learning_rate": 8.566569484936832e-05, | |
| "loss": 3.248, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.43359446165057386, | |
| "grad_norm": 0.6015625, | |
| "learning_rate": 8.554421768707483e-05, | |
| "loss": 3.3052, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.437238112588814, | |
| "grad_norm": 0.5546875, | |
| "learning_rate": 8.542274052478134e-05, | |
| "loss": 3.2036, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.4408817635270541, | |
| "grad_norm": 0.64453125, | |
| "learning_rate": 8.530126336248787e-05, | |
| "loss": 3.2199, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.4445254144652942, | |
| "grad_norm": 0.68359375, | |
| "learning_rate": 8.517978620019436e-05, | |
| "loss": 3.2594, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.44816906540353435, | |
| "grad_norm": 0.6953125, | |
| "learning_rate": 8.505830903790087e-05, | |
| "loss": 3.26, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.45181271634177445, | |
| "grad_norm": 0.66015625, | |
| "learning_rate": 8.49368318756074e-05, | |
| "loss": 3.3623, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.4554563672800146, | |
| "grad_norm": 0.7421875, | |
| "learning_rate": 8.48153547133139e-05, | |
| "loss": 3.2625, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.4591000182182547, | |
| "grad_norm": 0.6875, | |
| "learning_rate": 8.469387755102041e-05, | |
| "loss": 3.2738, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.4627436691564948, | |
| "grad_norm": 0.61328125, | |
| "learning_rate": 8.457240038872692e-05, | |
| "loss": 3.2688, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.46638732009473494, | |
| "grad_norm": 0.609375, | |
| "learning_rate": 8.445092322643343e-05, | |
| "loss": 3.2392, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.47003097103297503, | |
| "grad_norm": 0.56640625, | |
| "learning_rate": 8.432944606413996e-05, | |
| "loss": 3.2414, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.4736746219712152, | |
| "grad_norm": 0.640625, | |
| "learning_rate": 8.420796890184645e-05, | |
| "loss": 3.2461, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.4773182729094553, | |
| "grad_norm": 0.578125, | |
| "learning_rate": 8.408649173955296e-05, | |
| "loss": 3.3459, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.48096192384769537, | |
| "grad_norm": 0.6953125, | |
| "learning_rate": 8.396501457725948e-05, | |
| "loss": 3.2631, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.4846055747859355, | |
| "grad_norm": 0.59765625, | |
| "learning_rate": 8.3843537414966e-05, | |
| "loss": 3.2883, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.4882492257241756, | |
| "grad_norm": 0.625, | |
| "learning_rate": 8.372206025267249e-05, | |
| "loss": 3.2085, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.49189287666241577, | |
| "grad_norm": 0.6640625, | |
| "learning_rate": 8.360058309037901e-05, | |
| "loss": 3.3132, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.49553652760065586, | |
| "grad_norm": 0.61328125, | |
| "learning_rate": 8.347910592808552e-05, | |
| "loss": 3.3076, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.49918017853889596, | |
| "grad_norm": 0.7265625, | |
| "learning_rate": 8.335762876579204e-05, | |
| "loss": 3.3183, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.5028238294771361, | |
| "grad_norm": 0.55859375, | |
| "learning_rate": 8.323615160349854e-05, | |
| "loss": 3.1761, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.5064674804153763, | |
| "grad_norm": 0.60546875, | |
| "learning_rate": 8.311467444120505e-05, | |
| "loss": 3.2079, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.5101111313536163, | |
| "grad_norm": 0.703125, | |
| "learning_rate": 8.299319727891157e-05, | |
| "loss": 3.2844, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.5137547822918564, | |
| "grad_norm": 0.578125, | |
| "learning_rate": 8.287172011661808e-05, | |
| "loss": 3.2492, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.5173984332300966, | |
| "grad_norm": 0.6328125, | |
| "learning_rate": 8.275024295432459e-05, | |
| "loss": 3.2525, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.5210420841683366, | |
| "grad_norm": 0.5703125, | |
| "learning_rate": 8.26287657920311e-05, | |
| "loss": 3.2449, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.5246857351065768, | |
| "grad_norm": 0.54296875, | |
| "learning_rate": 8.250728862973761e-05, | |
| "loss": 3.2279, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.5283293860448169, | |
| "grad_norm": 0.5859375, | |
| "learning_rate": 8.238581146744413e-05, | |
| "loss": 3.2751, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.531973036983057, | |
| "grad_norm": 0.57421875, | |
| "learning_rate": 8.226433430515063e-05, | |
| "loss": 3.2404, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.5356166879212971, | |
| "grad_norm": 0.67578125, | |
| "learning_rate": 8.214285714285714e-05, | |
| "loss": 3.2911, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.5392603388595373, | |
| "grad_norm": 0.6796875, | |
| "learning_rate": 8.202137998056366e-05, | |
| "loss": 3.2637, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.5429039897977773, | |
| "grad_norm": 0.61328125, | |
| "learning_rate": 8.189990281827017e-05, | |
| "loss": 3.2004, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.5465476407360175, | |
| "grad_norm": 0.6875, | |
| "learning_rate": 8.177842565597668e-05, | |
| "loss": 3.2958, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.5501912916742576, | |
| "grad_norm": 0.609375, | |
| "learning_rate": 8.165694849368319e-05, | |
| "loss": 3.2371, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.5538349426124978, | |
| "grad_norm": 0.6171875, | |
| "learning_rate": 8.15354713313897e-05, | |
| "loss": 3.2798, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.5574785935507378, | |
| "grad_norm": 0.6953125, | |
| "learning_rate": 8.141399416909622e-05, | |
| "loss": 3.2608, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.561122244488978, | |
| "grad_norm": 0.62109375, | |
| "learning_rate": 8.129251700680273e-05, | |
| "loss": 3.2374, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.5647658954272181, | |
| "grad_norm": 0.625, | |
| "learning_rate": 8.117103984450923e-05, | |
| "loss": 3.189, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.5684095463654582, | |
| "grad_norm": 0.57421875, | |
| "learning_rate": 8.104956268221575e-05, | |
| "loss": 3.2008, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.5720531973036983, | |
| "grad_norm": 0.58984375, | |
| "learning_rate": 8.092808551992226e-05, | |
| "loss": 3.219, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.5756968482419385, | |
| "grad_norm": 0.58203125, | |
| "learning_rate": 8.080660835762877e-05, | |
| "loss": 3.2417, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.5793404991801785, | |
| "grad_norm": 0.63671875, | |
| "learning_rate": 8.068513119533528e-05, | |
| "loss": 3.236, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.5829841501184186, | |
| "grad_norm": 0.703125, | |
| "learning_rate": 8.056365403304179e-05, | |
| "loss": 3.3037, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.5866278010566588, | |
| "grad_norm": 0.703125, | |
| "learning_rate": 8.04421768707483e-05, | |
| "loss": 3.2412, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.5902714519948989, | |
| "grad_norm": 0.66796875, | |
| "learning_rate": 8.032069970845482e-05, | |
| "loss": 3.2293, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.593915102933139, | |
| "grad_norm": 0.6640625, | |
| "learning_rate": 8.019922254616132e-05, | |
| "loss": 3.2208, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.5975587538713791, | |
| "grad_norm": 0.671875, | |
| "learning_rate": 8.007774538386784e-05, | |
| "loss": 3.2251, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.6012024048096193, | |
| "grad_norm": 0.63671875, | |
| "learning_rate": 7.995626822157435e-05, | |
| "loss": 3.284, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.6048460557478593, | |
| "grad_norm": 0.6484375, | |
| "learning_rate": 7.983479105928086e-05, | |
| "loss": 3.2404, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.6084897066860995, | |
| "grad_norm": 0.69140625, | |
| "learning_rate": 7.971331389698737e-05, | |
| "loss": 3.3335, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.6121333576243396, | |
| "grad_norm": 0.59765625, | |
| "learning_rate": 7.959183673469388e-05, | |
| "loss": 3.276, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.6157770085625797, | |
| "grad_norm": 0.63671875, | |
| "learning_rate": 7.947035957240039e-05, | |
| "loss": 3.2263, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.6194206595008198, | |
| "grad_norm": 0.546875, | |
| "learning_rate": 7.934888241010691e-05, | |
| "loss": 3.1878, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.62306431043906, | |
| "grad_norm": 0.625, | |
| "learning_rate": 7.922740524781341e-05, | |
| "loss": 3.294, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.6267079613773, | |
| "grad_norm": 0.578125, | |
| "learning_rate": 7.910592808551993e-05, | |
| "loss": 3.2183, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.6303516123155402, | |
| "grad_norm": 0.69140625, | |
| "learning_rate": 7.898445092322644e-05, | |
| "loss": 3.1985, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.6339952632537803, | |
| "grad_norm": 0.74609375, | |
| "learning_rate": 7.886297376093295e-05, | |
| "loss": 3.1563, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.6376389141920205, | |
| "grad_norm": 0.6484375, | |
| "learning_rate": 7.874149659863946e-05, | |
| "loss": 3.2806, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.6412825651302605, | |
| "grad_norm": 0.6328125, | |
| "learning_rate": 7.862001943634597e-05, | |
| "loss": 3.2288, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.6449262160685006, | |
| "grad_norm": 0.5859375, | |
| "learning_rate": 7.849854227405248e-05, | |
| "loss": 3.2785, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.6485698670067408, | |
| "grad_norm": 0.6875, | |
| "learning_rate": 7.8377065111759e-05, | |
| "loss": 3.2952, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.6522135179449808, | |
| "grad_norm": 0.6796875, | |
| "learning_rate": 7.82555879494655e-05, | |
| "loss": 3.1665, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.655857168883221, | |
| "grad_norm": 0.6796875, | |
| "learning_rate": 7.8134110787172e-05, | |
| "loss": 3.1984, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.6595008198214611, | |
| "grad_norm": 0.625, | |
| "learning_rate": 7.801263362487853e-05, | |
| "loss": 3.2051, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.6631444707597012, | |
| "grad_norm": 0.6640625, | |
| "learning_rate": 7.789115646258504e-05, | |
| "loss": 3.2141, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.6667881216979413, | |
| "grad_norm": 0.59375, | |
| "learning_rate": 7.776967930029155e-05, | |
| "loss": 3.312, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.6704317726361815, | |
| "grad_norm": 0.65234375, | |
| "learning_rate": 7.764820213799806e-05, | |
| "loss": 3.2473, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.6740754235744215, | |
| "grad_norm": 0.61328125, | |
| "learning_rate": 7.752672497570457e-05, | |
| "loss": 3.2924, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.6777190745126617, | |
| "grad_norm": 0.71484375, | |
| "learning_rate": 7.740524781341109e-05, | |
| "loss": 3.2799, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.6813627254509018, | |
| "grad_norm": 0.55078125, | |
| "learning_rate": 7.72837706511176e-05, | |
| "loss": 3.2251, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.685006376389142, | |
| "grad_norm": 0.70703125, | |
| "learning_rate": 7.71622934888241e-05, | |
| "loss": 3.209, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.688650027327382, | |
| "grad_norm": 0.63671875, | |
| "learning_rate": 7.704081632653062e-05, | |
| "loss": 3.2312, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.6922936782656222, | |
| "grad_norm": 0.6328125, | |
| "learning_rate": 7.691933916423713e-05, | |
| "loss": 3.2487, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.6959373292038623, | |
| "grad_norm": 0.5703125, | |
| "learning_rate": 7.679786200194364e-05, | |
| "loss": 3.3157, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 0.6995809801421023, | |
| "grad_norm": 0.63671875, | |
| "learning_rate": 7.667638483965015e-05, | |
| "loss": 3.299, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.7032246310803425, | |
| "grad_norm": 0.69140625, | |
| "learning_rate": 7.655490767735666e-05, | |
| "loss": 3.2755, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 0.7068682820185826, | |
| "grad_norm": 0.625, | |
| "learning_rate": 7.643343051506318e-05, | |
| "loss": 3.317, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.7105119329568227, | |
| "grad_norm": 0.55078125, | |
| "learning_rate": 7.631195335276969e-05, | |
| "loss": 3.1871, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.7141555838950628, | |
| "grad_norm": 0.74609375, | |
| "learning_rate": 7.619047619047618e-05, | |
| "loss": 3.2405, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.717799234833303, | |
| "grad_norm": 0.69921875, | |
| "learning_rate": 7.606899902818271e-05, | |
| "loss": 3.3068, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 0.7214428857715431, | |
| "grad_norm": 0.578125, | |
| "learning_rate": 7.594752186588922e-05, | |
| "loss": 3.335, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.7250865367097832, | |
| "grad_norm": 0.6484375, | |
| "learning_rate": 7.582604470359573e-05, | |
| "loss": 3.2617, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.7287301876480233, | |
| "grad_norm": 0.5234375, | |
| "learning_rate": 7.570456754130224e-05, | |
| "loss": 3.2335, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.7323738385862635, | |
| "grad_norm": 0.640625, | |
| "learning_rate": 7.558309037900875e-05, | |
| "loss": 3.2604, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 0.7360174895245035, | |
| "grad_norm": 0.57421875, | |
| "learning_rate": 7.546161321671527e-05, | |
| "loss": 3.2632, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.7396611404627437, | |
| "grad_norm": 0.61328125, | |
| "learning_rate": 7.534013605442178e-05, | |
| "loss": 3.2184, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 0.7433047914009838, | |
| "grad_norm": 0.6171875, | |
| "learning_rate": 7.521865889212827e-05, | |
| "loss": 3.2848, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.7469484423392239, | |
| "grad_norm": 0.6484375, | |
| "learning_rate": 7.50971817298348e-05, | |
| "loss": 3.2473, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.750592093277464, | |
| "grad_norm": 0.6953125, | |
| "learning_rate": 7.49757045675413e-05, | |
| "loss": 3.195, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.7542357442157042, | |
| "grad_norm": 0.73046875, | |
| "learning_rate": 7.485422740524782e-05, | |
| "loss": 3.2248, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 0.7578793951539442, | |
| "grad_norm": 0.5390625, | |
| "learning_rate": 7.473275024295433e-05, | |
| "loss": 3.1511, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.7615230460921844, | |
| "grad_norm": 0.66796875, | |
| "learning_rate": 7.461127308066083e-05, | |
| "loss": 3.2719, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 0.7651666970304245, | |
| "grad_norm": 0.57421875, | |
| "learning_rate": 7.448979591836736e-05, | |
| "loss": 3.2339, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.7688103479686647, | |
| "grad_norm": 0.61328125, | |
| "learning_rate": 7.436831875607387e-05, | |
| "loss": 3.2863, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 0.7724539989069047, | |
| "grad_norm": 0.55859375, | |
| "learning_rate": 7.424684159378036e-05, | |
| "loss": 3.2057, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.7760976498451448, | |
| "grad_norm": 0.73046875, | |
| "learning_rate": 7.412536443148689e-05, | |
| "loss": 3.2397, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 0.779741300783385, | |
| "grad_norm": 0.59375, | |
| "learning_rate": 7.40038872691934e-05, | |
| "loss": 3.2323, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.783384951721625, | |
| "grad_norm": 0.63671875, | |
| "learning_rate": 7.38824101068999e-05, | |
| "loss": 3.2764, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.7870286026598652, | |
| "grad_norm": 0.60546875, | |
| "learning_rate": 7.376093294460641e-05, | |
| "loss": 3.2668, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.7906722535981053, | |
| "grad_norm": 0.63671875, | |
| "learning_rate": 7.363945578231292e-05, | |
| "loss": 3.2953, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 0.7943159045363454, | |
| "grad_norm": 0.5625, | |
| "learning_rate": 7.351797862001945e-05, | |
| "loss": 3.1915, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.7979595554745855, | |
| "grad_norm": 0.66015625, | |
| "learning_rate": 7.339650145772596e-05, | |
| "loss": 3.2622, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 0.8016032064128257, | |
| "grad_norm": 0.6171875, | |
| "learning_rate": 7.327502429543247e-05, | |
| "loss": 3.2522, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.8052468573510657, | |
| "grad_norm": 0.64453125, | |
| "learning_rate": 7.315354713313898e-05, | |
| "loss": 3.1673, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 0.8088905082893059, | |
| "grad_norm": 0.625, | |
| "learning_rate": 7.303206997084548e-05, | |
| "loss": 3.2722, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.812534159227546, | |
| "grad_norm": 0.6640625, | |
| "learning_rate": 7.2910592808552e-05, | |
| "loss": 3.2377, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 0.8161778101657862, | |
| "grad_norm": 0.6171875, | |
| "learning_rate": 7.27891156462585e-05, | |
| "loss": 3.179, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.8198214611040262, | |
| "grad_norm": 0.57421875, | |
| "learning_rate": 7.266763848396501e-05, | |
| "loss": 3.2588, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.8234651120422664, | |
| "grad_norm": 0.578125, | |
| "learning_rate": 7.254616132167152e-05, | |
| "loss": 3.2664, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.8271087629805065, | |
| "grad_norm": 0.73046875, | |
| "learning_rate": 7.242468415937805e-05, | |
| "loss": 3.2515, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 0.8307524139187465, | |
| "grad_norm": 0.6328125, | |
| "learning_rate": 7.230320699708455e-05, | |
| "loss": 3.2102, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.8343960648569867, | |
| "grad_norm": 0.6484375, | |
| "learning_rate": 7.218172983479106e-05, | |
| "loss": 3.246, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 0.8380397157952268, | |
| "grad_norm": 0.58203125, | |
| "learning_rate": 7.206025267249757e-05, | |
| "loss": 3.3321, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.8416833667334669, | |
| "grad_norm": 0.59765625, | |
| "learning_rate": 7.193877551020408e-05, | |
| "loss": 3.0889, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 0.845327017671707, | |
| "grad_norm": 0.66015625, | |
| "learning_rate": 7.18172983479106e-05, | |
| "loss": 3.2811, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.8489706686099472, | |
| "grad_norm": 0.65234375, | |
| "learning_rate": 7.16958211856171e-05, | |
| "loss": 3.1688, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 0.8526143195481873, | |
| "grad_norm": 0.76171875, | |
| "learning_rate": 7.157434402332361e-05, | |
| "loss": 3.2495, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.8562579704864274, | |
| "grad_norm": 0.6484375, | |
| "learning_rate": 7.145286686103013e-05, | |
| "loss": 3.1742, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.8599016214246675, | |
| "grad_norm": 0.5859375, | |
| "learning_rate": 7.133138969873664e-05, | |
| "loss": 3.2293, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 0.8635452723629077, | |
| "grad_norm": 0.640625, | |
| "learning_rate": 7.120991253644315e-05, | |
| "loss": 3.2574, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 0.8671889233011477, | |
| "grad_norm": 0.55078125, | |
| "learning_rate": 7.108843537414966e-05, | |
| "loss": 3.2496, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 0.8708325742393879, | |
| "grad_norm": 0.7109375, | |
| "learning_rate": 7.096695821185617e-05, | |
| "loss": 3.2527, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 0.874476225177628, | |
| "grad_norm": 0.6640625, | |
| "learning_rate": 7.08454810495627e-05, | |
| "loss": 3.1984, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.8781198761158681, | |
| "grad_norm": 0.58984375, | |
| "learning_rate": 7.072400388726919e-05, | |
| "loss": 3.2517, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 0.8817635270541082, | |
| "grad_norm": 0.6171875, | |
| "learning_rate": 7.06025267249757e-05, | |
| "loss": 3.2105, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 0.8854071779923484, | |
| "grad_norm": 0.62890625, | |
| "learning_rate": 7.048104956268222e-05, | |
| "loss": 3.2125, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 0.8890508289305884, | |
| "grad_norm": 0.72265625, | |
| "learning_rate": 7.035957240038873e-05, | |
| "loss": 3.255, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 0.8926944798688285, | |
| "grad_norm": 0.671875, | |
| "learning_rate": 7.023809523809524e-05, | |
| "loss": 3.3331, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.8963381308070687, | |
| "grad_norm": 0.65234375, | |
| "learning_rate": 7.011661807580175e-05, | |
| "loss": 3.3545, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 0.8999817817453089, | |
| "grad_norm": 0.62890625, | |
| "learning_rate": 6.999514091350826e-05, | |
| "loss": 3.2776, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 0.9036254326835489, | |
| "grad_norm": 0.76953125, | |
| "learning_rate": 6.987366375121478e-05, | |
| "loss": 3.2331, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 0.907269083621789, | |
| "grad_norm": 0.78515625, | |
| "learning_rate": 6.975218658892128e-05, | |
| "loss": 3.2803, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 0.9109127345600292, | |
| "grad_norm": 0.671875, | |
| "learning_rate": 6.963070942662779e-05, | |
| "loss": 3.256, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.9145563854982692, | |
| "grad_norm": 0.59765625, | |
| "learning_rate": 6.950923226433431e-05, | |
| "loss": 3.2896, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 0.9182000364365094, | |
| "grad_norm": 0.62890625, | |
| "learning_rate": 6.938775510204082e-05, | |
| "loss": 3.2555, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 0.9218436873747495, | |
| "grad_norm": 0.7421875, | |
| "learning_rate": 6.926627793974733e-05, | |
| "loss": 3.2682, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 0.9254873383129896, | |
| "grad_norm": 0.671875, | |
| "learning_rate": 6.914480077745384e-05, | |
| "loss": 3.1564, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 0.9291309892512297, | |
| "grad_norm": 0.6484375, | |
| "learning_rate": 6.902332361516035e-05, | |
| "loss": 3.1445, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.9327746401894699, | |
| "grad_norm": 0.51953125, | |
| "learning_rate": 6.890184645286687e-05, | |
| "loss": 3.2515, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 0.9364182911277099, | |
| "grad_norm": 0.65625, | |
| "learning_rate": 6.878036929057337e-05, | |
| "loss": 3.1962, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 0.9400619420659501, | |
| "grad_norm": 0.59375, | |
| "learning_rate": 6.865889212827988e-05, | |
| "loss": 3.3199, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 0.9437055930041902, | |
| "grad_norm": 0.65234375, | |
| "learning_rate": 6.85374149659864e-05, | |
| "loss": 3.264, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 0.9473492439424304, | |
| "grad_norm": 0.63671875, | |
| "learning_rate": 6.841593780369291e-05, | |
| "loss": 3.1853, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.9509928948806704, | |
| "grad_norm": 0.72265625, | |
| "learning_rate": 6.829446064139942e-05, | |
| "loss": 3.3017, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 0.9546365458189106, | |
| "grad_norm": 0.6953125, | |
| "learning_rate": 6.817298347910593e-05, | |
| "loss": 3.2358, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 0.9582801967571507, | |
| "grad_norm": 0.6328125, | |
| "learning_rate": 6.805150631681244e-05, | |
| "loss": 3.2854, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 0.9619238476953907, | |
| "grad_norm": 0.5859375, | |
| "learning_rate": 6.793002915451895e-05, | |
| "loss": 3.1873, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 0.9655674986336309, | |
| "grad_norm": 0.59375, | |
| "learning_rate": 6.780855199222547e-05, | |
| "loss": 3.2274, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.969211149571871, | |
| "grad_norm": 0.63671875, | |
| "learning_rate": 6.768707482993197e-05, | |
| "loss": 3.2037, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 0.9728548005101111, | |
| "grad_norm": 0.5703125, | |
| "learning_rate": 6.756559766763849e-05, | |
| "loss": 3.3132, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 0.9764984514483512, | |
| "grad_norm": 0.72265625, | |
| "learning_rate": 6.7444120505345e-05, | |
| "loss": 3.2734, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 0.9801421023865914, | |
| "grad_norm": 0.70703125, | |
| "learning_rate": 6.732264334305151e-05, | |
| "loss": 3.1784, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 0.9837857533248315, | |
| "grad_norm": 0.57421875, | |
| "learning_rate": 6.720116618075802e-05, | |
| "loss": 3.2181, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.9874294042630716, | |
| "grad_norm": 0.6953125, | |
| "learning_rate": 6.707968901846453e-05, | |
| "loss": 3.2676, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 0.9910730552013117, | |
| "grad_norm": 0.6875, | |
| "learning_rate": 6.695821185617104e-05, | |
| "loss": 3.1952, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 0.9947167061395519, | |
| "grad_norm": 0.609375, | |
| "learning_rate": 6.683673469387756e-05, | |
| "loss": 3.3135, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 0.9983603570777919, | |
| "grad_norm": 0.6484375, | |
| "learning_rate": 6.671525753158406e-05, | |
| "loss": 3.2643, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 1.002004008016032, | |
| "grad_norm": 0.6015625, | |
| "learning_rate": 6.659378036929058e-05, | |
| "loss": 3.1996, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 1.0056476589542722, | |
| "grad_norm": 0.75, | |
| "learning_rate": 6.647230320699709e-05, | |
| "loss": 3.0862, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 1.0092913098925123, | |
| "grad_norm": 0.671875, | |
| "learning_rate": 6.63508260447036e-05, | |
| "loss": 3.1886, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 1.0129349608307525, | |
| "grad_norm": 0.65625, | |
| "learning_rate": 6.622934888241011e-05, | |
| "loss": 3.1478, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 1.0165786117689926, | |
| "grad_norm": 0.69921875, | |
| "learning_rate": 6.610787172011662e-05, | |
| "loss": 3.1577, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 1.0202222627072326, | |
| "grad_norm": 0.77734375, | |
| "learning_rate": 6.598639455782313e-05, | |
| "loss": 3.148, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.0238659136454729, | |
| "grad_norm": 0.640625, | |
| "learning_rate": 6.586491739552965e-05, | |
| "loss": 3.1971, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 1.027509564583713, | |
| "grad_norm": 0.58984375, | |
| "learning_rate": 6.574344023323615e-05, | |
| "loss": 3.1351, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 1.031153215521953, | |
| "grad_norm": 0.734375, | |
| "learning_rate": 6.562196307094267e-05, | |
| "loss": 3.2304, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 1.0347968664601932, | |
| "grad_norm": 0.71484375, | |
| "learning_rate": 6.550048590864918e-05, | |
| "loss": 3.1582, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 1.0384405173984332, | |
| "grad_norm": 0.71875, | |
| "learning_rate": 6.537900874635569e-05, | |
| "loss": 3.1183, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 1.0420841683366733, | |
| "grad_norm": 0.8046875, | |
| "learning_rate": 6.52575315840622e-05, | |
| "loss": 3.2056, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 1.0457278192749135, | |
| "grad_norm": 0.765625, | |
| "learning_rate": 6.513605442176871e-05, | |
| "loss": 3.1694, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 1.0493714702131536, | |
| "grad_norm": 0.890625, | |
| "learning_rate": 6.501457725947522e-05, | |
| "loss": 3.1428, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 1.0530151211513936, | |
| "grad_norm": 0.65625, | |
| "learning_rate": 6.489310009718174e-05, | |
| "loss": 3.1052, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 1.0566587720896339, | |
| "grad_norm": 0.83203125, | |
| "learning_rate": 6.477162293488824e-05, | |
| "loss": 3.1195, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.060302423027874, | |
| "grad_norm": 0.7421875, | |
| "learning_rate": 6.465014577259475e-05, | |
| "loss": 3.2278, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 1.063946073966114, | |
| "grad_norm": 0.71875, | |
| "learning_rate": 6.452866861030127e-05, | |
| "loss": 3.1563, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 1.0675897249043542, | |
| "grad_norm": 0.69140625, | |
| "learning_rate": 6.440719144800778e-05, | |
| "loss": 3.1505, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 1.0712333758425943, | |
| "grad_norm": 0.8515625, | |
| "learning_rate": 6.428571428571429e-05, | |
| "loss": 3.1681, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 1.0748770267808343, | |
| "grad_norm": 0.71484375, | |
| "learning_rate": 6.41642371234208e-05, | |
| "loss": 3.17, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 1.0785206777190746, | |
| "grad_norm": 0.90625, | |
| "learning_rate": 6.40427599611273e-05, | |
| "loss": 3.1775, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 1.0821643286573146, | |
| "grad_norm": 0.73828125, | |
| "learning_rate": 6.392128279883383e-05, | |
| "loss": 3.0921, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 1.0858079795955549, | |
| "grad_norm": 0.75390625, | |
| "learning_rate": 6.379980563654034e-05, | |
| "loss": 3.1666, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 1.089451630533795, | |
| "grad_norm": 0.80859375, | |
| "learning_rate": 6.367832847424684e-05, | |
| "loss": 3.1935, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 1.093095281472035, | |
| "grad_norm": 0.67578125, | |
| "learning_rate": 6.355685131195336e-05, | |
| "loss": 3.0588, | |
| "step": 3000 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 8232, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.570661967366676e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |